Only spawn request threads if necessary

.github/workflows/bench-manual.yml

@@ -18,9 +18,11 @@ jobs:
         timeout-minutes: 180 # 3h
         steps:
             - uses: actions/checkout@v3
-            - uses: dtolnay/rust-toolchain@1.79
+            - uses: actions-rs/toolchain@v1
               with:
                 profile: minimal
+                toolchain: stable
+                override: true
 
             - name: Run benchmarks - workload ${WORKLOAD_NAME} - branch ${{ github.ref }} - commit ${{ github.sha }}
               run: |

.github/workflows/bench-pr.yml

@@ -16,37 +16,6 @@ jobs:
       runs-on: benchmarks
       timeout-minutes: 180 # 3h
       steps:
-        - name: Check permissions
-          id: permission
-          env:
-            PR_AUTHOR: ${{github.event.issue.user.login }}
-            COMMENT_AUTHOR: ${{github.event.comment.user.login }}
-            REPOSITORY: ${{github.repository}}
-            PR_ID: ${{github.event.issue.number}}
-          run: |
-            PR_REPOSITORY=$(gh api /repos/"$REPOSITORY"/pulls/"$PR_ID" --jq .head.repo.full_name)
-            if $(gh api /repos/"$REPOSITORY"/collaborators/"$PR_AUTHOR"/permission --jq .user.permissions.push)
-            then
-              echo "::notice title=Authentication success::PR author authenticated"
-            else
-              echo "::error title=Authentication error::PR author doesn't have push permission on this repository"
-              exit 1
-            fi
-            if $(gh api /repos/"$REPOSITORY"/collaborators/"$COMMENT_AUTHOR"/permission --jq .user.permissions.push)
-            then
-              echo "::notice title=Authentication success::Comment author authenticated"
-            else
-              echo "::error title=Authentication error::Comment author doesn't have push permission on this repository"
-              exit 1
-            fi
-            if [ "$PR_REPOSITORY" = "$REPOSITORY" ]
-            then
-              echo "::notice title=Authentication success::PR started from main repository"
-            else
-              echo "::error title=Authentication error::PR started from a fork"
-              exit 1
-            fi
-
         - name: Check for Command
           id: command
           uses: xt0rted/slash-command-action@v2
@@ -66,17 +35,12 @@ jobs:
             fetch-depth: 0 # fetch full history to be able to get main commit sha
             ref: ${{ steps.comment-branch.outputs.head_ref }}
 
-        - uses: dtolnay/rust-toolchain@1.79
+        - uses: actions-rs/toolchain@v1
           with:
             profile: minimal
+            toolchain: stable
+            override: true
 
         - name: Run benchmarks on PR ${{ github.event.issue.id }}
           run: |
-            cargo xtask bench --api-key "${{ secrets.BENCHMARK_API_KEY }}" \
-               --dashboard-url "${{ vars.BENCHMARK_DASHBOARD_URL }}" \
-               --reason "[Comment](${{ github.event.comment.html_url }}) on [#${{ github.event.issue.number }}](${{ github.event.issue.html_url }})" \
-               -- ${{ steps.command.outputs.command-arguments }} > benchlinks.txt
-
-        - name: Send comment in PR
-          run: |
-            gh pr comment ${{github.event.issue.number}} --body-file benchlinks.txt
+            cargo xtask bench --api-key "${{ secrets.BENCHMARK_API_KEY }}" --dashboard-url "${{ vars.BENCHMARK_DASHBOARD_URL }}" --reason "[Comment](${{ github.event.comment.html_url }}) on [#${{ github.event.issue.number }}](${{ github.event.issue.html_url }})" -- ${{ steps.command.outputs.command-arguments }}

.github/workflows/bench-push-indexing.yml

@@ -12,9 +12,11 @@ jobs:
         timeout-minutes: 180 # 3h
         steps:
           - uses: actions/checkout@v3
-          - uses: dtolnay/rust-toolchain@1.79
+          - uses: actions-rs/toolchain@v1
             with:
               profile: minimal
+              toolchain: stable
+              override: true
 
           # Run benchmarks
           - name: Run benchmarks - Dataset ${BENCH_NAME} - Branch main - Commit ${{ github.sha }}

.github/workflows/benchmarks-manual.yml

@@ -18,9 +18,11 @@ jobs:
     timeout-minutes: 4320 # 72h
     steps:
       - uses: actions/checkout@v3
-      - uses: dtolnay/rust-toolchain@1.79
+      - uses: actions-rs/toolchain@v1
         with:
           profile: minimal
+          toolchain: stable
+          override: true
 
       # Set variables
       - name: Set current branch name

.github/workflows/benchmarks-pr.yml

@@ -13,40 +13,11 @@ jobs:
     runs-on: benchmarks
     timeout-minutes: 4320 # 72h
     steps:
-      - name: Check permissions
-        id: permission
-        env:
-          PR_AUTHOR: ${{github.event.issue.user.login }}
-          COMMENT_AUTHOR: ${{github.event.comment.user.login }}
-          REPOSITORY: ${{github.repository}}
-          PR_ID: ${{github.event.issue.number}}
-        run: |
-          PR_REPOSITORY=$(gh api /repos/"$REPOSITORY"/pulls/"$PR_ID" --jq .head.repo.full_name)
-          if $(gh api /repos/"$REPOSITORY"/collaborators/"$PR_AUTHOR"/permission --jq .user.permissions.push)
-          then
-            echo "::notice title=Authentication success::PR author authenticated"
-          else
-            echo "::error title=Authentication error::PR author doesn't have push permission on this repository"
-            exit 1
-          fi
-          if $(gh api /repos/"$REPOSITORY"/collaborators/"$COMMENT_AUTHOR"/permission --jq .user.permissions.push)
-          then
-            echo "::notice title=Authentication success::Comment author authenticated"
-          else
-            echo "::error title=Authentication error::Comment author doesn't have push permission on this repository"
-            exit 1
-          fi
-          if [ "$PR_REPOSITORY" = "$REPOSITORY" ]
-          then
-            echo "::notice title=Authentication success::PR started from main repository"
-          else
-            echo "::error title=Authentication error::PR started from a fork"
-            exit 1
-          fi
-
-      - uses: dtolnay/rust-toolchain@1.79
+      - uses: actions-rs/toolchain@v1
         with:
           profile: minimal
+          toolchain: stable
+          override: true
 
       - name: Check for Command
         id: command

.github/workflows/benchmarks-push-indexing.yml

@@ -16,9 +16,11 @@ jobs:
     timeout-minutes: 4320 # 72h
     steps:
       - uses: actions/checkout@v3
-      - uses: dtolnay/rust-toolchain@1.79
+      - uses: actions-rs/toolchain@v1
         with:
           profile: minimal
+          toolchain: stable
+          override: true
 
       # Set variables
       - name: Set current branch name

.github/workflows/benchmarks-push-search-geo.yml

@@ -15,9 +15,11 @@ jobs:
     runs-on: benchmarks
     steps:
       - uses: actions/checkout@v3
-      - uses: dtolnay/rust-toolchain@1.79
+      - uses: actions-rs/toolchain@v1
         with:
           profile: minimal
+          toolchain: stable
+          override: true
 
       # Set variables
       - name: Set current branch name
@@ -40,7 +42,7 @@ jobs:
       # Run benchmarks
       - name: Run benchmarks - Dataset ${BENCH_NAME} - Branch ${{ steps.current_branch.outputs.name }} - Commit ${{ steps.commit_sha.outputs.short }}
         run: |
-          cd crates/benchmarks
+          cd benchmarks
           cargo bench --bench ${BENCH_NAME} -- --save-baseline ${{ steps.file.outputs.basename }}
 
       # Generate critcmp files

.github/workflows/benchmarks-push-search-songs.yml

@@ -15,9 +15,11 @@ jobs:
     runs-on: benchmarks
     steps:
       - uses: actions/checkout@v3
-      - uses: dtolnay/rust-toolchain@1.79
+      - uses: actions-rs/toolchain@v1
         with:
           profile: minimal
+          toolchain: stable
+          override: true
 
       # Set variables
       - name: Set current branch name

.github/workflows/benchmarks-push-search-wiki.yml

@@ -15,9 +15,11 @@ jobs:
     runs-on: benchmarks
     steps:
       - uses: actions/checkout@v3
-      - uses: dtolnay/rust-toolchain@1.79
+      - uses: actions-rs/toolchain@v1
         with:
           profile: minimal
+          toolchain: stable
+          override: true
 
       # Set variables
       - name: Set current branch name

.github/workflows/flaky-tests.yml

@@ -1,5 +1,4 @@
 name: Look for flaky tests
-
 on:
   workflow_dispatch:
   schedule:
@@ -9,15 +8,18 @@ jobs:
   flaky:
     runs-on: ubuntu-latest
     container:
-      # Use ubuntu-20.04 to compile with glibc 2.28
-      image: ubuntu:20.04
+      # Use ubuntu-18.04 to compile with glibc 2.27, which are the production expectations
+      image: ubuntu:18.04
     steps:
     - uses: actions/checkout@v3
     - name: Install needed dependencies
       run: |
         apt-get update && apt-get install -y curl
         apt-get install build-essential -y
-    - uses: dtolnay/rust-toolchain@1.79
+    - uses: actions-rs/toolchain@v1
+      with:
+        toolchain: stable
+        override: true
     - name: Install cargo-flaky
       run: cargo install cargo-flaky
     - name: Run cargo flaky in the dumps

.github/workflows/fuzzer-indexing.yml

@@ -12,9 +12,11 @@ jobs:
     timeout-minutes: 4320 # 72h
     steps:
       - uses: actions/checkout@v3
-      - uses: dtolnay/rust-toolchain@1.79
+      - uses: actions-rs/toolchain@v1
         with:
           profile: minimal
+          toolchain: stable
+          override: true
 
       # Run benchmarks
       - name: Run the fuzzer

.github/workflows/publish-apt-brew-pkg.yml

@@ -18,14 +18,17 @@ jobs:
     runs-on: ubuntu-latest
     needs: check-version
     container:
-      # Use ubuntu-20.04 to compile with glibc 2.28
-      image: ubuntu:20.04
+      # Use ubuntu-18.04 to compile with glibc 2.27
+      image: ubuntu:18.04
     steps:
     - name: Install needed dependencies
       run: |
         apt-get update && apt-get install -y curl
         apt-get install build-essential -y
-    - uses: dtolnay/rust-toolchain@1.79
+    - uses: actions-rs/toolchain@v1
+      with:
+        toolchain: stable
+        override: true
     - name: Install cargo-deb
       run: cargo install cargo-deb
     - uses: actions/checkout@v3

.github/workflows/publish-binaries.yml

@@ -37,15 +37,18 @@ jobs:
     runs-on: ubuntu-latest
     needs: check-version
     container:
-      # Use ubuntu-20.04 to compile with glibc 2.28
-      image: ubuntu:20.04
+      # Use ubuntu-18.04 to compile with glibc 2.27
+      image: ubuntu:18.04
     steps:
     - uses: actions/checkout@v3
     - name: Install needed dependencies
       run: |
         apt-get update && apt-get install -y curl
         apt-get install build-essential -y
-    - uses: dtolnay/rust-toolchain@1.79
+    - uses: actions-rs/toolchain@v1
+      with:
+        toolchain: stable
+        override: true
     - name: Build
       run: cargo build --release --locked
     # No need to upload binaries for dry run (cron)
@@ -65,9 +68,9 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        os: [macos-13, windows-2022]
+        os: [macos-12, windows-2022]
         include:
-          - os: macos-13
+          - os: macos-12
             artifact_name: meilisearch
             asset_name: meilisearch-macos-amd64
           - os: windows-2022
@@ -75,7 +78,10 @@ jobs:
             asset_name: meilisearch-windows-amd64.exe
     steps:
     - uses: actions/checkout@v3
-    - uses: dtolnay/rust-toolchain@1.79
+    - uses: actions-rs/toolchain@v1
+      with:
+        toolchain: stable
+        override: true
     - name: Build
       run: cargo build --release --locked
     # No need to upload binaries for dry run (cron)
@@ -90,7 +96,7 @@ jobs:
 
   publish-macos-apple-silicon:
     name: Publish binary for macOS silicon
-    runs-on: macos-13
+    runs-on: macos-12
     needs: check-version
     strategy:
       matrix:
@@ -101,10 +107,12 @@ jobs:
       - name: Checkout repository
         uses: actions/checkout@v3
       - name: Installing Rust toolchain
-        uses: dtolnay/rust-toolchain@1.79
+        uses: actions-rs/toolchain@v1
         with:
+          toolchain: stable
           profile: minimal
           target: ${{ matrix.target }}
+          override: true
       - name: Cargo build
         uses: actions-rs/cargo@v1
         with:
@@ -124,11 +132,9 @@ jobs:
     name: Publish binary for aarch64
     runs-on: ubuntu-latest
     needs: check-version
-    env:
-      DEBIAN_FRONTEND: noninteractive
     container:
-      # Use ubuntu-20.04 to compile with glibc 2.28
-      image: ubuntu:20.04
+      # Use ubuntu-18.04 to compile with glibc 2.27
+      image: ubuntu:18.04
     strategy:
       matrix:
         include:
@@ -148,10 +154,12 @@ jobs:
           add-apt-repository "deb [arch=$(dpkg --print-architecture)] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable"
           apt-get update -y && apt-get install -y docker-ce
       - name: Installing Rust toolchain
-        uses: dtolnay/rust-toolchain@1.79
+        uses: actions-rs/toolchain@v1
         with:
+          toolchain: stable
           profile: minimal
           target: ${{ matrix.target }}
+          override: true
       - name: Configure target aarch64 GNU
         ## Environment variable is not passed using env:
         ## LD gold won't work with MUSL
@@ -162,9 +170,6 @@ jobs:
           echo '[target.aarch64-unknown-linux-gnu]' >> ~/.cargo/config
           echo 'linker = "aarch64-linux-gnu-gcc"' >> ~/.cargo/config
           echo 'JEMALLOC_SYS_WITH_LG_PAGE=16' >> $GITHUB_ENV
-      - name: Install a default toolchain that will be used to build cargo cross
-        run: |
-          rustup default stable
       - name: Cargo build
         uses: actions-rs/cargo@v1
         with:

.github/workflows/publish-docker-images.yml

@@ -80,11 +80,10 @@ jobs:
             type=ref,event=tag
             type=raw,value=nightly,enable=${{ github.event_name != 'push' }}
             type=semver,pattern=v{{major}}.{{minor}},enable=${{ steps.check-tag-format.outputs.stable == 'true' }}
-            type=semver,pattern=v{{major}},enable=${{ steps.check-tag-format.outputs.stable == 'true' }}
             type=raw,value=latest,enable=${{ steps.check-tag-format.outputs.stable == 'true' && steps.check-tag-format.outputs.latest == 'true' }}
 
       - name: Build and push
-        uses: docker/build-push-action@v6
+        uses: docker/build-push-action@v5
         with:
           push: true
           platforms: linux/amd64,linux/arm64

.github/workflows/test-suite.yml

@@ -19,11 +19,11 @@ env:
 
 jobs:
   test-linux:
-    name: Tests on ubuntu-20.04
+    name: Tests on ubuntu-18.04
     runs-on: ubuntu-latest
     container:
-      # Use ubuntu-20.04 to compile with glibc 2.28
-      image: ubuntu:20.04
+      # Use ubuntu-18.04 to compile with glibc 2.27, which are the production expectations
+      image: ubuntu:18.04
     steps:
       - uses: actions/checkout@v3
       - name: Install needed dependencies
@@ -31,7 +31,10 @@ jobs:
           apt-get update && apt-get install -y curl
           apt-get install build-essential -y
       - name: Setup test with Rust stable
-        uses: dtolnay/rust-toolchain@1.79
+        uses: actions-rs/toolchain@v1
+        with:
+          toolchain: stable
+          override: true
       - name: Cache dependencies
         uses: Swatinem/rust-cache@v2.7.1
       - name: Run cargo check without any default features
@@ -51,12 +54,15 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        os: [macos-13, windows-2022]
+        os: [macos-12, windows-2022]
     steps:
       - uses: actions/checkout@v3
       - name: Cache dependencies
         uses: Swatinem/rust-cache@v2.7.1
-      - uses: dtolnay/rust-toolchain@1.79
+      - uses: actions-rs/toolchain@v1
+        with:
+          toolchain: stable
+          override: true
       - name: Run cargo check without any default features
         uses: actions-rs/cargo@v1
         with:
@@ -72,8 +78,8 @@ jobs:
     name: Tests almost all features
     runs-on: ubuntu-latest
     container:
-      # Use ubuntu-20.04 to compile with glibc 2.28
-      image: ubuntu:20.04
+      # Use ubuntu-18.04 to compile with glibc 2.27, which are the production expectations
+      image: ubuntu:18.04
     if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
     steps:
       - uses: actions/checkout@v3
@@ -81,7 +87,10 @@ jobs:
         run: |
           apt-get update
           apt-get install --assume-yes build-essential curl
-      - uses: dtolnay/rust-toolchain@1.79
+      - uses: actions-rs/toolchain@v1
+        with:
+          toolchain: stable
+          override: true
       - name: Run cargo build with almost all features
         run: |
           cargo build --workspace --locked --release --features "$(cargo xtask list-features --exclude-feature cuda)"
@@ -93,7 +102,7 @@ jobs:
     name: Test disabled tokenization
     runs-on: ubuntu-latest
     container:
-      image: ubuntu:20.04
+      image: ubuntu:18.04
     if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
     steps:
       - uses: actions/checkout@v3
@@ -101,10 +110,13 @@ jobs:
         run: |
           apt-get update
           apt-get install --assume-yes build-essential curl
-      - uses: dtolnay/rust-toolchain@1.79
+      - uses: actions-rs/toolchain@v1
+        with:
+          toolchain: stable
+          override: true
       - name: Run cargo tree without default features and check lindera is not present
         run: |
-          if cargo tree -f '{p} {f}' -e normal --no-default-features | grep -qz lindera; then
+          if cargo tree -f '{p} {f}' -e normal --no-default-features | grep -vqz lindera; then
             echo "lindera has been found in the sources and it shouldn't"
             exit 1
           fi
@@ -117,15 +129,18 @@ jobs:
     name: Run tests in debug
     runs-on: ubuntu-latest
     container:
-      # Use ubuntu-20.04 to compile with glibc 2.28
-      image: ubuntu:20.04
+      # Use ubuntu-18.04 to compile with glibc 2.27, which are the production expectations
+      image: ubuntu:18.04
     steps:
       - uses: actions/checkout@v3
       - name: Install needed dependencies
         run: |
           apt-get update && apt-get install -y curl
           apt-get install build-essential -y
-      - uses: dtolnay/rust-toolchain@1.79
+      - uses: actions-rs/toolchain@v1
+        with:
+          toolchain: stable
+          override: true
       - name: Cache dependencies
         uses: Swatinem/rust-cache@v2.7.1
       - name: Run tests in debug
@@ -139,9 +154,11 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v3
-      - uses: dtolnay/rust-toolchain@1.79
+      - uses: actions-rs/toolchain@v1
         with:
           profile: minimal
+          toolchain: 1.75.0
+          override: true
           components: clippy
       - name: Cache dependencies
         uses: Swatinem/rust-cache@v2.7.1
@@ -156,10 +173,10 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v3
-      - uses: dtolnay/rust-toolchain@1.79
+      - uses: actions-rs/toolchain@v1
         with:
           profile: minimal
-          toolchain: nightly-2024-07-09
+          toolchain: nightly
           override: true
           components: rustfmt
       - name: Cache dependencies
@@ -169,5 +186,5 @@ jobs:
         # Since we want to trigger (and fail) this action as fast as possible, instead of building the benchmark crate
         # we are going to create an empty file where rustfmt expects it.
         run: |
-          echo -ne "\n" > crates/benchmarks/benches/datasets_paths.rs
+          echo -ne "\n" > benchmarks/benches/datasets_paths.rs
           cargo fmt --all -- --check

.github/workflows/update-cargo-toml-version.yml

@@ -18,9 +18,11 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v3
-      - uses: dtolnay/rust-toolchain@1.79
+      - uses: actions-rs/toolchain@v1
         with:
           profile: minimal
+          toolchain: stable
+          override: true
       - name: Install sd
         run: cargo install sd
       - name: Update Cargo.toml file

.gitignore

@@ -5,6 +5,7 @@
 **/*.json_lines
 **/*.rs.bk
 /*.mdb
+/query-history.txt
 /data.ms
 /snapshots
 /dumps
@@ -18,4 +19,4 @@
 *.snap.new
 
 # Fuzzcheck data for the facet indexing fuzz test
-crates/milli/fuzz/update::facet::incremental::fuzz::fuzz/
+milli/fuzz/update::facet::incremental::fuzz::fuzz/

BENCHMARKS.md

@@ -109,12 +109,6 @@ They are JSON files with the following structure (comments are not actually supp
   "run_count": 3,
   // List of arguments to add to the Meilisearch command line.
   "extra_cli_args": ["--max-indexing-threads=1"],
-  // An expression that can be parsed as a comma-separated list of targets and levels
-  // as described in [tracing_subscriber's documentation](https://docs.rs/tracing-subscriber/latest/tracing_subscriber/filter/targets/struct.Targets.html#examples).
-  // The expression is used to filter the spans that are measured for profiling purposes.
-  // Optional, defaults to "indexing::=trace" (for indexing workloads), common other values is
-  // "search::=trace"
-  "target": "indexing::=trace",
   // List of named assets that can be used in the commands.
   "assets": {
     // name of the asset.
@@ -193,8 +187,8 @@ They are JSON files with the following structure (comments are not actually supp
   },
   // Core of the workload.
   // A list of commands to run sequentially.
-  // Optional: A precommand is a request to the Meilisearch instance that is executed before the profiling runs.
-  "precommands": [
+  // A command is a request to the Meilisearch instance that is executed while the profiling runs.
+  "commands": [
     {
       // Meilisearch route to call. `http://localhost:7700/` will be prepended.
       "route": "indexes/movies/settings",
@@ -230,11 +224,8 @@ They are JSON files with the following structure (comments are not actually supp
       // - DontWait: run the next command without waiting the response to this one.
       // - WaitForResponse: run the next command as soon as the response from the server is received.
       // - WaitForTask: run the next command once **all** the Meilisearch tasks created up to now have finished processing.
-      "synchronous": "WaitForTask"
-    }
-  ],
-  // A command is a request to the Meilisearch instance that is executed while the profiling runs.
-  "commands": [
+      "synchronous": "DontWait"
+    },
     {
       "route": "indexes/movies/documents",
       "method": "POST",

CONTRIBUTING.md

@@ -52,20 +52,6 @@ cargo test
 
 This command will be triggered to each PR as a requirement for merging it.
 
-#### Faster build
-
-You can set the `LINDERA_CACHE` environment variable to speed up your successive builds by up to 2 minutes.
-It'll store some built artifacts in the directory of your choice.
-
-We recommend using the standard `$HOME/.cache/lindera` directory:
-```sh
-export LINDERA_CACHE=$HOME/.cache/lindera
-```
-
-Furthermore, you can improve incremental compilation by setting the `MEILI_NO_VERGEN` environment variable.
-Setting this variable will prevent the Meilisearch binary from being rebuilt each time the directory that hosts the Meilisearch repository changes.
-Do not enable this environment variable for production builds (as it will break the `version` route, among other things).
-
 #### Snapshot-based tests
 
 We are using [insta](https://insta.rs) to perform snapshot-based testing.
@@ -77,7 +63,7 @@ Furthermore, we provide some macros on top of insta, notably a way to use snapsh
 
 To effectively debug snapshot-based hashes, we recommend you export the `MEILI_TEST_FULL_SNAPS` environment variable so that snapshot are fully created locally:
 
-```sh
+```
 export MEILI_TEST_FULL_SNAPS=true # add this to your .bashrc, .zshrc, ...
 ```
 

Cargo.toml

@@ -1,28 +1,28 @@
 [workspace]
 resolver = "2"
 members = [
-    "crates/meilisearch",
-    "crates/meilitool",
-    "crates/meilisearch-types",
-    "crates/meilisearch-auth",
-    "crates/meili-snap",
-    "crates/index-scheduler",
-    "crates/dump",
-    "crates/file-store",
-    "crates/permissive-json-pointer",
-    "crates/milli",
-    "crates/filter-parser",
-    "crates/flatten-serde-json",
-    "crates/json-depth-checker",
-    "crates/benchmarks",
-    "crates/fuzzers",
-    "crates/tracing-trace",
-    "crates/xtask",
-    "crates/build-info",
+    "meilisearch",
+    "meilitool",
+    "meilisearch-types",
+    "meilisearch-auth",
+    "meili-snap",
+    "index-scheduler",
+    "dump",
+    "file-store",
+    "permissive-json-pointer",
+    "milli",
+    "filter-parser",
+    "flatten-serde-json",
+    "json-depth-checker",
+    "benchmarks",
+    "fuzzers",
+    "tracing-trace",
+    "xtask",
+    "build-info",
 ]
 
 [workspace.package]
-version = "1.11.0"
+version = "1.8.0"
 authors = [
     "Quentin de Quelen <quentin@dequelen.me>",
     "Clément Renault <clement@meilisearch.com>",

Dockerfile

@@ -1,7 +1,7 @@
 # Compile
-FROM    rust:1.79.0-alpine3.20 AS compiler
+FROM    rust:1.75.0-alpine3.18 AS compiler
 
-RUN     apk add -q --no-cache build-base openssl-dev
+RUN     apk add -q --update-cache --no-cache build-base openssl-dev
 
 WORKDIR /
 
@@ -20,13 +20,13 @@ RUN     set -eux; \
         cargo build --release -p meilisearch -p meilitool
 
 # Run
-FROM    alpine:3.20
-LABEL   org.opencontainers.image.source="https://github.com/meilisearch/meilisearch"
+FROM    alpine:3.16
 
 ENV     MEILI_HTTP_ADDR 0.0.0.0:7700
 ENV     MEILI_SERVER_PROVIDER docker
 
-RUN     apk add -q --no-cache libgcc tini curl
+RUN     apk update --quiet \
+        && apk add -q --no-cache libgcc tini curl
 
 # add meilisearch and meilitool to the `/bin` so you can run it from anywhere
 # and it's easy to find.

README.md

@@ -25,7 +25,7 @@
 
 <p align="center">⚡ A lightning-fast search engine that fits effortlessly into your apps, websites, and workflow 🔍</p>
 
-[Meilisearch](https://www.meilisearch.com?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=intro) helps you shape a delightful search experience in a snap, offering features that work out of the box to speed up your workflow.
+Meilisearch helps you shape a delightful search experience in a snap, offering features that work out-of-the-box to speed up your workflow.
 
 <p align="center" name="demo">
   <a href="https://where2watch.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demo-gif#gh-light-mode-only" target="_blank">
@@ -36,41 +36,34 @@
   </a>
 </p>
 
-## 🖥 Examples
-
-- [**Movies**](https://where2watch.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=organization) — An application to help you find streaming platforms to watch movies using [hybrid search](https://www.meilisearch.com/solutions/hybrid-search?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos).
-- [**Ecommerce**](https://ecommerce.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos) — Ecommerce website using disjunctive [facets](https://www.meilisearch.com/docs/learn/fine_tuning_results/faceted_search?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos), range and rating filtering, and pagination.
-- [**Songs**](https://music.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos) — Search through 47 million of songs.
-- [**SaaS**](https://saas.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos) — Search for contacts, deals, and companies in this [multi-tenant](https://www.meilisearch.com/docs/learn/security/multitenancy_tenant_tokens?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos) CRM application.
-
-See the list of all our example apps in our [demos repository](https://github.com/meilisearch/demos).
+🔥 [**Try it!**](https://where2watch.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demo-link) 🔥
 
 ## ✨ Features
-- **Hybrid search:** Combine the best of both [semantic](https://www.meilisearch.com/docs/learn/experimental/vector_search?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features) & full-text search to get the most relevant results
-- **Search-as-you-type:** Find & display results in less than 50 milliseconds to provide an intuitive experience
-- **[Typo tolerance](https://www.meilisearch.com/docs/learn/relevancy/typo_tolerance_settings?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** get relevant matches even when queries contain typos and misspellings
+
+- **Search-as-you-type:** find search results in less than 50 milliseconds
+- **[Typo tolerance](https://www.meilisearch.com/docs/learn/configuration/typo_tolerance?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** get relevant matches even when queries contain typos and misspellings
 - **[Filtering](https://www.meilisearch.com/docs/learn/fine_tuning_results/filtering?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features) and [faceted search](https://www.meilisearch.com/docs/learn/fine_tuning_results/faceted_search?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** enhance your users' search experience with custom filters and build a faceted search interface in a few lines of code
 - **[Sorting](https://www.meilisearch.com/docs/learn/fine_tuning_results/sorting?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** sort results based on price, date, or pretty much anything else your users need
-- **[Synonym support](https://www.meilisearch.com/docs/learn/relevancy/synonyms?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** configure synonyms to include more relevant content in your search results
+- **[Synonym support](https://www.meilisearch.com/docs/learn/configuration/synonyms?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** configure synonyms to include more relevant content in your search results
 - **[Geosearch](https://www.meilisearch.com/docs/learn/fine_tuning_results/geosearch?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** filter and sort documents based on geographic data
 - **[Extensive language support](https://www.meilisearch.com/docs/learn/what_is_meilisearch/language?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** search datasets in any language, with optimized support for Chinese, Japanese, Hebrew, and languages using the Latin alphabet
 - **[Security management](https://www.meilisearch.com/docs/learn/security/master_api_keys?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** control which users can access what data with API keys that allow fine-grained permissions handling
-- **[Multi-Tenancy](https://www.meilisearch.com/docs/learn/security/multitenancy_tenant_tokens?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** personalize search results for any number of application tenants
+- **[Multi-Tenancy](https://www.meilisearch.com/docs/learn/security/tenant_tokens?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** personalize search results for any number of application tenants
 - **Highly Customizable:** customize Meilisearch to your specific needs or use our out-of-the-box and hassle-free presets
 - **[RESTful API](https://www.meilisearch.com/docs/reference/api/overview?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** integrate Meilisearch in your technical stack with our plugins and SDKs
 - **Easy to install, deploy, and maintain**
 
 ## 📖 Documentation
 
-You can consult Meilisearch's documentation at [meilisearch.com/docs](https://www.meilisearch.com/docs/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=docs).
+You can consult Meilisearch's documentation at [https://www.meilisearch.com/docs](https://www.meilisearch.com/docs/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=docs).
 
 ## 🚀 Getting started
 
-For basic instructions on how to set up Meilisearch, add documents to an index, and search for documents, take a look at our [documentation](https://www.meilisearch.com/docs?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=get-started) guide.
+For basic instructions on how to set up Meilisearch, add documents to an index, and search for documents, take a look at our [Quick Start](https://www.meilisearch.com/docs/learn/getting_started/quick_start?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=get-started) guide.
 
-## 🌍 Supercharge your Meilisearch experience
+## ⚡ Supercharge your Meilisearch experience
 
-Say goodbye to server deployment and manual updates with [Meilisearch Cloud](https://www.meilisearch.com/cloud?utm_campaign=oss&utm_source=github&utm_medium=meilisearch). Additional features include analytics & monitoring in many regions around the world. No credit card is required.
+Say goodbye to server deployment and manual updates with [Meilisearch Cloud](https://www.meilisearch.com/cloud?utm_campaign=oss&utm_source=github&utm_medium=meilisearch). No credit card required.
 
 ## 🧰 SDKs & integration tools
 
@@ -90,15 +83,15 @@ Finally, for more in-depth information, refer to our articles explaining fundame
 
 ## 📊 Telemetry
 
-Meilisearch collects **anonymized** user data to help us improve our product. You can [deactivate this](https://www.meilisearch.com/docs/learn/what_is_meilisearch/telemetry?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=telemetry#how-to-disable-data-collection) whenever you want.
+Meilisearch collects **anonymized** data from users to help us improve our product. You can [deactivate this](https://www.meilisearch.com/docs/learn/what_is_meilisearch/telemetry?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=telemetry#how-to-disable-data-collection) whenever you want.
 
-To request deletion of collected data, please write to us at [privacy@meilisearch.com](mailto:privacy@meilisearch.com). Remember to include your `Instance UID` in the message, as this helps us quickly find and delete your data.
+To request deletion of collected data, please write to us at [privacy@meilisearch.com](mailto:privacy@meilisearch.com). Don't forget to include your `Instance UID` in the message, as this helps us quickly find and delete your data.
 
 If you want to know more about the kind of data we collect and what we use it for, check the [telemetry section](https://www.meilisearch.com/docs/learn/what_is_meilisearch/telemetry?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=telemetry#how-to-disable-data-collection) of our documentation.
 
 ## 📫 Get in touch!
 
-Meilisearch is a search engine created by [Meili]([https://www.welcometothejungle.com/en/companies/meilisearch](https://www.meilisearch.com/careers)), a software development company headquartered in France and with team members all over the world. Want to know more about us? [Check out our blog!](https://blog.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=contact)
+Meilisearch is a search engine created by [Meili](https://www.welcometothejungle.com/en/companies/meilisearch), a software development company based in France and with team members all over the world. Want to know more about us? [Check out our blog!](https://blog.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=contact)
 
 🗞 [Subscribe to our newsletter](https://meilisearch.us2.list-manage.com/subscribe?u=27870f7b71c908a8b359599fb&id=79582d828e) if you don't want to miss any updates! We promise we won't clutter your mailbox: we only send one edition every two months.
 
@@ -112,11 +105,11 @@ Thank you for your support!
 
 ## 👩‍💻 Contributing
 
-Meilisearch is, and will always be, open-source! If you want to contribute to the project, please look at [our contribution guidelines](CONTRIBUTING.md).
+Meilisearch is, and will always be, open-source! If you want to contribute to the project, please take a look at [our contribution guidelines](CONTRIBUTING.md).
 
 ## 📦 Versioning
 
-Meilisearch releases and their associated binaries are available on the project's [releases page](https://github.com/meilisearch/meilisearch/releases).
+Meilisearch releases and their associated binaries are available [in this GitHub page](https://github.com/meilisearch/meilisearch/releases).
 
 The binaries are versioned following [SemVer conventions](https://semver.org/). To know more, read our [versioning policy](https://github.com/meilisearch/engine-team/blob/main/resources/versioning-policy.md).
 

benchmarks/Cargo.toml

@@ -11,24 +11,24 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-anyhow = "1.0.86"
+anyhow = "1.0.79"
 csv = "1.3.0"
 milli = { path = "../milli" }
-mimalloc = { version = "0.1.43", default-features = false }
-serde_json = { version = "1.0.120", features = ["preserve_order"] }
+mimalloc = { version = "0.1.39", default-features = false }
+serde_json = { version = "1.0.111", features = ["preserve_order"] }
 
 [dev-dependencies]
 criterion = { version = "0.5.1", features = ["html_reports"] }
 rand = "0.8.5"
 rand_chacha = "0.3.1"
-roaring = "0.10.6"
+roaring = "0.10.2"
 
 [build-dependencies]
-anyhow = "1.0.86"
-bytes = "1.6.0"
+anyhow = "1.0.79"
+bytes = "1.5.0"
 convert_case = "0.6.0"
-flate2 = "1.0.30"
-reqwest = { version = "0.12.5", features = ["blocking", "rustls-tls"], default-features = false }
+flate2 = "1.0.28"
+reqwest = { version = "0.11.23", features = ["blocking", "rustls-tls"], default-features = false }
 
 [features]
 default = ["milli/all-tokenizations"]

bors.toml

@@ -1,6 +1,6 @@
 status = [
-    'Tests on ubuntu-20.04',
-    'Tests on macos-13',
+    'Tests on ubuntu-18.04',
+    'Tests on macos-12',
     'Tests on windows-2022',
     'Run Clippy',
     'Run Rustfmt',

build-info/Cargo.toml

@@ -11,8 +11,8 @@ license.workspace = true
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
-time = { version = "0.3.36", features = ["parsing"] }
+time = { version = "0.3.34", features = ["parsing"] }
 
 [build-dependencies]
-anyhow = "1.0.86"
-vergen-git2 = "1.0.0"
+anyhow = "1.0.80"
+vergen-git2 = "1.0.0-beta.2"

build-info/build.rs

@@ -5,13 +5,6 @@ fn main() {
 }
 
 fn emit_git_variables() -> anyhow::Result<()> {
-    println!("cargo::rerun-if-env-changed=MEILI_NO_VERGEN");
-
-    let has_vergen =
-        !matches!(std::env::var_os("MEILI_NO_VERGEN"), Some(x) if x != "false" && x != "0");
-
-    anyhow::ensure!(has_vergen, "disabled via `MEILI_NO_VERGEN`");
-
     // Note: any code that needs VERGEN_ environment variables should take care to define them manually in the Dockerfile and pass them
     // in the corresponding GitHub workflow (publish_docker.yml).
     // This is due to the Dockerfile building the binary outside of the git directory.

crates/dump/src/reader/snapshots/dump__reader__test__import_dump_v6_with_vectors-5.snap

@@ -1,56 +0,0 @@
----
-source: dump/src/reader/mod.rs
-expression: vector_index.settings().unwrap()
----
-{
-  "displayedAttributes": [
-    "*"
-  ],
-  "searchableAttributes": [
-    "*"
-  ],
-  "filterableAttributes": [],
-  "sortableAttributes": [],
-  "rankingRules": [
-    "words",
-    "typo",
-    "proximity",
-    "attribute",
-    "sort",
-    "exactness"
-  ],
-  "stopWords": [],
-  "nonSeparatorTokens": [],
-  "separatorTokens": [],
-  "dictionary": [],
-  "synonyms": {},
-  "distinctAttribute": null,
-  "proximityPrecision": "byWord",
-  "typoTolerance": {
-    "enabled": true,
-    "minWordSizeForTypos": {
-      "oneTypo": 5,
-      "twoTypos": 9
-    },
-    "disableOnWords": [],
-    "disableOnAttributes": []
-  },
-  "faceting": {
-    "maxValuesPerFacet": 100,
-    "sortFacetValuesBy": {
-      "*": "alpha"
-    }
-  },
-  "pagination": {
-    "maxTotalHits": 1000
-  },
-  "embedders": {
-    "default": {
-      "source": "huggingFace",
-      "model": "BAAI/bge-base-en-v1.5",
-      "revision": "617ca489d9e86b49b8167676d8220688b99db36e",
-      "documentTemplate": "{% for field in fields %} {{ field.name }}: {{ field.value }}\n{% endfor %}"
-    }
-  },
-  "searchCutoffMs": null
-}

crates/dump/src/reader/snapshots/dump__reader__test__import_dump_v6_with_vectors-6.snap

@@ -1,783 +0,0 @@
----
-source: dump/src/reader/mod.rs
-expression: document
----
-{
-  "id": "e3",
-  "desc": "overriden vector + map",
-  "_vectors": {
-    "default": [
-      0.2,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1
-    ],
-    "toto": [
-      0.1
-    ]
-  }
-}

crates/dump/src/reader/snapshots/dump__reader__test__import_dump_v6_with_vectors-7.snap

@@ -1,786 +0,0 @@
----
-source: dump/src/reader/mod.rs
-expression: document
----
-{
-  "id": "e2",
-  "desc": "natural vector + map",
-  "_vectors": {
-    "toto": [],
-    "default": {
-      "embeddings": [
-        [
-          -0.05189208313822746,
-          -0.9273212552070618,
-          0.1443813145160675,
-          0.0932632014155388,
-          0.2665371894836426,
-          0.36266782879829407,
-          0.6402910947799683,
-          0.32014018297195435,
-          0.030915971845388412,
-          -0.9312191605567932,
-          -0.3718109726905823,
-          -0.2700554132461548,
-          -1.1014580726623535,
-          0.9154956936836244,
-          -0.3406888246536255,
-          1.0077725648880005,
-          0.6577560901641846,
-          -0.3955195546150207,
-          -0.4148270785808563,
-          0.1855088472366333,
-          0.5062315464019775,
-          -0.3632686734199524,
-          -0.2277890294790268,
-          0.2560805082321167,
-          -0.3853609561920166,
-          -0.1604762226343155,
-          -0.13947471976280212,
-          -0.20147813856601715,
-          -0.4466346800327301,
-          -0.3761846721172333,
-          0.1443382054567337,
-          0.18205296993255615,
-          0.49359792470932007,
-          -0.22538000345230105,
-          -0.4996317625045776,
-          -0.22734887897968292,
-          -0.6034309267997742,
-          -0.7857939600944519,
-          -0.34923747181892395,
-          -0.3466345965862274,
-          0.21176661550998688,
-          -0.5101462006568909,
-          -0.3403083384037018,
-          0.000315118464641273,
-          0.236465722322464,
-          -0.10246097296476364,
-          -1.3013339042663574,
-          0.3419138789176941,
-          -0.32963496446609497,
-          -0.0901619717478752,
-          -0.5426247119903564,
-          0.22656650841236117,
-          -0.44758284091949463,
-          0.14151698350906372,
-          -0.1089438870549202,
-          0.5500766634941101,
-          -0.670711100101471,
-          -0.6227269768714905,
-          0.3894464075565338,
-          -0.27609574794769287,
-          0.7028202414512634,
-          -0.19697771966457367,
-          0.328511506319046,
-          0.5063360929489136,
-          0.4065195322036743,
-          0.2614171802997589,
-          -0.30274391174316406,
-          1.0393824577331543,
-          -0.7742937207221985,
-          -0.7874112129211426,
-          -0.6749666929244995,
-          0.5190866589546204,
-          0.004123548045754433,
-          -0.28312963247299194,
-          -0.038731709122657776,
-          -1.0142987966537476,
-          -0.09519586712121964,
-          0.8755272626876831,
-          0.4876938760280609,
-          0.7811151742935181,
-          0.85174959897995,
-          0.11826585978269576,
-          0.5373436808586121,
-          0.3649002015590668,
-          0.19064077734947205,
-          -0.00287026260048151,
-          -0.7305403351783752,
-          -0.015206154435873032,
-          -0.7899249196052551,
-          0.19407285749912265,
-          0.08596625179052353,
-          -0.28976231813430786,
-          -0.1525907665491104,
-          0.3798313438892365,
-          0.050306469202041626,
-          -0.5697937607765198,
-          0.4219021201133728,
-          0.276252806186676,
-          0.1559903472661972,
-          0.10030482709407806,
-          -0.4043720066547394,
-          -0.1969818025827408,
-          0.5739826560020447,
-          0.2116064727306366,
-          -1.4620544910430908,
-          -0.7802462577819824,
-          -0.24739810824394223,
-          -0.09791352599859238,
-          -0.4413802027702331,
-          0.21549351513385773,
-          -0.9520436525344848,
-          -0.08762510865926743,
-          0.08154498040676117,
-          -0.6154940724372864,
-          -1.01079523563385,
-          0.885427713394165,
-          0.6967288851737976,
-          0.27186504006385803,
-          -0.43194177746772766,
-          -0.11248451471328735,
-          0.7576630711555481,
-          0.4998855590820313,
-          0.0264343973249197,
-          0.9872855544090272,
-          0.5634694695472717,
-          0.053698331117630005,
-          0.19410227239131927,
-          0.3570743501186371,
-          -0.23670297861099243,
-          -0.9114483594894408,
-          0.07884842902421951,
-          0.7318344116210938,
-          0.44630110263824463,
-          0.08745364099740982,
-          -0.347101628780365,
-          -0.4314247667789459,
-          -0.5060274004936218,
-          0.003706763498485088,
-          0.44320008158683777,
-          -0.00788921769708395,
-          -0.1368623524904251,
-          -0.17391923069953918,
-          0.14473655819892883,
-          0.10927865654230118,
-          0.6974599361419678,
-          0.005052129738032818,
-          -0.016953065991401672,
-          -0.1256176233291626,
-          -0.036742497235536575,
-          0.5591985583305359,
-          -0.37619709968566895,
-          0.22429119050502777,
-          0.5403043031692505,
-          -0.8603790998458862,
-          -0.3456307053565979,
-          0.9292937517166138,
-          0.5074859261512756,
-          0.6310645937919617,
-          -0.3091641068458557,
-          0.46902573108673096,
-          0.7891915440559387,
-          0.4499550759792328,
-          0.2744995653629303,
-          0.2712305784225464,
-          -0.04349074140191078,
-          -0.3638863265514374,
-          0.7839881777763367,
-          0.7352104783058167,
-          -0.19457511603832245,
-          -0.5957832932472229,
-          -0.43704694509506226,
-          -1.084769368171692,
-          0.4904985725879669,
-          0.5385226011276245,
-          0.1891629993915558,
-          0.12338479608297348,
-          0.8315675258636475,
-          -0.07830192148685455,
-          1.0916285514831543,
-          -0.28066861629486084,
-          -1.3585069179534912,
-          0.5203898549079895,
-          0.08678033947944641,
-          -0.2566044330596924,
-          0.09484415501356123,
-          -0.0180208683013916,
-          1.0264745950698853,
-          -0.023572135716676712,
-          0.5864979028701782,
-          0.7625196576118469,
-          -0.2543414533138275,
-          -0.8877770900726318,
-          0.7611982822418213,
-          -0.06220436468720436,
-          0.937336564064026,
-          0.2704363465309143,
-          -0.37733694911003113,
-          0.5076137781143188,
-          -0.30641937255859375,
-          0.6252772808074951,
-          -0.0823579877614975,
-          -0.03736555948853493,
-          0.4131673276424408,
-          -0.6514252424240112,
-          0.12918265163898468,
-          -0.4483584463596344,
-          0.6750786304473877,
-          -0.37008383870124817,
-          -0.02324833907186985,
-          0.38027650117874146,
-          -0.26374951004981995,
-          0.4346931278705597,
-          0.42882832884788513,
-          -0.48798441886901855,
-          1.1882442235946655,
-          0.5132288336753845,
-          0.5284568667411804,
-          -0.03538886830210686,
-          0.29620853066444397,
-          -1.0683696269989014,
-          0.25936177372932434,
-          0.10404160618782043,
-          -0.25796034932136536,
-          0.027896970510482788,
-          -0.09225251525640488,
-          1.4811025857925415,
-          0.641173779964447,
-          -0.13838383555412292,
-          -0.3437179923057556,
-          0.5667019486427307,
-          -0.5400741696357727,
-          0.31090837717056274,
-          0.6470608115196228,
-          -0.3747067153453827,
-          -0.7364534735679626,
-          -0.07431528717279434,
-          0.5173454880714417,
-          -0.6578747034072876,
-          0.7107478976249695,
-          -0.7918999791145325,
-          -0.0648345872759819,
-          0.609937846660614,
-          -0.7329513430595398,
-          0.9741371870040894,
-          0.17912346124649048,
-          -0.02658769302070141,
-          0.5162150859832764,
-          -0.3978803157806397,
-          -0.7833885550498962,
-          -0.6497276425361633,
-          -0.3898126780986786,
-          -0.0952848568558693,
-          0.2663288116455078,
-          -0.1604052186012268,
-          0.373076468706131,
-          -0.8357769250869751,
-          -0.05217683315277099,
-          -0.2680160701274872,
-          0.8389158248901367,
-          0.6833611130714417,
-          -0.6712407469749451,
-          0.7406917214393616,
-          -0.44522786140441895,
-          -0.34645363688468933,
-          -0.27384576201438904,
-          -0.9878405928611756,
-          -0.8166060447692871,
-          0.06268279999494553,
-          0.38567957282066345,
-          -0.3274703919887543,
-          0.5296315550804138,
-          -0.11810623109340668,
-          0.23029841482639313,
-          0.08616159111261368,
-          -0.2195747196674347,
-          0.09430307894945145,
-          0.4057176411151886,
-          0.4892159104347229,
-          -0.1636916548013687,
-          -0.6071445345878601,
-          0.41256585717201233,
-          0.622254490852356,
-          -0.41223976016044617,
-          -0.6686707139015198,
-          -0.7474371790885925,
-          -0.8509522080421448,
-          -0.16754287481307983,
-          -0.9078601002693176,
-          -0.29653599858283997,
-          -0.5020652413368225,
-          0.4692700505256653,
-          0.01281109917908907,
-          -0.16071580350399017,
-          0.03388889133930206,
-          -0.020511148497462273,
-          0.5027827024459839,
-          -0.20729811489582065,
-          0.48107290267944336,
-          0.33669769763946533,
-          -0.5275911688804626,
-          0.48271527886390686,
-          0.2738940715789795,
-          -0.033152539283037186,
-          -0.13629786670207977,
-          -0.05965912342071533,
-          -0.26200807094573975,
-          0.04002794995903969,
-          -0.34095603227615356,
-          -3.986898899078369,
-          -0.46819332242012024,
-          -0.422744482755661,
-          -0.169097900390625,
-          0.6008929014205933,
-          0.058016058057546616,
-          -0.11401277780532836,
-          -0.3077819049358368,
-          -0.09595538675785063,
-          0.6723822355270386,
-          0.19367831945419312,
-          0.28304359316825867,
-          0.1609862744808197,
-          0.7567598819732666,
-          0.6889985799789429,
-          0.06907720118761063,
-          -0.04188092052936554,
-          -0.7434936165809631,
-          0.13321782648563385,
-          0.8456063270568848,
-          -0.10364038497209548,
-          -0.45084846019744873,
-          -0.4758241474628449,
-          0.43882066011428833,
-          -0.6432598829269409,
-          0.7217311859130859,
-          -0.24189773201942444,
-          0.12737572193145752,
-          -1.1008601188659668,
-          -0.3305315673351288,
-          0.14614742994308472,
-          -0.7819333076477051,
-          0.5287120342254639,
-          -0.055538054555654526,
-          0.1877404749393463,
-          -0.6907662153244019,
-          0.5616975426673889,
-          -0.4611121714115143,
-          -0.26109233498573303,
-          -0.12898315489292145,
-          -0.3724522292613983,
-          -0.7191406488418579,
-          -0.4425233602523804,
-          -0.644108235836029,
-          0.8424481153488159,
-          0.17532426118850708,
-          -0.5121750235557556,
-          -0.6467239260673523,
-          -0.0008507720194756985,
-          0.7866212129592896,
-          -0.02644744887948036,
-          -0.005045140627771616,
-          0.015782782807946205,
-          0.16334445774555206,
-          -0.1913367658853531,
-          -0.13697923719882965,
-          -0.6684983372688293,
-          0.18346354365348816,
-          -0.341105580329895,
-          0.5427411198616028,
-          0.3779832422733307,
-          -0.6778115034103394,
-          -0.2931850254535675,
-          -0.8805161714553833,
-          -0.4212774932384491,
-          -0.5368952751159668,
-          -1.3937891721725464,
-          -1.225494146347046,
-          0.4276703894138336,
-          1.1205668449401855,
-          -0.6005299687385559,
-          0.15732505917549133,
-          -0.3914784789085388,
-          -1.357046604156494,
-          -0.4707142114639282,
-          -0.1497287154197693,
-          -0.25035548210144043,
-          -0.34328439831733704,
-          0.39083412289619446,
-          0.1623048633337021,
-          -0.9275814294815063,
-          -0.6430015563964844,
-          0.2973862886428833,
-          0.5580436587333679,
-          -0.6232585310935974,
-          -0.6611042022705078,
-          0.4015969038009643,
-          -1.0232892036437988,
-          -0.2585645020008087,
-          -0.5431421399116516,
-          0.5021264553070068,
-          -0.48601630330085754,
-          -0.010242084041237833,
-          0.5862035155296326,
-          0.7316920161247253,
-          0.4036808013916016,
-          0.4269520044326782,
-          -0.705938458442688,
-          0.7747307419776917,
-          0.10164368897676468,
-          0.7887958884239197,
-          -0.9612497091293336,
-          0.12755516171455383,
-          0.06812842190265656,
-          -0.022603651508688927,
-          0.14722754061222076,
-          -0.5588505268096924,
-          -0.20689940452575684,
-          0.3557641804218292,
-          -0.6812759637832642,
-          0.2860803008079529,
-          -0.38954633474349976,
-          0.1759403496980667,
-          -0.5678874850273132,
-          -0.1692986786365509,
-          -0.14578519761562347,
-          0.5711379051208496,
-          1.0208125114440918,
-          0.7759483456611633,
-          -0.372348427772522,
-          -0.5460885763168335,
-          0.7190321683883667,
-          -0.6914990544319153,
-          0.13365162909030914,
-          -0.4854792356491089,
-          0.4054908752441406,
-          0.4502798914909363,
-          -0.3041122555732727,
-          -0.06726965308189392,
-          -0.05570871382951737,
-          -0.0455719493329525,
-          0.4785125255584717,
-          0.8867972493171692,
-          0.4107886850833893,
-          0.6121342182159424,
-          -0.20477132499217987,
-          -0.5598517656326294,
-          -0.6443566679954529,
-          -0.5905212759971619,
-          -0.5571200251579285,
-          0.17573799192905426,
-          -0.28621870279312134,
-          0.1685224026441574,
-          0.09719007462263109,
-          -0.04223639518022537,
-          -0.28623101115226746,
-          -0.1449810117483139,
-          -0.3789580464363098,
-          -0.5227636098861694,
-          -0.049728814512491226,
-          0.7849089503288269,
-          0.16792525351047516,
-          0.9849340915679932,
-          -0.6559549570083618,
-          0.35723909735679626,
-          -0.6822739243507385,
-          1.2873116731643677,
-          0.19993330538272855,
-          0.03512010723352432,
-          -0.6972134113311768,
-          0.18453484773635864,
-          -0.2437680810689926,
-          0.2156416028738022,
-          0.5230382680892944,
-          0.22020135819911957,
-          0.8314080238342285,
-          0.15627102553844452,
-          -0.7330264449119568,
-          0.3888184726238251,
-          -0.22034703195095065,
-          0.5457669496536255,
-          -0.48084837198257446,
-          -0.45576658844947815,
-          -0.09287727624177931,
-          -0.06968110054731369,
-          0.35125672817230225,
-          -0.4278119504451752,
-          0.2038476765155792,
-          0.11392722278833388,
-          0.9433983564376832,
-          -0.4097744226455689,
-          0.035297419875860214,
-          -0.4274404048919678,
-          -0.25100165605545044,
-          1.0943366289138794,
-          -0.07634022831916809,
-          -0.2925529479980469,
-          -0.7512530088424683,
-          0.2649727463722229,
-          -0.4078235328197479,
-          -0.3372223973274231,
-          0.05190162733197212,
-          0.005654910113662481,
-          -0.0001571219472680241,
-          -0.35445958375930786,
-          -0.7837416529655457,
-          0.1500556766986847,
-          0.4383024573326111,
-          0.6099548935890198,
-          0.05951934307813645,
-          -0.21325334906578064,
-          0.0199207104742527,
-          -0.22704418003559113,
-          -0.6481077671051025,
-          0.37442275881767273,
-          -1.015955924987793,
-          0.38637226819992065,
-          -0.06489371508359909,
-          -0.494120329618454,
-          0.3469836115837097,
-          0.15402406454086304,
-          -0.7660972476005554,
-          -0.7053225040435791,
-          -0.25964751839637756,
-          0.014004424214363098,
-          -0.2860170006752014,
-          -0.17565494775772095,
-          -0.45117494463920593,
-          -0.0031954257283359766,
-          0.09676837921142578,
-          -0.514464259147644,
-          0.41698193550109863,
-          -0.21642713248729703,
-          -0.5398141145706177,
-          -0.3647628426551819,
-          0.37005379796028137,
-          0.239425927400589,
-          -0.08833975344896317,
-          0.934946596622467,
-          -0.48340797424316406,
-          0.6241437792778015,
-          -0.7253676652908325,
-          -0.04303571209311485,
-          1.1125205755233765,
-          -0.15692919492721558,
-          -0.2914651036262512,
-          -0.5117168426513672,
-          0.21365483105182648,
-          0.4924402534961701,
-          0.5269662141799927,
-          0.0352792888879776,
-          -0.149167999625206,
-          -0.6019760370254517,
-          0.08245442807674408,
-          0.4900692105293274,
-          0.518824577331543,
-          -0.00005570516441366635,
-          -0.553304135799408,
-          0.22217543423175812,
-          0.5047767758369446,
-          0.135724738240242,
-          1.1511540412902832,
-          -0.3541218340396881,
-          -0.9712511897087096,
-          0.8353699445724487,
-          -0.39227569103240967,
-          -0.9117669463157654,
-          -0.26349931955337524,
-          0.05597023293375969,
-          0.20695461332798004,
-          0.3178807199001312,
-          1.0663238763809204,
-          0.5062212347984314,
-          0.7288597822189331,
-          0.09899299591779707,
-          0.553720235824585,
-          0.675009548664093,
-          -0.20067055523395536,
-          0.3138423264026642,
-          -0.6886593103408813,
-          -0.2910398542881012,
-          -1.3186300992965698,
-          -0.4684459865093231,
-          -0.095743365585804,
-          -0.1257995069026947,
-          -0.4858281314373016,
-          -0.4935407340526581,
-          -0.3266896903514862,
-          -0.3928797245025635,
-          -0.40803104639053345,
-          -0.9975396394729614,
-          0.4229583740234375,
-          0.37309643626213074,
-          0.4431034922599793,
-          0.30364808440208435,
-          -0.3765178918838501,
-          0.5616499185562134,
-          0.16904796659946442,
-          -0.7343707084655762,
-          0.2560209631919861,
-          0.6166825294494629,
-          0.3200829327106476,
-          -0.4483652710914612,
-          0.16224201023578644,
-          -0.31495288014411926,
-          -0.42713335156440735,
-          0.7270734906196594,
-          0.7049484848976135,
-          -0.0571461021900177,
-          0.04477125033736229,
-          -0.6647796034812927,
-          1.183672308921814,
-          0.36199676990509033,
-          0.046881116926670074,
-          0.4515796303749085,
-          0.9278061985969543,
-          0.31471705436706543,
-          -0.7073333859443665,
-          -0.3443860113620758,
-          0.5440067052841187,
-          -0.15020819008350372,
-          -0.541202962398529,
-          0.5203295946121216,
-          1.2192286252975464,
-          -0.9983593225479126,
-          -0.18758884072303772,
-          0.2758221924304962,
-          -0.6511523723602295,
-          -0.1584404855966568,
-          -0.236241415143013,
-          0.2692437767982483,
-          -0.4941152036190033,
-          0.4987454116344452,
-          -0.3331359028816223,
-          0.3163745701313019,
-          0.745529294013977,
-          -0.2905873656272888,
-          0.13602906465530396,
-          0.4679684340953827,
-          1.0555986166000366,
-          1.075700044631958,
-          0.5368486046791077,
-          -0.5118206739425659,
-          0.8668332099914551,
-          -0.5726966857910156,
-          -0.7811751961708069,
-          0.1938626915216446,
-          -0.1929349899291992,
-          0.1757766306400299,
-          0.6384295225143433,
-          0.26462844014167786,
-          0.9542630314826964,
-          0.19313029944896695,
-          1.264248013496399,
-          -0.6304428577423096,
-          0.0487106591463089,
-          -0.16211535036563873,
-          -0.7894763350486755,
-          0.3582514822483063,
-          -0.04153040423989296,
-          0.635784387588501,
-          0.6554391980171204,
-          -0.47010496258735657,
-          -0.8302040696144104,
-          -0.1350124627351761,
-          0.2568812072277069,
-          0.13614831864833832,
-          -0.2563649117946625,
-          -1.0434694290161133,
-          0.3232482671737671,
-          0.47882452607154846,
-          0.4298652410507202,
-          1.0563770532608032,
-          -0.28917592763900757,
-          -0.8533256649971008,
-          0.10648339986801147,
-          0.6376127004623413,
-          -0.20832888782024384,
-          0.2370245456695557,
-          0.0018312990432605147,
-          -0.2034837007522583,
-          0.01051164511591196,
-          -1.105310082435608,
-          0.29724350571632385,
-          0.15604574978351593,
-          0.1973688006401062,
-          0.44394731521606445,
-          0.3974513411521912,
-          -0.13625948131084442,
-          0.9571986198425292,
-          0.2257384955883026,
-          0.2323588728904724,
-          -0.5583669543266296,
-          -0.7854922413825989,
-          0.1647188365459442,
-          -1.6098142862319946,
-          0.318587988615036,
-          -0.13399995863437653,
-          -0.2172701060771942,
-          -0.767514705657959,
-          -0.5813586711883545,
-          -0.3195130527019501,
-          -0.04894036799669266,
-          0.2929930090904236,
-          -0.8213384747505188,
-          0.07181350141763687,
-          0.7469993829727173,
-          0.6407455801963806,
-          0.16365697979927063,
-          0.7870153188705444,
-          0.6524736881256104,
-          0.6399973630905151,
-          -0.04992736503481865,
-          -0.03959266096353531,
-          -0.2512352466583252,
-          0.8448855876922607,
-          -0.1422702670097351,
-          0.1216789186000824,
-          -1.2647287845611572,
-          0.5931149125099182,
-          0.7186052203178406,
-          -0.06118432432413101,
-          -1.1942816972732544,
-          -0.17677085101604462,
-          0.31543800234794617,
-          -0.32252824306488037,
-          0.8255583047866821,
-          -0.14529970288276672,
-          -0.2695446312427521,
-          -0.33378756046295166,
-          -0.1653425395488739,
-          0.1454019844532013,
-          -0.3920115828514099,
-          0.912214994430542,
-          -0.7279734015464783,
-          0.7374742031097412,
-          0.933980405330658,
-          0.13429680466651917,
-          -0.514870285987854,
-          0.3989711999893189,
-          -0.11613689363002776,
-          0.4022413492202759,
-          -0.9990655779838562,
-          -0.33749932050704956,
-          -0.4334589838981629,
-          -1.376373291015625,
-          -0.2993924915790558,
-          -0.09454808384180068,
-          -0.01314175222069025,
-          -0.001090060803107917,
-          0.2137461006641388,
-          0.2938512861728668,
-          0.17508235573768616,
-          0.8260607123374939,
-          -0.7218498587608337,
-          0.2414487451314926,
-          -0.47296759486198425,
-          -0.3002610504627228,
-          -1.238540768623352,
-          0.08663805574178696,
-          0.6805586218833923,
-          0.5909030437469482,
-          -0.42807504534721375,
-          -0.22887496650218964,
-          0.47537800669670105,
-          -1.0474627017974854,
-          0.6338009238243103,
-          0.06548397243022919,
-          0.4971011281013489,
-          1.3484878540039063
-        ]
-      ],
-      "regenerate": true
-    }
-  }
-}

crates/dump/src/reader/snapshots/dump__reader__test__import_dump_v6_with_vectors-8.snap

@@ -1,785 +0,0 @@
----
-source: dump/src/reader/mod.rs
-expression: document
----
-{
-  "id": "e1",
-  "desc": "natural vector",
-  "_vectors": {
-    "default": {
-      "embeddings": [
-        [
-          -0.2979458272457123,
-          -0.5288640856742859,
-          -0.019957859069108963,
-          -0.18495318293571472,
-          0.7429973483085632,
-          0.5238497257232666,
-          0.432366281747818,
-          0.32744166254997253,
-          0.0020762972999364138,
-          -0.9507834911346436,
-          -0.35097137093544006,
-          0.08469701558351517,
-          -1.4176613092422483,
-          0.4647577106952667,
-          -0.69340580701828,
-          1.0372896194458008,
-          0.3716741800308227,
-          0.06031008064746857,
-          -0.6152024269104004,
-          0.007914665155112743,
-          0.7954924702644348,
-          -0.20773003995418549,
-          0.09376765787601472,
-          0.04508133605122566,
-          -0.2084471583366394,
-          -0.1518009901046753,
-          0.018195509910583496,
-          -0.07044368237257004,
-          -0.18119366466999057,
-          -0.4480230510234833,
-          0.3822529911994934,
-          0.1911812424659729,
-          0.4674372375011444,
-          0.06963984668254852,
-          -0.09341949224472046,
-          0.005675444379448891,
-          -0.6774799227714539,
-          -0.7066726684570313,
-          -0.39256376028060913,
-          0.04005039855837822,
-          0.2084812968969345,
-          -0.7872875928878784,
-          -0.8205880522727966,
-          0.2919981777667999,
-          -0.06004738807678223,
-          -0.4907574355602264,
-          -1.5937862396240234,
-          0.24249385297298431,
-          -0.14709846675395966,
-          -0.11860740929841997,
-          -0.8299489617347717,
-          0.472964346408844,
-          -0.497518390417099,
-          -0.22205302119255063,
-          -0.4196169078350067,
-          0.32697558403015137,
-          -0.360930860042572,
-          -0.9789686799049376,
-          0.1887447088956833,
-          -0.403737336397171,
-          0.18524253368377688,
-          0.3768732249736786,
-          0.3666233420372009,
-          0.3511938452720642,
-          0.6985810995101929,
-          0.41721710562705994,
-          0.09754953533411026,
-          0.6204307079315186,
-          -1.0762996673583984,
-          -0.06263761967420578,
-          -0.7376511693000793,
-          0.6849768161773682,
-          -0.1745152473449707,
-          -0.40449759364128113,
-          0.20757411420345304,
-          -0.8424443006515503,
-          0.330015629529953,
-          0.3489064872264862,
-          1.0954371690750122,
-          0.8487558960914612,
-          1.1076823472976685,
-          0.61430823802948,
-          0.4155903458595276,
-          0.4111340939998626,
-          0.05753209814429283,
-          -0.06429877132177353,
-          -0.765606164932251,
-          -0.41703930497169495,
-          -0.508820652961731,
-          0.19859947264194489,
-          -0.16607828438282013,
-          -0.28112146258354187,
-          0.11032675206661224,
-          0.38809511065483093,
-          -0.36498191952705383,
-          -0.48671194911003113,
-          0.6755134463310242,
-          0.03958442434668541,
-          0.4478721618652344,
-          -0.10335399955511092,
-          -0.9546685814857484,
-          -0.6087718605995178,
-          0.17498846352100372,
-          0.08320838958024979,
-          -1.4478336572647097,
-          -0.605027437210083,
-          -0.5867993235588074,
-          -0.14711688458919525,
-          -0.5447602272033691,
-          -0.026259321719408035,
-          -0.6997418403625488,
-          -0.07349082082509995,
-          0.10638900846242905,
-          -0.7133527398109436,
-          -0.9396815299987792,
-          1.087092399597168,
-          1.1885089874267578,
-          0.4011896848678589,
-          -0.4089202582836151,
-          -0.10938972979784012,
-          0.6726722121238708,
-          0.24576938152313232,
-          -0.24247920513153076,
-          1.1499971151351929,
-          0.47813335061073303,
-          -0.05331678315997124,
-          0.32338133454322815,
-          0.4870913326740265,
-          -0.23144258558750153,
-          -1.2023426294326782,
-          0.2349330335855484,
-          1.080536961555481,
-          0.29334118962287903,
-          0.391574501991272,
-          -0.15818795561790466,
-          -0.2948290705680847,
-          -0.024689948186278343,
-          0.06602869182825089,
-          0.5937030911445618,
-          -0.047901444137096405,
-          -0.512734591960907,
-          -0.35780075192451477,
-          0.28751692175865173,
-          0.4298716187477112,
-          0.9242428541183472,
-          -0.17208744585514069,
-          0.11515070497989656,
-          -0.0335976779460907,
-          -0.3422986567020416,
-          0.5344581604003906,
-          0.19895796477794647,
-          0.33001241087913513,
-          0.6390730142593384,
-          -0.6074934005737305,
-          -0.2553696632385254,
-          0.9644920229911804,
-          0.2699219584465027,
-          0.6403993368148804,
-          -0.6380003690719604,
-          -0.027310986071825027,
-          0.638815701007843,
-          0.27719101309776306,
-          -0.13553589582443237,
-          0.750195324420929,
-          0.1224869191646576,
-          -0.20613941550254825,
-          0.8444448709487915,
-          0.16200250387191772,
-          -0.24750925600528717,
-          -0.739950954914093,
-          -0.28443849086761475,
-          -1.176282525062561,
-          0.516107976436615,
-          0.3774825632572174,
-          0.10906043648719788,
-          0.07962015271186829,
-          0.7384604215621948,
-          -0.051241904497146606,
-          1.1730090379714966,
-          -0.4828610122203827,
-          -1.404372215270996,
-          0.8811132311820984,
-          -0.3839482367038727,
-          0.022516896948218346,
-          -0.0491158664226532,
-          -0.43027013540267944,
-          1.2049334049224854,
-          -0.27309560775756836,
-          0.6883630752563477,
-          0.8264574408531189,
-          -0.5020735263824463,
-          -0.4874092042446137,
-          0.6007202863693237,
-          -0.4965405762195587,
-          1.1302915811538696,
-          0.032572727650403976,
-          -0.3731859028339386,
-          0.658271849155426,
-          -0.9023059010505676,
-          0.7400162220001221,
-          0.014550759457051754,
-          -0.19699542224407196,
-          0.2319706380367279,
-          -0.789058268070221,
-          -0.14905710518360138,
-          -0.5826214551925659,
-          0.207652747631073,
-          -0.4507439732551574,
-          -0.3163885474205017,
-          0.3604124188423157,
-          -0.45119962096214294,
-          0.3428427278995514,
-          0.3005594313144684,
-          -0.36026081442832947,
-          1.1014249324798584,
-          0.40884315967559814,
-          0.34991952776908875,
-          -0.1806638240814209,
-          0.27440476417541504,
-          -0.7118373513221741,
-          0.4645499587059021,
-          0.214790478348732,
-          -0.2343102991580963,
-          0.10500429570674896,
-          -0.28034430742263794,
-          1.2267805337905884,
-          1.0561333894729614,
-          -0.497364342212677,
-          -0.6143305897712708,
-          0.24963727593421936,
-          -0.33136463165283203,
-          -0.01473914459347725,
-          0.495918869972229,
-          -0.6985538005828857,
-          -1.0033197402954102,
-          0.35937801003456116,
-          0.6325868368148804,
-          -0.6808838844299316,
-          1.0354058742523191,
-          -0.7214401960372925,
-          -0.33318862318992615,
-          0.874398410320282,
-          -0.6594992280006409,
-          0.6830640435218811,
-          -0.18534131348133087,
-          0.024834271520376205,
-          0.19901277124881744,
-          -0.5992477536201477,
-          -1.2126628160476685,
-          -0.9245557188987732,
-          -0.3898217976093292,
-          -0.1286519467830658,
-          0.4217943847179413,
-          -0.1143646091222763,
-          0.5630772709846497,
-          -0.5240639448165894,
-          0.21152715384960177,
-          -0.3792001008987427,
-          0.8266305327415466,
-          1.170984387397766,
-          -0.8072142004966736,
-          0.11382893472909927,
-          -0.17953898012638092,
-          -0.1789460331201553,
-          -0.15078622102737427,
-          -1.2082908153533936,
-          -0.7812382578849792,
-          -0.10903695970773696,
-          0.7303897142410278,
-          -0.39054441452026367,
-          0.19511254131793976,
-          -0.09121843427419662,
-          0.22400228679180145,
-          0.30143046379089355,
-          0.1141919493675232,
-          0.48112115263938904,
-          0.7307931780815125,
-          0.09701362252235413,
-          -0.2795647978782654,
-          -0.3997688889503479,
-          0.5540812611579895,
-          0.564578115940094,
-          -0.40065160393714905,
-          -0.3629159033298493,
-          -0.3789091110229492,
-          -0.7298538088798523,
-          -0.6996853351593018,
-          -0.4477842152118683,
-          -0.289089560508728,
-          -0.6430277824401855,
-          0.2344944179058075,
-          0.3742927014827728,
-          -0.5079357028007507,
-          0.28841453790664673,
-          0.06515737622976303,
-          0.707315981388092,
-          0.09498685598373412,
-          0.8365515470504761,
-          0.10002726316452026,
-          -0.7695478200912476,
-          0.6264724135398865,
-          0.7562043070793152,
-          -0.23112858831882477,
-          -0.2871039807796478,
-          -0.25010058283805847,
-          0.2783474028110504,
-          -0.03224996477365494,
-          -0.9119359850883484,
-          -3.6940200328826904,
-          -0.5099936127662659,
-          -0.1604711413383484,
-          0.17453284561634064,
-          0.41759559512138367,
-          0.1419190913438797,
-          -0.11362407356500626,
-          -0.33312007784843445,
-          0.11511333286762238,
-          0.4667884409427643,
-          -0.0031647447030991316,
-          0.15879854559898376,
-          0.3042248487472534,
-          0.5404849052429199,
-          0.8515422344207764,
-          0.06286454200744629,
-          0.43790125846862793,
-          -0.8682025074958801,
-          -0.06363756954669952,
-          0.5547921657562256,
-          -0.01483887154608965,
-          -0.07361344993114471,
-          -0.929947018623352,
-          0.3502565622329712,
-          -0.5080993175506592,
-          1.0380364656448364,
-          -0.2017953395843506,
-          0.21319580078125,
-          -1.0763001441955566,
-          -0.556368887424469,
-          0.1949922740459442,
-          -0.6445739269256592,
-          0.6791343688964844,
-          0.21188358962535855,
-          0.3736183941364288,
-          -0.21800459921360016,
-          0.7597446441650391,
-          -0.3732394874095917,
-          -0.4710160195827484,
-          0.025146087631583217,
-          0.05341297015547752,
-          -0.9522109627723694,
-          -0.6000866889953613,
-          -0.08469046652317047,
-          0.5966026186943054,
-          0.3444081246852875,
-          -0.461188405752182,
-          -0.5279349088668823,
-          0.10296865552663804,
-          0.5175143480300903,
-          -0.20671147108078003,
-          0.13392412662506104,
-          0.4812754988670349,
-          0.2993808686733246,
-          -0.3005635440349579,
-          0.5141698122024536,
-          -0.6239235401153564,
-          0.2877119481563568,
-          -0.4452739953994751,
-          0.5621107816696167,
-          0.5047508478164673,
-          -0.4226335883140564,
-          -0.18578553199768064,
-          -1.1967322826385498,
-          0.28178197145462036,
-          -0.8692031502723694,
-          -1.1812998056411743,
-          -1.4526212215423584,
-          0.4645712077617645,
-          0.9327932000160216,
-          -0.6560136675834656,
-          0.461549699306488,
-          -0.5621527433395386,
-          -1.328449010848999,
-          -0.08676894754171371,
-          0.00021918353741057217,
-          -0.18864136934280396,
-          0.1259666532278061,
-          0.18240638077259064,
-          -0.14919660985469818,
-          -0.8965857625007629,
-          -0.7539900541305542,
-          0.013973715715110302,
-          0.504276692867279,
-          -0.704748272895813,
-          -0.6428424119949341,
-          0.6303996443748474,
-          -0.5404738187789917,
-          -0.31176653504371643,
-          -0.21262824535369873,
-          0.18736739456653595,
-          -0.7998970746994019,
-          0.039946746081113815,
-          0.7390344738960266,
-          0.4283199906349182,
-          0.3795057237148285,
-          0.07204607129096985,
-          -0.9230587482452391,
-          0.9440426230430604,
-          0.26272690296173096,
-          0.5598306655883789,
-          -1.0520871877670288,
-          -0.2677186131477356,
-          -0.1888762265443802,
-          0.30426350235939026,
-          0.4746131896972656,
-          -0.5746733546257019,
-          -0.4197768568992615,
-          0.8565112948417664,
-          -0.6767723560333252,
-          0.23448683321475983,
-          -0.2010004222393036,
-          0.4112907350063324,
-          -0.6497949957847595,
-          -0.418667733669281,
-          -0.4950824975967407,
-          0.44438859820365906,
-          1.026281714439392,
-          0.482397586107254,
-          -0.26220494508743286,
-          -0.3640787005424499,
-          0.5907743573188782,
-          -0.8771642446517944,
-          0.09708411991596222,
-          -0.3671700060367584,
-          0.4331349730491638,
-          0.619417667388916,
-          -0.2684665620326996,
-          -0.5123821496963501,
-          -0.1502324342727661,
-          -0.012190685607492924,
-          0.3580845892429352,
-          0.8617186546325684,
-          0.3493645489215851,
-          1.0270192623138428,
-          0.18297909200191495,
-          -0.5881339311599731,
-          -0.1733516901731491,
-          -0.5040576457977295,
-          -0.340370237827301,
-          -0.26767754554748535,
-          -0.28570041060447693,
-          -0.032928116619586945,
-          0.6029254794120789,
-          0.17397655546665192,
-          0.09346921741962431,
-          0.27815181016921997,
-          -0.46699589490890503,
-          -0.8148876428604126,
-          -0.3964351713657379,
-          0.3812595009803772,
-          0.13547226786613464,
-          0.7126688361167908,
-          -0.3473474085330963,
-          -0.06573959439992905,
-          -0.6483767032623291,
-          1.4808889627456665,
-          0.30924928188323975,
-          -0.5085946917533875,
-          -0.8613000512123108,
-          0.3048902451992035,
-          -0.4241599142551422,
-          0.15909206867218018,
-          0.5764641761779785,
-          -0.07879110425710678,
-          1.015336513519287,
-          0.07599356025457382,
-          -0.7025855779647827,
-          0.30047643184661865,
-          -0.35094937682151794,
-          0.2522146999835968,
-          -0.2338722199201584,
-          -0.8326804637908936,
-          -0.13695412874221802,
-          -0.03452421352267265,
-          0.47974953055381775,
-          -0.18385636806488037,
-          0.32438594102859497,
-          0.1797013282775879,
-          0.787494957447052,
-          -0.12579888105392456,
-          -0.07507286965847015,
-          -0.4389670491218567,
-          0.2720070779323578,
-          0.8138866424560547,
-          0.01974171027541161,
-          -0.3057698905467987,
-          -0.6709924936294556,
-          0.0885881632566452,
-          -0.2862754464149475,
-          0.03475658595561981,
-          -0.1285519152879715,
-          0.3838353455066681,
-          -0.2944154739379883,
-          -0.4204859137535095,
-          -0.4416137933731079,
-          0.13426260650157928,
-          0.36733248829841614,
-          0.573428750038147,
-          -0.14928072690963745,
-          -0.026076916605234143,
-          0.33286052942276,
-          -0.5340145826339722,
-          -0.17279052734375,
-          -0.01154550164937973,
-          -0.6620771884918213,
-          0.18390542268753052,
-          -0.08265615254640579,
-          -0.2489682286977768,
-          0.2429984211921692,
-          -0.044153645634651184,
-          -0.986578404903412,
-          -0.33574509620666504,
-          -0.5387663841247559,
-          0.19767941534519196,
-          0.12540718913078308,
-          -0.3403128981590271,
-          -0.4154576361179352,
-          0.17275673151016235,
-          0.09407442808151244,
-          -0.5414086580276489,
-          0.4393929839134216,
-          0.1725579798221588,
-          -0.4998118281364441,
-          -0.6926208138465881,
-          0.16552448272705078,
-          0.6659538149833679,
-          -0.10949844866991044,
-          0.986426830291748,
-          0.01748848147690296,
-          0.4003709554672241,
-          -0.5430638194084167,
-          0.35347291827201843,
-          0.6887399554252625,
-          0.08274628221988678,
-          0.13407137989997864,
-          -0.591465950012207,
-          0.3446292281150818,
-          0.6069018244743347,
-          0.1935492902994156,
-          -0.0989871397614479,
-          0.07008486241102219,
-          -0.8503749370574951,
-          -0.09507356584072112,
-          0.6259510517120361,
-          0.13934025168418884,
-          0.06392545253038406,
-          -0.4112265408039093,
-          -0.08475656062364578,
-          0.4974113404750824,
-          -0.30606114864349365,
-          1.111435890197754,
-          -0.018766529858112335,
-          -0.8422622680664063,
-          0.4325508773326874,
-          -0.2832120656967163,
-          -0.4859798848628998,
-          -0.41498348116874695,
-          0.015977520495653152,
-          0.5292825698852539,
-          0.4538311660289765,
-          1.1328668594360352,
-          0.22632671892642975,
-          0.7918671369552612,
-          0.33401933312416077,
-          0.7306135296821594,
-          0.3548600673675537,
-          0.12506209313869476,
-          0.8573207855224609,
-          -0.5818327069282532,
-          -0.6953738927841187,
-          -1.6171947717666626,
-          -0.1699674427509308,
-          0.6318262815475464,
-          -0.05671752244234085,
-          -0.28145185112953186,
-          -0.3976689279079437,
-          -0.2041076272726059,
-          -0.5495951175689697,
-          -0.5152917504310608,
-          -0.9309796094894408,
-          0.101932130753994,
-          0.1367802917957306,
-          0.1490798443555832,
-          0.5304336547851563,
-          -0.5082434415817261,
-          0.06688683480024338,
-          0.14657628536224365,
-          -0.782435953617096,
-          0.2962816655635834,
-          0.6965363621711731,
-          0.8496337532997131,
-          -0.3042965829372406,
-          0.04343798756599426,
-          0.0330701619386673,
-          -0.5662598013877869,
-          1.1086925268173218,
-          0.756072998046875,
-          -0.204134538769722,
-          0.2404300570487976,
-          -0.47848284244537354,
-          1.3659011125564575,
-          0.5645433068275452,
-          -0.15836156904697418,
-          0.43395575881004333,
-          0.5944653749465942,
-          1.0043466091156006,
-          -0.49446743726730347,
-          -0.5954391360282898,
-          0.5341240763664246,
-          0.020598189905285835,
-          -0.4036853015422821,
-          0.4473709762096405,
-          1.1998231410980225,
-          -0.9317775368690492,
-          -0.23321466147899628,
-          0.2052552700042725,
-          -0.7423108816146851,
-          -0.19917210936546328,
-          -0.1722569614648819,
-          -0.034072667360305786,
-          -0.00671181408688426,
-          0.46396249532699585,
-          -0.1372445821762085,
-          0.053376372903585434,
-          0.7392690777778625,
-          -0.38447609543800354,
-          0.07497968524694443,
-          0.5197252631187439,
-          1.3746477365493774,
-          0.9060075879096984,
-          0.20000585913658145,
-          -0.4053704142570496,
-          0.7497360110282898,
-          -0.34087055921554565,
-          -1.101803183555603,
-          0.273650586605072,
-          -0.5125769376754761,
-          0.22472351789474487,
-          0.480757474899292,
-          -0.19845178723335263,
-          0.8857700824737549,
-          0.30752456188201904,
-          1.1109285354614258,
-          -0.6768012642860413,
-          0.524367094039917,
-          -0.22495046257972717,
-          -0.4224412739276886,
-          0.40753406286239624,
-          -0.23133376240730288,
-          0.3297771215438843,
-          0.4905449151992798,
-          -0.6813114285469055,
-          -0.7543983459472656,
-          -0.5599071383476257,
-          0.14351597428321838,
-          -0.029278717935085297,
-          -0.3970443606376648,
-          -0.303079217672348,
-          0.24161772429943085,
-          0.008353390730917454,
-          -0.0062365154735744,
-          1.0824860334396362,
-          -0.3704061508178711,
-          -1.0337258577346802,
-          0.04638749733567238,
-          1.163011074066162,
-          -0.31737643480300903,
-          0.013986887410283089,
-          0.19223114848136905,
-          -0.2260770797729492,
-          -0.210910826921463,
-          -1.0191949605941772,
-          0.22356095910072327,
-          0.09353553503751756,
-          0.18096882104873657,
-          0.14867214858531952,
-          0.43408671021461487,
-          -0.33312076330184937,
-          0.8173948526382446,
-          0.6428242921829224,
-          0.20215003192424777,
-          -0.6634518504142761,
-          -0.4132290482521057,
-          0.29815030097961426,
-          -1.579406976699829,
-          -0.0981958732008934,
-          -0.03941014781594277,
-          0.1709178239107132,
-          -0.5481140613555908,
-          -0.5338194966316223,
-          -0.3528362512588501,
-          -0.11561278253793716,
-          -0.21793591976165771,
-          -1.1570470333099363,
-          0.2157980799674988,
-          0.42083489894866943,
-          0.9639263153076172,
-          0.09747201204299928,
-          0.15671424567699432,
-          0.4034591615200043,
-          0.6728067994117737,
-          -0.5216875672340393,
-          0.09657668322324751,
-          -0.2416689097881317,
-          0.747975766658783,
-          0.1021689772605896,
-          0.11652665585279463,
-          -1.0484966039657593,
-          0.8489304780960083,
-          0.7169828414916992,
-          -0.09012343734502792,
-          -1.3173753023147583,
-          0.057890523225069046,
-          -0.006231260951608419,
-          -0.1018214002251625,
-          0.936040461063385,
-          -0.0502331368625164,
-          -0.4284322261810303,
-          -0.38209280371665955,
-          -0.22668412327766416,
-          0.0782942995429039,
-          -0.4881664514541626,
-          0.9268959760665894,
-          0.001867273123934865,
-          0.42261114716529846,
-          0.8283362984657288,
-          0.4256294071674347,
-          -0.7965338826179504,
-          0.4840078353881836,
-          -0.19861412048339844,
-          0.33977967500686646,
-          -0.4604192078113556,
-          -0.3107339143753052,
-          -0.2839638590812683,
-          -1.5734281539916992,
-          0.005220232997089624,
-          0.09239906817674635,
-          -0.7828494906425476,
-          -0.1397123783826828,
-          0.2576255202293396,
-          0.21372435986995697,
-          -0.23169949650764465,
-          0.4016408920288086,
-          -0.462497353553772,
-          -0.2186472862958908,
-          -0.5617868900299072,
-          -0.3649831712245941,
-          -1.1585862636566162,
-          -0.08222806453704834,
-          0.931126832962036,
-          0.4327389597892761,
-          -0.46451422572135925,
-          -0.5430706143379211,
-          -0.27434298396110535,
-          -0.9479129314422609,
-          0.1845661848783493,
-          0.3972720205783844,
-          0.4883299469947815,
-          1.04031240940094
-        ]
-      ],
-      "regenerate": true
-    }
-  }
-}

crates/dump/src/reader/snapshots/dump__reader__test__import_dump_v6_with_vectors-9.snap

@@ -1,780 +0,0 @@
----
-source: dump/src/reader/mod.rs
-expression: document
----
-{
-  "id": "e0",
-  "desc": "overriden vector",
-  "_vectors": {
-    "default": [
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1
-    ]
-  }
-}

crates/index-scheduler/src/snapshots/index_scheduler__tests__import_vectors-15.snap

@@ -1,15 +0,0 @@
----
-source: index-scheduler/src/lib.rs
-expression: doc
----
-{
-  "doggo": "Intel",
-  "breed": "beagle",
-  "_vectors": {
-    "noise": [
-      0.1,
-      0.2,
-      0.3
-    ]
-  }
-}

crates/index-scheduler/src/snapshots/index_scheduler__tests__import_vectors-2.snap

@@ -1,22 +0,0 @@
----
-source: index-scheduler/src/lib.rs
-expression: task.details
----
-{
-  "embedders": {
-    "A_fakerest": {
-      "source": "rest",
-      "apiKey": "MyXXXX...",
-      "dimensions": 384,
-      "url": "http://localhost:7777",
-      "request": "{{text}}",
-      "response": "{{embedding}}"
-    },
-    "B_small_hf": {
-      "source": "huggingFace",
-      "model": "sentence-transformers/all-MiniLM-L6-v2",
-      "revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
-      "documentTemplate": "{{doc.doggo}} the {{doc.breed}} best doggo"
-    }
-  }
-}

crates/index-scheduler/src/snapshots/index_scheduler__tests__import_vectors-22.snap

@@ -1,15 +0,0 @@
----
-source: index-scheduler/src/lib.rs
-expression: doc
----
-{
-  "doggo": "kefir",
-  "breed": "patou",
-  "_vectors": {
-    "noise": [
-      0.1,
-      0.2,
-      0.3
-    ]
-  }
-}

crates/index-scheduler/src/snapshots/index_scheduler__tests__import_vectors-5.snap

@@ -1,15 +0,0 @@
----
-source: index-scheduler/src/lib.rs
-expression: fakerest_config.embedder_options
----
-{
-  "Rest": {
-    "api_key": "My super secret",
-    "distribution": null,
-    "dimensions": 384,
-    "url": "http://localhost:7777",
-    "request": "{{text}}",
-    "response": "{{embedding}}",
-    "headers": {}
-  }
-}

crates/index-scheduler/src/snapshots/index_scheduler__tests__import_vectors-8.snap

@@ -1,11 +0,0 @@
----
-source: index-scheduler/src/lib.rs
-expression: simple_hf_config.embedder_options
----
-{
-  "HuggingFace": {
-    "model": "sentence-transformers/all-MiniLM-L6-v2",
-    "revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
-    "distribution": null
-  }
-}

crates/index-scheduler/src/snapshots/index_scheduler__tests__import_vectors.snap

@@ -1,22 +0,0 @@
----
-source: index-scheduler/src/lib.rs
-expression: task.details
----
-{
-  "embedders": {
-    "A_fakerest": {
-      "source": "rest",
-      "apiKey": "MyXXXX...",
-      "dimensions": 384,
-      "url": "http://localhost:7777",
-      "request": "{{text}}",
-      "response": "{{embedding}}"
-    },
-    "B_small_hf": {
-      "source": "huggingFace",
-      "model": "sentence-transformers/all-MiniLM-L6-v2",
-      "revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
-      "documentTemplate": "{{doc.doggo}} the {{doc.breed}} best doggo"
-    }
-  }
-}

crates/index-scheduler/src/snapshots/index_scheduler__tests__settings_update-5.snap

@@ -1,15 +0,0 @@
----
-source: index-scheduler/src/lib.rs
-expression: config.embedder_options
----
-{
-  "Rest": {
-    "api_key": "My super secret",
-    "distribution": null,
-    "dimensions": 4,
-    "url": "http://localhost:7777",
-    "request": "{{text}}",
-    "response": "{{embedding}}",
-    "headers": {}
-  }
-}

crates/index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_document_deletion/after_adding_the_documents.snap

@@ -1,44 +0,0 @@
----
-source: index-scheduler/src/lib.rs
----
-### Autobatching Enabled = true
-### Processing Tasks:
-[]
-----------------------------------------------------------------------
-### All Tasks:
-0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
-1 {uid: 1, status: succeeded, details: { received_documents: 3, indexed_documents: Some(3) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
-----------------------------------------------------------------------
-### Status:
-enqueued []
-succeeded [0,1,]
-----------------------------------------------------------------------
-### Kind:
-"documentAdditionOrUpdate" [1,]
-"settingsUpdate" [0,]
-----------------------------------------------------------------------
-### Index Tasks:
-doggos [0,1,]
-----------------------------------------------------------------------
-### Index Mapper:
-doggos: { number_of_documents: 3, field_distribution: {"catto": 1, "doggo": 2, "id": 3} }
-
-----------------------------------------------------------------------
-### Canceled By:
-
-----------------------------------------------------------------------
-### Enqueued At:
-[timestamp] [0,]
-[timestamp] [1,]
-----------------------------------------------------------------------
-### Started At:
-[timestamp] [0,]
-[timestamp] [1,]
-----------------------------------------------------------------------
-### Finished At:
-[timestamp] [0,]
-[timestamp] [1,]
-----------------------------------------------------------------------
-### File Store:
-
-----------------------------------------------------------------------

crates/index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_document_deletion/after_adding_the_settings.snap

@@ -1,43 +0,0 @@
----
-source: index-scheduler/src/lib.rs
----
-### Autobatching Enabled = true
-### Processing Tasks:
-[]
-----------------------------------------------------------------------
-### All Tasks:
-0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
-1 {uid: 1, status: enqueued, details: { received_documents: 3, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
-----------------------------------------------------------------------
-### Status:
-enqueued [1,]
-succeeded [0,]
-----------------------------------------------------------------------
-### Kind:
-"documentAdditionOrUpdate" [1,]
-"settingsUpdate" [0,]
-----------------------------------------------------------------------
-### Index Tasks:
-doggos [0,1,]
-----------------------------------------------------------------------
-### Index Mapper:
-doggos: { number_of_documents: 0, field_distribution: {} }
-
-----------------------------------------------------------------------
-### Canceled By:
-
-----------------------------------------------------------------------
-### Enqueued At:
-[timestamp] [0,]
-[timestamp] [1,]
-----------------------------------------------------------------------
-### Started At:
-[timestamp] [0,]
-----------------------------------------------------------------------
-### Finished At:
-[timestamp] [0,]
-----------------------------------------------------------------------
-### File Store:
-00000000-0000-0000-0000-000000000000
-
-----------------------------------------------------------------------

crates/index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_document_deletion/after_adding_the_settings_and_documents.snap

@@ -1,43 +0,0 @@
----
-source: index-scheduler/src/lib.rs
----
-### Autobatching Enabled = true
-### Processing Tasks:
-[]
-----------------------------------------------------------------------
-### All Tasks:
-0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
-1 {uid: 1, status: enqueued, details: { received_documents: 3, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
-----------------------------------------------------------------------
-### Status:
-enqueued [1,]
-succeeded [0,]
-----------------------------------------------------------------------
-### Kind:
-"documentAdditionOrUpdate" [1,]
-"settingsUpdate" [0,]
-----------------------------------------------------------------------
-### Index Tasks:
-doggos [0,1,]
-----------------------------------------------------------------------
-### Index Mapper:
-doggos: { number_of_documents: 0, field_distribution: {} }
-
-----------------------------------------------------------------------
-### Canceled By:
-
-----------------------------------------------------------------------
-### Enqueued At:
-[timestamp] [0,]
-[timestamp] [1,]
-----------------------------------------------------------------------
-### Started At:
-[timestamp] [0,]
-----------------------------------------------------------------------
-### Finished At:
-[timestamp] [0,]
-----------------------------------------------------------------------
-### File Store:
-00000000-0000-0000-0000-000000000000
-
-----------------------------------------------------------------------

crates/index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_document_deletion/after_removing_the_documents.snap

@@ -1,56 +0,0 @@
----
-source: index-scheduler/src/lib.rs
----
-### Autobatching Enabled = true
-### Processing Tasks:
-[]
-----------------------------------------------------------------------
-### All Tasks:
-0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
-1 {uid: 1, status: succeeded, details: { received_documents: 3, indexed_documents: Some(3) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
-2 {uid: 2, status: succeeded, details: { received_document_ids: 1, deleted_documents: Some(1) }, kind: DocumentDeletion { index_uid: "doggos", documents_ids: ["1"] }}
-3 {uid: 3, status: failed, error: ResponseError { code: 200, message: "Invalid type for filter subexpression: expected: String, Array, found: true.", error_code: "invalid_document_filter", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#invalid_document_filter" }, details: { original_filter: true, deleted_documents: Some(0) }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: Bool(true) }}
-4 {uid: 4, status: failed, error: ResponseError { code: 200, message: "Attribute `id` is not filterable. Available filterable attributes are: `catto`.\n1:3 id = 2", error_code: "invalid_document_filter", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#invalid_document_filter" }, details: { original_filter: "id = 2", deleted_documents: Some(0) }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: String("id = 2") }}
-5 {uid: 5, status: succeeded, details: { original_filter: "catto EXISTS", deleted_documents: Some(1) }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: String("catto EXISTS") }}
-----------------------------------------------------------------------
-### Status:
-enqueued []
-succeeded [0,1,2,5,]
-failed [3,4,]
-----------------------------------------------------------------------
-### Kind:
-"documentAdditionOrUpdate" [1,]
-"documentDeletion" [2,3,4,5,]
-"settingsUpdate" [0,]
-----------------------------------------------------------------------
-### Index Tasks:
-doggos [0,1,2,3,4,5,]
-----------------------------------------------------------------------
-### Index Mapper:
-doggos: { number_of_documents: 1, field_distribution: {"doggo": 1, "id": 1} }
-
-----------------------------------------------------------------------
-### Canceled By:
-
-----------------------------------------------------------------------
-### Enqueued At:
-[timestamp] [0,]
-[timestamp] [1,]
-[timestamp] [2,]
-[timestamp] [3,]
-[timestamp] [4,]
-[timestamp] [5,]
-----------------------------------------------------------------------
-### Started At:
-[timestamp] [0,]
-[timestamp] [1,]
-[timestamp] [2,3,4,5,]
-----------------------------------------------------------------------
-### Finished At:
-[timestamp] [0,]
-[timestamp] [1,]
-[timestamp] [2,3,4,5,]
-----------------------------------------------------------------------
-### File Store:
-
-----------------------------------------------------------------------

crates/index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_document_deletion/documents_remaining_should_only_be_bork.snap

@@ -1,9 +0,0 @@
----
-source: index-scheduler/src/lib.rs
----
-[
-  {
-    "id": 3,
-    "doggo": "bork"
-  }
-]

crates/index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_document_deletion/registered_the_document_deletions.snap

@@ -1,53 +0,0 @@
----
-source: index-scheduler/src/lib.rs
----
-### Autobatching Enabled = true
-### Processing Tasks:
-[]
-----------------------------------------------------------------------
-### All Tasks:
-0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
-1 {uid: 1, status: succeeded, details: { received_documents: 3, indexed_documents: Some(3) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
-2 {uid: 2, status: enqueued, details: { received_document_ids: 1, deleted_documents: None }, kind: DocumentDeletion { index_uid: "doggos", documents_ids: ["1"] }}
-3 {uid: 3, status: enqueued, details: { original_filter: true, deleted_documents: None }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: Bool(true) }}
-4 {uid: 4, status: enqueued, details: { original_filter: "id = 2", deleted_documents: None }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: String("id = 2") }}
-5 {uid: 5, status: enqueued, details: { original_filter: "catto EXISTS", deleted_documents: None }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: String("catto EXISTS") }}
-----------------------------------------------------------------------
-### Status:
-enqueued [2,3,4,5,]
-succeeded [0,1,]
-----------------------------------------------------------------------
-### Kind:
-"documentAdditionOrUpdate" [1,]
-"documentDeletion" [2,3,4,5,]
-"settingsUpdate" [0,]
-----------------------------------------------------------------------
-### Index Tasks:
-doggos [0,1,2,3,4,5,]
-----------------------------------------------------------------------
-### Index Mapper:
-doggos: { number_of_documents: 3, field_distribution: {"catto": 1, "doggo": 2, "id": 3} }
-
-----------------------------------------------------------------------
-### Canceled By:
-
-----------------------------------------------------------------------
-### Enqueued At:
-[timestamp] [0,]
-[timestamp] [1,]
-[timestamp] [2,]
-[timestamp] [3,]
-[timestamp] [4,]
-[timestamp] [5,]
-----------------------------------------------------------------------
-### Started At:
-[timestamp] [0,]
-[timestamp] [1,]
-----------------------------------------------------------------------
-### Finished At:
-[timestamp] [0,]
-[timestamp] [1,]
-----------------------------------------------------------------------
-### File Store:
-
-----------------------------------------------------------------------

crates/index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_document_deletion/registered_the_setting_and_document_addition.snap

@@ -1,39 +0,0 @@
----
-source: index-scheduler/src/lib.rs
----
-### Autobatching Enabled = true
-### Processing Tasks:
-[]
-----------------------------------------------------------------------
-### All Tasks:
-0 {uid: 0, status: enqueued, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
-1 {uid: 1, status: enqueued, details: { received_documents: 3, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
-----------------------------------------------------------------------
-### Status:
-enqueued [0,1,]
-----------------------------------------------------------------------
-### Kind:
-"documentAdditionOrUpdate" [1,]
-"settingsUpdate" [0,]
-----------------------------------------------------------------------
-### Index Tasks:
-doggos [0,1,]
-----------------------------------------------------------------------
-### Index Mapper:
-
-----------------------------------------------------------------------
-### Canceled By:
-
-----------------------------------------------------------------------
-### Enqueued At:
-[timestamp] [0,]
-[timestamp] [1,]
-----------------------------------------------------------------------
-### Started At:
-----------------------------------------------------------------------
-### Finished At:
-----------------------------------------------------------------------
-### File Store:
-00000000-0000-0000-0000-000000000000
-
-----------------------------------------------------------------------

crates/index-scheduler/src/snapshots/lib.rs/import_vectors/Intel to kefir succeeds.snap

@@ -1,48 +0,0 @@
----
-source: index-scheduler/src/lib.rs
----
-### Autobatching Enabled = true
-### Processing Tasks:
-[]
-----------------------------------------------------------------------
-### All Tasks:
-0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
-1 {uid: 1, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
-2 {uid: 2, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: None, method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
-----------------------------------------------------------------------
-### Status:
-enqueued []
-succeeded [0,1,2,]
-----------------------------------------------------------------------
-### Kind:
-"documentAdditionOrUpdate" [1,2,]
-"settingsUpdate" [0,]
-----------------------------------------------------------------------
-### Index Tasks:
-doggos [0,1,2,]
-----------------------------------------------------------------------
-### Index Mapper:
-doggos: { number_of_documents: 1, field_distribution: {"_vectors": 1, "breed": 1, "doggo": 1, "id": 1} }
-
-----------------------------------------------------------------------
-### Canceled By:
-
-----------------------------------------------------------------------
-### Enqueued At:
-[timestamp] [0,]
-[timestamp] [1,]
-[timestamp] [2,]
-----------------------------------------------------------------------
-### Started At:
-[timestamp] [0,]
-[timestamp] [1,]
-[timestamp] [2,]
-----------------------------------------------------------------------
-### Finished At:
-[timestamp] [0,]
-[timestamp] [1,]
-[timestamp] [2,]
-----------------------------------------------------------------------
-### File Store:
-
-----------------------------------------------------------------------

crates/index-scheduler/src/snapshots/lib.rs/import_vectors/Intel to kefir.snap

@@ -1,47 +0,0 @@
----
-source: index-scheduler/src/lib.rs
----
-### Autobatching Enabled = true
-### Processing Tasks:
-[]
-----------------------------------------------------------------------
-### All Tasks:
-0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
-1 {uid: 1, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
-2 {uid: 2, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: None, method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
-----------------------------------------------------------------------
-### Status:
-enqueued [2,]
-succeeded [0,1,]
-----------------------------------------------------------------------
-### Kind:
-"documentAdditionOrUpdate" [1,2,]
-"settingsUpdate" [0,]
-----------------------------------------------------------------------
-### Index Tasks:
-doggos [0,1,2,]
-----------------------------------------------------------------------
-### Index Mapper:
-doggos: { number_of_documents: 1, field_distribution: {"_vectors": 1, "breed": 1, "doggo": 1, "id": 1} }
-
-----------------------------------------------------------------------
-### Canceled By:
-
-----------------------------------------------------------------------
-### Enqueued At:
-[timestamp] [0,]
-[timestamp] [1,]
-[timestamp] [2,]
-----------------------------------------------------------------------
-### Started At:
-[timestamp] [0,]
-[timestamp] [1,]
-----------------------------------------------------------------------
-### Finished At:
-[timestamp] [0,]
-[timestamp] [1,]
-----------------------------------------------------------------------
-### File Store:
-00000000-0000-0000-0000-000000000001
-
-----------------------------------------------------------------------

crates/index-scheduler/src/snapshots/lib.rs/import_vectors/adding Intel succeeds.snap

@@ -1,44 +0,0 @@
----
-source: index-scheduler/src/lib.rs
----
-### Autobatching Enabled = true
-### Processing Tasks:
-[]
-----------------------------------------------------------------------
-### All Tasks:
-0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
-1 {uid: 1, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
-----------------------------------------------------------------------
-### Status:
-enqueued []
-succeeded [0,1,]
-----------------------------------------------------------------------
-### Kind:
-"documentAdditionOrUpdate" [1,]
-"settingsUpdate" [0,]
-----------------------------------------------------------------------
-### Index Tasks:
-doggos [0,1,]
-----------------------------------------------------------------------
-### Index Mapper:
-doggos: { number_of_documents: 1, field_distribution: {"_vectors": 1, "breed": 1, "doggo": 1, "id": 1} }
-
-----------------------------------------------------------------------
-### Canceled By:
-
-----------------------------------------------------------------------
-### Enqueued At:
-[timestamp] [0,]
-[timestamp] [1,]
-----------------------------------------------------------------------
-### Started At:
-[timestamp] [0,]
-[timestamp] [1,]
-----------------------------------------------------------------------
-### Finished At:
-[timestamp] [0,]
-[timestamp] [1,]
-----------------------------------------------------------------------
-### File Store:
-
-----------------------------------------------------------------------

crates/index-scheduler/src/snapshots/lib.rs/import_vectors/after adding Intel.snap

@@ -1,43 +0,0 @@
----
-source: index-scheduler/src/lib.rs
----
-### Autobatching Enabled = true
-### Processing Tasks:
-[]
-----------------------------------------------------------------------
-### All Tasks:
-0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
-1 {uid: 1, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
-----------------------------------------------------------------------
-### Status:
-enqueued [1,]
-succeeded [0,]
-----------------------------------------------------------------------
-### Kind:
-"documentAdditionOrUpdate" [1,]
-"settingsUpdate" [0,]
-----------------------------------------------------------------------
-### Index Tasks:
-doggos [0,1,]
-----------------------------------------------------------------------
-### Index Mapper:
-doggos: { number_of_documents: 0, field_distribution: {} }
-
-----------------------------------------------------------------------
-### Canceled By:
-
-----------------------------------------------------------------------
-### Enqueued At:
-[timestamp] [0,]
-[timestamp] [1,]
-----------------------------------------------------------------------
-### Started At:
-[timestamp] [0,]
-----------------------------------------------------------------------
-### Finished At:
-[timestamp] [0,]
-----------------------------------------------------------------------
-### File Store:
-00000000-0000-0000-0000-000000000000
-
-----------------------------------------------------------------------

crates/index-scheduler/src/snapshots/lib.rs/import_vectors/after_registering_settings_task_vectors.snap

@@ -1,35 +0,0 @@
----
-source: index-scheduler/src/lib.rs
----
-### Autobatching Enabled = true
-### Processing Tasks:
-[]
-----------------------------------------------------------------------
-### All Tasks:
-0 {uid: 0, status: enqueued, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
-----------------------------------------------------------------------
-### Status:
-enqueued [0,]
-----------------------------------------------------------------------
-### Kind:
-"settingsUpdate" [0,]
-----------------------------------------------------------------------
-### Index Tasks:
-doggos [0,]
-----------------------------------------------------------------------
-### Index Mapper:
-
-----------------------------------------------------------------------
-### Canceled By:
-
-----------------------------------------------------------------------
-### Enqueued At:
-[timestamp] [0,]
-----------------------------------------------------------------------
-### Started At:
-----------------------------------------------------------------------
-### Finished At:
-----------------------------------------------------------------------
-### File Store:
-
-----------------------------------------------------------------------

crates/index-scheduler/src/snapshots/lib.rs/import_vectors/settings_update_processed_vectors.snap

@@ -1,39 +0,0 @@
----
-source: index-scheduler/src/lib.rs
----
-### Autobatching Enabled = true
-### Processing Tasks:
-[]
-----------------------------------------------------------------------
-### All Tasks:
-0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
-----------------------------------------------------------------------
-### Status:
-enqueued []
-succeeded [0,]
-----------------------------------------------------------------------
-### Kind:
-"settingsUpdate" [0,]
-----------------------------------------------------------------------
-### Index Tasks:
-doggos [0,]
-----------------------------------------------------------------------
-### Index Mapper:
-doggos: { number_of_documents: 0, field_distribution: {} }
-
-----------------------------------------------------------------------
-### Canceled By:
-
-----------------------------------------------------------------------
-### Enqueued At:
-[timestamp] [0,]
-----------------------------------------------------------------------
-### Started At:
-[timestamp] [0,]
-----------------------------------------------------------------------
-### Finished At:
-[timestamp] [0,]
-----------------------------------------------------------------------
-### File Store:
-
-----------------------------------------------------------------------

crates/meilisearch-types/src/locales.rs

@@ -1,166 +0,0 @@
-use deserr::Deserr;
-use milli::LocalizedAttributesRule;
-use serde::{Deserialize, Serialize};
-
-#[derive(Debug, Clone, PartialEq, Eq, Deserr, Serialize, Deserialize)]
-#[deserr(rename_all = camelCase)]
-#[serde(rename_all = "camelCase")]
-pub struct LocalizedAttributesRuleView {
-    pub attribute_patterns: Vec<String>,
-    pub locales: Vec<Locale>,
-}
-
-impl From<LocalizedAttributesRule> for LocalizedAttributesRuleView {
-    fn from(rule: LocalizedAttributesRule) -> Self {
-        Self {
-            attribute_patterns: rule.attribute_patterns,
-            locales: rule.locales.into_iter().map(|l| l.into()).collect(),
-        }
-    }
-}
-
-impl From<LocalizedAttributesRuleView> for LocalizedAttributesRule {
-    fn from(view: LocalizedAttributesRuleView) -> Self {
-        Self {
-            attribute_patterns: view.attribute_patterns,
-            locales: view.locales.into_iter().map(|l| l.into()).collect(),
-        }
-    }
-}
-
-/// Generate a Locale enum and its From and Into implementations for milli::tokenizer::Language.
-///
-/// this enum implements `Deserr` in order to be used in the API.
-macro_rules! make_locale {
-    ($(($iso_639_1:ident, $iso_639_1_str:expr) => ($iso_639_3:ident, $iso_639_3_str:expr),)+) => {
-        #[derive(Debug, Copy, Clone, PartialEq, Eq, Deserr, Serialize, Deserialize, Ord, PartialOrd)]
-        #[deserr(rename_all = camelCase)]
-        #[serde(rename_all = "camelCase")]
-        pub enum Locale {
-            $($iso_639_1,)+
-            $($iso_639_3,)+
-            Cmn,
-        }
-
-        impl From<milli::tokenizer::Language> for Locale {
-            fn from(other: milli::tokenizer::Language) -> Locale {
-                match other {
-                    $(milli::tokenizer::Language::$iso_639_3 => Locale::$iso_639_3,)+
-                    milli::tokenizer::Language::Cmn => Locale::Cmn,
-                }
-            }
-        }
-
-        impl From<Locale> for milli::tokenizer::Language {
-            fn from(other: Locale) -> milli::tokenizer::Language {
-                match other {
-                    $(Locale::$iso_639_1 => milli::tokenizer::Language::$iso_639_3,)+
-                    $(Locale::$iso_639_3 => milli::tokenizer::Language::$iso_639_3,)+
-                    Locale::Cmn => milli::tokenizer::Language::Cmn,
-                }
-            }
-        }
-
-        impl std::str::FromStr for Locale {
-            type Err = LocaleFormatError;
-
-            fn from_str(s: &str) -> Result<Self, Self::Err> {
-                let locale = match s {
-                    $($iso_639_1_str => Locale::$iso_639_1,)+
-                    $($iso_639_3_str => Locale::$iso_639_3,)+
-                    "cmn" => Locale::Cmn,
-                    _ => return Err(LocaleFormatError { invalid_locale: s.to_string() }),
-                };
-
-                Ok(locale)
-            }
-        }
-
-        #[derive(Debug)]
-        pub struct LocaleFormatError {
-            pub invalid_locale: String,
-        }
-
-        impl std::fmt::Display for LocaleFormatError {
-            fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
-                let mut valid_locales = [$($iso_639_1_str),+,$($iso_639_3_str),+,"cmn"];
-                valid_locales.sort_by(|left, right| left.len().cmp(&right.len()).then(left.cmp(right)));
-                write!(f, "Unsupported locale `{}`, expected one of {}", self.invalid_locale, valid_locales.join(", "))
-            }
-        }
-
-        impl std::error::Error for LocaleFormatError {}
-    };
-}
-
-make_locale!(
-    (Af, "af") => (Afr, "afr"),
-    (Ak, "ak") => (Aka, "aka"),
-    (Am, "am") => (Amh, "amh"),
-    (Ar, "ar") => (Ara, "ara"),
-    (Az, "az") => (Aze, "aze"),
-    (Be, "be") => (Bel, "bel"),
-    (Bn, "bn") => (Ben, "ben"),
-    (Bg, "bg") => (Bul, "bul"),
-    (Ca, "ca") => (Cat, "cat"),
-    (Cs, "cs") => (Ces, "ces"),
-    (Da, "da") => (Dan, "dan"),
-    (De, "de") => (Deu, "deu"),
-    (El, "el") => (Ell, "ell"),
-    (En, "en") => (Eng, "eng"),
-    (Eo, "eo") => (Epo, "epo"),
-    (Et, "et") => (Est, "est"),
-    (Fi, "fi") => (Fin, "fin"),
-    (Fr, "fr") => (Fra, "fra"),
-    (Gu, "gu") => (Guj, "guj"),
-    (He, "he") => (Heb, "heb"),
-    (Hi, "hi") => (Hin, "hin"),
-    (Hr, "hr") => (Hrv, "hrv"),
-    (Hu, "hu") => (Hun, "hun"),
-    (Hy, "hy") => (Hye, "hye"),
-    (Id, "id") => (Ind, "ind"),
-    (It, "it") => (Ita, "ita"),
-    (Jv, "jv") => (Jav, "jav"),
-    (Ja, "ja") => (Jpn, "jpn"),
-    (Kn, "kn") => (Kan, "kan"),
-    (Ka, "ka") => (Kat, "kat"),
-    (Km, "km") => (Khm, "khm"),
-    (Ko, "ko") => (Kor, "kor"),
-    (La, "la") => (Lat, "lat"),
-    (Lv, "lv") => (Lav, "lav"),
-    (Lt, "lt") => (Lit, "lit"),
-    (Ml, "ml") => (Mal, "mal"),
-    (Mr, "mr") => (Mar, "mar"),
-    (Mk, "mk") => (Mkd, "mkd"),
-    (My, "my") => (Mya, "mya"),
-    (Ne, "ne") => (Nep, "nep"),
-    (Nl, "nl") => (Nld, "nld"),
-    (Nb, "nb") => (Nob, "nob"),
-    (Or, "or") => (Ori, "ori"),
-    (Pa, "pa") => (Pan, "pan"),
-    (Fa, "fa") => (Pes, "pes"),
-    (Pl, "pl") => (Pol, "pol"),
-    (Pt, "pt") => (Por, "por"),
-    (Ro, "ro") => (Ron, "ron"),
-    (Ru, "ru") => (Rus, "rus"),
-    (Si, "si") => (Sin, "sin"),
-    (Sk, "sk") => (Slk, "slk"),
-    (Sl, "sl") => (Slv, "slv"),
-    (Sn, "sn") => (Sna, "sna"),
-    (Es, "es") => (Spa, "spa"),
-    (Sr, "sr") => (Srp, "srp"),
-    (Sv, "sv") => (Swe, "swe"),
-    (Ta, "ta") => (Tam, "tam"),
-    (Te, "te") => (Tel, "tel"),
-    (Tl, "tl") => (Tgl, "tgl"),
-    (Th, "th") => (Tha, "tha"),
-    (Tk, "tk") => (Tuk, "tuk"),
-    (Tr, "tr") => (Tur, "tur"),
-    (Uk, "uk") => (Ukr, "ukr"),
-    (Ur, "ur") => (Urd, "urd"),
-    (Uz, "uz") => (Uzb, "uzb"),
-    (Vi, "vi") => (Vie, "vie"),
-    (Yi, "yi") => (Yid, "yid"),
-    (Zh, "zh") => (Zho, "zho"),
-    (Zu, "zu") => (Zul, "zul"),
-);

crates/meilisearch/Cargo.toml

@@ -1,161 +0,0 @@
-[package]
-name = "meilisearch"
-publish = false
-
-version.workspace = true
-authors.workspace = true
-description.workspace = true
-homepage.workspace = true
-readme.workspace = true
-edition.workspace = true
-license.workspace = true
-
-default-run = "meilisearch"
-
-[dependencies]
-actix-cors = "0.7.0"
-actix-http = { version = "3.8.0", default-features = false, features = [
-    "compress-brotli",
-    "compress-gzip",
-    "rustls-0_23",
-] }
-actix-utils = "3.0.1"
-actix-web = { version = "4.8.0", default-features = false, features = [
-    "macros",
-    "compress-brotli",
-    "compress-gzip",
-    "cookies",
-    "rustls-0_23",
-] }
-anyhow = { version = "1.0.86", features = ["backtrace"] }
-async-trait = "0.1.81"
-bstr = "1.9.1"
-byte-unit = { version = "5.1.4", default-features = false, features = [
-    "std",
-    "byte",
-    "serde",
-] }
-bytes = "1.6.0"
-clap = { version = "4.5.9", features = ["derive", "env"] }
-crossbeam-channel = "0.5.13"
-deserr = { version = "0.6.2", features = ["actix-web"] }
-dump = { path = "../dump" }
-either = "1.13.0"
-file-store = { path = "../file-store" }
-flate2 = "1.0.30"
-fst = "0.4.7"
-futures = "0.3.30"
-futures-util = "0.3.30"
-index-scheduler = { path = "../index-scheduler" }
-indexmap = { version = "2.2.6", features = ["serde"] }
-is-terminal = "0.4.12"
-itertools = "0.13.0"
-jsonwebtoken = "9.3.0"
-lazy_static = "1.5.0"
-meilisearch-auth = { path = "../meilisearch-auth" }
-meilisearch-types = { path = "../meilisearch-types" }
-mimalloc = { version = "0.1.43", default-features = false }
-mime = "0.3.17"
-num_cpus = "1.16.0"
-obkv = "0.2.2"
-once_cell = "1.19.0"
-ordered-float = "4.2.1"
-parking_lot = "0.12.3"
-permissive-json-pointer = { path = "../permissive-json-pointer" }
-pin-project-lite = "0.2.14"
-platform-dirs = "0.3.0"
-prometheus = { version = "0.13.4", features = ["process"] }
-rand = "0.8.5"
-rayon = "1.10.0"
-regex = "1.10.5"
-reqwest = { version = "0.12.5", features = [
-    "rustls-tls",
-    "json",
-], default-features = false }
-rustls = { version = "0.23.11", features = ["ring"], default-features = false }
-rustls-pki-types = { version = "1.7.0", features = ["alloc"] }
-rustls-pemfile = "2.1.2"
-segment = { version = "0.2.4" }
-serde = { version = "1.0.204", features = ["derive"] }
-serde_json = { version = "1.0.120", features = ["preserve_order"] }
-sha2 = "0.10.8"
-siphasher = "1.0.1"
-slice-group-by = "0.3.1"
-static-files = { version = "0.2.4", optional = true }
-sysinfo = "0.30.13"
-tar = "0.4.41"
-tempfile = "3.10.1"
-thiserror = "1.0.61"
-time = { version = "0.3.36", features = [
-    "serde-well-known",
-    "formatting",
-    "parsing",
-    "macros",
-] }
-tokio = { version = "1.38.0", features = ["full"] }
-toml = "0.8.14"
-uuid = { version = "1.10.0", features = ["serde", "v4"] }
-serde_urlencoded = "0.7.1"
-termcolor = "1.4.1"
-url = { version = "2.5.2", features = ["serde"] }
-tracing = "0.1.40"
-tracing-subscriber = { version = "0.3.18", features = ["json"] }
-tracing-trace = { version = "0.1.0", path = "../tracing-trace" }
-tracing-actix-web = "0.7.11"
-build-info = { version = "1.7.0", path = "../build-info" }
-roaring = "0.10.2"
-mopa-maintained = "0.2.3"
-
-[dev-dependencies]
-actix-rt = "2.10.0"
-brotli = "6.0.0"
-insta = "1.39.0"
-manifest-dir-macros = "0.1.18"
-maplit = "1.0.2"
-meili-snap = { path = "../meili-snap" }
-temp-env = "0.3.6"
-urlencoding = "2.1.3"
-wiremock = "0.6.0"
-yaup = "0.3.1"
-
-[build-dependencies]
-anyhow = { version = "1.0.86", optional = true }
-cargo_toml = { version = "0.20.3", optional = true }
-hex = { version = "0.4.3", optional = true }
-reqwest = { version = "0.12.5", features = [
-    "blocking",
-    "rustls-tls",
-], default-features = false, optional = true }
-sha-1 = { version = "0.10.1", optional = true }
-static-files = { version = "0.2.4", optional = true }
-tempfile = { version = "3.10.1", optional = true }
-zip = { version = "2.1.3", optional = true }
-
-[features]
-default = ["meilisearch-types/all-tokenizations", "mini-dashboard"]
-mini-dashboard = [
-    "static-files",
-    "anyhow",
-    "cargo_toml",
-    "hex",
-    "reqwest",
-    "sha-1",
-    "tempfile",
-    "zip",
-]
-chinese = ["meilisearch-types/chinese"]
-chinese-pinyin = ["meilisearch-types/chinese-pinyin"]
-hebrew = ["meilisearch-types/hebrew"]
-japanese = ["meilisearch-types/japanese"]
-korean = ["meilisearch-types/korean"]
-thai = ["meilisearch-types/thai"]
-greek = ["meilisearch-types/greek"]
-khmer = ["meilisearch-types/khmer"]
-vietnamese = ["meilisearch-types/vietnamese"]
-swedish-recomposition = ["meilisearch-types/swedish-recomposition"]
-german = ["meilisearch-types/german"]
-turkish = ["meilisearch-types/turkish"]
-
-[package.metadata.mini-dashboard]
-assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.2.15/build.zip"
-sha1 = "d057600b4a839a2e0c0be7a372cd1b2683f3ca7e"

crates/meilisearch/src/analytics/mod.rs

@@ -1,166 +0,0 @@
-pub mod segment_analytics;
-
-use std::fs;
-use std::path::{Path, PathBuf};
-use std::str::FromStr;
-use std::sync::Arc;
-
-use actix_web::HttpRequest;
-use index_scheduler::IndexScheduler;
-use meilisearch_auth::AuthController;
-use meilisearch_types::InstanceUid;
-use mopa::mopafy;
-use once_cell::sync::Lazy;
-use platform_dirs::AppDirs;
-
-// if the feature analytics is enabled we use the real analytics
-pub type SegmentAnalytics = segment_analytics::SegmentAnalytics;
-
-use crate::Opt;
-
-/// A macro used to quickly define events that don't aggregate or send anything besides an empty event with its name.
-#[macro_export]
-macro_rules! empty_analytics {
-    ($struct_name:ident, $event_name:literal) => {
-        #[derive(Default)]
-        struct $struct_name {}
-
-        impl $crate::analytics::Aggregate for $struct_name {
-            fn event_name(&self) -> &'static str {
-                $event_name
-            }
-
-            fn aggregate(self: Box<Self>, _other: Box<Self>) -> Box<Self> {
-                self
-            }
-
-            fn into_event(self: Box<Self>) -> serde_json::Value {
-                serde_json::json!({})
-            }
-        }
-    };
-}
-
-/// The Meilisearch config dir:
-/// `~/.config/Meilisearch` on *NIX or *BSD.
-/// `~/Library/ApplicationSupport` on macOS.
-/// `%APPDATA` (= `C:\Users%USERNAME%\AppData\Roaming`) on windows.
-static MEILISEARCH_CONFIG_PATH: Lazy<Option<PathBuf>> =
-    Lazy::new(|| AppDirs::new(Some("Meilisearch"), false).map(|appdir| appdir.config_dir));
-
-fn config_user_id_path(db_path: &Path) -> Option<PathBuf> {
-    db_path
-        .canonicalize()
-        .ok()
-        .map(|path| path.join("instance-uid").display().to_string().replace('/', "-"))
-        .zip(MEILISEARCH_CONFIG_PATH.as_ref())
-        .map(|(filename, config_path)| config_path.join(filename.trim_start_matches('-')))
-}
-
-/// Look for the instance-uid in the `data.ms` or in `~/.config/Meilisearch/path-to-db-instance-uid`
-fn find_user_id(db_path: &Path) -> Option<InstanceUid> {
-    fs::read_to_string(db_path.join("instance-uid"))
-        .ok()
-        .or_else(|| fs::read_to_string(config_user_id_path(db_path)?).ok())
-        .and_then(|uid| InstanceUid::from_str(&uid).ok())
-}
-
-#[derive(Copy, Clone, Debug, PartialEq, Eq)]
-pub enum DocumentDeletionKind {
-    PerDocumentId,
-    ClearAll,
-    PerBatch,
-    PerFilter,
-}
-
-#[derive(Copy, Clone, Debug, PartialEq, Eq)]
-pub enum DocumentFetchKind {
-    PerDocumentId { retrieve_vectors: bool },
-    Normal { with_filter: bool, limit: usize, offset: usize, retrieve_vectors: bool },
-}
-
-/// To send an event to segment, your event must be able to aggregate itself with another event of the same type.
-pub trait Aggregate: 'static + mopa::Any + Send {
-    /// The name of the event that will be sent to segment.
-    fn event_name(&self) -> &'static str;
-
-    /// Will be called every time an event has been used twice before segment flushed its buffer.
-    fn aggregate(self: Box<Self>, new: Box<Self>) -> Box<Self>
-    where
-        Self: Sized;
-
-    /// Converts your structure to the final event that'll be sent to segment.
-    fn into_event(self: Box<Self>) -> serde_json::Value;
-}
-
-mopafy!(Aggregate);
-
-/// Helper trait to define multiple aggregates with the same content but a different name.
-/// Commonly used when you must aggregate a search with POST or with GET, for example.
-pub trait AggregateMethod: 'static + Default + Send {
-    fn event_name() -> &'static str;
-}
-
-/// A macro used to quickly define multiple aggregate method with their name
-/// Usage:
-/// ```rust
-/// use meilisearch::aggregate_methods;
-///
-/// aggregate_methods!(
-///     SearchGET => "Documents Searched GET",
-///     SearchPOST => "Documents Searched POST",
-/// );
-/// ```
-#[macro_export]
-macro_rules! aggregate_methods {
-    ($method:ident => $event_name:literal) => {
-        #[derive(Default)]
-        pub struct $method {}
-
-        impl $crate::analytics::AggregateMethod for $method {
-            fn event_name() -> &'static str {
-                $event_name
-            }
-        }
-    };
-    ($($method:ident => $event_name:literal,)+) => {
-        $(
-            aggregate_methods!($method => $event_name);
-        )+
-
-    };
-}
-
-#[derive(Clone)]
-pub struct Analytics {
-    segment: Option<Arc<SegmentAnalytics>>,
-}
-
-impl Analytics {
-    pub async fn new(
-        opt: &Opt,
-        index_scheduler: Arc<IndexScheduler>,
-        auth_controller: Arc<AuthController>,
-    ) -> Self {
-        if opt.no_analytics {
-            Self { segment: None }
-        } else {
-            Self { segment: SegmentAnalytics::new(opt, index_scheduler, auth_controller).await }
-        }
-    }
-
-    pub fn no_analytics() -> Self {
-        Self { segment: None }
-    }
-
-    pub fn instance_uid(&self) -> Option<&InstanceUid> {
-        self.segment.as_ref().map(|segment| segment.instance_uid.as_ref())
-    }
-
-    /// The method used to publish most analytics that do not need to be batched every hours
-    pub fn publish<T: Aggregate>(&self, event: T, request: &HttpRequest) {
-        if let Some(ref segment) = self.segment {
-            let _ = segment.sender.try_send(segment_analytics::Message::new(event, request));
-        }
-    }
-}

crates/meilisearch/src/analytics/segment_analytics.rs

@@ -1,484 +0,0 @@
-use std::any::TypeId;
-use std::collections::{HashMap, HashSet};
-use std::fs;
-use std::path::{Path, PathBuf};
-use std::sync::Arc;
-use std::time::{Duration, Instant};
-
-use actix_web::http::header::USER_AGENT;
-use actix_web::HttpRequest;
-use byte_unit::Byte;
-use index_scheduler::IndexScheduler;
-use meilisearch_auth::{AuthController, AuthFilter};
-use meilisearch_types::features::RuntimeTogglableFeatures;
-use meilisearch_types::InstanceUid;
-use once_cell::sync::Lazy;
-use segment::message::{Identify, Track, User};
-use segment::{AutoBatcher, Batcher, HttpClient};
-use serde::Serialize;
-use serde_json::{json, Value};
-use sysinfo::{Disks, System};
-use time::OffsetDateTime;
-use tokio::select;
-use tokio::sync::mpsc::{self, Receiver, Sender};
-use uuid::Uuid;
-
-use super::{config_user_id_path, Aggregate, MEILISEARCH_CONFIG_PATH};
-use crate::option::{
-    default_http_addr, IndexerOpts, LogMode, MaxMemory, MaxThreads, ScheduleSnapshot,
-};
-use crate::routes::{create_all_stats, Stats};
-use crate::Opt;
-
-const ANALYTICS_HEADER: &str = "X-Meilisearch-Client";
-
-/// Write the instance-uid in the `data.ms` and in `~/.config/MeiliSearch/path-to-db-instance-uid`. Ignore the errors.
-fn write_user_id(db_path: &Path, user_id: &InstanceUid) {
-    let _ = fs::write(db_path.join("instance-uid"), user_id.to_string());
-    if let Some((meilisearch_config_path, user_id_path)) =
-        MEILISEARCH_CONFIG_PATH.as_ref().zip(config_user_id_path(db_path))
-    {
-        let _ = fs::create_dir_all(meilisearch_config_path);
-        let _ = fs::write(user_id_path, user_id.to_string());
-    }
-}
-
-const SEGMENT_API_KEY: &str = "P3FWhhEsJiEDCuEHpmcN9DHcK4hVfBvb";
-
-pub fn extract_user_agents(request: &HttpRequest) -> HashSet<String> {
-    request
-        .headers()
-        .get(ANALYTICS_HEADER)
-        .or_else(|| request.headers().get(USER_AGENT))
-        .and_then(|header| header.to_str().ok())
-        .unwrap_or("unknown")
-        .split(';')
-        .map(str::trim)
-        .map(ToString::to_string)
-        .collect()
-}
-
-pub struct Message {
-    // Since the type_id is solved statically we cannot retrieve it from the Box.
-    // Thus we have to send it in the message directly.
-    type_id: TypeId,
-    // Same for the aggregate function.
-    #[allow(clippy::type_complexity)]
-    aggregator_function: fn(Box<dyn Aggregate>, Box<dyn Aggregate>) -> Option<Box<dyn Aggregate>>,
-    event: Event,
-}
-
-pub struct Event {
-    original: Box<dyn Aggregate>,
-    timestamp: OffsetDateTime,
-    user_agents: HashSet<String>,
-    total: usize,
-}
-
-/// This function should always be called on the same type. If `this` and `other`
-/// aren't the same type the function will do nothing and return `None`.
-fn downcast_aggregate<ConcreteType: Aggregate>(
-    old: Box<dyn Aggregate>,
-    new: Box<dyn Aggregate>,
-) -> Option<Box<dyn Aggregate>> {
-    if old.is::<ConcreteType>() && new.is::<ConcreteType>() {
-        // Both the two following lines cannot fail, but just to be sure we don't crash, we're still avoiding unwrapping
-        let this = old.downcast::<ConcreteType>().ok()?;
-        let other = new.downcast::<ConcreteType>().ok()?;
-        Some(ConcreteType::aggregate(this, other))
-    } else {
-        None
-    }
-}
-
-impl Message {
-    pub fn new<T: Aggregate>(event: T, request: &HttpRequest) -> Self {
-        Self {
-            type_id: TypeId::of::<T>(),
-            event: Event {
-                original: Box::new(event),
-                timestamp: OffsetDateTime::now_utc(),
-                user_agents: extract_user_agents(request),
-                total: 1,
-            },
-            aggregator_function: downcast_aggregate::<T>,
-        }
-    }
-}
-
-pub struct SegmentAnalytics {
-    pub instance_uid: InstanceUid,
-    pub user: User,
-    pub sender: Sender<Message>,
-}
-
-impl SegmentAnalytics {
-    #[allow(clippy::new_ret_no_self)]
-    pub async fn new(
-        opt: &Opt,
-        index_scheduler: Arc<IndexScheduler>,
-        auth_controller: Arc<AuthController>,
-    ) -> Option<Arc<Self>> {
-        let instance_uid = super::find_user_id(&opt.db_path);
-        let first_time_run = instance_uid.is_none();
-        let instance_uid = instance_uid.unwrap_or_else(Uuid::new_v4);
-        write_user_id(&opt.db_path, &instance_uid);
-
-        let client = reqwest::Client::builder().connect_timeout(Duration::from_secs(10)).build();
-
-        // if reqwest throws an error we won't be able to send analytics
-        if client.is_err() {
-            return None;
-        }
-
-        let client =
-            HttpClient::new(client.unwrap(), "https://telemetry.meilisearch.com".to_string());
-        let user = User::UserId { user_id: instance_uid.to_string() };
-        let mut batcher = AutoBatcher::new(client, Batcher::new(None), SEGMENT_API_KEY.to_string());
-
-        // If Meilisearch is Launched for the first time:
-        // 1. Send an event Launched associated to the user `total_launch`.
-        // 2. Batch an event Launched with the real instance-id and send it in one hour.
-        if first_time_run {
-            let _ = batcher
-                .push(Track {
-                    user: User::UserId { user_id: "total_launch".to_string() },
-                    event: "Launched".to_string(),
-                    ..Default::default()
-                })
-                .await;
-            let _ = batcher.flush().await;
-            let _ = batcher
-                .push(Track {
-                    user: user.clone(),
-                    event: "Launched".to_string(),
-                    ..Default::default()
-                })
-                .await;
-        }
-
-        let (sender, inbox) = mpsc::channel(100); // How many analytics can we bufferize
-
-        let segment = Box::new(Segment {
-            inbox,
-            user: user.clone(),
-            opt: opt.clone(),
-            batcher,
-            events: HashMap::new(),
-        });
-        tokio::spawn(segment.run(index_scheduler.clone(), auth_controller.clone()));
-
-        let this = Self { instance_uid, sender, user: user.clone() };
-
-        Some(Arc::new(this))
-    }
-}
-
-/// This structure represent the `infos` field we send in the analytics.
-/// It's quite close to the `Opt` structure except all sensitive informations
-/// have been simplified to a boolean.
-/// It's send as-is in amplitude thus you should never update a name of the
-/// struct without the approval of the PM.
-#[derive(Debug, Clone, Serialize)]
-struct Infos {
-    env: String,
-    experimental_contains_filter: bool,
-    experimental_vector_store: bool,
-    experimental_enable_metrics: bool,
-    experimental_edit_documents_by_function: bool,
-    experimental_search_queue_size: usize,
-    experimental_drop_search_after: usize,
-    experimental_nb_searches_per_core: usize,
-    experimental_logs_mode: LogMode,
-    experimental_replication_parameters: bool,
-    experimental_enable_logs_route: bool,
-    experimental_reduce_indexing_memory_usage: bool,
-    experimental_max_number_of_batched_tasks: usize,
-    gpu_enabled: bool,
-    db_path: bool,
-    import_dump: bool,
-    dump_dir: bool,
-    ignore_missing_dump: bool,
-    ignore_dump_if_db_exists: bool,
-    import_snapshot: bool,
-    schedule_snapshot: Option<u64>,
-    snapshot_dir: bool,
-    ignore_missing_snapshot: bool,
-    ignore_snapshot_if_db_exists: bool,
-    http_addr: bool,
-    http_payload_size_limit: Byte,
-    task_queue_webhook: bool,
-    task_webhook_authorization_header: bool,
-    log_level: String,
-    max_indexing_memory: MaxMemory,
-    max_indexing_threads: MaxThreads,
-    with_configuration_file: bool,
-    ssl_auth_path: bool,
-    ssl_cert_path: bool,
-    ssl_key_path: bool,
-    ssl_ocsp_path: bool,
-    ssl_require_auth: bool,
-    ssl_resumption: bool,
-    ssl_tickets: bool,
-}
-
-impl Infos {
-    pub fn new(options: Opt, features: RuntimeTogglableFeatures) -> Self {
-        // We wants to decompose this whole struct by hand to be sure we don't forget
-        // to add analytics when we add a field in the Opt.
-        // Thus we must not insert `..` at the end.
-        let Opt {
-            db_path,
-            experimental_contains_filter,
-            experimental_enable_metrics,
-            experimental_search_queue_size,
-            experimental_drop_search_after,
-            experimental_nb_searches_per_core,
-            experimental_logs_mode,
-            experimental_replication_parameters,
-            experimental_enable_logs_route,
-            experimental_reduce_indexing_memory_usage,
-            experimental_max_number_of_batched_tasks,
-            http_addr,
-            master_key: _,
-            env,
-            task_webhook_url,
-            task_webhook_authorization_header,
-            max_index_size: _,
-            max_task_db_size: _,
-            http_payload_size_limit,
-            ssl_cert_path,
-            ssl_key_path,
-            ssl_auth_path,
-            ssl_ocsp_path,
-            ssl_require_auth,
-            ssl_resumption,
-            ssl_tickets,
-            import_snapshot,
-            ignore_missing_snapshot,
-            ignore_snapshot_if_db_exists,
-            snapshot_dir,
-            schedule_snapshot,
-            import_dump,
-            ignore_missing_dump,
-            ignore_dump_if_db_exists,
-            dump_dir,
-            log_level,
-            indexer_options,
-            config_file_path,
-            no_analytics: _,
-        } = options;
-
-        let schedule_snapshot = match schedule_snapshot {
-            ScheduleSnapshot::Disabled => None,
-            ScheduleSnapshot::Enabled(interval) => Some(interval),
-        };
-
-        let IndexerOpts { max_indexing_memory, max_indexing_threads, skip_index_budget: _ } =
-            indexer_options;
-
-        let RuntimeTogglableFeatures {
-            vector_store,
-            metrics,
-            logs_route,
-            edit_documents_by_function,
-            contains_filter,
-        } = features;
-
-        // We're going to override every sensible information.
-        // We consider information sensible if it contains a path, an address, or a key.
-        Self {
-            env,
-            experimental_contains_filter: experimental_contains_filter | contains_filter,
-            experimental_vector_store: vector_store,
-            experimental_edit_documents_by_function: edit_documents_by_function,
-            experimental_enable_metrics: experimental_enable_metrics | metrics,
-            experimental_search_queue_size,
-            experimental_drop_search_after: experimental_drop_search_after.into(),
-            experimental_nb_searches_per_core: experimental_nb_searches_per_core.into(),
-            experimental_logs_mode,
-            experimental_replication_parameters,
-            experimental_enable_logs_route: experimental_enable_logs_route | logs_route,
-            experimental_reduce_indexing_memory_usage,
-            gpu_enabled: meilisearch_types::milli::vector::is_cuda_enabled(),
-            db_path: db_path != PathBuf::from("./data.ms"),
-            import_dump: import_dump.is_some(),
-            dump_dir: dump_dir != PathBuf::from("dumps/"),
-            ignore_missing_dump,
-            ignore_dump_if_db_exists,
-            import_snapshot: import_snapshot.is_some(),
-            schedule_snapshot,
-            snapshot_dir: snapshot_dir != PathBuf::from("snapshots/"),
-            ignore_missing_snapshot,
-            ignore_snapshot_if_db_exists,
-            http_addr: http_addr != default_http_addr(),
-            http_payload_size_limit,
-            experimental_max_number_of_batched_tasks,
-            task_queue_webhook: task_webhook_url.is_some(),
-            task_webhook_authorization_header: task_webhook_authorization_header.is_some(),
-            log_level: log_level.to_string(),
-            max_indexing_memory,
-            max_indexing_threads,
-            with_configuration_file: config_file_path.is_some(),
-            ssl_auth_path: ssl_auth_path.is_some(),
-            ssl_cert_path: ssl_cert_path.is_some(),
-            ssl_key_path: ssl_key_path.is_some(),
-            ssl_ocsp_path: ssl_ocsp_path.is_some(),
-            ssl_require_auth,
-            ssl_resumption,
-            ssl_tickets,
-        }
-    }
-}
-
-pub struct Segment {
-    inbox: Receiver<Message>,
-    user: User,
-    opt: Opt,
-    batcher: AutoBatcher,
-    events: HashMap<TypeId, Event>,
-}
-
-impl Segment {
-    fn compute_traits(opt: &Opt, stats: Stats, features: RuntimeTogglableFeatures) -> Value {
-        static FIRST_START_TIMESTAMP: Lazy<Instant> = Lazy::new(Instant::now);
-        static SYSTEM: Lazy<Value> = Lazy::new(|| {
-            let disks = Disks::new_with_refreshed_list();
-            let mut sys = System::new_all();
-            sys.refresh_all();
-            let kernel_version = System::kernel_version()
-                .and_then(|k| k.split_once('-').map(|(k, _)| k.to_string()));
-            json!({
-                    "distribution": System::name(),
-                    "kernel_version": kernel_version,
-                    "cores": sys.cpus().len(),
-                    "ram_size": sys.total_memory(),
-                    "disk_size": disks.iter().map(|disk| disk.total_space()).max(),
-                    "server_provider": std::env::var("MEILI_SERVER_PROVIDER").ok(),
-            })
-        });
-        let number_of_documents =
-            stats.indexes.values().map(|index| index.number_of_documents).collect::<Vec<u64>>();
-
-        json!({
-            "start_since_days": FIRST_START_TIMESTAMP.elapsed().as_secs() / (60 * 60 * 24), // one day
-            "system": *SYSTEM,
-            "stats": {
-                "database_size": stats.database_size,
-                "indexes_number": stats.indexes.len(),
-                "documents_number": number_of_documents,
-            },
-            "infos": Infos::new(opt.clone(), features),
-        })
-    }
-
-    async fn run(
-        mut self,
-        index_scheduler: Arc<IndexScheduler>,
-        auth_controller: Arc<AuthController>,
-    ) {
-        const INTERVAL: Duration = Duration::from_secs(60 * 60); // one hour
-                                                                 // The first batch must be sent after one hour.
-        let mut interval =
-            tokio::time::interval_at(tokio::time::Instant::now() + INTERVAL, INTERVAL);
-
-        loop {
-            select! {
-                _ = interval.tick() => {
-                    self.tick(index_scheduler.clone(), auth_controller.clone()).await;
-                },
-                Some(msg) = self.inbox.recv() => {
-                    self.handle_msg(msg);
-               }
-            }
-        }
-    }
-
-    fn handle_msg(&mut self, Message { type_id, aggregator_function, event }: Message) {
-        let new_event = match self.events.remove(&type_id) {
-            Some(old) => {
-                // The function should never fail since we retrieved the corresponding TypeId in the map. But in the unfortunate
-                // case it could happens we're going to silently ignore the error
-                let Some(original) = (aggregator_function)(old.original, event.original) else {
-                    return;
-                };
-                Event {
-                    original,
-                    // We always want to return the FIRST timestamp ever encountered
-                    timestamp: old.timestamp,
-                    user_agents: old.user_agents.union(&event.user_agents).cloned().collect(),
-                    total: old.total.saturating_add(event.total),
-                }
-            }
-            None => event,
-        };
-        self.events.insert(type_id, new_event);
-    }
-
-    async fn tick(
-        &mut self,
-        index_scheduler: Arc<IndexScheduler>,
-        auth_controller: Arc<AuthController>,
-    ) {
-        if let Ok(stats) = create_all_stats(
-            index_scheduler.clone().into(),
-            auth_controller.into(),
-            &AuthFilter::default(),
-        ) {
-            // Replace the version number with the prototype name if any.
-            let version = if let Some(prototype) = build_info::DescribeResult::from_build()
-                .and_then(|describe| describe.as_prototype())
-            {
-                prototype
-            } else {
-                env!("CARGO_PKG_VERSION")
-            };
-
-            let _ = self
-                .batcher
-                .push(Identify {
-                    context: Some(json!({
-                        "app": {
-                            "version": version.to_string(),
-                        },
-                    })),
-                    user: self.user.clone(),
-                    traits: Self::compute_traits(
-                        &self.opt,
-                        stats,
-                        index_scheduler.features().runtime_features(),
-                    ),
-                    ..Default::default()
-                })
-                .await;
-        }
-
-        // We empty the list of events
-        let events = std::mem::take(&mut self.events);
-
-        for (_, event) in events {
-            let Event { original, timestamp, user_agents, total } = event;
-            let name = original.event_name();
-            let mut properties = original.into_event();
-            if properties["user-agent"].is_null() {
-                properties["user-agent"] = json!(user_agents);
-            };
-            if properties["requests"]["total_received"].is_null() {
-                properties["requests"]["total_received"] = total.into();
-            };
-
-            let _ = self
-                .batcher
-                .push(Track {
-                    user: self.user.clone(),
-                    event: name.to_string(),
-                    properties,
-                    timestamp: Some(timestamp),
-                    ..Default::default()
-                })
-                .await;
-        }
-
-        let _ = self.batcher.flush().await;
-    }
-}

crates/meilisearch/src/routes/indexes/facet_search.rs

@@ -1,260 +0,0 @@
-use std::collections::{BinaryHeap, HashSet};
-
-use actix_web::web::Data;
-use actix_web::{web, HttpRequest, HttpResponse};
-use deserr::actix_web::AwebJson;
-use index_scheduler::IndexScheduler;
-use meilisearch_types::deserr::DeserrJsonError;
-use meilisearch_types::error::deserr_codes::*;
-use meilisearch_types::error::ResponseError;
-use meilisearch_types::index_uid::IndexUid;
-use meilisearch_types::locales::Locale;
-use serde_json::Value;
-use tracing::debug;
-
-use crate::analytics::{Aggregate, Analytics};
-use crate::extractors::authentication::policies::*;
-use crate::extractors::authentication::GuardedData;
-use crate::routes::indexes::search::search_kind;
-use crate::search::{
-    add_search_rules, perform_facet_search, FacetSearchResult, HybridQuery, MatchingStrategy,
-    RankingScoreThreshold, SearchQuery, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER,
-    DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT,
-    DEFAULT_SEARCH_OFFSET,
-};
-use crate::search_queue::SearchQueue;
-
-pub fn configure(cfg: &mut web::ServiceConfig) {
-    cfg.service(web::resource("").route(web::post().to(search)));
-}
-
-/// # Important
-///
-/// Intentionally don't use `deny_unknown_fields` to ignore search parameters sent by user
-#[derive(Debug, Clone, Default, PartialEq, deserr::Deserr)]
-#[deserr(error = DeserrJsonError, rename_all = camelCase)]
-pub struct FacetSearchQuery {
-    #[deserr(default, error = DeserrJsonError<InvalidFacetSearchQuery>)]
-    pub facet_query: Option<String>,
-    #[deserr(error = DeserrJsonError<InvalidFacetSearchFacetName>, missing_field_error = DeserrJsonError::missing_facet_search_facet_name)]
-    pub facet_name: String,
-    #[deserr(default, error = DeserrJsonError<InvalidSearchQ>)]
-    pub q: Option<String>,
-    #[deserr(default, error = DeserrJsonError<InvalidSearchVector>)]
-    pub vector: Option<Vec<f32>>,
-    #[deserr(default, error = DeserrJsonError<InvalidHybridQuery>)]
-    pub hybrid: Option<HybridQuery>,
-    #[deserr(default, error = DeserrJsonError<InvalidSearchFilter>)]
-    pub filter: Option<Value>,
-    #[deserr(default, error = DeserrJsonError<InvalidSearchMatchingStrategy>, default)]
-    pub matching_strategy: MatchingStrategy,
-    #[deserr(default, error = DeserrJsonError<InvalidSearchAttributesToSearchOn>, default)]
-    pub attributes_to_search_on: Option<Vec<String>>,
-    #[deserr(default, error = DeserrJsonError<InvalidSearchRankingScoreThreshold>, default)]
-    pub ranking_score_threshold: Option<RankingScoreThreshold>,
-    #[deserr(default, error = DeserrJsonError<InvalidSearchLocales>, default)]
-    pub locales: Option<Vec<Locale>>,
-}
-
-#[derive(Default)]
-pub struct FacetSearchAggregator {
-    // requests
-    total_received: usize,
-    total_succeeded: usize,
-    time_spent: BinaryHeap<usize>,
-
-    // The set of all facetNames that were used
-    facet_names: HashSet<String>,
-
-    // As there been any other parameter than the facetName or facetQuery ones?
-    additional_search_parameters_provided: bool,
-}
-
-impl FacetSearchAggregator {
-    #[allow(clippy::field_reassign_with_default)]
-    pub fn from_query(query: &FacetSearchQuery) -> Self {
-        let FacetSearchQuery {
-            facet_query: _,
-            facet_name,
-            vector,
-            q,
-            filter,
-            matching_strategy,
-            attributes_to_search_on,
-            hybrid,
-            ranking_score_threshold,
-            locales,
-        } = query;
-
-        Self {
-            total_received: 1,
-            facet_names: Some(facet_name.clone()).into_iter().collect(),
-            additional_search_parameters_provided: q.is_some()
-                || vector.is_some()
-                || filter.is_some()
-                || *matching_strategy != MatchingStrategy::default()
-                || attributes_to_search_on.is_some()
-                || hybrid.is_some()
-                || ranking_score_threshold.is_some()
-                || locales.is_some(),
-            ..Default::default()
-        }
-    }
-
-    pub fn succeed(&mut self, result: &FacetSearchResult) {
-        let FacetSearchResult { facet_hits: _, facet_query: _, processing_time_ms } = result;
-        self.total_succeeded = 1;
-        self.time_spent.push(*processing_time_ms as usize);
-    }
-}
-
-impl Aggregate for FacetSearchAggregator {
-    fn event_name(&self) -> &'static str {
-        "Facet Searched POST"
-    }
-
-    fn aggregate(mut self: Box<Self>, new: Box<Self>) -> Box<Self> {
-        for time in new.time_spent {
-            self.time_spent.push(time);
-        }
-
-        Box::new(Self {
-            total_received: self.total_received.saturating_add(new.total_received),
-            total_succeeded: self.total_succeeded.saturating_add(new.total_succeeded),
-            time_spent: self.time_spent,
-            facet_names: self.facet_names.union(&new.facet_names).cloned().collect(),
-            additional_search_parameters_provided: self.additional_search_parameters_provided
-                | new.additional_search_parameters_provided,
-        })
-    }
-
-    fn into_event(self: Box<Self>) -> serde_json::Value {
-        let Self {
-            total_received,
-            total_succeeded,
-            time_spent,
-            facet_names,
-            additional_search_parameters_provided,
-        } = *self;
-        // the index of the 99th percentage of value
-        let percentile_99th = 0.99 * (total_succeeded as f64 - 1.) + 1.;
-        // we get all the values in a sorted manner
-        let time_spent = time_spent.into_sorted_vec();
-        // We are only interested by the slowest value of the 99th fastest results
-        let time_spent = time_spent.get(percentile_99th as usize);
-
-        serde_json::json!({
-            "requests": {
-                "99th_response_time":  time_spent.map(|t| format!("{:.2}", t)),
-                "total_succeeded": total_succeeded,
-                "total_failed": total_received.saturating_sub(total_succeeded), // just to be sure we never panics
-                "total_received": total_received,
-            },
-            "facets": {
-                "total_distinct_facet_count": facet_names.len(),
-                "additional_search_parameters_provided": additional_search_parameters_provided,
-            },
-        })
-    }
-}
-
-pub async fn search(
-    index_scheduler: GuardedData<ActionPolicy<{ actions::SEARCH }>, Data<IndexScheduler>>,
-    search_queue: Data<SearchQueue>,
-    index_uid: web::Path<String>,
-    params: AwebJson<FacetSearchQuery, DeserrJsonError>,
-    req: HttpRequest,
-    analytics: web::Data<Analytics>,
-) -> Result<HttpResponse, ResponseError> {
-    let index_uid = IndexUid::try_from(index_uid.into_inner())?;
-
-    let query = params.into_inner();
-    debug!(parameters = ?query, "Facet search");
-
-    let mut aggregate = FacetSearchAggregator::from_query(&query);
-
-    let facet_query = query.facet_query.clone();
-    let facet_name = query.facet_name.clone();
-    let locales = query.locales.clone().map(|l| l.into_iter().map(Into::into).collect());
-    let mut search_query = SearchQuery::from(query);
-
-    // Tenant token search_rules.
-    if let Some(search_rules) = index_scheduler.filters().get_index_search_rules(&index_uid) {
-        add_search_rules(&mut search_query.filter, search_rules);
-    }
-
-    let index = index_scheduler.index(&index_uid)?;
-    let features = index_scheduler.features();
-    let search_kind = search_kind(&search_query, &index_scheduler, &index, features)?;
-    let permit = search_queue.try_get_search_permit().await?;
-    let search_result = tokio::task::spawn_blocking(move || {
-        perform_facet_search(
-            &index,
-            search_query,
-            facet_query,
-            facet_name,
-            search_kind,
-            index_scheduler.features(),
-            locales,
-        )
-    })
-    .await;
-    permit.drop().await;
-    let search_result = search_result?;
-
-    if let Ok(ref search_result) = search_result {
-        aggregate.succeed(search_result);
-    }
-    analytics.publish(aggregate, &req);
-
-    let search_result = search_result?;
-
-    debug!(returns = ?search_result, "Facet search");
-    Ok(HttpResponse::Ok().json(search_result))
-}
-
-impl From<FacetSearchQuery> for SearchQuery {
-    fn from(value: FacetSearchQuery) -> Self {
-        let FacetSearchQuery {
-            facet_query: _,
-            facet_name: _,
-            q,
-            vector,
-            filter,
-            matching_strategy,
-            attributes_to_search_on,
-            hybrid,
-            ranking_score_threshold,
-            locales,
-        } = value;
-
-        SearchQuery {
-            q,
-            offset: DEFAULT_SEARCH_OFFSET(),
-            limit: DEFAULT_SEARCH_LIMIT(),
-            page: None,
-            hits_per_page: None,
-            attributes_to_retrieve: None,
-            retrieve_vectors: false,
-            attributes_to_crop: None,
-            crop_length: DEFAULT_CROP_LENGTH(),
-            attributes_to_highlight: None,
-            show_matches_position: false,
-            show_ranking_score: false,
-            show_ranking_score_details: false,
-            filter,
-            sort: None,
-            distinct: None,
-            facets: None,
-            highlight_pre_tag: DEFAULT_HIGHLIGHT_PRE_TAG(),
-            highlight_post_tag: DEFAULT_HIGHLIGHT_POST_TAG(),
-            crop_marker: DEFAULT_CROP_MARKER(),
-            matching_strategy,
-            vector,
-            attributes_to_search_on,
-            hybrid,
-            ranking_score_threshold,
-            locales,
-        }
-    }
-}

crates/meilisearch/src/routes/indexes/search_analytics.rs

@@ -1,483 +0,0 @@
-use std::collections::{BTreeSet, BinaryHeap, HashMap};
-
-use meilisearch_types::locales::Locale;
-use once_cell::sync::Lazy;
-use regex::Regex;
-use serde_json::{json, Value};
-
-use crate::aggregate_methods;
-use crate::analytics::{Aggregate, AggregateMethod};
-use crate::search::{
-    SearchQuery, SearchResult, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER,
-    DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT,
-    DEFAULT_SEMANTIC_RATIO,
-};
-
-aggregate_methods!(
-    SearchGET => "Documents Searched GET",
-    SearchPOST => "Documents Searched POST",
-);
-
-#[derive(Default)]
-pub struct SearchAggregator<Method: AggregateMethod> {
-    // requests
-    total_received: usize,
-    total_succeeded: usize,
-    total_degraded: usize,
-    total_used_negative_operator: usize,
-    time_spent: BinaryHeap<usize>,
-
-    // sort
-    sort_with_geo_point: bool,
-    // every time a request has a filter, this field must be incremented by the number of terms it contains
-    sort_sum_of_criteria_terms: usize,
-    // every time a request has a filter, this field must be incremented by one
-    sort_total_number_of_criteria: usize,
-
-    // distinct
-    distinct: bool,
-
-    // filter
-    filter_with_geo_radius: bool,
-    filter_with_geo_bounding_box: bool,
-    // every time a request has a filter, this field must be incremented by the number of terms it contains
-    filter_sum_of_criteria_terms: usize,
-    // every time a request has a filter, this field must be incremented by one
-    filter_total_number_of_criteria: usize,
-    used_syntax: HashMap<String, usize>,
-
-    // attributes_to_search_on
-    // every time a search is done using attributes_to_search_on
-    attributes_to_search_on_total_number_of_uses: usize,
-
-    // q
-    // The maximum number of terms in a q request
-    max_terms_number: usize,
-
-    // vector
-    // The maximum number of floats in a vector request
-    max_vector_size: usize,
-    // Whether the semantic ratio passed to a hybrid search equals the default ratio.
-    semantic_ratio: bool,
-    hybrid: bool,
-    retrieve_vectors: bool,
-
-    // every time a search is done, we increment the counter linked to the used settings
-    matching_strategy: HashMap<String, usize>,
-
-    // List of the unique Locales passed as parameter
-    locales: BTreeSet<Locale>,
-
-    // pagination
-    max_limit: usize,
-    max_offset: usize,
-    finite_pagination: usize,
-
-    // formatting
-    max_attributes_to_retrieve: usize,
-    max_attributes_to_highlight: usize,
-    highlight_pre_tag: bool,
-    highlight_post_tag: bool,
-    max_attributes_to_crop: usize,
-    crop_marker: bool,
-    show_matches_position: bool,
-    crop_length: bool,
-
-    // facets
-    facets_sum_of_terms: usize,
-    facets_total_number_of_facets: usize,
-
-    // scoring
-    show_ranking_score: bool,
-    show_ranking_score_details: bool,
-    ranking_score_threshold: bool,
-
-    marker: std::marker::PhantomData<Method>,
-}
-
-impl<Method: AggregateMethod> SearchAggregator<Method> {
-    #[allow(clippy::field_reassign_with_default)]
-    pub fn from_query(query: &SearchQuery) -> Self {
-        let SearchQuery {
-            q,
-            vector,
-            offset,
-            limit,
-            page,
-            hits_per_page,
-            attributes_to_retrieve: _,
-            retrieve_vectors,
-            attributes_to_crop: _,
-            crop_length,
-            attributes_to_highlight: _,
-            show_matches_position,
-            show_ranking_score,
-            show_ranking_score_details,
-            filter,
-            sort,
-            distinct,
-            facets: _,
-            highlight_pre_tag,
-            highlight_post_tag,
-            crop_marker,
-            matching_strategy,
-            attributes_to_search_on,
-            hybrid,
-            ranking_score_threshold,
-            locales,
-        } = query;
-
-        let mut ret = Self::default();
-
-        ret.total_received = 1;
-
-        if let Some(ref sort) = sort {
-            ret.sort_total_number_of_criteria = 1;
-            ret.sort_with_geo_point = sort.iter().any(|s| s.contains("_geoPoint("));
-            ret.sort_sum_of_criteria_terms = sort.len();
-        }
-
-        ret.distinct = distinct.is_some();
-
-        if let Some(ref filter) = filter {
-            static RE: Lazy<Regex> = Lazy::new(|| Regex::new("AND | OR").unwrap());
-            ret.filter_total_number_of_criteria = 1;
-
-            let syntax = match filter {
-                Value::String(_) => "string".to_string(),
-                Value::Array(values) => {
-                    if values.iter().map(|v| v.to_string()).any(|s| RE.is_match(&s)) {
-                        "mixed".to_string()
-                    } else {
-                        "array".to_string()
-                    }
-                }
-                _ => "none".to_string(),
-            };
-            // convert the string to a HashMap
-            ret.used_syntax.insert(syntax, 1);
-
-            let stringified_filters = filter.to_string();
-            ret.filter_with_geo_radius = stringified_filters.contains("_geoRadius(");
-            ret.filter_with_geo_bounding_box = stringified_filters.contains("_geoBoundingBox(");
-            ret.filter_sum_of_criteria_terms = RE.split(&stringified_filters).count();
-        }
-
-        // attributes_to_search_on
-        if attributes_to_search_on.is_some() {
-            ret.attributes_to_search_on_total_number_of_uses = 1;
-        }
-
-        if let Some(ref q) = q {
-            ret.max_terms_number = q.split_whitespace().count();
-        }
-
-        if let Some(ref vector) = vector {
-            ret.max_vector_size = vector.len();
-        }
-        ret.retrieve_vectors |= retrieve_vectors;
-
-        if query.is_finite_pagination() {
-            let limit = hits_per_page.unwrap_or_else(DEFAULT_SEARCH_LIMIT);
-            ret.max_limit = limit;
-            ret.max_offset = page.unwrap_or(1).saturating_sub(1) * limit;
-            ret.finite_pagination = 1;
-        } else {
-            ret.max_limit = *limit;
-            ret.max_offset = *offset;
-            ret.finite_pagination = 0;
-        }
-
-        ret.matching_strategy.insert(format!("{:?}", matching_strategy), 1);
-
-        if let Some(locales) = locales {
-            ret.locales = locales.iter().copied().collect();
-        }
-
-        ret.highlight_pre_tag = *highlight_pre_tag != DEFAULT_HIGHLIGHT_PRE_TAG();
-        ret.highlight_post_tag = *highlight_post_tag != DEFAULT_HIGHLIGHT_POST_TAG();
-        ret.crop_marker = *crop_marker != DEFAULT_CROP_MARKER();
-        ret.crop_length = *crop_length != DEFAULT_CROP_LENGTH();
-        ret.show_matches_position = *show_matches_position;
-
-        ret.show_ranking_score = *show_ranking_score;
-        ret.show_ranking_score_details = *show_ranking_score_details;
-        ret.ranking_score_threshold = ranking_score_threshold.is_some();
-
-        if let Some(hybrid) = hybrid {
-            ret.semantic_ratio = hybrid.semantic_ratio != DEFAULT_SEMANTIC_RATIO();
-            ret.hybrid = true;
-        }
-
-        ret
-    }
-
-    pub fn succeed(&mut self, result: &SearchResult) {
-        let SearchResult {
-            hits: _,
-            query: _,
-            processing_time_ms,
-            hits_info: _,
-            semantic_hit_count: _,
-            facet_distribution: _,
-            facet_stats: _,
-            degraded,
-            used_negative_operator,
-        } = result;
-
-        self.total_succeeded = self.total_succeeded.saturating_add(1);
-        if *degraded {
-            self.total_degraded = self.total_degraded.saturating_add(1);
-        }
-        if *used_negative_operator {
-            self.total_used_negative_operator = self.total_used_negative_operator.saturating_add(1);
-        }
-        self.time_spent.push(*processing_time_ms as usize);
-    }
-}
-
-impl<Method: AggregateMethod> Aggregate for SearchAggregator<Method> {
-    fn event_name(&self) -> &'static str {
-        Method::event_name()
-    }
-
-    fn aggregate(mut self: Box<Self>, new: Box<Self>) -> Box<Self> {
-        let Self {
-            total_received,
-            total_succeeded,
-            mut time_spent,
-            sort_with_geo_point,
-            sort_sum_of_criteria_terms,
-            sort_total_number_of_criteria,
-            distinct,
-            filter_with_geo_radius,
-            filter_with_geo_bounding_box,
-            filter_sum_of_criteria_terms,
-            filter_total_number_of_criteria,
-            used_syntax,
-            attributes_to_search_on_total_number_of_uses,
-            max_terms_number,
-            max_vector_size,
-            retrieve_vectors,
-            matching_strategy,
-            max_limit,
-            max_offset,
-            finite_pagination,
-            max_attributes_to_retrieve,
-            max_attributes_to_highlight,
-            highlight_pre_tag,
-            highlight_post_tag,
-            max_attributes_to_crop,
-            crop_marker,
-            show_matches_position,
-            crop_length,
-            facets_sum_of_terms,
-            facets_total_number_of_facets,
-            show_ranking_score,
-            show_ranking_score_details,
-            semantic_ratio,
-            hybrid,
-            total_degraded,
-            total_used_negative_operator,
-            ranking_score_threshold,
-            mut locales,
-            marker: _,
-        } = *new;
-
-        // request
-        self.total_received = self.total_received.saturating_add(total_received);
-        self.total_succeeded = self.total_succeeded.saturating_add(total_succeeded);
-        self.total_degraded = self.total_degraded.saturating_add(total_degraded);
-        self.total_used_negative_operator =
-            self.total_used_negative_operator.saturating_add(total_used_negative_operator);
-        self.time_spent.append(&mut time_spent);
-
-        // sort
-        self.sort_with_geo_point |= sort_with_geo_point;
-        self.sort_sum_of_criteria_terms =
-            self.sort_sum_of_criteria_terms.saturating_add(sort_sum_of_criteria_terms);
-        self.sort_total_number_of_criteria =
-            self.sort_total_number_of_criteria.saturating_add(sort_total_number_of_criteria);
-
-        // distinct
-        self.distinct |= distinct;
-
-        // filter
-        self.filter_with_geo_radius |= filter_with_geo_radius;
-        self.filter_with_geo_bounding_box |= filter_with_geo_bounding_box;
-        self.filter_sum_of_criteria_terms =
-            self.filter_sum_of_criteria_terms.saturating_add(filter_sum_of_criteria_terms);
-        self.filter_total_number_of_criteria =
-            self.filter_total_number_of_criteria.saturating_add(filter_total_number_of_criteria);
-        for (key, value) in used_syntax.into_iter() {
-            let used_syntax = self.used_syntax.entry(key).or_insert(0);
-            *used_syntax = used_syntax.saturating_add(value);
-        }
-
-        // attributes_to_search_on
-        self.attributes_to_search_on_total_number_of_uses = self
-            .attributes_to_search_on_total_number_of_uses
-            .saturating_add(attributes_to_search_on_total_number_of_uses);
-
-        // q
-        self.max_terms_number = self.max_terms_number.max(max_terms_number);
-
-        // vector
-        self.max_vector_size = self.max_vector_size.max(max_vector_size);
-        self.retrieve_vectors |= retrieve_vectors;
-        self.semantic_ratio |= semantic_ratio;
-        self.hybrid |= hybrid;
-
-        // pagination
-        self.max_limit = self.max_limit.max(max_limit);
-        self.max_offset = self.max_offset.max(max_offset);
-        self.finite_pagination += finite_pagination;
-
-        // formatting
-        self.max_attributes_to_retrieve =
-            self.max_attributes_to_retrieve.max(max_attributes_to_retrieve);
-        self.max_attributes_to_highlight =
-            self.max_attributes_to_highlight.max(max_attributes_to_highlight);
-        self.highlight_pre_tag |= highlight_pre_tag;
-        self.highlight_post_tag |= highlight_post_tag;
-        self.max_attributes_to_crop = self.max_attributes_to_crop.max(max_attributes_to_crop);
-        self.crop_marker |= crop_marker;
-        self.show_matches_position |= show_matches_position;
-        self.crop_length |= crop_length;
-
-        // facets
-        self.facets_sum_of_terms = self.facets_sum_of_terms.saturating_add(facets_sum_of_terms);
-        self.facets_total_number_of_facets =
-            self.facets_total_number_of_facets.saturating_add(facets_total_number_of_facets);
-
-        // matching strategy
-        for (key, value) in matching_strategy.into_iter() {
-            let matching_strategy = self.matching_strategy.entry(key).or_insert(0);
-            *matching_strategy = matching_strategy.saturating_add(value);
-        }
-
-        // scoring
-        self.show_ranking_score |= show_ranking_score;
-        self.show_ranking_score_details |= show_ranking_score_details;
-        self.ranking_score_threshold |= ranking_score_threshold;
-
-        // locales
-        self.locales.append(&mut locales);
-
-        self
-    }
-
-    fn into_event(self: Box<Self>) -> serde_json::Value {
-        let Self {
-            total_received,
-            total_succeeded,
-            time_spent,
-            sort_with_geo_point,
-            sort_sum_of_criteria_terms,
-            sort_total_number_of_criteria,
-            distinct,
-            filter_with_geo_radius,
-            filter_with_geo_bounding_box,
-            filter_sum_of_criteria_terms,
-            filter_total_number_of_criteria,
-            used_syntax,
-            attributes_to_search_on_total_number_of_uses,
-            max_terms_number,
-            max_vector_size,
-            retrieve_vectors,
-            matching_strategy,
-            max_limit,
-            max_offset,
-            finite_pagination,
-            max_attributes_to_retrieve,
-            max_attributes_to_highlight,
-            highlight_pre_tag,
-            highlight_post_tag,
-            max_attributes_to_crop,
-            crop_marker,
-            show_matches_position,
-            crop_length,
-            facets_sum_of_terms,
-            facets_total_number_of_facets,
-            show_ranking_score,
-            show_ranking_score_details,
-            semantic_ratio,
-            hybrid,
-            total_degraded,
-            total_used_negative_operator,
-            ranking_score_threshold,
-            locales,
-            marker: _,
-        } = *self;
-
-        // we get all the values in a sorted manner
-        let time_spent = time_spent.into_sorted_vec();
-        // the index of the 99th percentage of value
-        let percentile_99th = time_spent.len() * 99 / 100;
-        // We are only interested by the slowest value of the 99th fastest results
-        let time_spent = time_spent.get(percentile_99th);
-
-        json!({
-            "requests": {
-                "99th_response_time": time_spent.map(|t| format!("{:.2}", t)),
-                "total_succeeded": total_succeeded,
-                "total_failed": total_received.saturating_sub(total_succeeded), // just to be sure we never panics
-                "total_received": total_received,
-                "total_degraded": total_degraded,
-                "total_used_negative_operator": total_used_negative_operator,
-            },
-            "sort": {
-                "with_geoPoint": sort_with_geo_point,
-                "avg_criteria_number": format!("{:.2}", sort_sum_of_criteria_terms as f64 / sort_total_number_of_criteria as f64),
-            },
-            "distinct": distinct,
-            "filter": {
-               "with_geoRadius": filter_with_geo_radius,
-               "with_geoBoundingBox": filter_with_geo_bounding_box,
-               "avg_criteria_number": format!("{:.2}", filter_sum_of_criteria_terms as f64 / filter_total_number_of_criteria as f64),
-               "most_used_syntax": used_syntax.iter().max_by_key(|(_, v)| *v).map(|(k, _)| json!(k)).unwrap_or_else(|| json!(null)),
-            },
-            "attributes_to_search_on": {
-               "total_number_of_uses": attributes_to_search_on_total_number_of_uses,
-            },
-            "q": {
-               "max_terms_number": max_terms_number,
-            },
-            "vector": {
-                "max_vector_size": max_vector_size,
-                "retrieve_vectors": retrieve_vectors,
-            },
-            "hybrid": {
-                "enabled": hybrid,
-                "semantic_ratio": semantic_ratio,
-            },
-            "pagination": {
-               "max_limit": max_limit,
-               "max_offset": max_offset,
-               "most_used_navigation": if finite_pagination > (total_received / 2) { "exhaustive" } else { "estimated" },
-            },
-            "formatting": {
-                "max_attributes_to_retrieve": max_attributes_to_retrieve,
-                "max_attributes_to_highlight": max_attributes_to_highlight,
-                "highlight_pre_tag": highlight_pre_tag,
-                "highlight_post_tag": highlight_post_tag,
-                "max_attributes_to_crop": max_attributes_to_crop,
-                "crop_marker": crop_marker,
-                "show_matches_position": show_matches_position,
-                "crop_length": crop_length,
-            },
-            "facets": {
-                "avg_facets_number": format!("{:.2}", facets_sum_of_terms as f64 / facets_total_number_of_facets as f64),
-            },
-            "matching_strategy": {
-                "most_used_strategy": matching_strategy.iter().max_by_key(|(_, v)| *v).map(|(k, _)| json!(k)).unwrap_or_else(|| json!(null)),
-            },
-            "locales": locales,
-            "scoring": {
-                "show_ranking_score": show_ranking_score,
-                "show_ranking_score_details": show_ranking_score_details,
-                "ranking_score_threshold": ranking_score_threshold,
-            },
-        })
-    }
-}

crates/meilisearch/src/routes/indexes/settings.rs

@@ -1,532 +0,0 @@
-use actix_web::web::Data;
-use actix_web::{web, HttpRequest, HttpResponse};
-use deserr::actix_web::AwebJson;
-use index_scheduler::IndexScheduler;
-use meilisearch_types::deserr::DeserrJsonError;
-use meilisearch_types::error::ResponseError;
-use meilisearch_types::index_uid::IndexUid;
-use meilisearch_types::milli::update::Setting;
-use meilisearch_types::settings::{settings, SecretPolicy, Settings, Unchecked};
-use meilisearch_types::tasks::KindWithContent;
-use tracing::debug;
-
-use super::settings_analytics::*;
-use crate::analytics::Analytics;
-use crate::extractors::authentication::policies::*;
-use crate::extractors::authentication::GuardedData;
-use crate::routes::{get_task_id, is_dry_run, SummarizedTaskView};
-use crate::Opt;
-
-#[macro_export]
-macro_rules! make_setting_route {
-    ($route:literal, $update_verb:ident, $type:ty, $err_ty:ty, $attr:ident, $camelcase_attr:literal, $analytics:ident) => {
-        pub mod $attr {
-            use actix_web::web::Data;
-            use actix_web::{web, HttpRequest, HttpResponse, Resource};
-            use index_scheduler::IndexScheduler;
-            use meilisearch_types::error::ResponseError;
-            use meilisearch_types::index_uid::IndexUid;
-            use meilisearch_types::milli::update::Setting;
-            use meilisearch_types::settings::{settings, Settings};
-            use meilisearch_types::tasks::KindWithContent;
-            use tracing::debug;
-            use $crate::analytics::Analytics;
-            use $crate::extractors::authentication::policies::*;
-            use $crate::extractors::authentication::GuardedData;
-            use $crate::extractors::sequential_extractor::SeqHandler;
-            use $crate::Opt;
-            use $crate::routes::{is_dry_run, get_task_id, SummarizedTaskView};
-
-            pub async fn delete(
-                index_scheduler: GuardedData<
-                    ActionPolicy<{ actions::SETTINGS_UPDATE }>,
-                    Data<IndexScheduler>,
-                >,
-                index_uid: web::Path<String>,
-                req: HttpRequest,
-                opt: web::Data<Opt>,
-            ) -> Result<HttpResponse, ResponseError> {
-                let index_uid = IndexUid::try_from(index_uid.into_inner())?;
-
-                let new_settings = Settings { $attr: Setting::Reset.into(), ..Default::default() };
-
-                let allow_index_creation =
-                    index_scheduler.filters().allow_index_creation(&index_uid);
-
-                let task = KindWithContent::SettingsUpdate {
-                    index_uid: index_uid.to_string(),
-                    new_settings: Box::new(new_settings),
-                    is_deletion: true,
-                    allow_index_creation,
-                };
-                let uid = get_task_id(&req, &opt)?;
-                let dry_run = is_dry_run(&req, &opt)?;
-                let task: SummarizedTaskView =
-                    tokio::task::spawn_blocking(move || index_scheduler.register(task, uid, dry_run))
-                        .await??
-                        .into();
-
-                debug!(returns = ?task, "Delete settings");
-                Ok(HttpResponse::Accepted().json(task))
-            }
-
-            pub async fn update(
-                index_scheduler: GuardedData<
-                    ActionPolicy<{ actions::SETTINGS_UPDATE }>,
-                    Data<IndexScheduler>,
-                >,
-                index_uid: actix_web::web::Path<String>,
-                body: deserr::actix_web::AwebJson<Option<$type>, $err_ty>,
-                req: HttpRequest,
-                opt: web::Data<Opt>,
-                analytics: web::Data<Analytics>,
-            ) -> std::result::Result<HttpResponse, ResponseError> {
-                let index_uid = IndexUid::try_from(index_uid.into_inner())?;
-
-                let body = body.into_inner();
-                debug!(parameters = ?body, "Update settings");
-
-                #[allow(clippy::redundant_closure_call)]
-                analytics.publish(
-                    $crate::routes::indexes::settings_analytics::$analytics::new(body.as_ref()).into_settings(),
-                    &req,
-                );
-
-                let new_settings = Settings {
-                    $attr: match body {
-                        Some(inner_body) => Setting::Set(inner_body).into(),
-                        None => Setting::Reset.into(),
-                    },
-                    ..Default::default()
-                };
-
-                let new_settings = $crate::routes::indexes::settings::validate_settings(
-                    new_settings,
-                    &index_scheduler,
-                )?;
-
-                let allow_index_creation =
-                    index_scheduler.filters().allow_index_creation(&index_uid);
-
-                let task = KindWithContent::SettingsUpdate {
-                    index_uid: index_uid.to_string(),
-                    new_settings: Box::new(new_settings),
-                    is_deletion: false,
-                    allow_index_creation,
-                };
-                let uid = get_task_id(&req, &opt)?;
-                let dry_run = is_dry_run(&req, &opt)?;
-                let task: SummarizedTaskView =
-                    tokio::task::spawn_blocking(move || index_scheduler.register(task, uid, dry_run))
-                        .await??
-                        .into();
-
-                debug!(returns = ?task, "Update settings");
-                Ok(HttpResponse::Accepted().json(task))
-            }
-
-            pub async fn get(
-                index_scheduler: GuardedData<
-                    ActionPolicy<{ actions::SETTINGS_GET }>,
-                    Data<IndexScheduler>,
-                >,
-                index_uid: actix_web::web::Path<String>,
-            ) -> std::result::Result<HttpResponse, ResponseError> {
-                let index_uid = IndexUid::try_from(index_uid.into_inner())?;
-
-                let index = index_scheduler.index(&index_uid)?;
-                let rtxn = index.read_txn()?;
-                let settings = settings(&index, &rtxn, meilisearch_types::settings::SecretPolicy::HideSecrets)?;
-
-                debug!(returns = ?settings, "Update settings");
-
-                Ok(HttpResponse::Ok().json(settings.$attr))
-            }
-
-            pub fn resources() -> Resource {
-                Resource::new($route)
-                    .route(web::get().to(SeqHandler(get)))
-                    .route(web::$update_verb().to(SeqHandler(update)))
-                    .route(web::delete().to(SeqHandler(delete)))
-            }
-        }
-    };
-}
-
-make_setting_route!(
-    "/filterable-attributes",
-    put,
-    std::collections::BTreeSet<String>,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsFilterableAttributes,
-    >,
-    filterable_attributes,
-    "filterableAttributes",
-    FilterableAttributesAnalytics
-);
-
-make_setting_route!(
-    "/sortable-attributes",
-    put,
-    std::collections::BTreeSet<String>,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsSortableAttributes,
-    >,
-    sortable_attributes,
-    "sortableAttributes",
-    SortableAttributesAnalytics
-);
-
-make_setting_route!(
-    "/displayed-attributes",
-    put,
-    Vec<String>,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsDisplayedAttributes,
-    >,
-    displayed_attributes,
-    "displayedAttributes",
-    DisplayedAttributesAnalytics
-);
-
-make_setting_route!(
-    "/typo-tolerance",
-    patch,
-    meilisearch_types::settings::TypoSettings,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsTypoTolerance,
-    >,
-    typo_tolerance,
-    "typoTolerance",
-    TypoToleranceAnalytics
-);
-
-make_setting_route!(
-    "/searchable-attributes",
-    put,
-    Vec<String>,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsSearchableAttributes,
-    >,
-    searchable_attributes,
-    "searchableAttributes",
-    SearchableAttributesAnalytics
-);
-
-make_setting_route!(
-    "/stop-words",
-    put,
-    std::collections::BTreeSet<String>,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsStopWords,
-    >,
-    stop_words,
-    "stopWords",
-    StopWordsAnalytics
-);
-
-make_setting_route!(
-    "/non-separator-tokens",
-    put,
-    std::collections::BTreeSet<String>,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsNonSeparatorTokens,
-    >,
-    non_separator_tokens,
-    "nonSeparatorTokens",
-    NonSeparatorTokensAnalytics
-);
-
-make_setting_route!(
-    "/separator-tokens",
-    put,
-    std::collections::BTreeSet<String>,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsSeparatorTokens,
-    >,
-    separator_tokens,
-    "separatorTokens",
-    SeparatorTokensAnalytics
-);
-
-make_setting_route!(
-    "/dictionary",
-    put,
-    std::collections::BTreeSet<String>,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsDictionary,
-    >,
-    dictionary,
-    "dictionary",
-    DictionaryAnalytics
-);
-
-make_setting_route!(
-    "/synonyms",
-    put,
-    std::collections::BTreeMap<String, Vec<String>>,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsSynonyms,
-    >,
-    synonyms,
-    "synonyms",
-    SynonymsAnalytics
-);
-
-make_setting_route!(
-    "/distinct-attribute",
-    put,
-    String,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsDistinctAttribute,
-    >,
-    distinct_attribute,
-    "distinctAttribute",
-    DistinctAttributeAnalytics
-);
-
-make_setting_route!(
-    "/proximity-precision",
-    put,
-    meilisearch_types::settings::ProximityPrecisionView,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsProximityPrecision,
-    >,
-    proximity_precision,
-    "proximityPrecision",
-    ProximityPrecisionAnalytics
-);
-
-make_setting_route!(
-    "/localized-attributes",
-    put,
-    Vec<meilisearch_types::locales::LocalizedAttributesRuleView>,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsLocalizedAttributes,
-    >,
-    localized_attributes,
-    "localizedAttributes",
-    LocalesAnalytics
-);
-
-make_setting_route!(
-    "/ranking-rules",
-    put,
-    Vec<meilisearch_types::settings::RankingRuleView>,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsRankingRules,
-    >,
-    ranking_rules,
-    "rankingRules",
-    RankingRulesAnalytics
-);
-
-make_setting_route!(
-    "/faceting",
-    patch,
-    meilisearch_types::settings::FacetingSettings,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsFaceting,
-    >,
-    faceting,
-    "faceting",
-    FacetingAnalytics
-);
-
-make_setting_route!(
-    "/pagination",
-    patch,
-    meilisearch_types::settings::PaginationSettings,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsPagination,
-    >,
-    pagination,
-    "pagination",
-    PaginationAnalytics
-);
-
-make_setting_route!(
-    "/embedders",
-    patch,
-    std::collections::BTreeMap<String, Setting<meilisearch_types::milli::vector::settings::EmbeddingSettings>>,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsEmbedders,
-    >,
-    embedders,
-    "embedders",
-    EmbeddersAnalytics
-);
-
-make_setting_route!(
-    "/search-cutoff-ms",
-    put,
-    u64,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsSearchCutoffMs,
-    >,
-    search_cutoff_ms,
-    "searchCutoffMs",
-    SearchCutoffMsAnalytics
-);
-
-macro_rules! generate_configure {
-    ($($mod:ident),*) => {
-        pub fn configure(cfg: &mut web::ServiceConfig) {
-            use crate::extractors::sequential_extractor::SeqHandler;
-            cfg.service(
-                web::resource("")
-                .route(web::patch().to(SeqHandler(update_all)))
-                .route(web::get().to(SeqHandler(get_all)))
-                .route(web::delete().to(SeqHandler(delete_all))))
-                $(.service($mod::resources()))*;
-        }
-    };
-}
-
-generate_configure!(
-    filterable_attributes,
-    sortable_attributes,
-    displayed_attributes,
-    localized_attributes,
-    searchable_attributes,
-    distinct_attribute,
-    proximity_precision,
-    stop_words,
-    separator_tokens,
-    non_separator_tokens,
-    dictionary,
-    synonyms,
-    ranking_rules,
-    typo_tolerance,
-    pagination,
-    faceting,
-    embedders,
-    search_cutoff_ms
-);
-
-pub async fn update_all(
-    index_scheduler: GuardedData<ActionPolicy<{ actions::SETTINGS_UPDATE }>, Data<IndexScheduler>>,
-    index_uid: web::Path<String>,
-    body: AwebJson<Settings<Unchecked>, DeserrJsonError>,
-    req: HttpRequest,
-    opt: web::Data<Opt>,
-    analytics: web::Data<Analytics>,
-) -> Result<HttpResponse, ResponseError> {
-    let index_uid = IndexUid::try_from(index_uid.into_inner())?;
-
-    let new_settings = body.into_inner();
-    debug!(parameters = ?new_settings, "Update all settings");
-    let new_settings = validate_settings(new_settings, &index_scheduler)?;
-
-    analytics.publish(
-        SettingsAnalytics {
-            ranking_rules: RankingRulesAnalytics::new(new_settings.ranking_rules.as_ref().set()),
-            searchable_attributes: SearchableAttributesAnalytics::new(
-                new_settings.searchable_attributes.as_ref().set(),
-            ),
-            displayed_attributes: DisplayedAttributesAnalytics::new(
-                new_settings.displayed_attributes.as_ref().set(),
-            ),
-            sortable_attributes: SortableAttributesAnalytics::new(
-                new_settings.sortable_attributes.as_ref().set(),
-            ),
-            filterable_attributes: FilterableAttributesAnalytics::new(
-                new_settings.filterable_attributes.as_ref().set(),
-            ),
-            distinct_attribute: DistinctAttributeAnalytics::new(
-                new_settings.distinct_attribute.as_ref().set(),
-            ),
-            proximity_precision: ProximityPrecisionAnalytics::new(
-                new_settings.proximity_precision.as_ref().set(),
-            ),
-            typo_tolerance: TypoToleranceAnalytics::new(new_settings.typo_tolerance.as_ref().set()),
-            faceting: FacetingAnalytics::new(new_settings.faceting.as_ref().set()),
-            pagination: PaginationAnalytics::new(new_settings.pagination.as_ref().set()),
-            stop_words: StopWordsAnalytics::new(new_settings.stop_words.as_ref().set()),
-            synonyms: SynonymsAnalytics::new(new_settings.synonyms.as_ref().set()),
-            embedders: EmbeddersAnalytics::new(new_settings.embedders.as_ref().set()),
-            search_cutoff_ms: SearchCutoffMsAnalytics::new(
-                new_settings.search_cutoff_ms.as_ref().set(),
-            ),
-            locales: LocalesAnalytics::new(new_settings.localized_attributes.as_ref().set()),
-            dictionary: DictionaryAnalytics::new(new_settings.dictionary.as_ref().set()),
-            separator_tokens: SeparatorTokensAnalytics::new(
-                new_settings.separator_tokens.as_ref().set(),
-            ),
-            non_separator_tokens: NonSeparatorTokensAnalytics::new(
-                new_settings.non_separator_tokens.as_ref().set(),
-            ),
-        },
-        &req,
-    );
-
-    let allow_index_creation = index_scheduler.filters().allow_index_creation(&index_uid);
-    let index_uid = IndexUid::try_from(index_uid.into_inner())?.into_inner();
-    let task = KindWithContent::SettingsUpdate {
-        index_uid,
-        new_settings: Box::new(new_settings),
-        is_deletion: false,
-        allow_index_creation,
-    };
-    let uid = get_task_id(&req, &opt)?;
-    let dry_run = is_dry_run(&req, &opt)?;
-    let task: SummarizedTaskView =
-        tokio::task::spawn_blocking(move || index_scheduler.register(task, uid, dry_run))
-            .await??
-            .into();
-
-    debug!(returns = ?task, "Update all settings");
-    Ok(HttpResponse::Accepted().json(task))
-}
-
-pub async fn get_all(
-    index_scheduler: GuardedData<ActionPolicy<{ actions::SETTINGS_GET }>, Data<IndexScheduler>>,
-    index_uid: web::Path<String>,
-) -> Result<HttpResponse, ResponseError> {
-    let index_uid = IndexUid::try_from(index_uid.into_inner())?;
-
-    let index = index_scheduler.index(&index_uid)?;
-    let rtxn = index.read_txn()?;
-    let new_settings = settings(&index, &rtxn, SecretPolicy::HideSecrets)?;
-    debug!(returns = ?new_settings, "Get all settings");
-    Ok(HttpResponse::Ok().json(new_settings))
-}
-
-pub async fn delete_all(
-    index_scheduler: GuardedData<ActionPolicy<{ actions::SETTINGS_UPDATE }>, Data<IndexScheduler>>,
-    index_uid: web::Path<String>,
-    req: HttpRequest,
-    opt: web::Data<Opt>,
-) -> Result<HttpResponse, ResponseError> {
-    let index_uid = IndexUid::try_from(index_uid.into_inner())?;
-
-    let new_settings = Settings::cleared().into_unchecked();
-
-    let allow_index_creation = index_scheduler.filters().allow_index_creation(&index_uid);
-    let index_uid = IndexUid::try_from(index_uid.into_inner())?.into_inner();
-    let task = KindWithContent::SettingsUpdate {
-        index_uid,
-        new_settings: Box::new(new_settings),
-        is_deletion: true,
-        allow_index_creation,
-    };
-    let uid = get_task_id(&req, &opt)?;
-    let dry_run = is_dry_run(&req, &opt)?;
-    let task: SummarizedTaskView =
-        tokio::task::spawn_blocking(move || index_scheduler.register(task, uid, dry_run))
-            .await??
-            .into();
-
-    debug!(returns = ?task, "Delete all settings");
-    Ok(HttpResponse::Accepted().json(task))
-}
-
-fn validate_settings(
-    settings: Settings<Unchecked>,
-    index_scheduler: &IndexScheduler,
-) -> Result<Settings<Unchecked>, ResponseError> {
-    if matches!(settings.embedders, Setting::Set(_)) {
-        index_scheduler.features().check_vector("Passing `embedders` in settings")?
-    }
-    Ok(settings.validate()?)
-}

crates/meilisearch/src/routes/indexes/settings_analytics.rs

@@ -1,622 +0,0 @@
-//! All the structures used to make the analytics on the settings works.
-//! The signatures of the `new` functions are not very rust idiomatic because they must match the types received
-//! through the sub-settings route directly without any manipulation.
-//! This is why we often use a `Option<&Vec<_>>` instead of a `Option<&[_]>`.
-
-use std::collections::{BTreeMap, BTreeSet, HashSet};
-
-use meilisearch_types::facet_values_sort::FacetValuesSort;
-use meilisearch_types::locales::{Locale, LocalizedAttributesRuleView};
-use meilisearch_types::milli::update::Setting;
-use meilisearch_types::milli::vector::settings::EmbeddingSettings;
-use meilisearch_types::settings::{
-    FacetingSettings, PaginationSettings, ProximityPrecisionView, RankingRuleView, TypoSettings,
-};
-use serde::Serialize;
-
-use crate::analytics::Aggregate;
-
-#[derive(Serialize, Default)]
-pub struct SettingsAnalytics {
-    pub ranking_rules: RankingRulesAnalytics,
-    pub searchable_attributes: SearchableAttributesAnalytics,
-    pub displayed_attributes: DisplayedAttributesAnalytics,
-    pub sortable_attributes: SortableAttributesAnalytics,
-    pub filterable_attributes: FilterableAttributesAnalytics,
-    pub distinct_attribute: DistinctAttributeAnalytics,
-    pub proximity_precision: ProximityPrecisionAnalytics,
-    pub typo_tolerance: TypoToleranceAnalytics,
-    pub faceting: FacetingAnalytics,
-    pub pagination: PaginationAnalytics,
-    pub stop_words: StopWordsAnalytics,
-    pub synonyms: SynonymsAnalytics,
-    pub embedders: EmbeddersAnalytics,
-    pub search_cutoff_ms: SearchCutoffMsAnalytics,
-    pub locales: LocalesAnalytics,
-    pub dictionary: DictionaryAnalytics,
-    pub separator_tokens: SeparatorTokensAnalytics,
-    pub non_separator_tokens: NonSeparatorTokensAnalytics,
-}
-
-impl Aggregate for SettingsAnalytics {
-    fn event_name(&self) -> &'static str {
-        "Settings Updated"
-    }
-
-    fn aggregate(self: Box<Self>, new: Box<Self>) -> Box<Self> {
-        Box::new(Self {
-            ranking_rules: RankingRulesAnalytics {
-                words_position: new
-                    .ranking_rules
-                    .words_position
-                    .or(self.ranking_rules.words_position),
-                typo_position: new.ranking_rules.typo_position.or(self.ranking_rules.typo_position),
-                proximity_position: new
-                    .ranking_rules
-                    .proximity_position
-                    .or(self.ranking_rules.proximity_position),
-                attribute_position: new
-                    .ranking_rules
-                    .attribute_position
-                    .or(self.ranking_rules.attribute_position),
-                sort_position: new.ranking_rules.sort_position.or(self.ranking_rules.sort_position),
-                exactness_position: new
-                    .ranking_rules
-                    .exactness_position
-                    .or(self.ranking_rules.exactness_position),
-                values: new.ranking_rules.values.or(self.ranking_rules.values),
-            },
-            searchable_attributes: SearchableAttributesAnalytics {
-                total: new.searchable_attributes.total.or(self.searchable_attributes.total),
-                with_wildcard: new
-                    .searchable_attributes
-                    .with_wildcard
-                    .or(self.searchable_attributes.with_wildcard),
-            },
-            displayed_attributes: DisplayedAttributesAnalytics {
-                total: new.displayed_attributes.total.or(self.displayed_attributes.total),
-                with_wildcard: new
-                    .displayed_attributes
-                    .with_wildcard
-                    .or(self.displayed_attributes.with_wildcard),
-            },
-            sortable_attributes: SortableAttributesAnalytics {
-                total: new.sortable_attributes.total.or(self.sortable_attributes.total),
-                has_geo: new.sortable_attributes.has_geo.or(self.sortable_attributes.has_geo),
-            },
-            filterable_attributes: FilterableAttributesAnalytics {
-                total: new.filterable_attributes.total.or(self.filterable_attributes.total),
-                has_geo: new.filterable_attributes.has_geo.or(self.filterable_attributes.has_geo),
-            },
-            distinct_attribute: DistinctAttributeAnalytics {
-                set: self.distinct_attribute.set | new.distinct_attribute.set,
-            },
-            proximity_precision: ProximityPrecisionAnalytics {
-                set: self.proximity_precision.set | new.proximity_precision.set,
-                value: new.proximity_precision.value.or(self.proximity_precision.value),
-            },
-            typo_tolerance: TypoToleranceAnalytics {
-                enabled: new.typo_tolerance.enabled.or(self.typo_tolerance.enabled),
-                disable_on_attributes: new
-                    .typo_tolerance
-                    .disable_on_attributes
-                    .or(self.typo_tolerance.disable_on_attributes),
-                disable_on_words: new
-                    .typo_tolerance
-                    .disable_on_words
-                    .or(self.typo_tolerance.disable_on_words),
-                min_word_size_for_one_typo: new
-                    .typo_tolerance
-                    .min_word_size_for_one_typo
-                    .or(self.typo_tolerance.min_word_size_for_one_typo),
-                min_word_size_for_two_typos: new
-                    .typo_tolerance
-                    .min_word_size_for_two_typos
-                    .or(self.typo_tolerance.min_word_size_for_two_typos),
-            },
-            faceting: FacetingAnalytics {
-                max_values_per_facet: new
-                    .faceting
-                    .max_values_per_facet
-                    .or(self.faceting.max_values_per_facet),
-                sort_facet_values_by_star_count: new
-                    .faceting
-                    .sort_facet_values_by_star_count
-                    .or(self.faceting.sort_facet_values_by_star_count),
-                sort_facet_values_by_total: new
-                    .faceting
-                    .sort_facet_values_by_total
-                    .or(self.faceting.sort_facet_values_by_total),
-            },
-            pagination: PaginationAnalytics {
-                max_total_hits: new.pagination.max_total_hits.or(self.pagination.max_total_hits),
-            },
-            stop_words: StopWordsAnalytics {
-                total: new.stop_words.total.or(self.stop_words.total),
-            },
-            synonyms: SynonymsAnalytics { total: new.synonyms.total.or(self.synonyms.total) },
-            embedders: EmbeddersAnalytics {
-                total: new.embedders.total.or(self.embedders.total),
-                sources: match (self.embedders.sources, new.embedders.sources) {
-                    (None, None) => None,
-                    (Some(sources), None) | (None, Some(sources)) => Some(sources),
-                    (Some(this), Some(other)) => Some(this.union(&other).cloned().collect()),
-                },
-                document_template_used: match (
-                    self.embedders.document_template_used,
-                    new.embedders.document_template_used,
-                ) {
-                    (None, None) => None,
-                    (Some(used), None) | (None, Some(used)) => Some(used),
-                    (Some(this), Some(other)) => Some(this | other),
-                },
-                document_template_max_bytes: match (
-                    self.embedders.document_template_max_bytes,
-                    new.embedders.document_template_max_bytes,
-                ) {
-                    (None, None) => None,
-                    (Some(bytes), None) | (None, Some(bytes)) => Some(bytes),
-                    (Some(this), Some(other)) => Some(this.max(other)),
-                },
-                binary_quantization_used: match (
-                    self.embedders.binary_quantization_used,
-                    new.embedders.binary_quantization_used,
-                ) {
-                    (None, None) => None,
-                    (Some(bq), None) | (None, Some(bq)) => Some(bq),
-                    (Some(this), Some(other)) => Some(this | other),
-                },
-            },
-            search_cutoff_ms: SearchCutoffMsAnalytics {
-                search_cutoff_ms: new
-                    .search_cutoff_ms
-                    .search_cutoff_ms
-                    .or(self.search_cutoff_ms.search_cutoff_ms),
-            },
-            locales: LocalesAnalytics { locales: new.locales.locales.or(self.locales.locales) },
-            dictionary: DictionaryAnalytics {
-                total: new.dictionary.total.or(self.dictionary.total),
-            },
-            separator_tokens: SeparatorTokensAnalytics {
-                total: new.non_separator_tokens.total.or(self.separator_tokens.total),
-            },
-            non_separator_tokens: NonSeparatorTokensAnalytics {
-                total: new.non_separator_tokens.total.or(self.non_separator_tokens.total),
-            },
-        })
-    }
-
-    fn into_event(self: Box<Self>) -> serde_json::Value {
-        serde_json::to_value(*self).unwrap_or_default()
-    }
-}
-
-#[derive(Serialize, Default)]
-pub struct RankingRulesAnalytics {
-    pub words_position: Option<usize>,
-    pub typo_position: Option<usize>,
-    pub proximity_position: Option<usize>,
-    pub attribute_position: Option<usize>,
-    pub sort_position: Option<usize>,
-    pub exactness_position: Option<usize>,
-    pub values: Option<String>,
-}
-
-impl RankingRulesAnalytics {
-    pub fn new(rr: Option<&Vec<RankingRuleView>>) -> Self {
-        RankingRulesAnalytics {
-            words_position: rr.as_ref().and_then(|rr| {
-                rr.iter()
-                    .position(|s| matches!(s, meilisearch_types::settings::RankingRuleView::Words))
-            }),
-            typo_position: rr.as_ref().and_then(|rr| {
-                rr.iter()
-                    .position(|s| matches!(s, meilisearch_types::settings::RankingRuleView::Typo))
-            }),
-            proximity_position: rr.as_ref().and_then(|rr| {
-                rr.iter().position(|s| {
-                    matches!(s, meilisearch_types::settings::RankingRuleView::Proximity)
-                })
-            }),
-            attribute_position: rr.as_ref().and_then(|rr| {
-                rr.iter().position(|s| {
-                    matches!(s, meilisearch_types::settings::RankingRuleView::Attribute)
-                })
-            }),
-            sort_position: rr.as_ref().and_then(|rr| {
-                rr.iter()
-                    .position(|s| matches!(s, meilisearch_types::settings::RankingRuleView::Sort))
-            }),
-            exactness_position: rr.as_ref().and_then(|rr| {
-                rr.iter().position(|s| {
-                    matches!(s, meilisearch_types::settings::RankingRuleView::Exactness)
-                })
-            }),
-            values: rr.as_ref().map(|rr| {
-                rr.iter()
-                    .filter(|s| {
-                        matches!(
-                            s,
-                            meilisearch_types::settings::RankingRuleView::Asc(_)
-                                | meilisearch_types::settings::RankingRuleView::Desc(_)
-                        )
-                    })
-                    .map(|x| x.to_string())
-                    .collect::<Vec<_>>()
-                    .join(", ")
-            }),
-        }
-    }
-
-    pub fn into_settings(self) -> SettingsAnalytics {
-        SettingsAnalytics { ranking_rules: self, ..Default::default() }
-    }
-}
-
-#[derive(Serialize, Default)]
-pub struct SearchableAttributesAnalytics {
-    pub total: Option<usize>,
-    pub with_wildcard: Option<bool>,
-}
-
-impl SearchableAttributesAnalytics {
-    pub fn new(setting: Option<&Vec<String>>) -> Self {
-        Self {
-            total: setting.as_ref().map(|searchable| searchable.len()),
-            with_wildcard: setting
-                .as_ref()
-                .map(|searchable| searchable.iter().any(|searchable| searchable == "*")),
-        }
-    }
-
-    pub fn into_settings(self) -> SettingsAnalytics {
-        SettingsAnalytics { searchable_attributes: self, ..Default::default() }
-    }
-}
-
-#[derive(Serialize, Default)]
-pub struct DisplayedAttributesAnalytics {
-    pub total: Option<usize>,
-    pub with_wildcard: Option<bool>,
-}
-
-impl DisplayedAttributesAnalytics {
-    pub fn new(displayed: Option<&Vec<String>>) -> Self {
-        Self {
-            total: displayed.as_ref().map(|displayed| displayed.len()),
-            with_wildcard: displayed
-                .as_ref()
-                .map(|displayed| displayed.iter().any(|displayed| displayed == "*")),
-        }
-    }
-
-    pub fn into_settings(self) -> SettingsAnalytics {
-        SettingsAnalytics { displayed_attributes: self, ..Default::default() }
-    }
-}
-
-#[derive(Serialize, Default)]
-pub struct SortableAttributesAnalytics {
-    pub total: Option<usize>,
-    pub has_geo: Option<bool>,
-}
-
-impl SortableAttributesAnalytics {
-    pub fn new(setting: Option<&BTreeSet<String>>) -> Self {
-        Self {
-            total: setting.as_ref().map(|sort| sort.len()),
-            has_geo: setting.as_ref().map(|sort| sort.contains("_geo")),
-        }
-    }
-
-    pub fn into_settings(self) -> SettingsAnalytics {
-        SettingsAnalytics { sortable_attributes: self, ..Default::default() }
-    }
-}
-
-#[derive(Serialize, Default)]
-pub struct FilterableAttributesAnalytics {
-    pub total: Option<usize>,
-    pub has_geo: Option<bool>,
-}
-
-impl FilterableAttributesAnalytics {
-    pub fn new(setting: Option<&BTreeSet<String>>) -> Self {
-        Self {
-            total: setting.as_ref().map(|filter| filter.len()),
-            has_geo: setting.as_ref().map(|filter| filter.contains("_geo")),
-        }
-    }
-
-    pub fn into_settings(self) -> SettingsAnalytics {
-        SettingsAnalytics { filterable_attributes: self, ..Default::default() }
-    }
-}
-
-#[derive(Serialize, Default)]
-pub struct DistinctAttributeAnalytics {
-    pub set: bool,
-}
-
-impl DistinctAttributeAnalytics {
-    pub fn new(distinct: Option<&String>) -> Self {
-        Self { set: distinct.is_some() }
-    }
-
-    pub fn into_settings(self) -> SettingsAnalytics {
-        SettingsAnalytics { distinct_attribute: self, ..Default::default() }
-    }
-}
-
-#[derive(Serialize, Default)]
-pub struct ProximityPrecisionAnalytics {
-    pub set: bool,
-    pub value: Option<ProximityPrecisionView>,
-}
-
-impl ProximityPrecisionAnalytics {
-    pub fn new(precision: Option<&ProximityPrecisionView>) -> Self {
-        Self { set: precision.is_some(), value: precision.cloned() }
-    }
-
-    pub fn into_settings(self) -> SettingsAnalytics {
-        SettingsAnalytics { proximity_precision: self, ..Default::default() }
-    }
-}
-
-#[derive(Serialize, Default)]
-pub struct TypoToleranceAnalytics {
-    pub enabled: Option<bool>,
-    pub disable_on_attributes: Option<bool>,
-    pub disable_on_words: Option<bool>,
-    pub min_word_size_for_one_typo: Option<u8>,
-    pub min_word_size_for_two_typos: Option<u8>,
-}
-
-impl TypoToleranceAnalytics {
-    pub fn new(setting: Option<&TypoSettings>) -> Self {
-        Self {
-            enabled: setting.as_ref().map(|s| !matches!(s.enabled, Setting::Set(false))),
-            disable_on_attributes: setting
-                .as_ref()
-                .and_then(|s| s.disable_on_attributes.as_ref().set().map(|m| !m.is_empty())),
-            disable_on_words: setting
-                .as_ref()
-                .and_then(|s| s.disable_on_words.as_ref().set().map(|m| !m.is_empty())),
-            min_word_size_for_one_typo: setting
-                .as_ref()
-                .and_then(|s| s.min_word_size_for_typos.as_ref().set().map(|s| s.one_typo.set()))
-                .flatten(),
-            min_word_size_for_two_typos: setting
-                .as_ref()
-                .and_then(|s| s.min_word_size_for_typos.as_ref().set().map(|s| s.two_typos.set()))
-                .flatten(),
-        }
-    }
-    pub fn into_settings(self) -> SettingsAnalytics {
-        SettingsAnalytics { typo_tolerance: self, ..Default::default() }
-    }
-}
-
-#[derive(Serialize, Default)]
-pub struct FacetingAnalytics {
-    pub max_values_per_facet: Option<usize>,
-    pub sort_facet_values_by_star_count: Option<bool>,
-    pub sort_facet_values_by_total: Option<usize>,
-}
-
-impl FacetingAnalytics {
-    pub fn new(setting: Option<&FacetingSettings>) -> Self {
-        Self {
-            max_values_per_facet: setting.as_ref().and_then(|s| s.max_values_per_facet.set()),
-            sort_facet_values_by_star_count: setting.as_ref().and_then(|s| {
-                s.sort_facet_values_by
-                    .as_ref()
-                    .set()
-                    .map(|s| s.iter().any(|(k, v)| k == "*" && v == &FacetValuesSort::Count))
-            }),
-            sort_facet_values_by_total: setting
-                .as_ref()
-                .and_then(|s| s.sort_facet_values_by.as_ref().set().map(|s| s.len())),
-        }
-    }
-
-    pub fn into_settings(self) -> SettingsAnalytics {
-        SettingsAnalytics { faceting: self, ..Default::default() }
-    }
-}
-
-#[derive(Serialize, Default)]
-pub struct PaginationAnalytics {
-    pub max_total_hits: Option<usize>,
-}
-
-impl PaginationAnalytics {
-    pub fn new(setting: Option<&PaginationSettings>) -> Self {
-        Self { max_total_hits: setting.as_ref().and_then(|s| s.max_total_hits.set()) }
-    }
-
-    pub fn into_settings(self) -> SettingsAnalytics {
-        SettingsAnalytics { pagination: self, ..Default::default() }
-    }
-}
-
-#[derive(Serialize, Default)]
-pub struct StopWordsAnalytics {
-    pub total: Option<usize>,
-}
-
-impl StopWordsAnalytics {
-    pub fn new(stop_words: Option<&BTreeSet<String>>) -> Self {
-        Self { total: stop_words.as_ref().map(|stop_words| stop_words.len()) }
-    }
-
-    pub fn into_settings(self) -> SettingsAnalytics {
-        SettingsAnalytics { stop_words: self, ..Default::default() }
-    }
-}
-
-#[derive(Serialize, Default)]
-pub struct SynonymsAnalytics {
-    pub total: Option<usize>,
-}
-
-impl SynonymsAnalytics {
-    pub fn new(synonyms: Option<&BTreeMap<String, Vec<String>>>) -> Self {
-        Self { total: synonyms.as_ref().map(|synonyms| synonyms.len()) }
-    }
-
-    pub fn into_settings(self) -> SettingsAnalytics {
-        SettingsAnalytics { synonyms: self, ..Default::default() }
-    }
-}
-
-#[derive(Serialize, Default)]
-pub struct EmbeddersAnalytics {
-    // last
-    pub total: Option<usize>,
-    // Merge the sources
-    pub sources: Option<HashSet<String>>,
-    // |=
-    pub document_template_used: Option<bool>,
-    // max
-    pub document_template_max_bytes: Option<usize>,
-    // |=
-    pub binary_quantization_used: Option<bool>,
-}
-
-impl EmbeddersAnalytics {
-    pub fn new(setting: Option<&BTreeMap<String, Setting<EmbeddingSettings>>>) -> Self {
-        let mut sources = std::collections::HashSet::new();
-
-        if let Some(s) = &setting {
-            for source in s
-                .values()
-                .filter_map(|config| config.clone().set())
-                .filter_map(|config| config.source.set())
-            {
-                use meilisearch_types::milli::vector::settings::EmbedderSource;
-                match source {
-                    EmbedderSource::OpenAi => sources.insert("openAi".to_string()),
-                    EmbedderSource::HuggingFace => sources.insert("huggingFace".to_string()),
-                    EmbedderSource::UserProvided => sources.insert("userProvided".to_string()),
-                    EmbedderSource::Ollama => sources.insert("ollama".to_string()),
-                    EmbedderSource::Rest => sources.insert("rest".to_string()),
-                };
-            }
-        };
-
-        Self {
-            total: setting.as_ref().map(|s| s.len()),
-            sources: Some(sources),
-            document_template_used: setting.as_ref().map(|map| {
-                map.values()
-                    .filter_map(|config| config.clone().set())
-                    .any(|config| config.document_template.set().is_some())
-            }),
-            document_template_max_bytes: setting.as_ref().and_then(|map| {
-                map.values()
-                    .filter_map(|config| config.clone().set())
-                    .filter_map(|config| config.document_template_max_bytes.set())
-                    .max()
-            }),
-            binary_quantization_used: setting.as_ref().map(|map| {
-                map.values()
-                    .filter_map(|config| config.clone().set())
-                    .any(|config| config.binary_quantized.set().is_some())
-            }),
-        }
-    }
-
-    pub fn into_settings(self) -> SettingsAnalytics {
-        SettingsAnalytics { embedders: self, ..Default::default() }
-    }
-}
-
-#[derive(Serialize, Default)]
-#[serde(transparent)]
-pub struct SearchCutoffMsAnalytics {
-    pub search_cutoff_ms: Option<u64>,
-}
-
-impl SearchCutoffMsAnalytics {
-    pub fn new(setting: Option<&u64>) -> Self {
-        Self { search_cutoff_ms: setting.copied() }
-    }
-
-    pub fn into_settings(self) -> SettingsAnalytics {
-        SettingsAnalytics { search_cutoff_ms: self, ..Default::default() }
-    }
-}
-
-#[derive(Serialize, Default)]
-#[serde(transparent)]
-pub struct LocalesAnalytics {
-    pub locales: Option<BTreeSet<Locale>>,
-}
-
-impl LocalesAnalytics {
-    pub fn new(rules: Option<&Vec<LocalizedAttributesRuleView>>) -> Self {
-        LocalesAnalytics {
-            locales: rules.as_ref().map(|rules| {
-                rules
-                    .iter()
-                    .flat_map(|rule| rule.locales.iter().cloned())
-                    .collect::<std::collections::BTreeSet<_>>()
-            }),
-        }
-    }
-
-    pub fn into_settings(self) -> SettingsAnalytics {
-        SettingsAnalytics { locales: self, ..Default::default() }
-    }
-}
-
-#[derive(Serialize, Default)]
-pub struct DictionaryAnalytics {
-    pub total: Option<usize>,
-}
-
-impl DictionaryAnalytics {
-    pub fn new(dictionary: Option<&BTreeSet<String>>) -> Self {
-        Self { total: dictionary.as_ref().map(|dictionary| dictionary.len()) }
-    }
-
-    pub fn into_settings(self) -> SettingsAnalytics {
-        SettingsAnalytics { dictionary: self, ..Default::default() }
-    }
-}
-
-#[derive(Serialize, Default)]
-pub struct SeparatorTokensAnalytics {
-    pub total: Option<usize>,
-}
-
-impl SeparatorTokensAnalytics {
-    pub fn new(separator_tokens: Option<&BTreeSet<String>>) -> Self {
-        Self { total: separator_tokens.as_ref().map(|separator_tokens| separator_tokens.len()) }
-    }
-
-    pub fn into_settings(self) -> SettingsAnalytics {
-        SettingsAnalytics { separator_tokens: self, ..Default::default() }
-    }
-}
-
-#[derive(Serialize, Default)]
-pub struct NonSeparatorTokensAnalytics {
-    pub total: Option<usize>,
-}
-
-impl NonSeparatorTokensAnalytics {
-    pub fn new(non_separator_tokens: Option<&BTreeSet<String>>) -> Self {
-        Self {
-            total: non_separator_tokens
-                .as_ref()
-                .map(|non_separator_tokens| non_separator_tokens.len()),
-        }
-    }
-
-    pub fn into_settings(self) -> SettingsAnalytics {
-        SettingsAnalytics { non_separator_tokens: self, ..Default::default() }
-    }
-}

crates/meilisearch/src/routes/indexes/similar.rs

@@ -1,201 +0,0 @@
-use actix_web::web::{self, Data};
-use actix_web::{HttpRequest, HttpResponse};
-use deserr::actix_web::{AwebJson, AwebQueryParameter};
-use index_scheduler::IndexScheduler;
-use meilisearch_types::deserr::query_params::Param;
-use meilisearch_types::deserr::{DeserrJsonError, DeserrQueryParamError};
-use meilisearch_types::error::deserr_codes::*;
-use meilisearch_types::error::{ErrorCode as _, ResponseError};
-use meilisearch_types::index_uid::IndexUid;
-use meilisearch_types::keys::actions;
-use meilisearch_types::serde_cs::vec::CS;
-use serde_json::Value;
-use tracing::debug;
-
-use super::ActionPolicy;
-use crate::analytics::Analytics;
-use crate::extractors::authentication::GuardedData;
-use crate::extractors::sequential_extractor::SeqHandler;
-use crate::routes::indexes::similar_analytics::{SimilarAggregator, SimilarGET, SimilarPOST};
-use crate::search::{
-    add_search_rules, perform_similar, RankingScoreThresholdSimilar, RetrieveVectors, SearchKind,
-    SimilarQuery, SimilarResult, DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET,
-};
-
-pub fn configure(cfg: &mut web::ServiceConfig) {
-    cfg.service(
-        web::resource("")
-            .route(web::get().to(SeqHandler(similar_get)))
-            .route(web::post().to(SeqHandler(similar_post))),
-    );
-}
-
-pub async fn similar_get(
-    index_scheduler: GuardedData<ActionPolicy<{ actions::SEARCH }>, Data<IndexScheduler>>,
-    index_uid: web::Path<String>,
-    params: AwebQueryParameter<SimilarQueryGet, DeserrQueryParamError>,
-    req: HttpRequest,
-    analytics: web::Data<Analytics>,
-) -> Result<HttpResponse, ResponseError> {
-    let index_uid = IndexUid::try_from(index_uid.into_inner())?;
-
-    let query = params.0.try_into()?;
-
-    let mut aggregate = SimilarAggregator::<SimilarGET>::from_query(&query);
-
-    debug!(parameters = ?query, "Similar get");
-
-    let similar = similar(index_scheduler, index_uid, query).await;
-
-    if let Ok(similar) = &similar {
-        aggregate.succeed(similar);
-    }
-    analytics.publish(aggregate, &req);
-
-    let similar = similar?;
-
-    debug!(returns = ?similar, "Similar get");
-    Ok(HttpResponse::Ok().json(similar))
-}
-
-pub async fn similar_post(
-    index_scheduler: GuardedData<ActionPolicy<{ actions::SEARCH }>, Data<IndexScheduler>>,
-    index_uid: web::Path<String>,
-    params: AwebJson<SimilarQuery, DeserrJsonError>,
-    req: HttpRequest,
-    analytics: web::Data<Analytics>,
-) -> Result<HttpResponse, ResponseError> {
-    let index_uid = IndexUid::try_from(index_uid.into_inner())?;
-
-    let query = params.into_inner();
-    debug!(parameters = ?query, "Similar post");
-
-    let mut aggregate = SimilarAggregator::<SimilarPOST>::from_query(&query);
-
-    let similar = similar(index_scheduler, index_uid, query).await;
-
-    if let Ok(similar) = &similar {
-        aggregate.succeed(similar);
-    }
-    analytics.publish(aggregate, &req);
-
-    let similar = similar?;
-
-    debug!(returns = ?similar, "Similar post");
-    Ok(HttpResponse::Ok().json(similar))
-}
-
-async fn similar(
-    index_scheduler: GuardedData<ActionPolicy<{ actions::SEARCH }>, Data<IndexScheduler>>,
-    index_uid: IndexUid,
-    mut query: SimilarQuery,
-) -> Result<SimilarResult, ResponseError> {
-    let features = index_scheduler.features();
-
-    features.check_vector("Using the similar API")?;
-
-    let retrieve_vectors = RetrieveVectors::new(query.retrieve_vectors, features)?;
-
-    // Tenant token search_rules.
-    if let Some(search_rules) = index_scheduler.filters().get_index_search_rules(&index_uid) {
-        add_search_rules(&mut query.filter, search_rules);
-    }
-
-    let index = index_scheduler.index(&index_uid)?;
-
-    let (embedder_name, embedder, quantized) =
-        SearchKind::embedder(&index_scheduler, &index, &query.embedder, None)?;
-
-    tokio::task::spawn_blocking(move || {
-        perform_similar(
-            &index,
-            query,
-            embedder_name,
-            embedder,
-            quantized,
-            retrieve_vectors,
-            index_scheduler.features(),
-        )
-    })
-    .await?
-}
-
-#[derive(Debug, deserr::Deserr)]
-#[deserr(error = DeserrQueryParamError, rename_all = camelCase, deny_unknown_fields)]
-pub struct SimilarQueryGet {
-    #[deserr(error = DeserrQueryParamError<InvalidSimilarId>)]
-    id: Param<String>,
-    #[deserr(default = Param(DEFAULT_SEARCH_OFFSET()), error = DeserrQueryParamError<InvalidSimilarOffset>)]
-    offset: Param<usize>,
-    #[deserr(default = Param(DEFAULT_SEARCH_LIMIT()), error = DeserrQueryParamError<InvalidSimilarLimit>)]
-    limit: Param<usize>,
-    #[deserr(default, error = DeserrQueryParamError<InvalidSimilarAttributesToRetrieve>)]
-    attributes_to_retrieve: Option<CS<String>>,
-    #[deserr(default, error = DeserrQueryParamError<InvalidSimilarRetrieveVectors>)]
-    retrieve_vectors: Param<bool>,
-    #[deserr(default, error = DeserrQueryParamError<InvalidSimilarFilter>)]
-    filter: Option<String>,
-    #[deserr(default, error = DeserrQueryParamError<InvalidSimilarShowRankingScore>)]
-    show_ranking_score: Param<bool>,
-    #[deserr(default, error = DeserrQueryParamError<InvalidSimilarShowRankingScoreDetails>)]
-    show_ranking_score_details: Param<bool>,
-    #[deserr(default, error = DeserrQueryParamError<InvalidSimilarRankingScoreThreshold>, default)]
-    pub ranking_score_threshold: Option<RankingScoreThresholdGet>,
-    #[deserr(error = DeserrQueryParamError<InvalidEmbedder>)]
-    pub embedder: String,
-}
-
-#[derive(Debug, Clone, Copy, PartialEq, deserr::Deserr)]
-#[deserr(try_from(String) = TryFrom::try_from -> InvalidSimilarRankingScoreThreshold)]
-pub struct RankingScoreThresholdGet(RankingScoreThresholdSimilar);
-
-impl std::convert::TryFrom<String> for RankingScoreThresholdGet {
-    type Error = InvalidSimilarRankingScoreThreshold;
-
-    fn try_from(s: String) -> Result<Self, Self::Error> {
-        let f: f64 = s.parse().map_err(|_| InvalidSimilarRankingScoreThreshold)?;
-        Ok(RankingScoreThresholdGet(RankingScoreThresholdSimilar::try_from(f)?))
-    }
-}
-
-impl TryFrom<SimilarQueryGet> for SimilarQuery {
-    type Error = ResponseError;
-
-    fn try_from(
-        SimilarQueryGet {
-            id,
-            offset,
-            limit,
-            attributes_to_retrieve,
-            retrieve_vectors,
-            filter,
-            show_ranking_score,
-            show_ranking_score_details,
-            embedder,
-            ranking_score_threshold,
-        }: SimilarQueryGet,
-    ) -> Result<Self, Self::Error> {
-        let filter = match filter {
-            Some(f) => match serde_json::from_str(&f) {
-                Ok(v) => Some(v),
-                _ => Some(Value::String(f)),
-            },
-            None => None,
-        };
-
-        Ok(SimilarQuery {
-            id: id.0.try_into().map_err(|code: InvalidSimilarId| {
-                ResponseError::from_msg(code.to_string(), code.error_code())
-            })?,
-            offset: offset.0,
-            limit: limit.0,
-            filter,
-            embedder,
-            attributes_to_retrieve: attributes_to_retrieve.map(|o| o.into_iter().collect()),
-            retrieve_vectors: retrieve_vectors.0,
-            show_ranking_score: show_ranking_score.0,
-            show_ranking_score_details: show_ranking_score_details.0,
-            ranking_score_threshold: ranking_score_threshold.map(|x| x.0),
-        })
-    }
-}

crates/meilisearch/src/routes/indexes/similar_analytics.rs

@@ -1,233 +0,0 @@
-use std::collections::{BinaryHeap, HashMap};
-
-use once_cell::sync::Lazy;
-use regex::Regex;
-use serde_json::{json, Value};
-
-use crate::aggregate_methods;
-use crate::analytics::{Aggregate, AggregateMethod};
-use crate::search::{SimilarQuery, SimilarResult};
-
-aggregate_methods!(
-    SimilarPOST => "Similar POST",
-    SimilarGET => "Similar GET",
-);
-
-#[derive(Default)]
-pub struct SimilarAggregator<Method: AggregateMethod> {
-    // requests
-    total_received: usize,
-    total_succeeded: usize,
-    time_spent: BinaryHeap<usize>,
-
-    // filter
-    filter_with_geo_radius: bool,
-    filter_with_geo_bounding_box: bool,
-    // every time a request has a filter, this field must be incremented by the number of terms it contains
-    filter_sum_of_criteria_terms: usize,
-    // every time a request has a filter, this field must be incremented by one
-    filter_total_number_of_criteria: usize,
-    used_syntax: HashMap<String, usize>,
-
-    // Whether a non-default embedder was specified
-    retrieve_vectors: bool,
-
-    // pagination
-    max_limit: usize,
-    max_offset: usize,
-
-    // formatting
-    max_attributes_to_retrieve: usize,
-
-    // scoring
-    show_ranking_score: bool,
-    show_ranking_score_details: bool,
-    ranking_score_threshold: bool,
-
-    marker: std::marker::PhantomData<Method>,
-}
-
-impl<Method: AggregateMethod> SimilarAggregator<Method> {
-    #[allow(clippy::field_reassign_with_default)]
-    pub fn from_query(query: &SimilarQuery) -> Self {
-        let SimilarQuery {
-            id: _,
-            embedder: _,
-            offset,
-            limit,
-            attributes_to_retrieve: _,
-            retrieve_vectors,
-            show_ranking_score,
-            show_ranking_score_details,
-            filter,
-            ranking_score_threshold,
-        } = query;
-
-        let mut ret = Self::default();
-
-        ret.total_received = 1;
-
-        if let Some(ref filter) = filter {
-            static RE: Lazy<Regex> = Lazy::new(|| Regex::new("AND | OR").unwrap());
-            ret.filter_total_number_of_criteria = 1;
-
-            let syntax = match filter {
-                Value::String(_) => "string".to_string(),
-                Value::Array(values) => {
-                    if values.iter().map(|v| v.to_string()).any(|s| RE.is_match(&s)) {
-                        "mixed".to_string()
-                    } else {
-                        "array".to_string()
-                    }
-                }
-                _ => "none".to_string(),
-            };
-            // convert the string to a HashMap
-            ret.used_syntax.insert(syntax, 1);
-
-            let stringified_filters = filter.to_string();
-            ret.filter_with_geo_radius = stringified_filters.contains("_geoRadius(");
-            ret.filter_with_geo_bounding_box = stringified_filters.contains("_geoBoundingBox(");
-            ret.filter_sum_of_criteria_terms = RE.split(&stringified_filters).count();
-        }
-
-        ret.max_limit = *limit;
-        ret.max_offset = *offset;
-
-        ret.show_ranking_score = *show_ranking_score;
-        ret.show_ranking_score_details = *show_ranking_score_details;
-        ret.ranking_score_threshold = ranking_score_threshold.is_some();
-
-        ret.retrieve_vectors = *retrieve_vectors;
-
-        ret
-    }
-
-    pub fn succeed(&mut self, result: &SimilarResult) {
-        let SimilarResult { id: _, hits: _, processing_time_ms, hits_info: _ } = result;
-
-        self.total_succeeded = self.total_succeeded.saturating_add(1);
-
-        self.time_spent.push(*processing_time_ms as usize);
-    }
-}
-
-impl<Method: AggregateMethod> Aggregate for SimilarAggregator<Method> {
-    fn event_name(&self) -> &'static str {
-        Method::event_name()
-    }
-
-    /// Aggregate one [SimilarAggregator] into another.
-    fn aggregate(mut self: Box<Self>, new: Box<Self>) -> Box<Self> {
-        let Self {
-            total_received,
-            total_succeeded,
-            mut time_spent,
-            filter_with_geo_radius,
-            filter_with_geo_bounding_box,
-            filter_sum_of_criteria_terms,
-            filter_total_number_of_criteria,
-            used_syntax,
-            max_limit,
-            max_offset,
-            max_attributes_to_retrieve,
-            show_ranking_score,
-            show_ranking_score_details,
-            ranking_score_threshold,
-            retrieve_vectors,
-            marker: _,
-        } = *new;
-
-        // request
-        self.total_received = self.total_received.saturating_add(total_received);
-        self.total_succeeded = self.total_succeeded.saturating_add(total_succeeded);
-        self.time_spent.append(&mut time_spent);
-
-        // filter
-        self.filter_with_geo_radius |= filter_with_geo_radius;
-        self.filter_with_geo_bounding_box |= filter_with_geo_bounding_box;
-        self.filter_sum_of_criteria_terms =
-            self.filter_sum_of_criteria_terms.saturating_add(filter_sum_of_criteria_terms);
-        self.filter_total_number_of_criteria =
-            self.filter_total_number_of_criteria.saturating_add(filter_total_number_of_criteria);
-        for (key, value) in used_syntax.into_iter() {
-            let used_syntax = self.used_syntax.entry(key).or_insert(0);
-            *used_syntax = used_syntax.saturating_add(value);
-        }
-
-        self.retrieve_vectors |= retrieve_vectors;
-
-        // pagination
-        self.max_limit = self.max_limit.max(max_limit);
-        self.max_offset = self.max_offset.max(max_offset);
-
-        // formatting
-        self.max_attributes_to_retrieve =
-            self.max_attributes_to_retrieve.max(max_attributes_to_retrieve);
-
-        // scoring
-        self.show_ranking_score |= show_ranking_score;
-        self.show_ranking_score_details |= show_ranking_score_details;
-        self.ranking_score_threshold |= ranking_score_threshold;
-
-        self
-    }
-
-    fn into_event(self: Box<Self>) -> serde_json::Value {
-        let Self {
-            total_received,
-            total_succeeded,
-            time_spent,
-            filter_with_geo_radius,
-            filter_with_geo_bounding_box,
-            filter_sum_of_criteria_terms,
-            filter_total_number_of_criteria,
-            used_syntax,
-            max_limit,
-            max_offset,
-            max_attributes_to_retrieve,
-            show_ranking_score,
-            show_ranking_score_details,
-            ranking_score_threshold,
-            retrieve_vectors,
-            marker: _,
-        } = *self;
-
-        // we get all the values in a sorted manner
-        let time_spent = time_spent.into_sorted_vec();
-        // the index of the 99th percentage of value
-        let percentile_99th = time_spent.len() * 99 / 100;
-        // We are only interested by the slowest value of the 99th fastest results
-        let time_spent = time_spent.get(percentile_99th);
-
-        json!({
-            "requests": {
-                "99th_response_time": time_spent.map(|t| format!("{:.2}", t)),
-                "total_succeeded": total_succeeded,
-                "total_failed": total_received.saturating_sub(total_succeeded), // just to be sure we never panics
-                "total_received": total_received,
-            },
-            "filter": {
-               "with_geoRadius": filter_with_geo_radius,
-               "with_geoBoundingBox": filter_with_geo_bounding_box,
-               "avg_criteria_number": format!("{:.2}", filter_sum_of_criteria_terms as f64 / filter_total_number_of_criteria as f64),
-               "most_used_syntax": used_syntax.iter().max_by_key(|(_, v)| *v).map(|(k, _)| json!(k)).unwrap_or_else(|| json!(null)),
-            },
-            "vector": {
-                "retrieve_vectors": retrieve_vectors,
-            },
-            "pagination": {
-               "max_limit": max_limit,
-               "max_offset": max_offset,
-            },
-            "formatting": {
-                "max_attributes_to_retrieve": max_attributes_to_retrieve,
-            },
-            "scoring": {
-                "show_ranking_score": show_ranking_score,
-                "show_ranking_score_details": show_ranking_score_details,
-                "ranking_score_threshold": ranking_score_threshold,
-            }
-        })
-    }
-}

crates/meilisearch/src/routes/multi_search.rs

@@ -1,184 +0,0 @@
-use actix_http::StatusCode;
-use actix_web::web::{self, Data};
-use actix_web::{HttpRequest, HttpResponse};
-use deserr::actix_web::AwebJson;
-use index_scheduler::IndexScheduler;
-use meilisearch_types::deserr::DeserrJsonError;
-use meilisearch_types::error::ResponseError;
-use meilisearch_types::keys::actions;
-use serde::Serialize;
-use tracing::debug;
-
-use super::multi_search_analytics::MultiSearchAggregator;
-use crate::analytics::Analytics;
-use crate::error::MeilisearchHttpError;
-use crate::extractors::authentication::policies::ActionPolicy;
-use crate::extractors::authentication::{AuthenticationError, GuardedData};
-use crate::extractors::sequential_extractor::SeqHandler;
-use crate::routes::indexes::search::search_kind;
-use crate::search::{
-    add_search_rules, perform_federated_search, perform_search, FederatedSearch, RetrieveVectors,
-    SearchQueryWithIndex, SearchResultWithIndex,
-};
-use crate::search_queue::SearchQueue;
-
-pub fn configure(cfg: &mut web::ServiceConfig) {
-    cfg.service(web::resource("").route(web::post().to(SeqHandler(multi_search_with_post))));
-}
-
-#[derive(Serialize)]
-struct SearchResults {
-    results: Vec<SearchResultWithIndex>,
-}
-
-pub async fn multi_search_with_post(
-    index_scheduler: GuardedData<ActionPolicy<{ actions::SEARCH }>, Data<IndexScheduler>>,
-    search_queue: Data<SearchQueue>,
-    params: AwebJson<FederatedSearch, DeserrJsonError>,
-    req: HttpRequest,
-    analytics: web::Data<Analytics>,
-) -> Result<HttpResponse, ResponseError> {
-    // Since we don't want to process half of the search requests and then get a permit refused
-    // we're going to get one permit for the whole duration of the multi-search request.
-    let permit = search_queue.try_get_search_permit().await?;
-
-    let federated_search = params.into_inner();
-
-    let mut multi_aggregate = MultiSearchAggregator::from_federated_search(&federated_search);
-
-    let FederatedSearch { mut queries, federation } = federated_search;
-
-    let features = index_scheduler.features();
-
-    // regardless of federation, check authorization and apply search rules
-    let auth = 'check_authorization: {
-        for (query_index, federated_query) in queries.iter_mut().enumerate() {
-            let index_uid = federated_query.index_uid.as_str();
-            // Check index from API key
-            if !index_scheduler.filters().is_index_authorized(index_uid) {
-                break 'check_authorization Err(AuthenticationError::InvalidToken)
-                    .with_index(query_index);
-            }
-            // Apply search rules from tenant token
-            if let Some(search_rules) = index_scheduler.filters().get_index_search_rules(index_uid)
-            {
-                add_search_rules(&mut federated_query.filter, search_rules);
-            }
-        }
-        Ok(())
-    };
-
-    auth.map_err(|(mut err, query_index)| {
-        // Add the query index that failed as context for the error message.
-        // We're doing it only here and not directly in the `WithIndex` trait so that the `with_index` function returns a different type
-        // of result and we can benefit from static typing.
-        err.message = format!("Inside `.queries[{query_index}]`: {}", err.message);
-        err
-    })?;
-
-    let response = match federation {
-        Some(federation) => {
-            let search_result = tokio::task::spawn_blocking(move || {
-                perform_federated_search(&index_scheduler, queries, federation, features)
-            })
-            .await;
-            permit.drop().await;
-
-            if let Ok(Ok(_)) = search_result {
-                multi_aggregate.succeed();
-            }
-
-            analytics.publish(multi_aggregate, &req);
-            HttpResponse::Ok().json(search_result??)
-        }
-        None => {
-            // Explicitly expect a `(ResponseError, usize)` for the error type rather than `ResponseError` only,
-            // so that `?` doesn't work if it doesn't use `with_index`, ensuring that it is not forgotten in case of code
-            // changes.
-            let search_results: Result<_, (ResponseError, usize)> = async {
-                let mut search_results = Vec::with_capacity(queries.len());
-                for (query_index, (index_uid, query, federation_options)) in queries
-                    .into_iter()
-                    .map(SearchQueryWithIndex::into_index_query_federation)
-                    .enumerate()
-                {
-                    debug!(on_index = query_index, parameters = ?query, "Multi-search");
-
-                    if federation_options.is_some() {
-                        return Err((
-                            MeilisearchHttpError::FederationOptionsInNonFederatedRequest(
-                                query_index,
-                            )
-                            .into(),
-                            query_index,
-                        ));
-                    }
-
-                    let index = index_scheduler
-                        .index(&index_uid)
-                        .map_err(|err| {
-                            let mut err = ResponseError::from(err);
-                            // Patch the HTTP status code to 400 as it defaults to 404 for `index_not_found`, but
-                            // here the resource not found is not part of the URL.
-                            err.code = StatusCode::BAD_REQUEST;
-                            err
-                        })
-                        .with_index(query_index)?;
-
-                    let search_kind =
-                        search_kind(&query, index_scheduler.get_ref(), &index, features)
-                            .with_index(query_index)?;
-                    let retrieve_vector = RetrieveVectors::new(query.retrieve_vectors, features)
-                        .with_index(query_index)?;
-
-                    let search_result = tokio::task::spawn_blocking(move || {
-                        perform_search(&index, query, search_kind, retrieve_vector, features)
-                    })
-                    .await
-                    .with_index(query_index)?;
-
-                    search_results.push(SearchResultWithIndex {
-                        index_uid: index_uid.into_inner(),
-                        result: search_result.with_index(query_index)?,
-                    });
-                }
-                Ok(search_results)
-            }
-            .await;
-            permit.drop().await;
-
-            if search_results.is_ok() {
-                multi_aggregate.succeed();
-            }
-            analytics.publish(multi_aggregate, &req);
-
-            let search_results = search_results.map_err(|(mut err, query_index)| {
-                // Add the query index that failed as context for the error message.
-                // We're doing it only here and not directly in the `WithIndex` trait so that the `with_index` function returns a different type
-                // of result and we can benefit from static typing.
-                err.message = format!("Inside `.queries[{query_index}]`: {}", err.message);
-                err
-            })?;
-
-            debug!(returns = ?search_results, "Multi-search");
-
-            HttpResponse::Ok().json(SearchResults { results: search_results })
-        }
-    };
-
-    Ok(response)
-}
-
-/// Local `Result` extension trait to avoid `map_err` boilerplate.
-trait WithIndex {
-    type T;
-    /// convert the error type inside of the `Result` to a `ResponseError`, and return a couple of it + the usize.
-    fn with_index(self, index: usize) -> Result<Self::T, (ResponseError, usize)>;
-}
-
-impl<T, E: Into<ResponseError>> WithIndex for Result<T, E> {
-    type T = T;
-    fn with_index(self, index: usize) -> Result<T, (ResponseError, usize)> {
-        self.map_err(|err| (err.into(), index))
-    }
-}

crates/meilisearch/src/routes/multi_search_analytics.rs

@@ -1,168 +0,0 @@
-use std::collections::HashSet;
-
-use serde_json::json;
-
-use crate::analytics::Aggregate;
-use crate::search::{FederatedSearch, SearchQueryWithIndex};
-
-#[derive(Default)]
-pub struct MultiSearchAggregator {
-    // requests
-    total_received: usize,
-    total_succeeded: usize,
-
-    // sum of the number of distinct indexes in each single request, use with total_received to compute an avg
-    total_distinct_index_count: usize,
-    // number of queries with a single index, use with total_received to compute a proportion
-    total_single_index: usize,
-
-    // sum of the number of search queries in the requests, use with total_received to compute an average
-    total_search_count: usize,
-
-    // scoring
-    show_ranking_score: bool,
-    show_ranking_score_details: bool,
-
-    // federation
-    use_federation: bool,
-}
-
-impl MultiSearchAggregator {
-    pub fn from_federated_search(federated_search: &FederatedSearch) -> Self {
-        let use_federation = federated_search.federation.is_some();
-
-        let distinct_indexes: HashSet<_> = federated_search
-            .queries
-            .iter()
-            .map(|query| {
-                let query = &query;
-                // make sure we get a compilation error if a field gets added to / removed from SearchQueryWithIndex
-                let SearchQueryWithIndex {
-                    index_uid,
-                    federation_options: _,
-                    q: _,
-                    vector: _,
-                    offset: _,
-                    limit: _,
-                    page: _,
-                    hits_per_page: _,
-                    attributes_to_retrieve: _,
-                    retrieve_vectors: _,
-                    attributes_to_crop: _,
-                    crop_length: _,
-                    attributes_to_highlight: _,
-                    show_ranking_score: _,
-                    show_ranking_score_details: _,
-                    show_matches_position: _,
-                    filter: _,
-                    sort: _,
-                    distinct: _,
-                    facets: _,
-                    highlight_pre_tag: _,
-                    highlight_post_tag: _,
-                    crop_marker: _,
-                    matching_strategy: _,
-                    attributes_to_search_on: _,
-                    hybrid: _,
-                    ranking_score_threshold: _,
-                    locales: _,
-                } = query;
-
-                index_uid.as_str()
-            })
-            .collect();
-
-        let show_ranking_score =
-            federated_search.queries.iter().any(|query| query.show_ranking_score);
-        let show_ranking_score_details =
-            federated_search.queries.iter().any(|query| query.show_ranking_score_details);
-
-        Self {
-            total_received: 1,
-            total_succeeded: 0,
-            total_distinct_index_count: distinct_indexes.len(),
-            total_single_index: if distinct_indexes.len() == 1 { 1 } else { 0 },
-            total_search_count: federated_search.queries.len(),
-            show_ranking_score,
-            show_ranking_score_details,
-            use_federation,
-        }
-    }
-
-    pub fn succeed(&mut self) {
-        self.total_succeeded = self.total_succeeded.saturating_add(1);
-    }
-}
-
-impl Aggregate for MultiSearchAggregator {
-    fn event_name(&self) -> &'static str {
-        "Documents Searched by Multi-Search POST"
-    }
-
-    /// Aggregate one [MultiSearchAggregator] into another.
-    fn aggregate(self: Box<Self>, new: Box<Self>) -> Box<Self> {
-        // write the aggregate in a way that will cause a compilation error if a field is added.
-
-        // get ownership of self, replacing it by a default value.
-        let this = *self;
-
-        let total_received = this.total_received.saturating_add(new.total_received);
-        let total_succeeded = this.total_succeeded.saturating_add(new.total_succeeded);
-        let total_distinct_index_count =
-            this.total_distinct_index_count.saturating_add(new.total_distinct_index_count);
-        let total_single_index = this.total_single_index.saturating_add(new.total_single_index);
-        let total_search_count = this.total_search_count.saturating_add(new.total_search_count);
-        let show_ranking_score = this.show_ranking_score || new.show_ranking_score;
-        let show_ranking_score_details =
-            this.show_ranking_score_details || new.show_ranking_score_details;
-        let use_federation = this.use_federation || new.use_federation;
-
-        Box::new(Self {
-            total_received,
-            total_succeeded,
-            total_distinct_index_count,
-            total_single_index,
-            total_search_count,
-            show_ranking_score,
-            show_ranking_score_details,
-            use_federation,
-        })
-    }
-
-    fn into_event(self: Box<Self>) -> serde_json::Value {
-        let Self {
-            total_received,
-            total_succeeded,
-            total_distinct_index_count,
-            total_single_index,
-            total_search_count,
-            show_ranking_score,
-            show_ranking_score_details,
-            use_federation,
-        } = *self;
-
-        json!({
-            "requests": {
-                "total_succeeded": total_succeeded,
-                "total_failed": total_received.saturating_sub(total_succeeded), // just to be sure we never panics
-                "total_received": total_received,
-            },
-            "indexes": {
-                "total_single_index": total_single_index,
-                "total_distinct_index_count": total_distinct_index_count,
-                "avg_distinct_index_count": (total_distinct_index_count as f64) / (total_received as f64), // not 0 else returned early
-            },
-            "searches": {
-                "total_search_count": total_search_count,
-                "avg_search_count": (total_search_count as f64) / (total_received as f64),
-            },
-            "scoring": {
-                "show_ranking_score": show_ranking_score,
-                "show_ranking_score_details": show_ranking_score_details,
-            },
-            "federation": {
-                "use_federation": use_federation,
-            }
-        })
-    }
-}

crates/meilisearch/src/search/federated.rs

@@ -1,910 +0,0 @@
-use std::cmp::Ordering;
-use std::collections::BTreeMap;
-use std::fmt;
-use std::iter::Zip;
-use std::rc::Rc;
-use std::str::FromStr as _;
-use std::time::Duration;
-use std::vec::{IntoIter, Vec};
-
-use actix_http::StatusCode;
-use index_scheduler::{IndexScheduler, RoFeatures};
-use indexmap::IndexMap;
-use meilisearch_types::deserr::DeserrJsonError;
-use meilisearch_types::error::deserr_codes::{
-    InvalidMultiSearchFacetsByIndex, InvalidMultiSearchMaxValuesPerFacet,
-    InvalidMultiSearchMergeFacets, InvalidMultiSearchWeight, InvalidSearchLimit,
-    InvalidSearchOffset,
-};
-use meilisearch_types::error::ResponseError;
-use meilisearch_types::index_uid::IndexUid;
-use meilisearch_types::milli::score_details::{ScoreDetails, ScoreValue};
-use meilisearch_types::milli::{self, DocumentId, OrderBy, TimeBudget};
-use roaring::RoaringBitmap;
-use serde::Serialize;
-
-use super::ranking_rules::{self, RankingRules};
-use super::{
-    compute_facet_distribution_stats, prepare_search, AttributesFormat, ComputedFacets, FacetStats,
-    HitMaker, HitsInfo, RetrieveVectors, SearchHit, SearchKind, SearchQuery, SearchQueryWithIndex,
-};
-use crate::error::MeilisearchHttpError;
-use crate::routes::indexes::search::search_kind;
-
-pub const DEFAULT_FEDERATED_WEIGHT: f64 = 1.0;
-
-#[derive(Debug, Default, Clone, Copy, PartialEq, deserr::Deserr)]
-#[deserr(error = DeserrJsonError, rename_all = camelCase, deny_unknown_fields)]
-pub struct FederationOptions {
-    #[deserr(default, error = DeserrJsonError<InvalidMultiSearchWeight>)]
-    pub weight: Weight,
-}
-
-#[derive(Debug, Clone, Copy, PartialEq, deserr::Deserr)]
-#[deserr(try_from(f64) = TryFrom::try_from -> InvalidMultiSearchWeight)]
-pub struct Weight(f64);
-
-impl Default for Weight {
-    fn default() -> Self {
-        Weight(DEFAULT_FEDERATED_WEIGHT)
-    }
-}
-
-impl std::convert::TryFrom<f64> for Weight {
-    type Error = InvalidMultiSearchWeight;
-
-    fn try_from(f: f64) -> Result<Self, Self::Error> {
-        if f < 0.0 {
-            Err(InvalidMultiSearchWeight)
-        } else {
-            Ok(Weight(f))
-        }
-    }
-}
-
-impl std::ops::Deref for Weight {
-    type Target = f64;
-
-    fn deref(&self) -> &Self::Target {
-        &self.0
-    }
-}
-
-#[derive(Debug, deserr::Deserr)]
-#[deserr(error = DeserrJsonError, rename_all = camelCase, deny_unknown_fields)]
-pub struct Federation {
-    #[deserr(default = super::DEFAULT_SEARCH_LIMIT(), error = DeserrJsonError<InvalidSearchLimit>)]
-    pub limit: usize,
-    #[deserr(default = super::DEFAULT_SEARCH_OFFSET(), error = DeserrJsonError<InvalidSearchOffset>)]
-    pub offset: usize,
-    #[deserr(default, error = DeserrJsonError<InvalidMultiSearchFacetsByIndex>)]
-    pub facets_by_index: BTreeMap<IndexUid, Option<Vec<String>>>,
-    #[deserr(default, error = DeserrJsonError<InvalidMultiSearchMergeFacets>)]
-    pub merge_facets: Option<MergeFacets>,
-}
-
-#[derive(Copy, Clone, Debug, deserr::Deserr, Default)]
-#[deserr(error = DeserrJsonError<InvalidMultiSearchMergeFacets>, rename_all = camelCase, deny_unknown_fields)]
-pub struct MergeFacets {
-    #[deserr(default, error = DeserrJsonError<InvalidMultiSearchMaxValuesPerFacet>)]
-    pub max_values_per_facet: Option<usize>,
-}
-
-#[derive(Debug, deserr::Deserr)]
-#[deserr(error = DeserrJsonError, rename_all = camelCase, deny_unknown_fields)]
-pub struct FederatedSearch {
-    pub queries: Vec<SearchQueryWithIndex>,
-    #[deserr(default)]
-    pub federation: Option<Federation>,
-}
-#[derive(Serialize, Clone)]
-#[serde(rename_all = "camelCase")]
-pub struct FederatedSearchResult {
-    pub hits: Vec<SearchHit>,
-    pub processing_time_ms: u128,
-    #[serde(flatten)]
-    pub hits_info: HitsInfo,
-
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub semantic_hit_count: Option<u32>,
-
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub facet_distribution: Option<BTreeMap<String, IndexMap<String, u64>>>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub facet_stats: Option<BTreeMap<String, FacetStats>>,
-    #[serde(skip_serializing_if = "FederatedFacets::is_empty")]
-    pub facets_by_index: FederatedFacets,
-
-    // These fields are only used for analytics purposes
-    #[serde(skip)]
-    pub degraded: bool,
-    #[serde(skip)]
-    pub used_negative_operator: bool,
-}
-
-impl fmt::Debug for FederatedSearchResult {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        let FederatedSearchResult {
-            hits,
-            processing_time_ms,
-            hits_info,
-            semantic_hit_count,
-            degraded,
-            used_negative_operator,
-            facet_distribution,
-            facet_stats,
-            facets_by_index,
-        } = self;
-
-        let mut debug = f.debug_struct("SearchResult");
-        // The most important thing when looking at a search result is the time it took to process
-        debug.field("processing_time_ms", &processing_time_ms);
-        debug.field("hits", &format!("[{} hits returned]", hits.len()));
-        debug.field("hits_info", &hits_info);
-        if *used_negative_operator {
-            debug.field("used_negative_operator", used_negative_operator);
-        }
-        if *degraded {
-            debug.field("degraded", degraded);
-        }
-        if let Some(facet_distribution) = facet_distribution {
-            debug.field("facet_distribution", &facet_distribution);
-        }
-        if let Some(facet_stats) = facet_stats {
-            debug.field("facet_stats", &facet_stats);
-        }
-        if let Some(semantic_hit_count) = semantic_hit_count {
-            debug.field("semantic_hit_count", &semantic_hit_count);
-        }
-        if !facets_by_index.is_empty() {
-            debug.field("facets_by_index", &facets_by_index);
-        }
-
-        debug.finish()
-    }
-}
-
-struct WeightedScore<'a> {
-    details: &'a [ScoreDetails],
-    weight: f64,
-}
-
-impl<'a> WeightedScore<'a> {
-    pub fn new(details: &'a [ScoreDetails], weight: f64) -> Self {
-        Self { details, weight }
-    }
-
-    pub fn weighted_global_score(&self) -> f64 {
-        ScoreDetails::global_score(self.details.iter()) * self.weight
-    }
-
-    pub fn compare_weighted_global_scores(&self, other: &Self) -> Ordering {
-        self.weighted_global_score()
-            .partial_cmp(&other.weighted_global_score())
-            // both are numbers, possibly infinite
-            .unwrap()
-    }
-
-    pub fn compare(&self, other: &Self) -> Ordering {
-        let mut left_it = ScoreDetails::score_values(self.details.iter());
-        let mut right_it = ScoreDetails::score_values(other.details.iter());
-
-        loop {
-            let left = left_it.next();
-            let right = right_it.next();
-
-            match (left, right) {
-                (None, None) => return Ordering::Equal,
-                (None, Some(_)) => return Ordering::Less,
-                (Some(_), None) => return Ordering::Greater,
-                (Some(ScoreValue::Score(left)), Some(ScoreValue::Score(right))) => {
-                    let left = left * self.weight;
-                    let right = right * other.weight;
-                    if (left - right).abs() <= f64::EPSILON {
-                        continue;
-                    }
-                    return left.partial_cmp(&right).unwrap();
-                }
-                (Some(ScoreValue::Sort(left)), Some(ScoreValue::Sort(right))) => {
-                    match left.partial_cmp(right) {
-                        Some(Ordering::Equal) => continue,
-                        Some(order) => return order,
-                        None => return self.compare_weighted_global_scores(other),
-                    }
-                }
-                (Some(ScoreValue::GeoSort(left)), Some(ScoreValue::GeoSort(right))) => {
-                    match left.partial_cmp(right) {
-                        Some(Ordering::Equal) => continue,
-                        Some(order) => return order,
-                        None => {
-                            return self.compare_weighted_global_scores(other);
-                        }
-                    }
-                }
-                // not comparable details, use global
-                (Some(ScoreValue::Score(_)), Some(_))
-                | (Some(_), Some(ScoreValue::Score(_)))
-                | (Some(ScoreValue::GeoSort(_)), Some(ScoreValue::Sort(_)))
-                | (Some(ScoreValue::Sort(_)), Some(ScoreValue::GeoSort(_))) => {
-                    let left_count = left_it.count();
-                    let right_count = right_it.count();
-                    // compare how many remaining groups of rules each side has.
-                    // the group with the most remaining groups wins.
-                    return left_count
-                        .cmp(&right_count)
-                        // breaks ties with the global ranking score
-                        .then_with(|| self.compare_weighted_global_scores(other));
-                }
-            }
-        }
-    }
-}
-
-struct QueryByIndex {
-    query: SearchQuery,
-    federation_options: FederationOptions,
-    query_index: usize,
-}
-
-struct SearchResultByQuery<'a> {
-    documents_ids: Vec<DocumentId>,
-    document_scores: Vec<Vec<ScoreDetails>>,
-    federation_options: FederationOptions,
-    hit_maker: HitMaker<'a>,
-    query_index: usize,
-}
-
-struct SearchResultByQueryIter<'a> {
-    it: Zip<IntoIter<DocumentId>, IntoIter<Vec<ScoreDetails>>>,
-    federation_options: FederationOptions,
-    hit_maker: Rc<HitMaker<'a>>,
-    query_index: usize,
-}
-
-impl<'a> SearchResultByQueryIter<'a> {
-    fn new(
-        SearchResultByQuery {
-            documents_ids,
-            document_scores,
-            federation_options,
-            hit_maker,
-            query_index,
-        }: SearchResultByQuery<'a>,
-    ) -> Self {
-        let it = documents_ids.into_iter().zip(document_scores);
-        Self { it, federation_options, hit_maker: Rc::new(hit_maker), query_index }
-    }
-}
-
-struct SearchResultByQueryIterItem<'a> {
-    docid: DocumentId,
-    score: Vec<ScoreDetails>,
-    federation_options: FederationOptions,
-    hit_maker: Rc<HitMaker<'a>>,
-    query_index: usize,
-}
-
-fn merge_index_local_results(
-    results_by_query: Vec<SearchResultByQuery<'_>>,
-) -> impl Iterator<Item = SearchResultByQueryIterItem> + '_ {
-    itertools::kmerge_by(
-        results_by_query.into_iter().map(SearchResultByQueryIter::new),
-        |left: &SearchResultByQueryIterItem, right: &SearchResultByQueryIterItem| {
-            let left_score = WeightedScore::new(&left.score, *left.federation_options.weight);
-            let right_score = WeightedScore::new(&right.score, *right.federation_options.weight);
-
-            match left_score.compare(&right_score) {
-                // the biggest score goes first
-                Ordering::Greater => true,
-                // break ties using query index
-                Ordering::Equal => left.query_index < right.query_index,
-                Ordering::Less => false,
-            }
-        },
-    )
-}
-
-fn merge_index_global_results(
-    results_by_index: Vec<SearchResultByIndex>,
-) -> impl Iterator<Item = SearchHitByIndex> {
-    itertools::kmerge_by(
-        results_by_index.into_iter().map(|result_by_index| result_by_index.hits.into_iter()),
-        |left: &SearchHitByIndex, right: &SearchHitByIndex| {
-            let left_score = WeightedScore::new(&left.score, *left.federation_options.weight);
-            let right_score = WeightedScore::new(&right.score, *right.federation_options.weight);
-
-            match left_score.compare(&right_score) {
-                // the biggest score goes first
-                Ordering::Greater => true,
-                // break ties using query index
-                Ordering::Equal => left.query_index < right.query_index,
-                Ordering::Less => false,
-            }
-        },
-    )
-}
-
-impl<'a> Iterator for SearchResultByQueryIter<'a> {
-    type Item = SearchResultByQueryIterItem<'a>;
-
-    fn next(&mut self) -> Option<Self::Item> {
-        let (docid, score) = self.it.next()?;
-        Some(SearchResultByQueryIterItem {
-            docid,
-            score,
-            federation_options: self.federation_options,
-            hit_maker: Rc::clone(&self.hit_maker),
-            query_index: self.query_index,
-        })
-    }
-}
-
-struct SearchHitByIndex {
-    hit: SearchHit,
-    score: Vec<ScoreDetails>,
-    federation_options: FederationOptions,
-    query_index: usize,
-}
-
-struct SearchResultByIndex {
-    index: String,
-    hits: Vec<SearchHitByIndex>,
-    estimated_total_hits: usize,
-    degraded: bool,
-    used_negative_operator: bool,
-    facets: Option<ComputedFacets>,
-}
-
-#[derive(Debug, Clone, Default, Serialize)]
-pub struct FederatedFacets(pub BTreeMap<String, ComputedFacets>);
-
-impl FederatedFacets {
-    pub fn insert(&mut self, index: String, facets: Option<ComputedFacets>) {
-        if let Some(facets) = facets {
-            self.0.insert(index, facets);
-        }
-    }
-
-    pub fn is_empty(&self) -> bool {
-        self.0.is_empty()
-    }
-
-    pub fn merge(
-        self,
-        MergeFacets { max_values_per_facet }: MergeFacets,
-        facet_order: BTreeMap<String, (String, OrderBy)>,
-    ) -> Option<ComputedFacets> {
-        if self.is_empty() {
-            return None;
-        }
-
-        let mut distribution: BTreeMap<String, _> = Default::default();
-        let mut stats: BTreeMap<String, FacetStats> = Default::default();
-
-        for facets_by_index in self.0.into_values() {
-            for (facet, index_distribution) in facets_by_index.distribution {
-                match distribution.entry(facet) {
-                    std::collections::btree_map::Entry::Vacant(entry) => {
-                        entry.insert(index_distribution);
-                    }
-                    std::collections::btree_map::Entry::Occupied(mut entry) => {
-                        let distribution = entry.get_mut();
-
-                        for (value, index_count) in index_distribution {
-                            distribution
-                                .entry(value)
-                                .and_modify(|count| *count += index_count)
-                                .or_insert(index_count);
-                        }
-                    }
-                }
-            }
-
-            for (facet, index_stats) in facets_by_index.stats {
-                match stats.entry(facet) {
-                    std::collections::btree_map::Entry::Vacant(entry) => {
-                        entry.insert(index_stats);
-                    }
-                    std::collections::btree_map::Entry::Occupied(mut entry) => {
-                        let stats = entry.get_mut();
-
-                        stats.min = f64::min(stats.min, index_stats.min);
-                        stats.max = f64::max(stats.max, index_stats.max);
-                    }
-                }
-            }
-        }
-
-        // fixup order
-        for (facet, values) in &mut distribution {
-            let order_by = facet_order.get(facet).map(|(_, order)| *order).unwrap_or_default();
-
-            match order_by {
-                OrderBy::Lexicographic => {
-                    values.sort_unstable_by(|left, _, right, _| left.cmp(right))
-                }
-                OrderBy::Count => {
-                    values.sort_unstable_by(|_, left, _, right| {
-                        left.cmp(right)
-                            // biggest first
-                            .reverse()
-                    })
-                }
-            }
-
-            if let Some(max_values_per_facet) = max_values_per_facet {
-                values.truncate(max_values_per_facet)
-            };
-        }
-
-        Some(ComputedFacets { distribution, stats })
-    }
-}
-
-pub fn perform_federated_search(
-    index_scheduler: &IndexScheduler,
-    queries: Vec<SearchQueryWithIndex>,
-    mut federation: Federation,
-    features: RoFeatures,
-) -> Result<FederatedSearchResult, ResponseError> {
-    let before_search = std::time::Instant::now();
-
-    // this implementation partition the queries by index to guarantee an important property:
-    // - all the queries to a particular index use the same read transaction.
-    // This is an important property, otherwise we cannot guarantee the self-consistency of the results.
-
-    // 1. partition queries by index
-    let mut queries_by_index: BTreeMap<String, Vec<QueryByIndex>> = Default::default();
-    for (query_index, federated_query) in queries.into_iter().enumerate() {
-        if let Some(pagination_field) = federated_query.has_pagination() {
-            return Err(MeilisearchHttpError::PaginationInFederatedQuery(
-                query_index,
-                pagination_field,
-            )
-            .into());
-        }
-
-        if let Some(facets) = federated_query.has_facets() {
-            let facets = facets.to_owned();
-            return Err(MeilisearchHttpError::FacetsInFederatedQuery(
-                query_index,
-                federated_query.index_uid.into_inner(),
-                facets,
-            )
-            .into());
-        }
-
-        let (index_uid, query, federation_options) = federated_query.into_index_query_federation();
-
-        queries_by_index.entry(index_uid.into_inner()).or_default().push(QueryByIndex {
-            query,
-            federation_options: federation_options.unwrap_or_default(),
-            query_index,
-        })
-    }
-
-    // 2. perform queries, merge and make hits index by index
-    let required_hit_count = federation.limit + federation.offset;
-
-    // In step (2), semantic_hit_count will be set to Some(0) if any search kind uses semantic
-    // Then in step (3), we'll update its value if there is any semantic search
-    let mut semantic_hit_count = None;
-    let mut results_by_index = Vec::with_capacity(queries_by_index.len());
-    let mut previous_query_data: Option<(RankingRules, usize, String)> = None;
-
-    // remember the order and name of first index for each facet when merging with index settings
-    // to detect if the order is inconsistent for a facet.
-    let mut facet_order: Option<BTreeMap<String, (String, OrderBy)>> = match federation.merge_facets
-    {
-        Some(MergeFacets { .. }) => Some(Default::default()),
-        _ => None,
-    };
-
-    for (index_uid, queries) in queries_by_index {
-        let first_query_index = queries.first().map(|query| query.query_index);
-
-        let index = match index_scheduler.index(&index_uid) {
-            Ok(index) => index,
-            Err(err) => {
-                let mut err = ResponseError::from(err);
-                // Patch the HTTP status code to 400 as it defaults to 404 for `index_not_found`, but
-                // here the resource not found is not part of the URL.
-                err.code = StatusCode::BAD_REQUEST;
-                if let Some(query_index) = first_query_index {
-                    err.message = format!("Inside `.queries[{}]`: {}", query_index, err.message);
-                }
-                return Err(err);
-            }
-        };
-
-        // Important: this is the only transaction we'll use for this index during this federated search
-        let rtxn = index.read_txn()?;
-
-        let criteria = index.criteria(&rtxn)?;
-
-        let dictionary = index.dictionary(&rtxn)?;
-        let dictionary: Option<Vec<_>> =
-            dictionary.as_ref().map(|x| x.iter().map(String::as_str).collect());
-        let separators = index.allowed_separators(&rtxn)?;
-        let separators: Option<Vec<_>> =
-            separators.as_ref().map(|x| x.iter().map(String::as_str).collect());
-
-        // each query gets its individual cutoff
-        let cutoff = index.search_cutoff(&rtxn)?;
-
-        let mut degraded = false;
-        let mut used_negative_operator = false;
-        let mut candidates = RoaringBitmap::new();
-
-        let facets_by_index = federation.facets_by_index.remove(&index_uid).flatten();
-
-        // TODO: recover the max size + facets_by_index as return value of this function so as not to ask it for all queries
-        if let Err(mut error) =
-            check_facet_order(&mut facet_order, &index_uid, &facets_by_index, &index, &rtxn)
-        {
-            error.message = format!(
-                "Inside `.federation.facetsByIndex.{index_uid}`: {error}{}",
-                if let Some(query_index) = first_query_index {
-                    format!("\n - Note: index `{index_uid}` used in `.queries[{query_index}]`")
-                } else {
-                    Default::default()
-                }
-            );
-            return Err(error);
-        }
-
-        // 2.1. Compute all candidates for each query in the index
-        let mut results_by_query = Vec::with_capacity(queries.len());
-
-        for QueryByIndex { query, federation_options, query_index } in queries {
-            // use an immediately invoked lambda to capture the result without returning from the function
-
-            let res: Result<(), ResponseError> = (|| {
-                let search_kind = search_kind(&query, index_scheduler, &index, features)?;
-
-                let canonicalization_kind = match (&search_kind, &query.q) {
-                    (SearchKind::SemanticOnly { .. }, _) => {
-                        ranking_rules::CanonicalizationKind::Vector
-                    }
-                    (_, Some(q)) if !q.is_empty() => ranking_rules::CanonicalizationKind::Keyword,
-                    _ => ranking_rules::CanonicalizationKind::Placeholder,
-                };
-
-                let sort = if let Some(sort) = &query.sort {
-                    let sorts: Vec<_> =
-                        match sort.iter().map(|s| milli::AscDesc::from_str(s)).collect() {
-                            Ok(sorts) => sorts,
-                            Err(asc_desc_error) => {
-                                return Err(milli::Error::from(milli::SortError::from(
-                                    asc_desc_error,
-                                ))
-                                .into())
-                            }
-                        };
-                    Some(sorts)
-                } else {
-                    None
-                };
-
-                let ranking_rules = ranking_rules::RankingRules::new(
-                    criteria.clone(),
-                    sort,
-                    query.matching_strategy.into(),
-                    canonicalization_kind,
-                );
-
-                if let Some((previous_ranking_rules, previous_query_index, previous_index_uid)) =
-                    previous_query_data.take()
-                {
-                    if let Err(error) = ranking_rules.is_compatible_with(&previous_ranking_rules) {
-                        return Err(error.to_response_error(
-                            &ranking_rules,
-                            &previous_ranking_rules,
-                            query_index,
-                            previous_query_index,
-                            &index_uid,
-                            &previous_index_uid,
-                        ));
-                    }
-                    previous_query_data = if previous_ranking_rules.constraint_count()
-                        > ranking_rules.constraint_count()
-                    {
-                        Some((previous_ranking_rules, previous_query_index, previous_index_uid))
-                    } else {
-                        Some((ranking_rules, query_index, index_uid.clone()))
-                    };
-                } else {
-                    previous_query_data = Some((ranking_rules, query_index, index_uid.clone()));
-                }
-
-                match search_kind {
-                    SearchKind::KeywordOnly => {}
-                    _ => semantic_hit_count = Some(0),
-                }
-
-                let retrieve_vectors = RetrieveVectors::new(query.retrieve_vectors, features)?;
-
-                let time_budget = match cutoff {
-                    Some(cutoff) => TimeBudget::new(Duration::from_millis(cutoff)),
-                    None => TimeBudget::default(),
-                };
-
-                let (mut search, _is_finite_pagination, _max_total_hits, _offset) =
-                    prepare_search(&index, &rtxn, &query, &search_kind, time_budget, features)?;
-
-                search.scoring_strategy(milli::score_details::ScoringStrategy::Detailed);
-                search.offset(0);
-                search.limit(required_hit_count);
-
-                let (result, _semantic_hit_count) = super::search_from_kind(search_kind, search)?;
-                let format = AttributesFormat {
-                    attributes_to_retrieve: query.attributes_to_retrieve,
-                    retrieve_vectors,
-                    attributes_to_highlight: query.attributes_to_highlight,
-                    attributes_to_crop: query.attributes_to_crop,
-                    crop_length: query.crop_length,
-                    crop_marker: query.crop_marker,
-                    highlight_pre_tag: query.highlight_pre_tag,
-                    highlight_post_tag: query.highlight_post_tag,
-                    show_matches_position: query.show_matches_position,
-                    sort: query.sort,
-                    show_ranking_score: query.show_ranking_score,
-                    show_ranking_score_details: query.show_ranking_score_details,
-                    locales: query.locales.map(|l| l.iter().copied().map(Into::into).collect()),
-                };
-
-                let milli::SearchResult {
-                    matching_words,
-                    candidates: query_candidates,
-                    documents_ids,
-                    document_scores,
-                    degraded: query_degraded,
-                    used_negative_operator: query_used_negative_operator,
-                } = result;
-
-                candidates |= query_candidates;
-                degraded |= query_degraded;
-                used_negative_operator |= query_used_negative_operator;
-
-                let tokenizer = HitMaker::tokenizer(dictionary.as_deref(), separators.as_deref());
-
-                let formatter_builder = HitMaker::formatter_builder(matching_words, tokenizer);
-
-                let hit_maker = HitMaker::new(&index, &rtxn, format, formatter_builder)?;
-
-                results_by_query.push(SearchResultByQuery {
-                    federation_options,
-                    hit_maker,
-                    query_index,
-                    documents_ids,
-                    document_scores,
-                });
-                Ok(())
-            })();
-
-            if let Err(mut error) = res {
-                error.message = format!("Inside `.queries[{query_index}]`: {}", error.message);
-                return Err(error);
-            }
-        }
-        // 2.2. merge inside index
-        let mut documents_seen = RoaringBitmap::new();
-        let merged_result: Result<Vec<_>, ResponseError> =
-            merge_index_local_results(results_by_query)
-                // skip documents we've already seen & mark that we saw the current document
-                .filter(|SearchResultByQueryIterItem { docid, .. }| documents_seen.insert(*docid))
-                .take(required_hit_count)
-                // 2.3 make hits
-                .map(
-                    |SearchResultByQueryIterItem {
-                         docid,
-                         score,
-                         federation_options,
-                         hit_maker,
-                         query_index,
-                     }| {
-                        let mut hit = hit_maker.make_hit(docid, &score)?;
-                        let weighted_score =
-                            ScoreDetails::global_score(score.iter()) * (*federation_options.weight);
-
-                        let _federation = serde_json::json!(
-                            {
-                                "indexUid": index_uid,
-                                "queriesPosition": query_index,
-                                "weightedRankingScore": weighted_score,
-                            }
-                        );
-                        hit.document.insert("_federation".to_string(), _federation);
-                        Ok(SearchHitByIndex { hit, score, federation_options, query_index })
-                    },
-                )
-                .collect();
-
-        let merged_result = merged_result?;
-
-        let estimated_total_hits = candidates.len() as usize;
-
-        let facets = facets_by_index
-            .map(|facets_by_index| {
-                compute_facet_distribution_stats(
-                    &facets_by_index,
-                    &index,
-                    &rtxn,
-                    candidates,
-                    super::Route::MultiSearch,
-                )
-            })
-            .transpose()
-            .map_err(|mut error| {
-                error.message = format!(
-                    "Inside `.federation.facetsByIndex.{index_uid}`: {}{}",
-                    error.message,
-                    if let Some(query_index) = first_query_index {
-                        format!("\n - Note: index `{index_uid}` used in `.queries[{query_index}]`")
-                    } else {
-                        Default::default()
-                    }
-                );
-                error
-            })?;
-
-        results_by_index.push(SearchResultByIndex {
-            index: index_uid,
-            hits: merged_result,
-            estimated_total_hits,
-            degraded,
-            used_negative_operator,
-            facets,
-        });
-    }
-
-    // bonus step, make sure to return an error if an index wants a non-faceted field, even if no query actually uses that index.
-    for (index_uid, facets) in federation.facets_by_index {
-        let index = match index_scheduler.index(&index_uid) {
-            Ok(index) => index,
-            Err(err) => {
-                let mut err = ResponseError::from(err);
-                // Patch the HTTP status code to 400 as it defaults to 404 for `index_not_found`, but
-                // here the resource not found is not part of the URL.
-                err.code = StatusCode::BAD_REQUEST;
-                err.message = format!(
-                    "Inside `.federation.facetsByIndex.{index_uid}`: {}\n - Note: index `{index_uid}` is not used in queries",
-                    err.message
-                );
-                return Err(err);
-            }
-        };
-
-        // Important: this is the only transaction we'll use for this index during this federated search
-        let rtxn = index.read_txn()?;
-
-        if let Err(mut error) =
-            check_facet_order(&mut facet_order, &index_uid, &facets, &index, &rtxn)
-        {
-            error.message = format!(
-                "Inside `.federation.facetsByIndex.{index_uid}`: {error}\n - Note: index `{index_uid}` is not used in queries",
-            );
-            return Err(error);
-        }
-
-        if let Some(facets) = facets {
-            if let Err(mut error) = compute_facet_distribution_stats(
-                &facets,
-                &index,
-                &rtxn,
-                Default::default(),
-                super::Route::MultiSearch,
-            ) {
-                error.message =
-                    format!("Inside `.federation.facetsByIndex.{index_uid}`: {}\n - Note: index `{index_uid}` is not used in queries", error.message);
-                return Err(error);
-            }
-        }
-    }
-
-    // 3. merge hits and metadata across indexes
-    // 3.1 merge metadata
-    let (estimated_total_hits, degraded, used_negative_operator, facets) = {
-        let mut estimated_total_hits = 0;
-        let mut degraded = false;
-        let mut used_negative_operator = false;
-
-        let mut facets: FederatedFacets = FederatedFacets::default();
-
-        for SearchResultByIndex {
-            index,
-            hits: _,
-            estimated_total_hits: estimated_total_hits_by_index,
-            facets: facets_by_index,
-            degraded: degraded_by_index,
-            used_negative_operator: used_negative_operator_by_index,
-        } in &mut results_by_index
-        {
-            estimated_total_hits += *estimated_total_hits_by_index;
-            degraded |= *degraded_by_index;
-            used_negative_operator |= *used_negative_operator_by_index;
-
-            let facets_by_index = std::mem::take(facets_by_index);
-            let index = std::mem::take(index);
-
-            facets.insert(index, facets_by_index);
-        }
-
-        (estimated_total_hits, degraded, used_negative_operator, facets)
-    };
-
-    // 3.2 merge hits
-    let merged_hits: Vec<_> = merge_index_global_results(results_by_index)
-        .skip(federation.offset)
-        .take(federation.limit)
-        .inspect(|hit| {
-            if let Some(semantic_hit_count) = &mut semantic_hit_count {
-                if hit.score.iter().any(|score| matches!(&score, ScoreDetails::Vector(_))) {
-                    *semantic_hit_count += 1;
-                }
-            }
-        })
-        .map(|hit| hit.hit)
-        .collect();
-
-    let (facet_distribution, facet_stats, facets_by_index) =
-        match federation.merge_facets.zip(facet_order) {
-            Some((merge_facets, facet_order)) => {
-                let facets = facets.merge(merge_facets, facet_order);
-
-                let (facet_distribution, facet_stats) = facets
-                    .map(|ComputedFacets { distribution, stats }| (distribution, stats))
-                    .unzip();
-
-                (facet_distribution, facet_stats, FederatedFacets::default())
-            }
-            None => (None, None, facets),
-        };
-
-    let search_result = FederatedSearchResult {
-        hits: merged_hits,
-        processing_time_ms: before_search.elapsed().as_millis(),
-        hits_info: HitsInfo::OffsetLimit {
-            limit: federation.limit,
-            offset: federation.offset,
-            estimated_total_hits,
-        },
-        semantic_hit_count,
-        degraded,
-        used_negative_operator,
-        facet_distribution,
-        facet_stats,
-        facets_by_index,
-    };
-
-    Ok(search_result)
-}
-
-fn check_facet_order(
-    facet_order: &mut Option<BTreeMap<String, (String, OrderBy)>>,
-    current_index: &str,
-    facets_by_index: &Option<Vec<String>>,
-    index: &milli::Index,
-    rtxn: &milli::heed::RoTxn<'_>,
-) -> Result<(), ResponseError> {
-    if let (Some(facet_order), Some(facets_by_index)) = (facet_order, facets_by_index) {
-        let index_facet_order = index.sort_facet_values_by(rtxn)?;
-        for facet in facets_by_index {
-            let index_facet_order = index_facet_order.get(facet);
-            let (previous_index, previous_facet_order) = facet_order
-                .entry(facet.to_owned())
-                .or_insert_with(|| (current_index.to_owned(), index_facet_order));
-            if previous_facet_order != &index_facet_order {
-                return Err(MeilisearchHttpError::InconsistentFacetOrder {
-                    facet: facet.clone(),
-                    previous_facet_order: *previous_facet_order,
-                    previous_uid: previous_index.clone(),
-                    current_uid: current_index.to_owned(),
-                    index_facet_order,
-                }
-                .into());
-            }
-        }
-    };
-    Ok(())
-}

crates/meilisearch/src/search/ranking_rules.rs

@@ -1,823 +0,0 @@
-use std::collections::HashMap;
-use std::fmt::Write;
-
-use itertools::Itertools as _;
-use meilisearch_types::error::{Code, ResponseError};
-use meilisearch_types::milli::{AscDesc, Criterion, Member, TermsMatchingStrategy};
-
-pub struct RankingRules {
-    canonical_criteria: Vec<Criterion>,
-    canonical_sort: Option<Vec<AscDesc>>,
-    canonicalization_actions: Vec<CanonicalizationAction>,
-    source_criteria: Vec<Criterion>,
-    source_sort: Option<Vec<AscDesc>>,
-}
-
-pub enum CanonicalizationAction {
-    PrependedWords {
-        prepended_index: RankingRuleSource,
-    },
-    RemovedDuplicate {
-        earlier_occurrence: RankingRuleSource,
-        removed_occurrence: RankingRuleSource,
-    },
-    RemovedWords {
-        reason: RemoveWords,
-        removed_occurrence: RankingRuleSource,
-    },
-    RemovedPlaceholder {
-        removed_occurrence: RankingRuleSource,
-    },
-    TruncatedVector {
-        vector_rule: RankingRuleSource,
-        truncated_from: RankingRuleSource,
-    },
-    RemovedVector {
-        vector_rule: RankingRuleSource,
-        removed_occurrence: RankingRuleSource,
-    },
-    RemovedSort {
-        removed_occurrence: RankingRuleSource,
-    },
-}
-
-pub enum RemoveWords {
-    WasPrepended,
-    MatchingStrategyAll,
-}
-
-impl std::fmt::Display for RemoveWords {
-    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
-        let reason = match self {
-            RemoveWords::WasPrepended => "it was previously prepended",
-            RemoveWords::MatchingStrategyAll => "`query.matchingWords` is set to `all`",
-        };
-        f.write_str(reason)
-    }
-}
-
-pub enum CanonicalizationKind {
-    Placeholder,
-    Keyword,
-    Vector,
-}
-
-pub struct CompatibilityError {
-    previous: RankingRule,
-    current: RankingRule,
-}
-impl CompatibilityError {
-    pub(crate) fn to_response_error(
-        &self,
-        ranking_rules: &RankingRules,
-        previous_ranking_rules: &RankingRules,
-        query_index: usize,
-        previous_query_index: usize,
-        index_uid: &str,
-        previous_index_uid: &str,
-    ) -> meilisearch_types::error::ResponseError {
-        let rule = self.current.as_string(
-            &ranking_rules.canonical_criteria,
-            &ranking_rules.canonical_sort,
-            query_index,
-            index_uid,
-        );
-        let previous_rule = self.previous.as_string(
-            &previous_ranking_rules.canonical_criteria,
-            &previous_ranking_rules.canonical_sort,
-            previous_query_index,
-            previous_index_uid,
-        );
-
-        let canonicalization_actions = ranking_rules.canonicalization_notes();
-        let previous_canonicalization_actions = previous_ranking_rules.canonicalization_notes();
-
-        let mut msg = String::new();
-        let reason = self.reason();
-        let _ = writeln!(
-            &mut msg,
-            "The results of queries #{previous_query_index} and #{query_index} are incompatible: "
-        );
-        let _ = writeln!(&mut msg, "  1. {previous_rule}");
-        let _ = writeln!(&mut msg, "  2. {rule}");
-        let _ = writeln!(&mut msg, "  - {reason}");
-
-        if !previous_canonicalization_actions.is_empty() {
-            let _ = write!(&mut msg, "  - note: The ranking rules of query #{previous_query_index} were modified during canonicalization:\n{previous_canonicalization_actions}");
-        }
-
-        if !canonicalization_actions.is_empty() {
-            let _ = write!(&mut msg, "  - note: The ranking rules of query #{query_index} were modified during canonicalization:\n{canonicalization_actions}");
-        }
-
-        ResponseError::from_msg(msg, Code::InvalidMultiSearchQueryRankingRules)
-    }
-    pub fn reason(&self) -> &'static str {
-        match (self.previous.kind, self.current.kind) {
-            (RankingRuleKind::Relevancy, RankingRuleKind::AscendingSort)
-            | (RankingRuleKind::Relevancy, RankingRuleKind::DescendingSort)
-            | (RankingRuleKind::AscendingSort, RankingRuleKind::Relevancy)
-            | (RankingRuleKind::DescendingSort, RankingRuleKind::Relevancy) => {
-                "cannot compare a relevancy rule with a sort rule"
-            }
-
-            (RankingRuleKind::Relevancy, RankingRuleKind::AscendingGeoSort)
-            | (RankingRuleKind::Relevancy, RankingRuleKind::DescendingGeoSort)
-            | (RankingRuleKind::AscendingGeoSort, RankingRuleKind::Relevancy)
-            | (RankingRuleKind::DescendingGeoSort, RankingRuleKind::Relevancy) => {
-                "cannot compare a relevancy rule with a geosort rule"
-            }
-
-            (RankingRuleKind::AscendingSort, RankingRuleKind::DescendingSort)
-            | (RankingRuleKind::DescendingSort, RankingRuleKind::AscendingSort) => {
-                "cannot compare two sort rules in opposite directions"
-            }
-
-            (RankingRuleKind::AscendingSort, RankingRuleKind::AscendingGeoSort)
-            | (RankingRuleKind::AscendingSort, RankingRuleKind::DescendingGeoSort)
-            | (RankingRuleKind::DescendingSort, RankingRuleKind::AscendingGeoSort)
-            | (RankingRuleKind::DescendingSort, RankingRuleKind::DescendingGeoSort)
-            | (RankingRuleKind::AscendingGeoSort, RankingRuleKind::AscendingSort)
-            | (RankingRuleKind::AscendingGeoSort, RankingRuleKind::DescendingSort)
-            | (RankingRuleKind::DescendingGeoSort, RankingRuleKind::AscendingSort)
-            | (RankingRuleKind::DescendingGeoSort, RankingRuleKind::DescendingSort) => {
-                "cannot compare a sort rule with a geosort rule"
-            }
-
-            (RankingRuleKind::AscendingGeoSort, RankingRuleKind::DescendingGeoSort)
-            | (RankingRuleKind::DescendingGeoSort, RankingRuleKind::AscendingGeoSort) => {
-                "cannot compare two geosort rules in opposite directions"
-            }
-            (RankingRuleKind::Relevancy, RankingRuleKind::Relevancy)
-            | (RankingRuleKind::AscendingSort, RankingRuleKind::AscendingSort)
-            | (RankingRuleKind::DescendingSort, RankingRuleKind::DescendingSort)
-            | (RankingRuleKind::AscendingGeoSort, RankingRuleKind::AscendingGeoSort)
-            | (RankingRuleKind::DescendingGeoSort, RankingRuleKind::DescendingGeoSort) => {
-                "internal error, comparison should be possible"
-            }
-        }
-    }
-}
-
-impl RankingRules {
-    pub fn new(
-        criteria: Vec<Criterion>,
-        sort: Option<Vec<AscDesc>>,
-        terms_matching_strategy: TermsMatchingStrategy,
-        canonicalization_kind: CanonicalizationKind,
-    ) -> Self {
-        let (canonical_criteria, canonical_sort, canonicalization_actions) =
-            Self::canonicalize(&criteria, &sort, terms_matching_strategy, canonicalization_kind);
-        Self {
-            canonical_criteria,
-            canonical_sort,
-            canonicalization_actions,
-            source_criteria: criteria,
-            source_sort: sort,
-        }
-    }
-
-    fn canonicalize(
-        criteria: &[Criterion],
-        sort: &Option<Vec<AscDesc>>,
-        terms_matching_strategy: TermsMatchingStrategy,
-        canonicalization_kind: CanonicalizationKind,
-    ) -> (Vec<Criterion>, Option<Vec<AscDesc>>, Vec<CanonicalizationAction>) {
-        match canonicalization_kind {
-            CanonicalizationKind::Placeholder => Self::canonicalize_placeholder(criteria, sort),
-            CanonicalizationKind::Keyword => {
-                Self::canonicalize_keyword(criteria, sort, terms_matching_strategy)
-            }
-            CanonicalizationKind::Vector => Self::canonicalize_vector(criteria, sort),
-        }
-    }
-
-    fn canonicalize_placeholder(
-        criteria: &[Criterion],
-        sort_query: &Option<Vec<AscDesc>>,
-    ) -> (Vec<Criterion>, Option<Vec<AscDesc>>, Vec<CanonicalizationAction>) {
-        let mut sort = None;
-
-        let mut sorted_fields = HashMap::new();
-        let mut canonicalization_actions = Vec::new();
-        let mut canonical_criteria = Vec::new();
-        let mut canonical_sort = None;
-
-        for (criterion_index, criterion) in criteria.iter().enumerate() {
-            match criterion.clone() {
-                Criterion::Words
-                | Criterion::Typo
-                | Criterion::Proximity
-                | Criterion::Attribute
-                | Criterion::Exactness => {
-                    canonicalization_actions.push(CanonicalizationAction::RemovedPlaceholder {
-                        removed_occurrence: RankingRuleSource::Criterion(criterion_index),
-                    })
-                }
-
-                Criterion::Sort => {
-                    if let Some(previous_index) = sort {
-                        canonicalization_actions.push(CanonicalizationAction::RemovedDuplicate {
-                            earlier_occurrence: RankingRuleSource::Criterion(previous_index),
-                            removed_occurrence: RankingRuleSource::Criterion(criterion_index),
-                        });
-                    } else if let Some(sort_query) = sort_query {
-                        sort = Some(criterion_index);
-                        canonical_criteria.push(criterion.clone());
-                        canonical_sort = Some(canonicalize_sort(
-                            &mut sorted_fields,
-                            sort_query.as_slice(),
-                            criterion_index,
-                            &mut canonicalization_actions,
-                        ));
-                    } else {
-                        canonicalization_actions.push(CanonicalizationAction::RemovedSort {
-                            removed_occurrence: RankingRuleSource::Criterion(criterion_index),
-                        })
-                    }
-                }
-                Criterion::Asc(s) | Criterion::Desc(s) => match sorted_fields.entry(s) {
-                    std::collections::hash_map::Entry::Occupied(entry) => canonicalization_actions
-                        .push(CanonicalizationAction::RemovedDuplicate {
-                            earlier_occurrence: *entry.get(),
-                            removed_occurrence: RankingRuleSource::Criterion(criterion_index),
-                        }),
-                    std::collections::hash_map::Entry::Vacant(entry) => {
-                        entry.insert(RankingRuleSource::Criterion(criterion_index));
-                        canonical_criteria.push(criterion.clone())
-                    }
-                },
-            }
-        }
-
-        (canonical_criteria, canonical_sort, canonicalization_actions)
-    }
-
-    fn canonicalize_vector(
-        criteria: &[Criterion],
-        sort_query: &Option<Vec<AscDesc>>,
-    ) -> (Vec<Criterion>, Option<Vec<AscDesc>>, Vec<CanonicalizationAction>) {
-        let mut sort = None;
-
-        let mut sorted_fields = HashMap::new();
-        let mut canonicalization_actions = Vec::new();
-        let mut canonical_criteria = Vec::new();
-        let mut canonical_sort = None;
-
-        let mut vector = None;
-
-        'criteria: for (criterion_index, criterion) in criteria.iter().enumerate() {
-            match criterion.clone() {
-                Criterion::Words
-                | Criterion::Typo
-                | Criterion::Proximity
-                | Criterion::Attribute
-                | Criterion::Exactness => match vector {
-                    Some(previous_occurrence) => {
-                        if sorted_fields.is_empty() {
-                            canonicalization_actions.push(CanonicalizationAction::RemovedVector {
-                                vector_rule: RankingRuleSource::Criterion(previous_occurrence),
-                                removed_occurrence: RankingRuleSource::Criterion(criterion_index),
-                            });
-                        } else {
-                            canonicalization_actions.push(
-                                CanonicalizationAction::TruncatedVector {
-                                    vector_rule: RankingRuleSource::Criterion(previous_occurrence),
-                                    truncated_from: RankingRuleSource::Criterion(criterion_index),
-                                },
-                            );
-                            break 'criteria;
-                        }
-                    }
-                    None => {
-                        canonical_criteria.push(criterion.clone());
-                        vector = Some(criterion_index);
-                    }
-                },
-
-                Criterion::Sort => {
-                    if let Some(previous_index) = sort {
-                        canonicalization_actions.push(CanonicalizationAction::RemovedDuplicate {
-                            earlier_occurrence: RankingRuleSource::Criterion(previous_index),
-                            removed_occurrence: RankingRuleSource::Criterion(criterion_index),
-                        });
-                    } else if let Some(sort_query) = sort_query {
-                        sort = Some(criterion_index);
-                        canonical_criteria.push(criterion.clone());
-                        canonical_sort = Some(canonicalize_sort(
-                            &mut sorted_fields,
-                            sort_query.as_slice(),
-                            criterion_index,
-                            &mut canonicalization_actions,
-                        ));
-                    } else {
-                        canonicalization_actions.push(CanonicalizationAction::RemovedSort {
-                            removed_occurrence: RankingRuleSource::Criterion(criterion_index),
-                        })
-                    }
-                }
-                Criterion::Asc(s) | Criterion::Desc(s) => match sorted_fields.entry(s) {
-                    std::collections::hash_map::Entry::Occupied(entry) => canonicalization_actions
-                        .push(CanonicalizationAction::RemovedDuplicate {
-                            earlier_occurrence: *entry.get(),
-                            removed_occurrence: RankingRuleSource::Criterion(criterion_index),
-                        }),
-                    std::collections::hash_map::Entry::Vacant(entry) => {
-                        entry.insert(RankingRuleSource::Criterion(criterion_index));
-                        canonical_criteria.push(criterion.clone())
-                    }
-                },
-            }
-        }
-
-        (canonical_criteria, canonical_sort, canonicalization_actions)
-    }
-
-    fn canonicalize_keyword(
-        criteria: &[Criterion],
-        sort_query: &Option<Vec<AscDesc>>,
-        terms_matching_strategy: TermsMatchingStrategy,
-    ) -> (Vec<Criterion>, Option<Vec<AscDesc>>, Vec<CanonicalizationAction>) {
-        let mut words = None;
-        let mut typo = None;
-        let mut proximity = None;
-        let mut sort = None;
-        let mut attribute = None;
-        let mut exactness = None;
-        let mut sorted_fields = HashMap::new();
-
-        let mut canonical_criteria = Vec::new();
-        let mut canonical_sort = None;
-
-        let mut canonicalization_actions = Vec::new();
-
-        for (criterion_index, criterion) in criteria.iter().enumerate() {
-            let criterion = criterion.clone();
-            match criterion.clone() {
-                Criterion::Words => {
-                    if let TermsMatchingStrategy::All = terms_matching_strategy {
-                        canonicalization_actions.push(CanonicalizationAction::RemovedWords {
-                            reason: RemoveWords::MatchingStrategyAll,
-                            removed_occurrence: RankingRuleSource::Criterion(criterion_index),
-                        });
-                        continue;
-                    }
-                    if let Some(maybe_previous_index) = words {
-                        if let Some(previous_index) = maybe_previous_index {
-                            canonicalization_actions.push(
-                                CanonicalizationAction::RemovedDuplicate {
-                                    earlier_occurrence: RankingRuleSource::Criterion(
-                                        previous_index,
-                                    ),
-                                    removed_occurrence: RankingRuleSource::Criterion(
-                                        criterion_index,
-                                    ),
-                                },
-                            );
-                            continue;
-                        }
-                        canonicalization_actions.push(CanonicalizationAction::RemovedWords {
-                            reason: RemoveWords::WasPrepended,
-                            removed_occurrence: RankingRuleSource::Criterion(criterion_index),
-                        })
-                    }
-                    words = Some(Some(criterion_index));
-                    canonical_criteria.push(criterion);
-                }
-                Criterion::Typo => {
-                    canonicalize_criterion(
-                        criterion,
-                        criterion_index,
-                        terms_matching_strategy,
-                        &mut words,
-                        &mut canonicalization_actions,
-                        &mut canonical_criteria,
-                        &mut typo,
-                    );
-                }
-                Criterion::Proximity => {
-                    canonicalize_criterion(
-                        criterion,
-                        criterion_index,
-                        terms_matching_strategy,
-                        &mut words,
-                        &mut canonicalization_actions,
-                        &mut canonical_criteria,
-                        &mut proximity,
-                    );
-                }
-                Criterion::Attribute => {
-                    canonicalize_criterion(
-                        criterion,
-                        criterion_index,
-                        terms_matching_strategy,
-                        &mut words,
-                        &mut canonicalization_actions,
-                        &mut canonical_criteria,
-                        &mut attribute,
-                    );
-                }
-                Criterion::Exactness => {
-                    canonicalize_criterion(
-                        criterion,
-                        criterion_index,
-                        terms_matching_strategy,
-                        &mut words,
-                        &mut canonicalization_actions,
-                        &mut canonical_criteria,
-                        &mut exactness,
-                    );
-                }
-
-                Criterion::Sort => {
-                    if let Some(previous_index) = sort {
-                        canonicalization_actions.push(CanonicalizationAction::RemovedDuplicate {
-                            earlier_occurrence: RankingRuleSource::Criterion(previous_index),
-                            removed_occurrence: RankingRuleSource::Criterion(criterion_index),
-                        });
-                    } else if let Some(sort_query) = sort_query {
-                        sort = Some(criterion_index);
-                        canonical_criteria.push(criterion);
-                        canonical_sort = Some(canonicalize_sort(
-                            &mut sorted_fields,
-                            sort_query.as_slice(),
-                            criterion_index,
-                            &mut canonicalization_actions,
-                        ));
-                    } else {
-                        canonicalization_actions.push(CanonicalizationAction::RemovedSort {
-                            removed_occurrence: RankingRuleSource::Criterion(criterion_index),
-                        })
-                    }
-                }
-                Criterion::Asc(s) | Criterion::Desc(s) => match sorted_fields.entry(s) {
-                    std::collections::hash_map::Entry::Occupied(entry) => canonicalization_actions
-                        .push(CanonicalizationAction::RemovedDuplicate {
-                            earlier_occurrence: *entry.get(),
-                            removed_occurrence: RankingRuleSource::Criterion(criterion_index),
-                        }),
-                    std::collections::hash_map::Entry::Vacant(entry) => {
-                        entry.insert(RankingRuleSource::Criterion(criterion_index));
-                        canonical_criteria.push(criterion)
-                    }
-                },
-            }
-        }
-
-        (canonical_criteria, canonical_sort, canonicalization_actions)
-    }
-
-    pub fn is_compatible_with(&self, previous: &Self) -> Result<(), CompatibilityError> {
-        for (current, previous) in self.coalesce_iterator().zip(previous.coalesce_iterator()) {
-            if current.kind != previous.kind {
-                return Err(CompatibilityError { current, previous });
-            }
-        }
-        Ok(())
-    }
-
-    pub fn constraint_count(&self) -> usize {
-        self.coalesce_iterator().count()
-    }
-
-    fn coalesce_iterator(&self) -> impl Iterator<Item = RankingRule> + '_ {
-        self.canonical_criteria
-            .iter()
-            .enumerate()
-            .flat_map(|(criterion_index, criterion)| {
-                RankingRule::from_criterion(criterion_index, criterion, &self.canonical_sort)
-            })
-            .coalesce(
-                |previous @ RankingRule { source: previous_source, kind: previous_kind },
-                 current @ RankingRule { source, kind }| {
-                    match (previous_kind, kind) {
-                        (RankingRuleKind::Relevancy, RankingRuleKind::Relevancy) => {
-                            let merged_source = match (previous_source, source) {
-                                (
-                                    RankingRuleSource::Criterion(previous),
-                                    RankingRuleSource::Criterion(current),
-                                ) => RankingRuleSource::CoalescedCriteria(previous, current),
-                                (
-                                    RankingRuleSource::CoalescedCriteria(begin, _end),
-                                    RankingRuleSource::Criterion(current),
-                                ) => RankingRuleSource::CoalescedCriteria(begin, current),
-                                (_previous, current) => current,
-                            };
-                            Ok(RankingRule { source: merged_source, kind })
-                        }
-                        _ => Err((previous, current)),
-                    }
-                },
-            )
-    }
-
-    fn canonicalization_notes(&self) -> String {
-        use CanonicalizationAction::*;
-        let mut notes = String::new();
-        for (index, action) in self.canonicalization_actions.iter().enumerate() {
-            let index = index + 1;
-            let _ = match action {
-                PrependedWords { prepended_index } => writeln!(
-                    &mut notes,
-                    "    {index}. Prepended rule `words` before first relevancy rule `{}` at position {}",
-                    prepended_index.rule_name(&self.source_criteria, &self.source_sort),
-                    prepended_index.rule_position()
-                ),
-                RemovedDuplicate { earlier_occurrence, removed_occurrence } => writeln!(
-                    &mut notes,
-                    "    {index}. Removed duplicate rule `{}` at position {} as it already appears at position {}",
-                    earlier_occurrence.rule_name(&self.source_criteria, &self.source_sort),
-                    removed_occurrence.rule_position(),
-                    earlier_occurrence.rule_position(),
-                ),
-                RemovedWords { reason, removed_occurrence } => writeln!(
-                    &mut notes,
-                    "    {index}. Removed rule `words` at position {} because {reason}",
-                    removed_occurrence.rule_position()
-                ),
-                RemovedPlaceholder { removed_occurrence } => writeln!(
-                    &mut notes,
-                    "    {index}. Removed relevancy rule `{}` at position {} because the query is a placeholder search (`q`: \"\")",
-                    removed_occurrence.rule_name(&self.source_criteria, &self.source_sort),
-                    removed_occurrence.rule_position()
-                ),
-                TruncatedVector { vector_rule, truncated_from } => writeln!(
-                    &mut notes,
-                    "    {index}. Truncated relevancy rule `{}` at position {} and later rules because the query is a vector search and `vector` was inserted at position {}",
-                    truncated_from.rule_name(&self.source_criteria, &self.source_sort),
-                    truncated_from.rule_position(),
-                    vector_rule.rule_position(),
-                ),
-                RemovedVector { vector_rule, removed_occurrence } => writeln!(
-                    &mut notes,
-                    "    {index}. Removed relevancy rule `{}` at position {} because the query is a vector search and `vector` was already inserted at position {}",
-                    removed_occurrence.rule_name(&self.source_criteria, &self.source_sort),
-                    removed_occurrence.rule_position(),
-                    vector_rule.rule_position(),
-                ),
-                RemovedSort { removed_occurrence } => writeln!(
-                    &mut notes,
-                    "   {index}. Removed rule `sort` at position {} because `query.sort` is empty",
-removed_occurrence.rule_position()
-                ),
-            };
-        }
-        notes
-    }
-}
-
-fn canonicalize_sort(
-    sorted_fields: &mut HashMap<String, RankingRuleSource>,
-    sort_query: &[AscDesc],
-    criterion_index: usize,
-    canonicalization_actions: &mut Vec<CanonicalizationAction>,
-) -> Vec<AscDesc> {
-    let mut geo_sorted = None;
-    let mut canonical_sort = Vec::new();
-    for (sort_index, asc_desc) in sort_query.iter().enumerate() {
-        let source = RankingRuleSource::Sort { criterion_index, sort_index };
-        let asc_desc = asc_desc.clone();
-        match asc_desc.clone() {
-            AscDesc::Asc(Member::Field(s)) | AscDesc::Desc(Member::Field(s)) => {
-                match sorted_fields.entry(s) {
-                    std::collections::hash_map::Entry::Occupied(entry) => canonicalization_actions
-                        .push(CanonicalizationAction::RemovedDuplicate {
-                            earlier_occurrence: *entry.get(),
-                            removed_occurrence: source,
-                        }),
-                    std::collections::hash_map::Entry::Vacant(entry) => {
-                        entry.insert(source);
-                        canonical_sort.push(asc_desc);
-                    }
-                }
-            }
-            AscDesc::Asc(Member::Geo(_)) | AscDesc::Desc(Member::Geo(_)) => match geo_sorted {
-                Some(earlier_sort_index) => {
-                    canonicalization_actions.push(CanonicalizationAction::RemovedDuplicate {
-                        earlier_occurrence: RankingRuleSource::Sort {
-                            criterion_index,
-                            sort_index: earlier_sort_index,
-                        },
-                        removed_occurrence: source,
-                    })
-                }
-                None => {
-                    geo_sorted = Some(sort_index);
-                    canonical_sort.push(asc_desc);
-                }
-            },
-        }
-    }
-    canonical_sort
-}
-
-fn canonicalize_criterion(
-    criterion: Criterion,
-    criterion_index: usize,
-    terms_matching_strategy: TermsMatchingStrategy,
-    words: &mut Option<Option<usize>>,
-    canonicalization_actions: &mut Vec<CanonicalizationAction>,
-    canonical_criteria: &mut Vec<Criterion>,
-    rule: &mut Option<usize>,
-) {
-    *words = match (terms_matching_strategy, words.take()) {
-        (TermsMatchingStrategy::All, words) => words,
-        (_, None) => {
-            // inject words
-            canonicalization_actions.push(CanonicalizationAction::PrependedWords {
-                prepended_index: RankingRuleSource::Criterion(criterion_index),
-            });
-            canonical_criteria.push(Criterion::Words);
-            Some(None)
-        }
-        (_, words) => words,
-    };
-    if let Some(previous_index) = *rule {
-        canonicalization_actions.push(CanonicalizationAction::RemovedDuplicate {
-            earlier_occurrence: RankingRuleSource::Criterion(previous_index),
-            removed_occurrence: RankingRuleSource::Criterion(criterion_index),
-        });
-    } else {
-        *rule = Some(criterion_index);
-        canonical_criteria.push(criterion)
-    }
-}
-
-#[derive(Debug, Clone, Copy, PartialEq, Eq)]
-enum RankingRuleKind {
-    Relevancy,
-    AscendingSort,
-    DescendingSort,
-    AscendingGeoSort,
-    DescendingGeoSort,
-}
-
-#[derive(Debug, Clone, Copy)]
-pub struct RankingRule {
-    source: RankingRuleSource,
-    kind: RankingRuleKind,
-}
-
-#[derive(Debug, Clone, Copy)]
-pub enum RankingRuleSource {
-    Criterion(usize),
-    CoalescedCriteria(usize, usize),
-    Sort { criterion_index: usize, sort_index: usize },
-}
-
-impl RankingRuleSource {
-    fn rule_name(&self, criteria: &[Criterion], sort: &Option<Vec<AscDesc>>) -> String {
-        match self {
-            RankingRuleSource::Criterion(criterion_index) => criteria
-                .get(*criterion_index)
-                .map(|c| c.to_string())
-                .unwrap_or_else(|| "unknown".into()),
-            RankingRuleSource::CoalescedCriteria(begin, end) => {
-                let rules: Vec<_> = criteria
-                    .get(*begin..=*end)
-                    .iter()
-                    .flat_map(|c| c.iter())
-                    .map(|c| c.to_string())
-                    .collect();
-                rules.join(", ")
-            }
-            RankingRuleSource::Sort { criterion_index: _, sort_index } => {
-                match sort.as_deref().and_then(|sort| sort.get(*sort_index)) {
-                    Some(sort) => match sort {
-                        AscDesc::Asc(Member::Field(field_name)) => format!("{field_name}:asc"),
-                        AscDesc::Desc(Member::Field(field_name)) => {
-                            format!("{field_name}:desc")
-                        }
-                        AscDesc::Asc(Member::Geo(_)) => "_geo(..):asc".to_string(),
-                        AscDesc::Desc(Member::Geo(_)) => "_geo(..):desc".to_string(),
-                    },
-                    None => "unknown".into(),
-                }
-            }
-        }
-    }
-
-    fn rule_position(&self) -> String {
-        match self {
-            RankingRuleSource::Criterion(criterion_index) => {
-                format!("#{criterion_index} in ranking rules")
-            }
-            RankingRuleSource::CoalescedCriteria(begin, end) => {
-                format!("#{begin} to #{end} in ranking rules")
-            }
-            RankingRuleSource::Sort { criterion_index, sort_index } => format!(
-                "#{sort_index} in `query.sort` (as `sort` is #{criterion_index} in ranking rules)"
-            ),
-        }
-    }
-}
-
-impl RankingRule {
-    fn from_criterion<'a>(
-        criterion_index: usize,
-        criterion: &'a Criterion,
-        sort: &'a Option<Vec<AscDesc>>,
-    ) -> impl Iterator<Item = Self> + 'a {
-        let kind = match criterion {
-            Criterion::Words
-            | Criterion::Typo
-            | Criterion::Proximity
-            | Criterion::Attribute
-            | Criterion::Exactness => RankingRuleKind::Relevancy,
-            Criterion::Asc(s) if s == "_geo" => RankingRuleKind::AscendingGeoSort,
-
-            Criterion::Asc(_) => RankingRuleKind::AscendingSort,
-            Criterion::Desc(s) if s == "_geo" => RankingRuleKind::DescendingGeoSort,
-
-            Criterion::Desc(_) => RankingRuleKind::DescendingSort,
-            Criterion::Sort => {
-                return either::Right(sort.iter().flatten().enumerate().map(
-                    move |(rule_index, asc_desc)| {
-                        Self::from_asc_desc(asc_desc, criterion_index, rule_index)
-                    },
-                ))
-            }
-        };
-
-        either::Left(std::iter::once(Self {
-            source: RankingRuleSource::Criterion(criterion_index),
-            kind,
-        }))
-    }
-
-    fn from_asc_desc(asc_desc: &AscDesc, sort_index: usize, rule_index_in_sort: usize) -> Self {
-        let kind = match asc_desc {
-            AscDesc::Asc(Member::Field(_)) => RankingRuleKind::AscendingSort,
-            AscDesc::Desc(Member::Field(_)) => RankingRuleKind::DescendingSort,
-            AscDesc::Asc(Member::Geo(_)) => RankingRuleKind::AscendingGeoSort,
-            AscDesc::Desc(Member::Geo(_)) => RankingRuleKind::DescendingGeoSort,
-        };
-        Self {
-            source: RankingRuleSource::Sort {
-                criterion_index: sort_index,
-                sort_index: rule_index_in_sort,
-            },
-            kind,
-        }
-    }
-
-    fn as_string(
-        &self,
-        canonical_criteria: &[Criterion],
-        canonical_sort: &Option<Vec<AscDesc>>,
-        query_index: usize,
-        index_uid: &str,
-    ) -> String {
-        let kind = match self.kind {
-            RankingRuleKind::Relevancy => "relevancy",
-            RankingRuleKind::AscendingSort => "ascending sort",
-            RankingRuleKind::DescendingSort => "descending sort",
-            RankingRuleKind::AscendingGeoSort => "ascending geo sort",
-            RankingRuleKind::DescendingGeoSort => "descending geo sort",
-        };
-        let rules = self.fetch_from_source(canonical_criteria, canonical_sort);
-
-        let source = match self.source {
-            RankingRuleSource::Criterion(criterion_index) => format!("`queries[{query_index}]`, `{index_uid}.rankingRules[{criterion_index}]`"),
-            RankingRuleSource::CoalescedCriteria(begin, end) => format!("`queries[{query_index}]`, `{index_uid}.rankingRules[{begin}..={end}]`"),
-            RankingRuleSource::Sort { criterion_index, sort_index } => format!("`queries[{query_index}].sort[{sort_index}]`, `{index_uid}.rankingRules[{criterion_index}]`"),
-        };
-
-        format!("{source}: {kind} {rules}")
-    }
-
-    fn fetch_from_source(
-        &self,
-        canonical_criteria: &[Criterion],
-        canonical_sort: &Option<Vec<AscDesc>>,
-    ) -> String {
-        let rule_name = match self.source {
-            RankingRuleSource::Criterion(index) => {
-                canonical_criteria.get(index).map(|criterion| criterion.to_string())
-            }
-            RankingRuleSource::CoalescedCriteria(begin, end) => {
-                let rules: Vec<String> = canonical_criteria
-                    .get(begin..=end)
-                    .into_iter()
-                    .flat_map(|criteria| criteria.iter())
-                    .map(|criterion| criterion.to_string())
-                    .collect();
-
-                (!rules.is_empty()).then_some(rules.join(", "))
-            }
-            RankingRuleSource::Sort { criterion_index: _, sort_index } => canonical_sort
-                .as_deref()
-                .and_then(|canonical_sort| canonical_sort.get(sort_index))
-                .and_then(|asc_desc: &AscDesc| match asc_desc {
-                    AscDesc::Asc(Member::Field(s)) | AscDesc::Desc(Member::Field(s)) => {
-                        Some(format!("on field `{s}`"))
-                    }
-                    _ => None,
-                }),
-        };
-
-        let rule_name = rule_name.unwrap_or_else(|| "default".into());
-
-        format!("rule(s) {rule_name}")
-    }
-}

crates/meilisearch/tests/auth/mod.rs

@@ -1,7 +0,0 @@
-mod api_keys;
-mod authorization;
-mod errors;
-mod payload;
-mod tenant_token;
-
-mod tenant_token_multi_search;

crates/meilisearch/tests/common/mod.rs

@@ -1,391 +0,0 @@
-pub mod encoder;
-pub mod index;
-pub mod server;
-pub mod service;
-
-use std::fmt::{self, Display};
-
-#[allow(unused)]
-pub use index::GetAllDocumentsOptions;
-use meili_snap::json_string;
-use once_cell::sync::Lazy;
-use serde::{Deserialize, Serialize};
-#[allow(unused)]
-pub use server::{default_settings, Server};
-use tokio::sync::OnceCell;
-
-use crate::common::index::Index;
-
-pub enum Shared {}
-pub enum Owned {}
-
-#[derive(Debug, Clone, Default, Serialize, Deserialize, PartialEq, Eq)]
-pub struct Value(pub serde_json::Value);
-
-impl Value {
-    #[track_caller]
-    pub fn uid(&self) -> u64 {
-        if let Some(uid) = self["uid"].as_u64() {
-            uid
-        } else if let Some(uid) = self["taskUid"].as_u64() {
-            uid
-        } else {
-            panic!("Didn't find any task id in: {self}");
-        }
-    }
-
-    /// Return `true` if the `status` field is set to `succeeded`.
-    /// Panic if the `status` field doesn't exists.
-    #[track_caller]
-    pub fn is_success(&self) -> bool {
-        if !self["status"].is_string() {
-            panic!("Called `is_success` on {}", serde_json::to_string_pretty(&self.0).unwrap());
-        }
-        self["status"] == serde_json::Value::String(String::from("succeeded"))
-    }
-
-    // Panic if the json doesn't contain the `status` field set to "succeeded"
-    #[track_caller]
-    pub fn succeeded(&self) -> &Self {
-        if !self.is_success() {
-            panic!("Called succeeded on {}", serde_json::to_string_pretty(&self.0).unwrap());
-        }
-        self
-    }
-}
-
-impl From<serde_json::Value> for Value {
-    fn from(value: serde_json::Value) -> Self {
-        Value(value)
-    }
-}
-
-impl std::ops::Deref for Value {
-    type Target = serde_json::Value;
-
-    fn deref(&self) -> &Self::Target {
-        &self.0
-    }
-}
-
-impl std::ops::DerefMut for Value {
-    fn deref_mut(&mut self) -> &mut Self::Target {
-        &mut self.0
-    }
-}
-
-impl PartialEq<serde_json::Value> for Value {
-    fn eq(&self, other: &serde_json::Value) -> bool {
-        &self.0 == other
-    }
-}
-
-impl PartialEq<Value> for serde_json::Value {
-    fn eq(&self, other: &Value) -> bool {
-        self == &other.0
-    }
-}
-
-impl PartialEq<&str> for Value {
-    fn eq(&self, other: &&str) -> bool {
-        self.0.eq(other)
-    }
-}
-
-impl Display for Value {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        write!(
-            f,
-            "{}",
-            json_string!(self, {
-                ".uid" => "[uid]",
-                ".enqueuedAt" => "[date]",
-                ".startedAt" => "[date]",
-                ".finishedAt" => "[date]",
-                ".duration" => "[duration]",
-                ".processingTimeMs" => "[duration]",
-                ".details.embedders.*.url" => "[url]"
-            })
-        )
-    }
-}
-
-impl From<Vec<Value>> for Value {
-    fn from(value: Vec<Value>) -> Self {
-        Self(value.into_iter().map(|value| value.0).collect::<serde_json::Value>())
-    }
-}
-
-#[macro_export]
-macro_rules! json {
-    ($($json:tt)+) => {
-        $crate::common::Value(serde_json::json!($($json)+))
-    };
-}
-
-/// Performs a search test on both post and get routes
-#[macro_export]
-macro_rules! test_post_get_search {
-    ($server:expr, $query:expr, |$response:ident, $status_code:ident | $block:expr) => {
-        let post_query: meilisearch::routes::search::SearchQueryPost =
-            serde_json::from_str(&$query.clone().to_string()).unwrap();
-        let get_query: meilisearch::routes::search::SearchQuery = post_query.into();
-        let get_query = ::serde_url_params::to_string(&get_query).unwrap();
-        let ($response, $status_code) = $server.search_get(&get_query).await;
-        let _ = ::std::panic::catch_unwind(|| $block)
-            .map_err(|e| panic!("panic in get route: {:?}", e.downcast_ref::<&str>().unwrap()));
-        let ($response, $status_code) = $server.search_post($query).await;
-        let _ = ::std::panic::catch_unwind(|| $block)
-            .map_err(|e| panic!("panic in post route: {:?}", e.downcast_ref::<&str>().unwrap()));
-    };
-}
-
-pub async fn shared_does_not_exists_index() -> &'static Index<'static, Shared> {
-    static INDEX: Lazy<Index<'static, Shared>> = Lazy::new(|| {
-        let server = Server::new_shared();
-        server._index("DOES_NOT_EXISTS").to_shared()
-    });
-    &INDEX
-}
-
-pub async fn shared_empty_index() -> &'static Index<'static, Shared> {
-    static INDEX: OnceCell<Index<'static, Shared>> = OnceCell::const_new();
-
-    INDEX
-        .get_or_init(|| async {
-            let server = Server::new_shared();
-            let index = server._index("EMPTY_INDEX").to_shared();
-            let (response, _code) = index._create(None).await;
-            index.wait_task(response.uid()).await.succeeded();
-            index
-        })
-        .await
-}
-
-pub static DOCUMENTS: Lazy<Value> = Lazy::new(|| {
-    json!([
-        {
-            "title": "Shazam!",
-            "id": "287947",
-            "color": ["green", "blue"],
-            "_vectors": { "manual": [1, 2, 3]},
-        },
-        {
-            "title": "Captain Marvel",
-            "id": "299537",
-            "color": ["yellow", "blue"],
-            "_vectors": { "manual": [1, 2, 54] },
-        },
-        {
-            "title": "Escape Room",
-            "id": "522681",
-            "color": ["yellow", "red"],
-            "_vectors": { "manual": [10, -23, 32] },
-        },
-        {
-            "title": "How to Train Your Dragon: The Hidden World",
-            "id": "166428",
-            "color": ["green", "red"],
-            "_vectors": { "manual": [-100, 231, 32] },
-        },
-        {
-            "title": "Gläss",
-            "id": "450465",
-            "color": ["blue", "red"],
-            "_vectors": { "manual": [-100, 340, 90] },
-        }
-    ])
-});
-
-pub async fn shared_index_with_documents() -> &'static Index<'static, Shared> {
-    static INDEX: OnceCell<Index<'static, Shared>> = OnceCell::const_new();
-    INDEX.get_or_init(|| async {
-        let server = Server::new_shared();
-        let index = server._index("SHARED_DOCUMENTS").to_shared();
-        let documents = DOCUMENTS.clone();
-        let (response, _code) = index._add_documents(documents, None).await;
-        index.wait_task(response.uid()).await.succeeded();
-        let (response, _code) = index
-            ._update_settings(
-                json!({"filterableAttributes": ["id", "title"], "sortableAttributes": ["id", "title"]}),
-            )
-            .await;
-        index.wait_task(response.uid()).await.succeeded();
-        index
-    }).await
-}
-
-pub static SCORE_DOCUMENTS: Lazy<Value> = Lazy::new(|| {
-    json!([
-        {
-            "title": "Batman the dark knight returns: Part 1",
-            "id": "A",
-        },
-        {
-            "title": "Batman the dark knight returns: Part 2",
-            "id": "B",
-        },
-        {
-            "title": "Batman Returns",
-            "id": "C",
-        },
-        {
-            "title": "Batman",
-            "id": "D",
-        },
-        {
-            "title": "Badman",
-            "id": "E",
-        }
-    ])
-});
-
-pub static NESTED_DOCUMENTS: Lazy<Value> = Lazy::new(|| {
-    json!([
-        {
-            "id": 852,
-            "father": "jean",
-            "mother": "michelle",
-            "doggos": [
-                {
-                    "name": "bobby",
-                    "age": 2,
-                },
-                {
-                    "name": "buddy",
-                    "age": 4,
-                },
-            ],
-            "cattos": "pésti",
-            "_vectors": { "manual": [1, 2, 3]},
-        },
-        {
-            "id": 654,
-            "father": "pierre",
-            "mother": "sabine",
-            "doggos": [
-                {
-                    "name": "gros bill",
-                    "age": 8,
-                },
-            ],
-            "cattos": ["simba", "pestiféré"],
-            "_vectors": { "manual": [1, 2, 54] },
-        },
-        {
-            "id": 750,
-            "father": "romain",
-            "mother": "michelle",
-            "cattos": ["enigma"],
-            "_vectors": { "manual": [10, 23, 32] },
-        },
-        {
-            "id": 951,
-            "father": "jean-baptiste",
-            "mother": "sophie",
-            "doggos": [
-                {
-                    "name": "turbo",
-                    "age": 5,
-                },
-                {
-                    "name": "fast",
-                    "age": 6,
-                },
-            ],
-            "cattos": ["moumoute", "gomez"],
-            "_vectors": { "manual": [10, 23, 32] },
-        },
-    ])
-});
-
-pub async fn shared_index_with_nested_documents() -> &'static Index<'static, Shared> {
-    static INDEX: OnceCell<Index<'static, Shared>> = OnceCell::const_new();
-    INDEX.get_or_init(|| async {
-        let server = Server::new_shared();
-        let index = server._index("SHARED_NESTED_DOCUMENTS").to_shared();
-        let documents = NESTED_DOCUMENTS.clone();
-        let (response, _code) = index._add_documents(documents, None).await;
-        index.wait_task(response.uid()).await.succeeded();
-        let (response, _code) = index
-            ._update_settings(
-                json!({"filterableAttributes": ["father", "doggos"], "sortableAttributes": ["doggos"]}),
-            )
-            .await;
-        index.wait_task(response.uid()).await.succeeded();
-        index
-    }).await
-}
-
-pub static FRUITS_DOCUMENTS: Lazy<Value> = Lazy::new(|| {
-    json!([
-        {
-            "name": "Exclusive sale: green apple",
-            "id": "green-apple-boosted",
-            "BOOST": true
-        },
-        {
-            "name": "Pear",
-            "id": "pear",
-        },
-        {
-            "name": "Red apple gala",
-            "id": "red-apple-gala",
-        },
-        {
-            "name": "Exclusive sale: Red Tomato",
-            "id": "red-tomatoes-boosted",
-            "BOOST": true
-        },
-        {
-            "name": "Exclusive sale: Red delicious apple",
-            "id": "red-delicious-boosted",
-            "BOOST": true,
-        }
-    ])
-});
-
-pub static VECTOR_DOCUMENTS: Lazy<Value> = Lazy::new(|| {
-    json!([
-      {
-        "id": "A",
-        "description": "the dog barks at the cat",
-        "_vectors": {
-          // dimensions [canine, feline, young]
-          "animal": [0.9, 0.8, 0.05],
-          // dimensions [negative/positive, energy]
-          "sentiment": [-0.1, 0.55]
-        }
-      },
-      {
-        "id": "B",
-        "description": "the kitten scratched the beagle",
-        "_vectors": {
-          // dimensions [canine, feline, young]
-          "animal": [0.8, 0.9, 0.5],
-          // dimensions [negative/positive, energy]
-          "sentiment": [-0.2, 0.65]
-        }
-      },
-      {
-        "id": "C",
-        "description": "the dog had to stay alone today",
-        "_vectors": {
-          // dimensions [canine, feline, young]
-          "animal": [0.85, 0.02, 0.1],
-          // dimensions [negative/positive, energy]
-          "sentiment": [-1.0, 0.1]
-        }
-      },
-      {
-        "id": "D",
-        "description": "the little boy pets the puppy",
-        "_vectors": {
-          // dimensions [canine, feline, young]
-          "animal": [0.8, 0.09, 0.8],
-          // dimensions [negative/positive, energy]
-          "sentiment": [0.8, 0.3]
-        }
-      },
-    ])
-});

crates/meilisearch/tests/common/server.rs

@@ -1,404 +0,0 @@
-#![allow(dead_code)]
-
-use std::marker::PhantomData;
-use std::path::Path;
-use std::str::FromStr;
-use std::time::Duration;
-
-use actix_http::body::MessageBody;
-use actix_web::dev::ServiceResponse;
-use actix_web::http::StatusCode;
-use byte_unit::{Byte, Unit};
-use clap::Parser;
-use meilisearch::option::{IndexerOpts, MaxMemory, MaxThreads, Opt};
-use meilisearch::setup_meilisearch;
-use once_cell::sync::Lazy;
-use tempfile::TempDir;
-use tokio::sync::OnceCell;
-use tokio::time::sleep;
-use uuid::Uuid;
-
-use super::index::Index;
-use super::service::Service;
-use super::{Owned, Shared};
-use crate::common::encoder::Encoder;
-use crate::common::Value;
-use crate::json;
-
-pub struct Server<State = Owned> {
-    pub service: Service,
-    // hold ownership to the tempdir while we use the server instance.
-    _dir: Option<TempDir>,
-    _marker: PhantomData<State>,
-}
-
-pub static TEST_TEMP_DIR: Lazy<TempDir> = Lazy::new(|| TempDir::new().unwrap());
-
-impl Server<Owned> {
-    fn into_shared(self) -> Server<Shared> {
-        Server { service: self.service, _dir: self._dir, _marker: PhantomData }
-    }
-
-    pub async fn new() -> Self {
-        let dir = TempDir::new().unwrap();
-
-        if cfg!(windows) {
-            std::env::set_var("TMP", TEST_TEMP_DIR.path());
-        } else {
-            std::env::set_var("TMPDIR", TEST_TEMP_DIR.path());
-        }
-
-        let options = default_settings(dir.path());
-
-        let (index_scheduler, auth) = setup_meilisearch(&options).unwrap();
-        let service = Service { index_scheduler, auth, options, api_key: None };
-
-        Server { service, _dir: Some(dir), _marker: PhantomData }
-    }
-
-    pub async fn new_auth_with_options(mut options: Opt, dir: TempDir) -> Self {
-        if cfg!(windows) {
-            std::env::set_var("TMP", TEST_TEMP_DIR.path());
-        } else {
-            std::env::set_var("TMPDIR", TEST_TEMP_DIR.path());
-        }
-
-        options.master_key = Some("MASTER_KEY".to_string());
-
-        let (index_scheduler, auth) = setup_meilisearch(&options).unwrap();
-        let service = Service { index_scheduler, auth, options, api_key: None };
-
-        Server { service, _dir: Some(dir), _marker: PhantomData }
-    }
-
-    pub async fn new_auth() -> Self {
-        let dir = TempDir::new().unwrap();
-        let options = default_settings(dir.path());
-        Self::new_auth_with_options(options, dir).await
-    }
-
-    pub async fn new_with_options(options: Opt) -> Result<Self, anyhow::Error> {
-        let (index_scheduler, auth) = setup_meilisearch(&options)?;
-        let service = Service { index_scheduler, auth, options, api_key: None };
-
-        Ok(Server { service, _dir: None, _marker: PhantomData })
-    }
-
-    pub fn use_api_key(&mut self, api_key: impl AsRef<str>) {
-        self.service.api_key = Some(api_key.as_ref().to_string());
-    }
-
-    /// Fetch and use the default admin key for nexts http requests.
-    pub async fn use_admin_key(&mut self, master_key: impl AsRef<str>) {
-        self.use_api_key(master_key);
-        let (response, code) = self.list_api_keys("").await;
-        assert_eq!(200, code, "{:?}", response);
-        let admin_key = &response["results"][1]["key"];
-        self.use_api_key(admin_key.as_str().unwrap());
-    }
-
-    pub async fn add_api_key(&self, content: Value) -> (Value, StatusCode) {
-        let url = "/keys";
-        self.service.post(url, content).await
-    }
-
-    pub async fn patch_api_key(&self, key: impl AsRef<str>, content: Value) -> (Value, StatusCode) {
-        let url = format!("/keys/{}", key.as_ref());
-        self.service.patch(url, content).await
-    }
-
-    pub async fn delete_api_key(&self, key: impl AsRef<str>) -> (Value, StatusCode) {
-        let url = format!("/keys/{}", key.as_ref());
-        self.service.delete(url).await
-    }
-
-    /// Returns a view to an index. There is no guarantee that the index exists.
-    pub fn index(&self, uid: impl AsRef<str>) -> Index<'_> {
-        self.index_with_encoder(uid, Encoder::Plain)
-    }
-
-    pub async fn create_index(&self, body: Value) -> (Value, StatusCode) {
-        self.service.post("/indexes", body).await
-    }
-
-    pub fn index_with_encoder(&self, uid: impl AsRef<str>, encoder: Encoder) -> Index<'_> {
-        Index {
-            uid: uid.as_ref().to_string(),
-            service: &self.service,
-            encoder,
-            marker: PhantomData,
-        }
-    }
-
-    pub async fn list_indexes(
-        &self,
-        offset: Option<usize>,
-        limit: Option<usize>,
-    ) -> (Value, StatusCode) {
-        let (offset, limit) = (
-            offset.map(|offset| format!("offset={offset}")),
-            limit.map(|limit| format!("limit={limit}")),
-        );
-        let query_parameter = offset
-            .as_ref()
-            .zip(limit.as_ref())
-            .map(|(offset, limit)| format!("{offset}&{limit}"))
-            .or_else(|| offset.xor(limit));
-        if let Some(query_parameter) = query_parameter {
-            self.service.get(format!("/indexes?{query_parameter}")).await
-        } else {
-            self.service.get("/indexes").await
-        }
-    }
-
-    pub async fn stats(&self) -> (Value, StatusCode) {
-        self.service.get("/stats").await
-    }
-
-    pub async fn tasks(&self) -> (Value, StatusCode) {
-        self.service.get("/tasks").await
-    }
-
-    pub async fn set_features(&self, value: Value) -> (Value, StatusCode) {
-        self.service.patch("/experimental-features", value).await
-    }
-
-    pub async fn get_metrics(&self) -> (Value, StatusCode) {
-        self.service.get("/metrics").await
-    }
-}
-
-impl Server<Shared> {
-    fn init_new_shared_instance() -> Server<Shared> {
-        let dir = TempDir::new().unwrap();
-
-        if cfg!(windows) {
-            std::env::set_var("TMP", TEST_TEMP_DIR.path());
-        } else {
-            std::env::set_var("TMPDIR", TEST_TEMP_DIR.path());
-        }
-
-        let options = default_settings(dir.path());
-
-        let (index_scheduler, auth) = setup_meilisearch(&options).unwrap();
-        let service = Service { index_scheduler, auth, api_key: None, options };
-
-        Server { service, _dir: Some(dir), _marker: PhantomData }
-    }
-
-    pub fn new_shared() -> &'static Server<Shared> {
-        static SERVER: Lazy<Server<Shared>> = Lazy::new(Server::init_new_shared_instance);
-        &SERVER
-    }
-
-    pub async fn new_shared_with_admin_key() -> &'static Server<Shared> {
-        static SERVER: OnceCell<Server<Shared>> = OnceCell::const_new();
-        SERVER
-            .get_or_init(|| async {
-                let mut server = Server::new_auth().await;
-                server.use_admin_key("MASTER_KEY").await;
-                server.into_shared()
-            })
-            .await
-    }
-
-    /// You shouldn't access random indexes on a shared instance thus this method
-    /// must fail.
-    pub async fn get_index_fail(&self, uid: impl AsRef<str>) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}", urlencoding::encode(uid.as_ref()));
-        let (value, code) = self.service.get(url).await;
-        if code.is_success() {
-            panic!("`get_index_fail` succeeded with uid: {}", uid.as_ref());
-        }
-        (value, code)
-    }
-
-    pub async fn delete_index_fail(&self, uid: impl AsRef<str>) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}", urlencoding::encode(uid.as_ref()));
-        let (value, code) = self.service.delete(url).await;
-        if code.is_success() {
-            panic!("`delete_index_fail` succeeded with uid: {}", uid.as_ref());
-        }
-        (value, code)
-    }
-
-    pub async fn update_raw_index_fail(
-        &self,
-        uid: impl AsRef<str>,
-        body: Value,
-    ) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}", urlencoding::encode(uid.as_ref()));
-        let (value, code) = self.service.patch_encoded(url, body, Encoder::Plain).await;
-        if code.is_success() {
-            panic!("`update_raw_index_fail` succeeded with uid: {}", uid.as_ref());
-        }
-        (value, code)
-    }
-
-    /// Since this call updates the state of the instance, it must fail.
-    /// If it doesn't fail, the test will panic to help you debug what
-    /// is going on.
-    pub async fn create_index_fail(&self, body: Value) -> (Value, StatusCode) {
-        let (mut task, code) = self._create_index(body).await;
-        if code.is_success() {
-            task = self.wait_task(task.uid()).await;
-            if task.is_success() {
-                panic!(
-                    "`create_index_fail` succeeded: {}",
-                    serde_json::to_string_pretty(&task).unwrap()
-                );
-            }
-        }
-        (task, code)
-    }
-}
-
-impl<State> Server<State> {
-    pub async fn init_web_app(
-        &self,
-    ) -> impl actix_web::dev::Service<
-        actix_http::Request,
-        Response = ServiceResponse<impl MessageBody>,
-        Error = actix_web::Error,
-    > {
-        self.service.init_web_app().await
-    }
-
-    pub async fn list_api_keys(&self, params: &str) -> (Value, StatusCode) {
-        let url = format!("/keys{params}");
-        self.service.get(url).await
-    }
-
-    pub async fn dummy_request(
-        &self,
-        method: impl AsRef<str>,
-        url: impl AsRef<str>,
-    ) -> (Value, StatusCode) {
-        match method.as_ref() {
-            "POST" => self.service.post(url, json!({})).await,
-            "PUT" => self.service.put(url, json!({})).await,
-            "PATCH" => self.service.patch(url, json!({})).await,
-            "GET" => self.service.get(url).await,
-            "DELETE" => self.service.delete(url).await,
-            _ => unreachable!(),
-        }
-    }
-
-    pub async fn get_api_key(&self, key: impl AsRef<str>) -> (Value, StatusCode) {
-        let url = format!("/keys/{}", key.as_ref());
-        self.service.get(url).await
-    }
-
-    pub(super) fn _index(&self, uid: impl AsRef<str>) -> Index<'_> {
-        Index {
-            uid: uid.as_ref().to_string(),
-            service: &self.service,
-            encoder: Encoder::Plain,
-            marker: PhantomData,
-        }
-    }
-
-    /// Returns a view to an index. There is no guarantee that the index exists.
-    pub fn unique_index(&self) -> Index<'_> {
-        let uuid = Uuid::new_v4();
-        Index {
-            uid: uuid.to_string(),
-            service: &self.service,
-            encoder: Encoder::Plain,
-            marker: PhantomData,
-        }
-    }
-
-    pub fn unique_index_with_encoder(&self, encoder: Encoder) -> Index<'_> {
-        let uuid = Uuid::new_v4();
-        Index { uid: uuid.to_string(), service: &self.service, encoder, marker: PhantomData }
-    }
-
-    pub(super) async fn _create_index(&self, body: Value) -> (Value, StatusCode) {
-        self.service.post("/indexes", body).await
-    }
-
-    pub async fn multi_search(&self, queries: Value) -> (Value, StatusCode) {
-        self.service.post("/multi-search", queries).await
-    }
-
-    pub async fn list_indexes_raw(&self, parameters: &str) -> (Value, StatusCode) {
-        self.service.get(format!("/indexes{parameters}")).await
-    }
-
-    pub async fn tasks_filter(&self, filter: &str) -> (Value, StatusCode) {
-        self.service.get(format!("/tasks?{}", filter)).await
-    }
-
-    pub async fn version(&self) -> (Value, StatusCode) {
-        self.service.get("/version").await
-    }
-
-    pub async fn create_dump(&self) -> (Value, StatusCode) {
-        self.service.post("/dumps", json!(null)).await
-    }
-
-    pub async fn create_snapshot(&self) -> (Value, StatusCode) {
-        self.service.post("/snapshots", json!(null)).await
-    }
-
-    pub async fn index_swap(&self, value: Value) -> (Value, StatusCode) {
-        self.service.post("/swap-indexes", value).await
-    }
-
-    pub async fn cancel_tasks(&self, value: &str) -> (Value, StatusCode) {
-        self.service.post(format!("/tasks/cancel?{}", value), json!(null)).await
-    }
-
-    pub async fn delete_tasks(&self, value: &str) -> (Value, StatusCode) {
-        self.service.delete(format!("/tasks?{}", value)).await
-    }
-
-    pub async fn wait_task(&self, update_id: u64) -> Value {
-        // try several times to get status, or panic to not wait forever
-        let url = format!("/tasks/{}", update_id);
-        for _ in 0..100 {
-            let (response, status_code) = self.service.get(&url).await;
-            assert_eq!(200, status_code, "response: {}", response);
-
-            if response["status"] == "succeeded" || response["status"] == "failed" {
-                return response;
-            }
-
-            // wait 0.5 second.
-            sleep(Duration::from_millis(500)).await;
-        }
-        panic!("Timeout waiting for update id");
-    }
-
-    pub async fn get_task(&self, update_id: u64) -> (Value, StatusCode) {
-        let url = format!("/tasks/{}", update_id);
-        self.service.get(url).await
-    }
-
-    pub async fn get_features(&self) -> (Value, StatusCode) {
-        self.service.get("/experimental-features").await
-    }
-}
-
-pub fn default_settings(dir: impl AsRef<Path>) -> Opt {
-    Opt {
-        db_path: dir.as_ref().join("db"),
-        dump_dir: dir.as_ref().join("dumps"),
-        env: "development".to_owned(),
-        no_analytics: true,
-        max_index_size: Byte::from_u64_with_unit(100, Unit::MiB).unwrap(),
-        max_task_db_size: Byte::from_u64_with_unit(1, Unit::GiB).unwrap(),
-        http_payload_size_limit: Byte::from_u64_with_unit(10, Unit::MiB).unwrap(),
-        snapshot_dir: ".".into(),
-        indexer_options: IndexerOpts {
-            // memory has to be unlimited because several meilisearch are running in test context.
-            max_indexing_memory: MaxMemory::unlimited(),
-            skip_index_budget: true,
-            // Having 2 threads makes the tests way faster
-            max_indexing_threads: MaxThreads::from_str("2").unwrap(),
-        },
-        experimental_enable_metrics: false,
-        ..Parser::parse_from(None as Option<&str>)
-    }
-}

crates/meilisearch/tests/dumps/snapshots/mod.rs/generate_and_import_dump_containing_vectors/1.snap

@@ -1,25 +0,0 @@
----
-source: meilisearch/tests/dumps/mod.rs
----
-{
-  "uid": "[uid]",
-  "indexUid": "pets",
-  "status": "succeeded",
-  "type": "settingsUpdate",
-  "canceledBy": null,
-  "details": {
-    "embedders": {
-      "doggo_embedder": {
-        "source": "huggingFace",
-        "model": "sentence-transformers/all-MiniLM-L6-v2",
-        "revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
-        "documentTemplate": "{{doc.doggo}}"
-      }
-    }
-  },
-  "error": null,
-  "duration": "[duration]",
-  "enqueuedAt": "[date]",
-  "startedAt": "[date]",
-  "finishedAt": "[date]"
-}

crates/meilisearch/tests/dumps/snapshots/mod.rs/generate_and_import_dump_containing_vectors/2.snap

@@ -1,19 +0,0 @@
----
-source: meilisearch/tests/dumps/mod.rs
----
-{
-  "uid": "[uid]",
-  "indexUid": "pets",
-  "status": "succeeded",
-  "type": "documentAdditionOrUpdate",
-  "canceledBy": null,
-  "details": {
-    "receivedDocuments": 5,
-    "indexedDocuments": 5
-  },
-  "error": null,
-  "duration": "[duration]",
-  "enqueuedAt": "[date]",
-  "startedAt": "[date]",
-  "finishedAt": "[date]"
-}

crates/meilisearch/tests/search/hybrid.rs

@@ -1,653 +0,0 @@
-use meili_snap::snapshot;
-use once_cell::sync::Lazy;
-
-use crate::common::index::Index;
-use crate::common::{Server, Value};
-use crate::json;
-
-async fn index_with_documents_user_provided<'a>(
-    server: &'a Server,
-    documents: &Value,
-) -> Index<'a> {
-    let index = server.index("test");
-
-    let (response, code) = server.set_features(json!({"vectorStore": true})).await;
-
-    meili_snap::snapshot!(code, @"200 OK");
-    meili_snap::snapshot!(meili_snap::json_string!(response), @r###"
-    {
-      "vectorStore": true,
-      "metrics": false,
-      "logsRoute": false,
-      "editDocumentsByFunction": false,
-      "containsFilter": false
-    }
-    "###);
-
-    let (response, code) = index
-        .update_settings(json!({ "embedders": {"default": {
-                "source": "userProvided",
-                "dimensions": 2}}} ))
-        .await;
-    assert_eq!(202, code, "{:?}", response);
-    index.wait_task(response.uid()).await;
-
-    let (response, code) = index.add_documents(documents.clone(), None).await;
-    assert_eq!(202, code, "{:?}", response);
-    index.wait_task(response.uid()).await;
-    index
-}
-
-async fn index_with_documents_hf<'a>(server: &'a Server, documents: &Value) -> Index<'a> {
-    let index = server.index("test");
-
-    let (response, code) = server.set_features(json!({"vectorStore": true})).await;
-
-    meili_snap::snapshot!(code, @"200 OK");
-    meili_snap::snapshot!(meili_snap::json_string!(response), @r###"
-    {
-      "vectorStore": true,
-      "metrics": false,
-      "logsRoute": false,
-      "editDocumentsByFunction": false,
-      "containsFilter": false
-    }
-    "###);
-
-    let (response, code) = index
-        .update_settings(json!({ "embedders": {"default": {
-            "source": "huggingFace",
-            "model": "sentence-transformers/all-MiniLM-L6-v2",
-            "revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
-            "documentTemplate": "{{doc.title}}, {{doc.desc}}"
-        }}} ))
-        .await;
-    assert_eq!(202, code, "{:?}", response);
-    index.wait_task(response.uid()).await;
-
-    let (response, code) = index.add_documents(documents.clone(), None).await;
-    assert_eq!(202, code, "{:?}", response);
-    index.wait_task(response.uid()).await;
-    index
-}
-
-static SIMPLE_SEARCH_DOCUMENTS_VEC: Lazy<Value> = Lazy::new(|| {
-    json!([
-    {
-        "title": "Shazam!",
-        "desc": "a Captain Marvel ersatz",
-        "id": "1",
-        "_vectors": {"default": [1.0, 3.0]},
-    },
-    {
-        "title": "Captain Planet",
-        "desc": "He's not part of the Marvel Cinematic Universe",
-        "id": "2",
-        "_vectors": {"default": [1.0, 2.0]},
-    },
-    {
-        "title": "Captain Marvel",
-        "desc": "a Shazam ersatz",
-        "id": "3",
-        "_vectors": {"default": [2.0, 3.0]},
-    }])
-});
-
-static SINGLE_DOCUMENT_VEC: Lazy<Value> = Lazy::new(|| {
-    json!([{
-            "title": "Shazam!",
-            "desc": "a Captain Marvel ersatz",
-            "id": "1",
-            "_vectors": {"default": [1.0, 3.0]},
-    }])
-});
-
-static SIMPLE_SEARCH_DOCUMENTS: Lazy<Value> = Lazy::new(|| {
-    json!([
-    {
-        "title": "Shazam!",
-        "desc": "a Captain Marvel ersatz",
-        "id": "1",
-    },
-    {
-        "title": "Captain Planet",
-        "desc": "He's not part of the Marvel Cinematic Universe",
-        "id": "2",
-    },
-    {
-        "title": "Captain Marvel",
-        "desc": "a Shazam ersatz",
-        "id": "3",
-    }])
-});
-
-#[actix_rt::test]
-async fn simple_search() {
-    let server = Server::new().await;
-    let index = index_with_documents_user_provided(&server, &SIMPLE_SEARCH_DOCUMENTS_VEC).await;
-
-    let (response, code) = index
-        .search_post(
-            json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": 0.2, "embedder": "default"}, "retrieveVectors": true}),
-        )
-        .await;
-    snapshot!(code, @"200 OK");
-    snapshot!(response["hits"], @r###"[{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":{"embeddings":[[1.0,2.0]],"regenerate":false}}},{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":{"embeddings":[[2.0,3.0]],"regenerate":false}}},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":{"embeddings":[[1.0,3.0]],"regenerate":false}}}]"###);
-    snapshot!(response["semanticHitCount"], @"0");
-
-    let (response, code) = index
-        .search_post(
-            json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": 0.5, "embedder": "default"}, "showRankingScore": true, "retrieveVectors": true}),
-        )
-        .await;
-    snapshot!(code, @"200 OK");
-    snapshot!(response["hits"], @r###"[{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":{"embeddings":[[2.0,3.0]],"regenerate":false}},"_rankingScore":0.990290343761444},{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":{"embeddings":[[1.0,2.0]],"regenerate":false}},"_rankingScore":0.9848484848484848},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":{"embeddings":[[1.0,3.0]],"regenerate":false}},"_rankingScore":0.9472135901451112}]"###);
-    snapshot!(response["semanticHitCount"], @"2");
-
-    let (response, code) = index
-        .search_post(
-            json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": 0.8, "embedder": "default"}, "showRankingScore": true, "retrieveVectors": true}),
-        )
-        .await;
-    snapshot!(code, @"200 OK");
-    snapshot!(response["hits"], @r###"[{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":{"embeddings":[[2.0,3.0]],"regenerate":false}},"_rankingScore":0.990290343761444},{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":{"embeddings":[[1.0,2.0]],"regenerate":false}},"_rankingScore":0.974341630935669},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":{"embeddings":[[1.0,3.0]],"regenerate":false}},"_rankingScore":0.9472135901451112}]"###);
-    snapshot!(response["semanticHitCount"], @"3");
-}
-
-#[actix_rt::test]
-async fn limit_offset() {
-    let server = Server::new().await;
-    let index = index_with_documents_user_provided(&server, &SIMPLE_SEARCH_DOCUMENTS_VEC).await;
-
-    let (response, code) = index
-        .search_post(
-            json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": 0.2, "embedder": "default"}, "retrieveVectors": true, "offset": 1, "limit": 1}),
-        )
-        .await;
-    snapshot!(code, @"200 OK");
-    snapshot!(response["hits"], @r###"[{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":{"embeddings":[[2.0,3.0]],"regenerate":false}}}]"###);
-    snapshot!(response["semanticHitCount"], @"0");
-    assert_eq!(response["hits"].as_array().unwrap().len(), 1);
-
-    let server = Server::new().await;
-    let index = index_with_documents_user_provided(&server, &SIMPLE_SEARCH_DOCUMENTS_VEC).await;
-
-    let (response, code) = index
-        .search_post(
-            json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"semanticRatio": 0.9, "embedder": "default"}, "retrieveVectors": true, "offset": 1, "limit": 1}),
-        )
-        .await;
-    snapshot!(code, @"200 OK");
-    snapshot!(response["hits"], @r###"[{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":{"embeddings":[[1.0,2.0]],"regenerate":false}}}]"###);
-    snapshot!(response["semanticHitCount"], @"1");
-    assert_eq!(response["hits"].as_array().unwrap().len(), 1);
-}
-
-#[actix_rt::test]
-async fn simple_search_hf() {
-    let server = Server::new().await;
-    let index = index_with_documents_hf(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
-
-    let (response, code) = index
-        .search_post(
-            json!({"q": "Captain", "hybrid": {"semanticRatio": 0.2, "embedder": "default"}}),
-        )
-        .await;
-    snapshot!(code, @"200 OK");
-    snapshot!(response["hits"], @r###"[{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2"},{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3"},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1"}]"###);
-    snapshot!(response["semanticHitCount"], @"0");
-
-    let (response, code) = index
-        .search_post(
-            // disable ranking score as the vectors between architectures are not equal
-            json!({"q": "Captain", "hybrid": {"embedder": "default", "semanticRatio": 0.55}, "showRankingScore": false}),
-        )
-        .await;
-    snapshot!(code, @"200 OK");
-    snapshot!(response["hits"], @r###"[{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2"},{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3"},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1"}]"###);
-    snapshot!(response["semanticHitCount"], @"1");
-
-    let (response, code) = index
-        .search_post(
-            json!({"q": "Captain", "hybrid": {"embedder": "default", "semanticRatio": 0.8}, "showRankingScore": false}),
-        )
-        .await;
-    snapshot!(code, @"200 OK");
-    snapshot!(response["hits"], @r###"[{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1"},{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3"},{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2"}]"###);
-    snapshot!(response["semanticHitCount"], @"3");
-
-    let (response, code) = index
-        .search_post(
-            json!({"q": "Movie World", "hybrid": {"embedder": "default", "semanticRatio": 0.2}, "showRankingScore": false}),
-        )
-        .await;
-    snapshot!(code, @"200 OK");
-    snapshot!(response["hits"], @r###"[{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2"},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1"},{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3"}]"###);
-    snapshot!(response["semanticHitCount"], @"3");
-
-    let (response, code) = index
-        .search_post(
-            json!({"q": "Wonder replacement", "hybrid": {"embedder": "default", "semanticRatio": 0.2}, "showRankingScore": false}),
-        )
-        .await;
-    snapshot!(code, @"200 OK");
-    snapshot!(response["hits"], @r###"[{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3"},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1"},{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2"}]"###);
-    snapshot!(response["semanticHitCount"], @"3");
-}
-
-#[actix_rt::test]
-async fn distribution_shift() {
-    let server = Server::new().await;
-    let index = index_with_documents_user_provided(&server, &SIMPLE_SEARCH_DOCUMENTS_VEC).await;
-
-    let search = json!({"q": "Captain", "vector": [1.0, 1.0], "showRankingScore": true, "hybrid": {"embedder": "default", "semanticRatio": 1.0}, "retrieveVectors": true});
-    let (response, code) = index.search_post(search.clone()).await;
-    snapshot!(code, @"200 OK");
-    snapshot!(response["hits"], @r###"[{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":{"embeddings":[[2.0,3.0]],"regenerate":false}},"_rankingScore":0.990290343761444},{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":{"embeddings":[[1.0,2.0]],"regenerate":false}},"_rankingScore":0.974341630935669},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":{"embeddings":[[1.0,3.0]],"regenerate":false}},"_rankingScore":0.9472135901451112}]"###);
-
-    let (response, code) = index
-        .update_settings(json!({
-            "embedders": {
-                "default": {
-                    "distribution": {
-                        "mean": 0.998,
-                        "sigma": 0.01
-                    }
-                }
-            }
-        }))
-        .await;
-
-    snapshot!(code, @"202 Accepted");
-    let response = server.wait_task(response.uid()).await;
-    snapshot!(response["details"], @r###"{"embedders":{"default":{"distribution":{"mean":0.998,"sigma":0.01}}}}"###);
-
-    let (response, code) = index.search_post(search).await;
-    snapshot!(code, @"200 OK");
-    snapshot!(response["hits"], @r###"[{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":{"embeddings":[[2.0,3.0]],"regenerate":false}},"_rankingScore":0.19161224365234375},{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":{"embeddings":[[1.0,2.0]],"regenerate":false}},"_rankingScore":1.1920928955078125e-7},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":{"embeddings":[[1.0,3.0]],"regenerate":false}},"_rankingScore":1.1920928955078125e-7}]"###);
-}
-
-#[actix_rt::test]
-async fn highlighter() {
-    let server = Server::new().await;
-    let index = index_with_documents_user_provided(&server, &SIMPLE_SEARCH_DOCUMENTS_VEC).await;
-
-    let (response, code) = index
-        .search_post(json!({"q": "Captain Marvel", "vector": [1.0, 1.0],
-            "hybrid": {"embedder": "default", "semanticRatio": 0.2},
-           "retrieveVectors": true,
-           "attributesToHighlight": [
-                     "desc",
-                     "_vectors",
-                   ],
-           "highlightPreTag": "**BEGIN**",
-           "highlightPostTag": "**END**",
-        }))
-        .await;
-    snapshot!(code, @"200 OK");
-    snapshot!(response["hits"], @r###"[{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":{"embeddings":[[2.0,3.0]],"regenerate":false}},"_formatted":{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3"}},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":{"embeddings":[[1.0,3.0]],"regenerate":false}},"_formatted":{"title":"Shazam!","desc":"a **BEGIN**Captain**END** **BEGIN**Marvel**END** ersatz","id":"1"}},{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":{"embeddings":[[1.0,2.0]],"regenerate":false}},"_formatted":{"title":"Captain Planet","desc":"He's not part of the **BEGIN**Marvel**END** Cinematic Universe","id":"2"}}]"###);
-    snapshot!(response["semanticHitCount"], @"0");
-
-    let (response, code) = index
-        .search_post(json!({"q": "Captain Marvel", "vector": [1.0, 1.0],
-            "hybrid": {"embedder": "default", "semanticRatio": 0.8},
-            "retrieveVectors": true,
-            "showRankingScore": true,
-            "attributesToHighlight": [
-                     "desc"
-                   ],
-                   "highlightPreTag": "**BEGIN**",
-                   "highlightPostTag": "**END**"
-        }))
-        .await;
-    snapshot!(code, @"200 OK");
-    snapshot!(response["hits"], @r###"[{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":{"embeddings":[[2.0,3.0]],"regenerate":false}},"_formatted":{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3"},"_rankingScore":0.990290343761444},{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":{"embeddings":[[1.0,2.0]],"regenerate":false}},"_formatted":{"title":"Captain Planet","desc":"He's not part of the **BEGIN**Marvel**END** Cinematic Universe","id":"2"},"_rankingScore":0.974341630935669},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":{"embeddings":[[1.0,3.0]],"regenerate":false}},"_formatted":{"title":"Shazam!","desc":"a **BEGIN**Captain**END** **BEGIN**Marvel**END** ersatz","id":"1"},"_rankingScore":0.9472135901451112}]"###);
-    snapshot!(response["semanticHitCount"], @"3");
-
-    // no highlighting on full semantic
-    let (response, code) = index
-        .search_post(json!({"q": "Captain Marvel", "vector": [1.0, 1.0],
-            "hybrid": {"embedder": "default", "semanticRatio": 1.0},
-            "retrieveVectors": true,
-            "showRankingScore": true,
-            "attributesToHighlight": [
-                     "desc"
-                   ],
-                   "highlightPreTag": "**BEGIN**",
-                   "highlightPostTag": "**END**"
-        }))
-        .await;
-    snapshot!(code, @"200 OK");
-    snapshot!(response["hits"], @r###"[{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":{"embeddings":[[2.0,3.0]],"regenerate":false}},"_formatted":{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3"},"_rankingScore":0.990290343761444},{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":{"embeddings":[[1.0,2.0]],"regenerate":false}},"_formatted":{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2"},"_rankingScore":0.974341630935669},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":{"embeddings":[[1.0,3.0]],"regenerate":false}},"_formatted":{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1"},"_rankingScore":0.9472135901451112}]"###);
-    snapshot!(response["semanticHitCount"], @"3");
-}
-
-#[actix_rt::test]
-async fn invalid_semantic_ratio() {
-    let server = Server::new().await;
-    let index = index_with_documents_user_provided(&server, &SIMPLE_SEARCH_DOCUMENTS_VEC).await;
-
-    let (response, code) = index
-        .search_post(
-            json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"embedder": "default", "semanticRatio": 1.2}}),
-        )
-        .await;
-    snapshot!(code, @"400 Bad Request");
-    snapshot!(response, @r###"
-    {
-      "message": "Invalid value at `.hybrid.semanticRatio`: the value of `semanticRatio` is invalid, expected a float between `0.0` and `1.0`.",
-      "code": "invalid_search_semantic_ratio",
-      "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#invalid_search_semantic_ratio"
-    }
-    "###);
-
-    let (response, code) = index
-        .search_post(
-            json!({"q": "Captain", "vector": [1.0, 1.0], "hybrid": {"embedder": "default", "semanticRatio": -0.8}}),
-        )
-        .await;
-    snapshot!(code, @"400 Bad Request");
-    snapshot!(response, @r###"
-    {
-      "message": "Invalid value at `.hybrid.semanticRatio`: the value of `semanticRatio` is invalid, expected a float between `0.0` and `1.0`.",
-      "code": "invalid_search_semantic_ratio",
-      "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#invalid_search_semantic_ratio"
-    }
-    "###);
-
-    let (response, code) = index
-        .search_get(
-            &yaup::to_string(
-                &json!({"q": "Captain", "vector": [1.0, 1.0], "hybridEmbedder": "default", "hybridSemanticRatio": 1.2}),
-            )
-            .unwrap(),
-        )
-        .await;
-    snapshot!(code, @"400 Bad Request");
-    snapshot!(response, @r###"
-    {
-      "message": "Invalid value in parameter `hybridSemanticRatio`: the value of `semanticRatio` is invalid, expected a float between `0.0` and `1.0`.",
-      "code": "invalid_search_semantic_ratio",
-      "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#invalid_search_semantic_ratio"
-    }
-    "###);
-
-    let (response, code) = index
-        .search_get(
-            &yaup::to_string(
-                &json!({"q": "Captain", "vector": [1.0, 1.0], "hybridEmbedder": "default", "hybridSemanticRatio": -0.2}),
-            )
-            .unwrap(),
-        )
-        .await;
-    snapshot!(code, @"400 Bad Request");
-    snapshot!(response, @r###"
-    {
-      "message": "Invalid value in parameter `hybridSemanticRatio`: the value of `semanticRatio` is invalid, expected a float between `0.0` and `1.0`.",
-      "code": "invalid_search_semantic_ratio",
-      "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#invalid_search_semantic_ratio"
-    }
-    "###);
-}
-
-#[actix_rt::test]
-async fn single_document() {
-    let server = Server::new().await;
-    let index = index_with_documents_user_provided(&server, &SINGLE_DOCUMENT_VEC).await;
-
-    let (response, code) = index
-    .search_post(
-        json!({"vector": [1.0, 3.0], "hybrid": {"semanticRatio": 1.0, "embedder": "default"}, "showRankingScore": true, "retrieveVectors": true}),
-    )
-    .await;
-
-    snapshot!(code, @"200 OK");
-    snapshot!(response["hits"][0], @r###"{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":{"embeddings":[[1.0,3.0]],"regenerate":false}},"_rankingScore":1.0}"###);
-    snapshot!(response["semanticHitCount"], @"1");
-}
-
-#[actix_rt::test]
-async fn query_combination() {
-    let server = Server::new().await;
-    let index = index_with_documents_user_provided(&server, &SIMPLE_SEARCH_DOCUMENTS_VEC).await;
-
-    // search without query and vector, but with hybrid => still placeholder
-    let (response, code) = index
-        .search_post(json!({"hybrid": {"embedder": "default", "semanticRatio": 1.0}, "showRankingScore": true, "retrieveVectors": true}))
-        .await;
-
-    snapshot!(code, @"200 OK");
-    snapshot!(response["hits"], @r###"[{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":{"embeddings":[[1.0,3.0]],"regenerate":false}},"_rankingScore":1.0},{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":{"embeddings":[[1.0,2.0]],"regenerate":false}},"_rankingScore":1.0},{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":{"embeddings":[[2.0,3.0]],"regenerate":false}},"_rankingScore":1.0}]"###);
-    snapshot!(response["semanticHitCount"], @"null");
-
-    // same with a different semantic ratio
-    let (response, code) = index
-        .search_post(json!({"hybrid": {"embedder": "default", "semanticRatio": 0.76}, "showRankingScore": true, "retrieveVectors": true}))
-        .await;
-
-    snapshot!(code, @"200 OK");
-    snapshot!(response["hits"], @r###"[{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":{"embeddings":[[1.0,3.0]],"regenerate":false}},"_rankingScore":1.0},{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":{"embeddings":[[1.0,2.0]],"regenerate":false}},"_rankingScore":1.0},{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":{"embeddings":[[2.0,3.0]],"regenerate":false}},"_rankingScore":1.0}]"###);
-    snapshot!(response["semanticHitCount"], @"null");
-
-    // wrong vector dimensions
-    let (response, code) = index
-    .search_post(json!({"vector": [1.0, 0.0, 1.0], "hybrid": {"embedder": "default", "semanticRatio": 1.0}, "showRankingScore": true, "retrieveVectors": true}))
-    .await;
-
-    snapshot!(code, @"400 Bad Request");
-    snapshot!(response, @r###"
-    {
-      "message": "Invalid vector dimensions: expected: `2`, found: `3`.",
-      "code": "invalid_vector_dimensions",
-      "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#invalid_vector_dimensions"
-    }
-    "###);
-
-    // full vector
-    let (response, code) = index
-    .search_post(json!({"vector": [1.0, 0.0], "hybrid": {"embedder": "default", "semanticRatio": 1.0}, "showRankingScore": true, "retrieveVectors": true}))
-    .await;
-
-    snapshot!(code, @"200 OK");
-    snapshot!(response["hits"], @r###"[{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":{"embeddings":[[2.0,3.0]],"regenerate":false}},"_rankingScore":0.7773500680923462},{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":{"embeddings":[[1.0,2.0]],"regenerate":false}},"_rankingScore":0.7236068248748779},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":{"embeddings":[[1.0,3.0]],"regenerate":false}},"_rankingScore":0.6581138968467712}]"###);
-    snapshot!(response["semanticHitCount"], @"3");
-
-    // full keyword, without a query
-    let (response, code) = index
-    .search_post(json!({"vector": [1.0, 0.0], "hybrid": {"embedder": "default", "semanticRatio": 0.0}, "showRankingScore": true, "retrieveVectors": true}))
-    .await;
-
-    snapshot!(code, @"200 OK");
-    snapshot!(response["hits"], @r###"[{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":{"embeddings":[[1.0,3.0]],"regenerate":false}},"_rankingScore":1.0},{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":{"embeddings":[[1.0,2.0]],"regenerate":false}},"_rankingScore":1.0},{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":{"embeddings":[[2.0,3.0]],"regenerate":false}},"_rankingScore":1.0}]"###);
-    snapshot!(response["semanticHitCount"], @"null");
-
-    // query + vector, full keyword => keyword
-    let (response, code) = index
-    .search_post(json!({"q": "Captain", "vector": [1.0, 0.0], "hybrid": {"embedder": "default", "semanticRatio": 0.0}, "showRankingScore": true, "retrieveVectors": true}))
-    .await;
-
-    snapshot!(code, @"200 OK");
-    snapshot!(response["hits"], @r###"[{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":{"embeddings":[[1.0,2.0]],"regenerate":false}},"_rankingScore":0.9848484848484848},{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":{"embeddings":[[2.0,3.0]],"regenerate":false}},"_rankingScore":0.9848484848484848},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":{"embeddings":[[1.0,3.0]],"regenerate":false}},"_rankingScore":0.9242424242424242}]"###);
-    snapshot!(response["semanticHitCount"], @"null");
-
-    // query + vector, no hybrid keyword =>
-    let (response, code) = index
-        .search_post(json!({"q": "Captain", "vector": [1.0, 0.0], "showRankingScore": true, "retrieveVectors": true}))
-        .await;
-
-    snapshot!(code, @"400 Bad Request");
-    snapshot!(response, @r###"
-    {
-      "message": "Invalid request: missing `hybrid` parameter when `vector` is present.",
-      "code": "missing_search_hybrid",
-      "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#missing_search_hybrid"
-    }
-    "###);
-
-    // full vector, without a vector => error
-    let (response, code) = index
-        .search_post(
-            json!({"q": "Captain", "hybrid": {"semanticRatio": 1.0, "embedder": "default"}, "showRankingScore": true, "retrieveVectors": true}),
-        )
-        .await;
-
-    snapshot!(code, @"400 Bad Request");
-    snapshot!(response, @r###"
-    {
-      "message": "Error while generating embeddings: user error: attempt to embed the following text in a configuration where embeddings must be user provided:\n  - `Captain`",
-      "code": "vector_embedding_error",
-      "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
-    }
-    "###);
-
-    // hybrid without a vector => full keyword
-    let (response, code) = index
-        .search_post(
-            json!({"q": "Planet", "hybrid": {"semanticRatio": 0.99, "embedder": "default"}, "showRankingScore": true, "retrieveVectors": true}),
-        )
-        .await;
-
-    snapshot!(code, @"200 OK");
-    snapshot!(response["hits"], @r###"[{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":{"embeddings":[[1.0,2.0]],"regenerate":false}},"_rankingScore":0.9242424242424242}]"###);
-    snapshot!(response["semanticHitCount"], @"0");
-}
-
-#[actix_rt::test]
-async fn retrieve_vectors() {
-    let server = Server::new().await;
-    let index = index_with_documents_hf(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
-
-    let (response, code) = index
-        .search_post(
-            json!({"q": "Captain", "hybrid": {"embedder": "default", "semanticRatio": 0.2}, "retrieveVectors": true}),
-        )
-        .await;
-    snapshot!(code, @"200 OK");
-    insta::assert_json_snapshot!(response["hits"], {"[]._vectors.default.embeddings" => "[vectors]"},  @r###"
-    [
-      {
-        "title": "Captain Planet",
-        "desc": "He's not part of the Marvel Cinematic Universe",
-        "id": "2",
-        "_vectors": {
-          "default": {
-            "embeddings": "[vectors]",
-            "regenerate": true
-          }
-        }
-      },
-      {
-        "title": "Captain Marvel",
-        "desc": "a Shazam ersatz",
-        "id": "3",
-        "_vectors": {
-          "default": {
-            "embeddings": "[vectors]",
-            "regenerate": true
-          }
-        }
-      },
-      {
-        "title": "Shazam!",
-        "desc": "a Captain Marvel ersatz",
-        "id": "1",
-        "_vectors": {
-          "default": {
-            "embeddings": "[vectors]",
-            "regenerate": true
-          }
-        }
-      }
-    ]
-    "###);
-
-    // use explicit `_vectors` in displayed attributes
-    let (response, code) = index
-        .update_settings(json!({ "displayedAttributes": ["id", "title", "desc", "_vectors"]} ))
-        .await;
-    assert_eq!(202, code, "{:?}", response);
-    index.wait_task(response.uid()).await;
-
-    let (response, code) = index
-        .search_post(
-            json!({"q": "Captain", "hybrid": {"embedder": "default", "semanticRatio": 0.2}, "retrieveVectors": true}),
-        )
-        .await;
-    snapshot!(code, @"200 OK");
-    insta::assert_json_snapshot!(response["hits"], {"[]._vectors.default.embeddings" => "[vectors]"},  @r###"
-    [
-      {
-        "title": "Captain Planet",
-        "desc": "He's not part of the Marvel Cinematic Universe",
-        "id": "2",
-        "_vectors": {
-          "default": {
-            "embeddings": "[vectors]",
-            "regenerate": true
-          }
-        }
-      },
-      {
-        "title": "Captain Marvel",
-        "desc": "a Shazam ersatz",
-        "id": "3",
-        "_vectors": {
-          "default": {
-            "embeddings": "[vectors]",
-            "regenerate": true
-          }
-        }
-      },
-      {
-        "title": "Shazam!",
-        "desc": "a Captain Marvel ersatz",
-        "id": "1",
-        "_vectors": {
-          "default": {
-            "embeddings": "[vectors]",
-            "regenerate": true
-          }
-        }
-      }
-    ]
-    "###);
-
-    // remove `_vectors` from displayed attributes
-    let (response, code) =
-        index.update_settings(json!({ "displayedAttributes": ["id", "title", "desc"]} )).await;
-    assert_eq!(202, code, "{:?}", response);
-    index.wait_task(response.uid()).await;
-
-    let (response, code) = index
-        .search_post(
-            json!({"q": "Captain", "hybrid": {"embedder": "default", "semanticRatio": 0.2}, "retrieveVectors": true}),
-        )
-        .await;
-    snapshot!(code, @"200 OK");
-    insta::assert_json_snapshot!(response["hits"], {"[]._vectors.default.embeddings" => "[vectors]"},  @r###"
-    [
-      {
-        "title": "Captain Planet",
-        "desc": "He's not part of the Marvel Cinematic Universe",
-        "id": "2"
-      },
-      {
-        "title": "Captain Marvel",
-        "desc": "a Shazam ersatz",
-        "id": "3"
-      },
-      {
-        "title": "Shazam!",
-        "desc": "a Captain Marvel ersatz",
-        "id": "1"
-      }
-    ]
-    "###);
-}

crates/meilisearch/tests/search/matching_strategy.rs

@@ -1,128 +0,0 @@
-use meili_snap::snapshot;
-use once_cell::sync::Lazy;
-
-use crate::common::index::Index;
-use crate::common::{Server, Value};
-use crate::json;
-
-async fn index_with_documents<'a>(server: &'a Server, documents: &Value) -> Index<'a> {
-    let index = server.index("test");
-
-    index.add_documents(documents.clone(), None).await;
-    index.wait_task(0).await;
-    index
-}
-
-static SIMPLE_SEARCH_DOCUMENTS: Lazy<Value> = Lazy::new(|| {
-    json!([
-    {
-        "title": "Shazam!",
-        "id": "1",
-    },
-    {
-        "title": "Captain Planet",
-        "id": "2",
-    },
-    {
-        "title": "Captain Marvel",
-        "id": "3",
-    },
-    {
-        "title": "a Captain Marvel ersatz",
-        "id": "4"
-    },
-    {
-        "title": "He's not part of the Marvel Cinematic Universe",
-        "id": "5"
-    },
-    {
-        "title": "a Shazam ersatz, but better than Captain Planet",
-        "id": "6"
-    },
-    {
-        "title": "Capitain CAAAAAVEEERNE!!!!",
-        "id": "7"
-    }
-    ])
-});
-
-#[actix_rt::test]
-async fn simple_search() {
-    let server = Server::new().await;
-    let index = index_with_documents(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
-
-    index
-        .search(json!({"q": "Captain Marvel", "matchingStrategy": "last", "attributesToRetrieve": ["id"]}), |response, code| {
-            snapshot!(code, @"200 OK");
-            snapshot!(response["hits"], @r###"[{"id":"3"},{"id":"4"},{"id":"2"},{"id":"6"},{"id":"7"}]"###);
-        })
-        .await;
-
-    index
-        .search(json!({"q": "Captain Marvel", "matchingStrategy": "all", "attributesToRetrieve": ["id"]}), |response, code| {
-            snapshot!(code, @"200 OK");
-            snapshot!(response["hits"], @r###"[{"id":"3"},{"id":"4"}]"###);
-        })
-        .await;
-
-    index
-        .search(json!({"q": "Captain Marvel", "matchingStrategy": "frequency", "attributesToRetrieve": ["id"]}), |response, code| {
-            snapshot!(code, @"200 OK");
-            snapshot!(response["hits"], @r###"[{"id":"3"},{"id":"4"},{"id":"5"}]"###);
-        })
-        .await;
-}
-
-#[actix_rt::test]
-async fn search_with_typo() {
-    let server = Server::new().await;
-    let index = index_with_documents(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
-
-    index
-        .search(json!({"q": "Capitain Marvel", "matchingStrategy": "last", "attributesToRetrieve": ["id"]}), |response, code| {
-            snapshot!(code, @"200 OK");
-            snapshot!(response["hits"], @r###"[{"id":"3"},{"id":"4"},{"id":"7"},{"id":"2"},{"id":"6"}]"###);
-        })
-        .await;
-
-    index
-        .search(json!({"q": "Capitain Marvel", "matchingStrategy": "all", "attributesToRetrieve": ["id"]}), |response, code| {
-            snapshot!(code, @"200 OK");
-            snapshot!(response["hits"], @r###"[{"id":"3"},{"id":"4"}]"###);
-        })
-        .await;
-
-    index
-        .search(json!({"q": "Capitain Marvel", "matchingStrategy": "frequency", "attributesToRetrieve": ["id"]}), |response, code| {
-            snapshot!(code, @"200 OK");
-            snapshot!(response["hits"], @r###"[{"id":"3"},{"id":"4"},{"id":"5"}]"###);
-        })
-        .await;
-}
-
-#[actix_rt::test]
-async fn search_with_unknown_word() {
-    let server = Server::new().await;
-    let index = index_with_documents(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
-
-    index
-        .search(json!({"q": "Captain Supercopter Marvel", "matchingStrategy": "last", "attributesToRetrieve": ["id"]}), |response, code| {
-            snapshot!(code, @"200 OK");
-            snapshot!(response["hits"], @r###"[{"id":"2"},{"id":"3"},{"id":"4"},{"id":"6"},{"id":"7"}]"###);
-        })
-        .await;
-
-    index
-        .search(json!({"q": "Captain Supercopter Marvel", "matchingStrategy": "all", "attributesToRetrieve": ["id"]}), |response, code| {
-            snapshot!(code, @"200 OK");
-            snapshot!(response["hits"], @"[]");
-        })
-        .await;
-
-    index
-        .search(json!({"q": "Captain Supercopter Marvel", "matchingStrategy": "frequency", "attributesToRetrieve": ["id"]}), |response, code| {
-            snapshot!(code, @"200 OK");
-            snapshot!(response["hits"], @r###"[{"id":"3"},{"id":"4"},{"id":"5"}]"###);
-        })
-        .await;
-}

crates/meilisearch/tests/search/snapshots/distinct.rs/distinct_at_search_time/succeed.snap

@@ -1,20 +0,0 @@
----
-source: meilisearch/tests/search/distinct.rs
----
-{
-  "uid": "[uid]",
-  "indexUid": "tamo",
-  "status": "succeeded",
-  "type": "settingsUpdate",
-  "canceledBy": null,
-  "details": {
-    "filterableAttributes": [
-      "color.main"
-    ]
-  },
-  "error": null,
-  "duration": "[duration]",
-  "enqueuedAt": "[date]",
-  "startedAt": "[date]",
-  "finishedAt": "[date]"
-}

crates/meilisearch/tests/search/snapshots/errors.rs/distinct_at_search_time/task-succeed.snap

@@ -1,18 +0,0 @@
----
-source: meilisearch/tests/search/errors.rs
----
-{
-  "uid": "[uid]",
-  "indexUid": "tamo",
-  "status": "succeeded",
-  "type": "indexCreation",
-  "canceledBy": null,
-  "details": {
-    "primaryKey": null
-  },
-  "error": null,
-  "duration": "[duration]",
-  "enqueuedAt": "[date]",
-  "startedAt": "[date]",
-  "finishedAt": "[date]"
-}

crates/meilisearch/tests/similar/errors.rs

@@ -1,841 +0,0 @@
-use meili_snap::*;
-
-use super::DOCUMENTS;
-use crate::common::Server;
-use crate::json;
-
-#[actix_rt::test]
-async fn similar_unexisting_index() {
-    let server = Server::new().await;
-    let index = server.index("test");
-    server.set_features(json!({"vectorStore": true})).await;
-
-    let expected_response = json!({
-        "message": "Index `test` not found.",
-        "code": "index_not_found",
-        "type": "invalid_request",
-        "link": "https://docs.meilisearch.com/errors#index_not_found"
-    });
-
-    index
-        .similar(json!({"id": 287947, "embedder": "manual"}), |response, code| {
-            assert_eq!(code, 404);
-            assert_eq!(response, expected_response);
-        })
-        .await;
-}
-
-#[actix_rt::test]
-async fn similar_unexisting_parameter() {
-    let server = Server::new().await;
-    let index = server.index("test");
-    server.set_features(json!({"vectorStore": true})).await;
-
-    index
-        .similar(json!({"id": 287947, "marin": "hello"}), |response, code| {
-            assert_eq!(code, 400, "{}", response);
-            assert_eq!(response["code"], "bad_request");
-        })
-        .await;
-}
-
-#[actix_rt::test]
-async fn similar_feature_not_enabled() {
-    let server = Server::new().await;
-    let index = server.index("test");
-
-    let (response, code) = index.similar_post(json!({"id": 287947, "embedder": "manual"})).await;
-    snapshot!(code, @"400 Bad Request");
-    snapshot!(json_string!(response), @r###"
-    {
-      "message": "Using the similar API requires enabling the `vector store` experimental feature. See https://github.com/meilisearch/product/discussions/677",
-      "code": "feature_not_enabled",
-      "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#feature_not_enabled"
-    }
-    "###);
-}
-
-#[actix_rt::test]
-async fn similar_bad_id() {
-    let server = Server::new().await;
-    let index = server.index("test");
-    server.set_features(json!({"vectorStore": true})).await;
-
-    let (response, code) = index
-        .update_settings(json!({
-        "embedders": {
-            "manual": {
-                "source": "userProvided",
-                "dimensions": 3,
-            }
-        },
-        "filterableAttributes": ["title"]}))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response.uid()).await;
-
-    let (response, code) = index.similar_post(json!({"id": ["doggo"]})).await;
-    snapshot!(code, @"400 Bad Request");
-    snapshot!(json_string!(response), @r###"
-    {
-      "message": "Invalid value at `.id`: the value of `id` is invalid. A document identifier can be of type integer or string, only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and underscores (_), and can not be more than 512 bytes.",
-      "code": "invalid_similar_id",
-      "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#invalid_similar_id"
-    }
-    "###);
-}
-
-#[actix_rt::test]
-async fn similar_bad_ranking_score_threshold() {
-    let server = Server::new().await;
-    let index = server.index("test");
-    server.set_features(json!({"vectorStore": true})).await;
-
-    let (response, code) = index
-        .update_settings(json!({
-        "embedders": {
-            "manual": {
-                "source": "userProvided",
-                "dimensions": 3,
-            }
-        },
-        "filterableAttributes": ["title"]}))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response.uid()).await;
-
-    let (response, code) = index.similar_post(json!({"rankingScoreThreshold": ["doggo"]})).await;
-    snapshot!(code, @"400 Bad Request");
-    snapshot!(json_string!(response), @r###"
-    {
-      "message": "Invalid value type at `.rankingScoreThreshold`: expected a number, but found an array: `[\"doggo\"]`",
-      "code": "invalid_similar_ranking_score_threshold",
-      "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#invalid_similar_ranking_score_threshold"
-    }
-    "###);
-}
-
-#[actix_rt::test]
-async fn similar_invalid_ranking_score_threshold() {
-    let server = Server::new().await;
-    let index = server.index("test");
-    server.set_features(json!({"vectorStore": true})).await;
-
-    let (response, code) = index
-        .update_settings(json!({
-        "embedders": {
-            "manual": {
-                "source": "userProvided",
-                "dimensions": 3,
-            }
-        },
-        "filterableAttributes": ["title"]}))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response.uid()).await;
-
-    let (response, code) = index.similar_post(json!({"rankingScoreThreshold": 42})).await;
-    snapshot!(code, @"400 Bad Request");
-    snapshot!(json_string!(response), @r###"
-    {
-      "message": "Invalid value at `.rankingScoreThreshold`: the value of `rankingScoreThreshold` is invalid, expected a float between `0.0` and `1.0`.",
-      "code": "invalid_similar_ranking_score_threshold",
-      "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#invalid_similar_ranking_score_threshold"
-    }
-    "###);
-}
-
-#[actix_rt::test]
-async fn similar_invalid_id() {
-    let server = Server::new().await;
-    let index = server.index("test");
-    server.set_features(json!({"vectorStore": true})).await;
-
-    let (response, code) = index
-        .update_settings(json!({
-        "embedders": {
-            "manual": {
-                "source": "userProvided",
-                "dimensions": 3,
-            }
-        },
-        "filterableAttributes": ["title"]}))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response.uid()).await;
-
-    let (response, code) = index.similar_post(json!({"id": "http://invalid-docid/"})).await;
-    snapshot!(code, @"400 Bad Request");
-    snapshot!(json_string!(response), @r###"
-    {
-      "message": "Invalid value at `.id`: the value of `id` is invalid. A document identifier can be of type integer or string, only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and underscores (_), and can not be more than 512 bytes.",
-      "code": "invalid_similar_id",
-      "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#invalid_similar_id"
-    }
-    "###);
-}
-
-#[actix_rt::test]
-async fn similar_not_found_id() {
-    let server = Server::new().await;
-    let index = server.index("test");
-    server.set_features(json!({"vectorStore": true})).await;
-
-    let (response, code) = index
-        .update_settings(json!({
-        "embedders": {
-            "manual": {
-                "source": "userProvided",
-                "dimensions": 3,
-            }
-        },
-        "filterableAttributes": ["title"]}))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response.uid()).await;
-
-    let (response, code) =
-        index.similar_post(json!({"id": "definitely-doesnt-exist", "embedder": "manual"})).await;
-    snapshot!(code, @"400 Bad Request");
-    snapshot!(json_string!(response), @r###"
-    {
-      "message": "Document `definitely-doesnt-exist` not found.",
-      "code": "not_found_similar_id",
-      "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#not_found_similar_id"
-    }
-    "###);
-}
-
-#[actix_rt::test]
-async fn similar_bad_offset() {
-    let server = Server::new().await;
-    let index = server.index("test");
-    server.set_features(json!({"vectorStore": true})).await;
-
-    let (response, code) = index
-        .update_settings(json!({
-        "embedders": {
-            "manual": {
-                "source": "userProvided",
-                "dimensions": 3,
-            }
-        },
-        "filterableAttributes": ["title"]}))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response.uid()).await;
-
-    let (response, code) =
-        index.similar_post(json!({"id": 287947, "offset": "doggo", "embedder": "manual"})).await;
-    snapshot!(code, @"400 Bad Request");
-    snapshot!(json_string!(response), @r###"
-    {
-      "message": "Invalid value type at `.offset`: expected a positive integer, but found a string: `\"doggo\"`",
-      "code": "invalid_similar_offset",
-      "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#invalid_similar_offset"
-    }
-    "###);
-
-    let (response, code) = index.similar_get("?id=287947&offset=doggo&embedder=manual").await;
-    snapshot!(code, @"400 Bad Request");
-    snapshot!(json_string!(response), @r###"
-    {
-      "message": "Invalid value in parameter `offset`: could not parse `doggo` as a positive integer",
-      "code": "invalid_similar_offset",
-      "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#invalid_similar_offset"
-    }
-    "###);
-}
-
-#[actix_rt::test]
-async fn similar_bad_limit() {
-    let server = Server::new().await;
-    let index = server.index("test");
-    server.set_features(json!({"vectorStore": true})).await;
-
-    let (response, code) = index
-        .update_settings(json!({
-        "embedders": {
-            "manual": {
-                "source": "userProvided",
-                "dimensions": 3,
-            }
-        },
-        "filterableAttributes": ["title"]}))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response.uid()).await;
-
-    let (response, code) =
-        index.similar_post(json!({"id": 287947, "limit": "doggo", "embedder": "manual"})).await;
-    snapshot!(code, @"400 Bad Request");
-    snapshot!(json_string!(response), @r###"
-    {
-      "message": "Invalid value type at `.limit`: expected a positive integer, but found a string: `\"doggo\"`",
-      "code": "invalid_similar_limit",
-      "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#invalid_similar_limit"
-    }
-    "###);
-
-    let (response, code) = index.similar_get("?id=287946&limit=doggo&embedder=manual").await;
-    snapshot!(code, @"400 Bad Request");
-    snapshot!(json_string!(response), @r###"
-    {
-      "message": "Invalid value in parameter `limit`: could not parse `doggo` as a positive integer",
-      "code": "invalid_similar_limit",
-      "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#invalid_similar_limit"
-    }
-    "###);
-}
-
-#[actix_rt::test]
-async fn similar_bad_filter() {
-    // Since a filter is deserialized as a json Value it will never fail to deserialize.
-    // Thus the error message is not generated by deserr but written by us.
-    let server = Server::new().await;
-    let index = server.index("test");
-    server.set_features(json!({"vectorStore": true})).await;
-
-    let (response, code) = index
-        .update_settings(json!({
-        "embedders": {
-            "manual": {
-                "source": "userProvided",
-                "dimensions": 3,
-            }
-        },
-        "filterableAttributes": ["title"]}))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response.uid()).await;
-
-    snapshot!(code, @"202 Accepted");
-
-    let documents = DOCUMENTS.clone();
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    index.wait_task(value.uid()).await;
-
-    let (response, code) =
-        index.similar_post(json!({ "id": 287947, "filter": true, "embedder": "manual" })).await;
-    snapshot!(code, @"400 Bad Request");
-    snapshot!(json_string!(response), @r###"
-    {
-      "message": "Invalid syntax for the filter parameter: `expected String, Array, found: true`.",
-      "code": "invalid_similar_filter",
-      "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
-    }
-    "###);
-    // Can't make the `filter` fail with a get search since it'll accept anything as a strings.
-}
-
-#[actix_rt::test]
-async fn filter_invalid_syntax_object() {
-    let server = Server::new().await;
-    let index = server.index("test");
-    server.set_features(json!({"vectorStore": true})).await;
-
-    let (response, code) = index
-        .update_settings(json!({
-        "embedders": {
-            "manual": {
-                "source": "userProvided",
-                "dimensions": 3,
-            }
-        },
-        "filterableAttributes": ["title"]}))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response.uid()).await;
-
-    let documents = DOCUMENTS.clone();
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    index.wait_task(value.uid()).await;
-
-    index
-        .similar(json!({"id": 287947, "filter": "title & Glass", "embedder": "manual"}), |response, code| {
-            snapshot!(response, @r###"
-            {
-              "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `STARTS WITH`, `NOT STARTS WITH`, `_geoRadius`, or `_geoBoundingBox` at `title & Glass`.\n1:14 title & Glass",
-              "code": "invalid_similar_filter",
-              "type": "invalid_request",
-              "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
-            }
-            "###);
-            snapshot!(code, @"400 Bad Request");
-        })
-        .await;
-}
-
-#[actix_rt::test]
-async fn filter_invalid_syntax_array() {
-    let server = Server::new().await;
-    let index = server.index("test");
-    server.set_features(json!({"vectorStore": true})).await;
-
-    let (response, code) = index
-        .update_settings(json!({
-        "embedders": {
-            "manual": {
-                "source": "userProvided",
-                "dimensions": 3,
-            }
-        },
-        "filterableAttributes": ["title"]}))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response.uid()).await;
-
-    let documents = DOCUMENTS.clone();
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    index.wait_task(value.uid()).await;
-
-    index
-        .similar(json!({"id": 287947, "filter": ["title & Glass"], "embedder": "manual"}), |response, code| {
-            snapshot!(response, @r###"
-            {
-              "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `STARTS WITH`, `NOT STARTS WITH`, `_geoRadius`, or `_geoBoundingBox` at `title & Glass`.\n1:14 title & Glass",
-              "code": "invalid_similar_filter",
-              "type": "invalid_request",
-              "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
-            }
-            "###);
-            snapshot!(code, @"400 Bad Request");
-        })
-        .await;
-}
-
-#[actix_rt::test]
-async fn filter_invalid_syntax_string() {
-    let server = Server::new().await;
-    let index = server.index("test");
-    server.set_features(json!({"vectorStore": true})).await;
-
-    let (response, code) = index
-        .update_settings(json!({
-        "embedders": {
-            "manual": {
-                "source": "userProvided",
-                "dimensions": 3,
-            }
-        },
-        "filterableAttributes": ["title"]}))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response.uid()).await;
-
-    let documents = DOCUMENTS.clone();
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    index.wait_task(value.uid()).await;
-
-    let expected_response = json!({
-        "message": "Found unexpected characters at the end of the filter: `XOR title = Glass`. You probably forgot an `OR` or an `AND` rule.\n15:32 title = Glass XOR title = Glass",
-        "code": "invalid_similar_filter",
-        "type": "invalid_request",
-        "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
-    });
-    index
-        .similar(
-            json!({"id": 287947, "filter": "title = Glass XOR title = Glass", "embedder": "manual"}),
-            |response, code| {
-                assert_eq!(response, expected_response);
-                assert_eq!(code, 400);
-            },
-        )
-        .await;
-}
-
-#[actix_rt::test]
-async fn filter_invalid_attribute_array() {
-    let server = Server::new().await;
-    let index = server.index("test");
-    server.set_features(json!({"vectorStore": true})).await;
-
-    let (response, code) = index
-        .update_settings(json!({
-        "embedders": {
-            "manual": {
-                "source": "userProvided",
-                "dimensions": 3,
-            }
-        },
-        "filterableAttributes": ["title"]}))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response.uid()).await;
-
-    let documents = DOCUMENTS.clone();
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    index.wait_task(value.uid()).await;
-
-    let expected_response = json!({
-        "message": "Attribute `many` is not filterable. Available filterable attributes are: `title`.\n1:5 many = Glass",
-        "code": "invalid_similar_filter",
-        "type": "invalid_request",
-        "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
-    });
-    index
-        .similar(
-            json!({"id": 287947, "filter": ["many = Glass"], "embedder": "manual"}),
-            |response, code| {
-                assert_eq!(response, expected_response);
-                assert_eq!(code, 400);
-            },
-        )
-        .await;
-}
-
-#[actix_rt::test]
-async fn filter_invalid_attribute_string() {
-    let server = Server::new().await;
-    let index = server.index("test");
-    server.set_features(json!({"vectorStore": true})).await;
-
-    let (response, code) = index
-        .update_settings(json!({
-        "embedders": {
-            "manual": {
-                "source": "userProvided",
-                "dimensions": 3,
-            }
-        },
-        "filterableAttributes": ["title"]}))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response.uid()).await;
-
-    let documents = DOCUMENTS.clone();
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    index.wait_task(value.uid()).await;
-
-    let expected_response = json!({
-        "message": "Attribute `many` is not filterable. Available filterable attributes are: `title`.\n1:5 many = Glass",
-        "code": "invalid_similar_filter",
-        "type": "invalid_request",
-        "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
-    });
-    index
-        .similar(
-            json!({"id": 287947, "filter": "many = Glass", "embedder": "manual"}),
-            |response, code| {
-                assert_eq!(response, expected_response);
-                assert_eq!(code, 400);
-            },
-        )
-        .await;
-}
-
-#[actix_rt::test]
-async fn filter_reserved_geo_attribute_array() {
-    let server = Server::new().await;
-    let index = server.index("test");
-    server.set_features(json!({"vectorStore": true})).await;
-
-    let (response, code) = index
-        .update_settings(json!({
-        "embedders": {
-            "manual": {
-                "source": "userProvided",
-                "dimensions": 3,
-            }
-        },
-        "filterableAttributes": ["title"]}))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response.uid()).await;
-
-    let documents = DOCUMENTS.clone();
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    index.wait_task(value.uid()).await;
-
-    let expected_response = json!({
-        "message": "`_geo` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates.\n1:13 _geo = Glass",
-        "code": "invalid_similar_filter",
-        "type": "invalid_request",
-        "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
-    });
-    index
-        .similar(
-            json!({"id": 287947, "filter": ["_geo = Glass"], "embedder": "manual"}),
-            |response, code| {
-                assert_eq!(response, expected_response);
-                assert_eq!(code, 400);
-            },
-        )
-        .await;
-}
-
-#[actix_rt::test]
-async fn filter_reserved_geo_attribute_string() {
-    let server = Server::new().await;
-    let index = server.index("test");
-    server.set_features(json!({"vectorStore": true})).await;
-
-    let (response, code) = index
-        .update_settings(json!({
-        "embedders": {
-            "manual": {
-                "source": "userProvided",
-                "dimensions": 3,
-            }
-        },
-        "filterableAttributes": ["title"]}))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response.uid()).await;
-
-    let documents = DOCUMENTS.clone();
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    index.wait_task(value.uid()).await;
-
-    let expected_response = json!({
-        "message": "`_geo` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates.\n1:13 _geo = Glass",
-        "code": "invalid_similar_filter",
-        "type": "invalid_request",
-        "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
-    });
-    index
-        .similar(
-            json!({"id": 287947, "filter": "_geo = Glass", "embedder": "manual"}),
-            |response, code| {
-                assert_eq!(response, expected_response);
-                assert_eq!(code, 400);
-            },
-        )
-        .await;
-}
-
-#[actix_rt::test]
-async fn filter_reserved_attribute_array() {
-    let server = Server::new().await;
-    let index = server.index("test");
-    server.set_features(json!({"vectorStore": true})).await;
-
-    let (response, code) = index
-        .update_settings(json!({
-        "embedders": {
-            "manual": {
-                "source": "userProvided",
-                "dimensions": 3,
-            }
-        },
-        "filterableAttributes": ["title"]}))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response.uid()).await;
-
-    let documents = DOCUMENTS.clone();
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    index.wait_task(value.uid()).await;
-
-    let expected_response = json!({
-        "message": "`_geoDistance` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates.\n1:21 _geoDistance = Glass",
-        "code": "invalid_similar_filter",
-        "type": "invalid_request",
-        "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
-    });
-    index
-        .similar(
-            json!({"id": 287947, "filter": ["_geoDistance = Glass"], "embedder": "manual"}),
-            |response, code| {
-                assert_eq!(response, expected_response);
-                assert_eq!(code, 400);
-            },
-        )
-        .await;
-}
-
-#[actix_rt::test]
-async fn filter_reserved_attribute_string() {
-    let server = Server::new().await;
-    let index = server.index("test");
-    server.set_features(json!({"vectorStore": true})).await;
-
-    let (response, code) = index
-        .update_settings(json!({
-        "embedders": {
-            "manual": {
-                "source": "userProvided",
-                "dimensions": 3,
-            }
-        },
-        "filterableAttributes": ["title"]}))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response.uid()).await;
-
-    let documents = DOCUMENTS.clone();
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    index.wait_task(value.uid()).await;
-
-    let expected_response = json!({
-       "message": "`_geoDistance` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates.\n1:21 _geoDistance = Glass",
-        "code": "invalid_similar_filter",
-        "type": "invalid_request",
-        "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
-    });
-    index
-        .similar(
-            json!({"id": 287947, "filter": "_geoDistance = Glass", "embedder": "manual"}),
-            |response, code| {
-                assert_eq!(response, expected_response);
-                assert_eq!(code, 400);
-            },
-        )
-        .await;
-}
-
-#[actix_rt::test]
-async fn filter_reserved_geo_point_array() {
-    let server = Server::new().await;
-    let index = server.index("test");
-    server.set_features(json!({"vectorStore": true})).await;
-
-    let (response, code) = index
-        .update_settings(json!({
-        "embedders": {
-            "manual": {
-                "source": "userProvided",
-                "dimensions": 3,
-            }
-        },
-        "filterableAttributes": ["title"]}))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response.uid()).await;
-
-    let documents = DOCUMENTS.clone();
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    index.wait_task(value.uid()).await;
-
-    let expected_response = json!({
-        "message": "`_geoPoint` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates.\n1:18 _geoPoint = Glass",
-        "code": "invalid_similar_filter",
-        "type": "invalid_request",
-        "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
-    });
-    index
-        .similar(
-            json!({"id": 287947, "filter": ["_geoPoint = Glass"], "embedder": "manual"}),
-            |response, code| {
-                assert_eq!(response, expected_response);
-                assert_eq!(code, 400);
-            },
-        )
-        .await;
-}
-
-#[actix_rt::test]
-async fn filter_reserved_geo_point_string() {
-    let server = Server::new().await;
-    let index = server.index("test");
-    server.set_features(json!({"vectorStore": true})).await;
-
-    let (response, code) = index
-        .update_settings(json!({
-        "embedders": {
-            "manual": {
-                "source": "userProvided",
-                "dimensions": 3,
-            }
-        },
-        "filterableAttributes": ["title"]}))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response.uid()).await;
-
-    let documents = DOCUMENTS.clone();
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    index.wait_task(value.uid()).await;
-
-    let expected_response = json!({
-       "message": "`_geoPoint` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates.\n1:18 _geoPoint = Glass",
-        "code": "invalid_similar_filter",
-        "type": "invalid_request",
-        "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
-    });
-    index
-        .similar(
-            json!({"id": 287947, "filter": "_geoPoint = Glass", "embedder": "manual"}),
-            |response, code| {
-                assert_eq!(response, expected_response);
-                assert_eq!(code, 400);
-            },
-        )
-        .await;
-}
-
-#[actix_rt::test]
-async fn similar_bad_retrieve_vectors() {
-    let server = Server::new().await;
-    server.set_features(json!({"vectorStore": true})).await;
-    let index = server.index("test");
-
-    let (response, code) =
-        index.similar_post(json!({"retrieveVectors": "doggo", "embedder": "manual"})).await;
-    snapshot!(code, @"400 Bad Request");
-    snapshot!(json_string!(response), @r###"
-    {
-      "message": "Invalid value type at `.retrieveVectors`: expected a boolean, but found a string: `\"doggo\"`",
-      "code": "invalid_similar_retrieve_vectors",
-      "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#invalid_similar_retrieve_vectors"
-    }
-    "###);
-
-    let (response, code) =
-        index.similar_post(json!({"retrieveVectors": [true], "embedder": "manual"})).await;
-    snapshot!(code, @"400 Bad Request");
-    snapshot!(json_string!(response), @r###"
-    {
-      "message": "Invalid value type at `.retrieveVectors`: expected a boolean, but found an array: `[true]`",
-      "code": "invalid_similar_retrieve_vectors",
-      "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#invalid_similar_retrieve_vectors"
-    }
-    "###);
-
-    let (response, code) = index.similar_get("?retrieveVectors=").await;
-    snapshot!(code, @"400 Bad Request");
-    snapshot!(json_string!(response), @r###"
-    {
-      "message": "Invalid value in parameter `retrieveVectors`: could not parse `` as a boolean, expected either `true` or `false`",
-      "code": "invalid_similar_retrieve_vectors",
-      "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#invalid_similar_retrieve_vectors"
-    }
-    "###);
-
-    let (response, code) = index.similar_get("?retrieveVectors=doggo").await;
-    snapshot!(code, @"400 Bad Request");
-    snapshot!(json_string!(response), @r###"
-    {
-      "message": "Invalid value in parameter `retrieveVectors`: could not parse `doggo` as a boolean, expected either `true` or `false`",
-      "code": "invalid_similar_retrieve_vectors",
-      "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#invalid_similar_retrieve_vectors"
-    }
-    "###);
-}

crates/meilisearch/tests/similar/mod.rs

@@ -1,748 +0,0 @@
-mod errors;
-
-use meili_snap::{json_string, snapshot};
-use once_cell::sync::Lazy;
-
-use crate::common::{Server, Value};
-use crate::json;
-
-static DOCUMENTS: Lazy<Value> = Lazy::new(|| {
-    json!([
-        {
-            "title": "Shazam!",
-            "release_year": 2019,
-            "id": "287947",
-            // Three semantic properties:
-            // 1. magic, anything that reminds you of magic
-            // 2. authority, anything that inspires command
-            // 3. horror, anything that inspires fear or dread
-            "_vectors": { "manual": [0.8, 0.4, -0.5]},
-        },
-        {
-            "title": "Captain Marvel",
-            "release_year": 2019,
-            "id": "299537",
-            "_vectors": { "manual": [0.6, 0.8, -0.2] },
-        },
-        {
-            "title": "Escape Room",
-            "release_year": 2019,
-            "id": "522681",
-            "_vectors": { "manual": [0.1, 0.6, 0.8] },
-        },
-        {
-            "title": "How to Train Your Dragon: The Hidden World",
-            "release_year": 2019,
-            "id": "166428",
-            "_vectors": { "manual": [0.7, 0.7, -0.4] },
-        },
-        {
-            "title": "All Quiet on the Western Front",
-            "release_year": 1930,
-            "id": "143",
-            "_vectors": { "manual": [-0.5, 0.3, 0.85] },
-        }
-    ])
-});
-
-#[actix_rt::test]
-async fn basic() {
-    let server = Server::new().await;
-    let index = server.index("test");
-    let (value, code) = server.set_features(json!({"vectorStore": true})).await;
-    snapshot!(code, @"200 OK");
-    snapshot!(value, @r###"
-    {
-      "vectorStore": true,
-      "metrics": false,
-      "logsRoute": false,
-      "editDocumentsByFunction": false,
-      "containsFilter": false
-    }
-    "###);
-
-    let (response, code) = index
-        .update_settings(json!({
-        "embedders": {
-            "manual": {
-                "source": "userProvided",
-                "dimensions": 3,
-            }
-        },
-        "filterableAttributes": ["title"]}))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response.uid()).await;
-
-    let documents = DOCUMENTS.clone();
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    index.wait_task(value.uid()).await;
-
-    index
-        .similar(
-            json!({"id": 143, "retrieveVectors": true, "embedder": "manual"}),
-            |response, code| {
-                snapshot!(code, @"200 OK");
-                snapshot!(json_string!(response["hits"]), @r###"
-            [
-              {
-                "title": "Escape Room",
-                "release_year": 2019,
-                "id": "522681",
-                "_vectors": {
-                  "manual": {
-                    "embeddings": [
-                      [
-                        0.10000000149011612,
-                        0.6000000238418579,
-                        0.800000011920929
-                      ]
-                    ],
-                    "regenerate": false
-                  }
-                }
-              },
-              {
-                "title": "Captain Marvel",
-                "release_year": 2019,
-                "id": "299537",
-                "_vectors": {
-                  "manual": {
-                    "embeddings": [
-                      [
-                        0.6000000238418579,
-                        0.800000011920929,
-                        -0.20000000298023224
-                      ]
-                    ],
-                    "regenerate": false
-                  }
-                }
-              },
-              {
-                "title": "How to Train Your Dragon: The Hidden World",
-                "release_year": 2019,
-                "id": "166428",
-                "_vectors": {
-                  "manual": {
-                    "embeddings": [
-                      [
-                        0.699999988079071,
-                        0.699999988079071,
-                        -0.4000000059604645
-                      ]
-                    ],
-                    "regenerate": false
-                  }
-                }
-              },
-              {
-                "title": "Shazam!",
-                "release_year": 2019,
-                "id": "287947",
-                "_vectors": {
-                  "manual": {
-                    "embeddings": [
-                      [
-                        0.800000011920929,
-                        0.4000000059604645,
-                        -0.5
-                      ]
-                    ],
-                    "regenerate": false
-                  }
-                }
-              }
-            ]
-            "###);
-            },
-        )
-        .await;
-
-    index
-        .similar(
-            json!({"id": "299537", "retrieveVectors": true, "embedder": "manual"}),
-            |response, code| {
-                snapshot!(code, @"200 OK");
-                snapshot!(json_string!(response["hits"]), @r###"
-            [
-              {
-                "title": "How to Train Your Dragon: The Hidden World",
-                "release_year": 2019,
-                "id": "166428",
-                "_vectors": {
-                  "manual": {
-                    "embeddings": [
-                      [
-                        0.699999988079071,
-                        0.699999988079071,
-                        -0.4000000059604645
-                      ]
-                    ],
-                    "regenerate": false
-                  }
-                }
-              },
-              {
-                "title": "Shazam!",
-                "release_year": 2019,
-                "id": "287947",
-                "_vectors": {
-                  "manual": {
-                    "embeddings": [
-                      [
-                        0.800000011920929,
-                        0.4000000059604645,
-                        -0.5
-                      ]
-                    ],
-                    "regenerate": false
-                  }
-                }
-              },
-              {
-                "title": "Escape Room",
-                "release_year": 2019,
-                "id": "522681",
-                "_vectors": {
-                  "manual": {
-                    "embeddings": [
-                      [
-                        0.10000000149011612,
-                        0.6000000238418579,
-                        0.800000011920929
-                      ]
-                    ],
-                    "regenerate": false
-                  }
-                }
-              },
-              {
-                "title": "All Quiet on the Western Front",
-                "release_year": 1930,
-                "id": "143",
-                "_vectors": {
-                  "manual": {
-                    "embeddings": [
-                      [
-                        -0.5,
-                        0.30000001192092896,
-                        0.8500000238418579
-                      ]
-                    ],
-                    "regenerate": false
-                  }
-                }
-              }
-            ]
-            "###);
-            },
-        )
-        .await;
-}
-
-#[actix_rt::test]
-async fn ranking_score_threshold() {
-    let server = Server::new().await;
-    let index = server.index("test");
-    let (value, code) = server.set_features(json!({"vectorStore": true})).await;
-    snapshot!(code, @"200 OK");
-    snapshot!(value, @r###"
-    {
-      "vectorStore": true,
-      "metrics": false,
-      "logsRoute": false,
-      "editDocumentsByFunction": false,
-      "containsFilter": false
-    }
-    "###);
-
-    let (response, code) = index
-        .update_settings(json!({
-        "embedders": {
-            "manual": {
-                "source": "userProvided",
-                "dimensions": 3,
-            }
-        },
-        "filterableAttributes": ["title"]}))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response.uid()).await;
-
-    let documents = DOCUMENTS.clone();
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    index.wait_task(value.uid()).await;
-
-    index
-        .similar(
-            json!({"id": 143, "showRankingScore": true, "rankingScoreThreshold": 0, "retrieveVectors": true, "embedder": "manual"}),
-            |response, code| {
-                snapshot!(code, @"200 OK");
-                meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @"4");
-                snapshot!(json_string!(response["hits"]), @r###"
-                [
-                  {
-                    "title": "Escape Room",
-                    "release_year": 2019,
-                    "id": "522681",
-                    "_vectors": {
-                      "manual": {
-                        "embeddings": [
-                          [
-                            0.10000000149011612,
-                            0.6000000238418579,
-                            0.800000011920929
-                          ]
-                        ],
-                        "regenerate": false
-                      }
-                    },
-                    "_rankingScore": 0.890957772731781
-                  },
-                  {
-                    "title": "Captain Marvel",
-                    "release_year": 2019,
-                    "id": "299537",
-                    "_vectors": {
-                      "manual": {
-                        "embeddings": [
-                          [
-                            0.6000000238418579,
-                            0.800000011920929,
-                            -0.20000000298023224
-                          ]
-                        ],
-                        "regenerate": false
-                      }
-                    },
-                    "_rankingScore": 0.39060014486312866
-                  },
-                  {
-                    "title": "How to Train Your Dragon: The Hidden World",
-                    "release_year": 2019,
-                    "id": "166428",
-                    "_vectors": {
-                      "manual": {
-                        "embeddings": [
-                          [
-                            0.699999988079071,
-                            0.699999988079071,
-                            -0.4000000059604645
-                          ]
-                        ],
-                        "regenerate": false
-                      }
-                    },
-                    "_rankingScore": 0.2819308042526245
-                  },
-                  {
-                    "title": "Shazam!",
-                    "release_year": 2019,
-                    "id": "287947",
-                    "_vectors": {
-                      "manual": {
-                        "embeddings": [
-                          [
-                            0.800000011920929,
-                            0.4000000059604645,
-                            -0.5
-                          ]
-                        ],
-                        "regenerate": false
-                      }
-                    },
-                    "_rankingScore": 0.1662663221359253
-                  }
-                ]
-                "###);
-            },
-        )
-        .await;
-
-    index
-        .similar(
-            json!({"id": 143, "showRankingScore": true, "rankingScoreThreshold": 0.2, "retrieveVectors": true, "embedder": "manual"}),
-            |response, code| {
-                snapshot!(code, @"200 OK");
-                meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @"3");
-                snapshot!(json_string!(response["hits"]), @r###"
-                [
-                  {
-                    "title": "Escape Room",
-                    "release_year": 2019,
-                    "id": "522681",
-                    "_vectors": {
-                      "manual": {
-                        "embeddings": [
-                          [
-                            0.10000000149011612,
-                            0.6000000238418579,
-                            0.800000011920929
-                          ]
-                        ],
-                        "regenerate": false
-                      }
-                    },
-                    "_rankingScore": 0.890957772731781
-                  },
-                  {
-                    "title": "Captain Marvel",
-                    "release_year": 2019,
-                    "id": "299537",
-                    "_vectors": {
-                      "manual": {
-                        "embeddings": [
-                          [
-                            0.6000000238418579,
-                            0.800000011920929,
-                            -0.20000000298023224
-                          ]
-                        ],
-                        "regenerate": false
-                      }
-                    },
-                    "_rankingScore": 0.39060014486312866
-                  },
-                  {
-                    "title": "How to Train Your Dragon: The Hidden World",
-                    "release_year": 2019,
-                    "id": "166428",
-                    "_vectors": {
-                      "manual": {
-                        "embeddings": [
-                          [
-                            0.699999988079071,
-                            0.699999988079071,
-                            -0.4000000059604645
-                          ]
-                        ],
-                        "regenerate": false
-                      }
-                    },
-                    "_rankingScore": 0.2819308042526245
-                  }
-                ]
-                "###);
-            },
-        )
-        .await;
-
-    index
-        .similar(
-            json!({"id": 143, "showRankingScore": true, "rankingScoreThreshold": 0.3, "retrieveVectors": true, "embedder": "manual"}),
-            |response, code| {
-                snapshot!(code, @"200 OK");
-                meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @"2");
-                snapshot!(json_string!(response["hits"]), @r###"
-                [
-                  {
-                    "title": "Escape Room",
-                    "release_year": 2019,
-                    "id": "522681",
-                    "_vectors": {
-                      "manual": {
-                        "embeddings": [
-                          [
-                            0.10000000149011612,
-                            0.6000000238418579,
-                            0.800000011920929
-                          ]
-                        ],
-                        "regenerate": false
-                      }
-                    },
-                    "_rankingScore": 0.890957772731781
-                  },
-                  {
-                    "title": "Captain Marvel",
-                    "release_year": 2019,
-                    "id": "299537",
-                    "_vectors": {
-                      "manual": {
-                        "embeddings": [
-                          [
-                            0.6000000238418579,
-                            0.800000011920929,
-                            -0.20000000298023224
-                          ]
-                        ],
-                        "regenerate": false
-                      }
-                    },
-                    "_rankingScore": 0.39060014486312866
-                  }
-                ]
-                "###);
-            },
-        )
-        .await;
-
-    index
-        .similar(
-            json!({"id": 143, "showRankingScore": true, "rankingScoreThreshold": 0.6, "retrieveVectors": true, "embedder": "manual"}),
-            |response, code| {
-                snapshot!(code, @"200 OK");
-                meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @"1");
-                snapshot!(json_string!(response["hits"]), @r###"
-                [
-                  {
-                    "title": "Escape Room",
-                    "release_year": 2019,
-                    "id": "522681",
-                    "_vectors": {
-                      "manual": {
-                        "embeddings": [
-                          [
-                            0.10000000149011612,
-                            0.6000000238418579,
-                            0.800000011920929
-                          ]
-                        ],
-                        "regenerate": false
-                      }
-                    },
-                    "_rankingScore": 0.890957772731781
-                  }
-                ]
-                "###);
-            },
-        )
-        .await;
-
-    index
-        .similar(
-            json!({"id": 143, "showRankingScore": true, "rankingScoreThreshold": 0.9, "retrieveVectors": true, "embedder": "manual"}),
-            |response, code| {
-                snapshot!(code, @"200 OK");
-                snapshot!(json_string!(response["hits"]), @"[]");
-            },
-        )
-        .await;
-}
-
-#[actix_rt::test]
-async fn filter() {
-    let server = Server::new().await;
-    let index = server.index("test");
-    let (value, code) = server.set_features(json!({"vectorStore": true})).await;
-    snapshot!(code, @"200 OK");
-    snapshot!(value, @r###"
-    {
-      "vectorStore": true,
-      "metrics": false,
-      "logsRoute": false,
-      "editDocumentsByFunction": false,
-      "containsFilter": false
-    }
-    "###);
-
-    let (response, code) = index
-        .update_settings(json!({
-        "embedders": {
-            "manual": {
-                "source": "userProvided",
-                "dimensions": 3,
-            }
-        },
-        "filterableAttributes": ["title", "release_year"]}))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response.uid()).await;
-
-    let documents = DOCUMENTS.clone();
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    index.wait_task(value.uid()).await;
-
-    index
-        .similar(
-            json!({"id": 522681, "filter": "release_year = 2019", "retrieveVectors": true, "embedder": "manual"}),
-            |response, code| {
-                snapshot!(code, @"200 OK");
-                snapshot!(json_string!(response["hits"]), @r###"
-                [
-                  {
-                    "title": "Captain Marvel",
-                    "release_year": 2019,
-                    "id": "299537",
-                    "_vectors": {
-                      "manual": {
-                        "embeddings": [
-                          [
-                            0.6000000238418579,
-                            0.800000011920929,
-                            -0.20000000298023224
-                          ]
-                        ],
-                        "regenerate": false
-                      }
-                    }
-                  },
-                  {
-                    "title": "How to Train Your Dragon: The Hidden World",
-                    "release_year": 2019,
-                    "id": "166428",
-                    "_vectors": {
-                      "manual": {
-                        "embeddings": [
-                          [
-                            0.699999988079071,
-                            0.699999988079071,
-                            -0.4000000059604645
-                          ]
-                        ],
-                        "regenerate": false
-                      }
-                    }
-                  },
-                  {
-                    "title": "Shazam!",
-                    "release_year": 2019,
-                    "id": "287947",
-                    "_vectors": {
-                      "manual": {
-                        "embeddings": [
-                          [
-                            0.800000011920929,
-                            0.4000000059604645,
-                            -0.5
-                          ]
-                        ],
-                        "regenerate": false
-                      }
-                    }
-                  }
-                ]
-                "###);
-            },
-        )
-        .await;
-
-    index
-        .similar(
-            json!({"id": 522681, "filter": "release_year < 2000", "retrieveVectors": true, "embedder": "manual"}),
-            |response, code| {
-                snapshot!(code, @"200 OK");
-                snapshot!(json_string!(response["hits"]), @r###"
-                [
-                  {
-                    "title": "All Quiet on the Western Front",
-                    "release_year": 1930,
-                    "id": "143",
-                    "_vectors": {
-                      "manual": {
-                        "embeddings": [
-                          [
-                            -0.5,
-                            0.30000001192092896,
-                            0.8500000238418579
-                          ]
-                        ],
-                        "regenerate": false
-                      }
-                    }
-                  }
-                ]
-                "###);
-            },
-        )
-        .await;
-}
-
-#[actix_rt::test]
-async fn limit_and_offset() {
-    let server = Server::new().await;
-    let index = server.index("test");
-    let (value, code) = server.set_features(json!({"vectorStore": true})).await;
-    snapshot!(code, @"200 OK");
-    snapshot!(value, @r###"
-    {
-      "vectorStore": true,
-      "metrics": false,
-      "logsRoute": false,
-      "editDocumentsByFunction": false,
-      "containsFilter": false
-    }
-    "###);
-
-    let (response, code) = index
-        .update_settings(json!({
-        "embedders": {
-            "manual": {
-                "source": "userProvided",
-                "dimensions": 3,
-            }
-        },
-        "filterableAttributes": ["title"]}))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response.uid()).await;
-
-    let documents = DOCUMENTS.clone();
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    index.wait_task(value.uid()).await;
-
-    index
-        .similar(
-            json!({"id": 143, "limit": 1, "retrieveVectors": true, "embedder": "manual"}),
-            |response, code| {
-                snapshot!(code, @"200 OK");
-                snapshot!(json_string!(response["hits"]), @r###"
-            [
-              {
-                "title": "Escape Room",
-                "release_year": 2019,
-                "id": "522681",
-                "_vectors": {
-                  "manual": {
-                    "embeddings": [
-                      [
-                        0.10000000149011612,
-                        0.6000000238418579,
-                        0.800000011920929
-                      ]
-                    ],
-                    "regenerate": false
-                  }
-                }
-              }
-            ]
-            "###);
-            },
-        )
-        .await;
-
-    index
-        .similar(
-            json!({"id": 143, "limit": 1, "offset": 1, "retrieveVectors": true, "embedder": "manual"}),
-            |response, code| {
-                snapshot!(code, @"200 OK");
-                snapshot!(json_string!(response["hits"]), @r###"
-                [
-                  {
-                    "title": "Captain Marvel",
-                    "release_year": 2019,
-                    "id": "299537",
-                    "_vectors": {
-                      "manual": {
-                        "embeddings": [
-                          [
-                            0.6000000238418579,
-                            0.800000011920929,
-                            -0.20000000298023224
-                          ]
-                        ],
-                        "regenerate": false
-                      }
-                    }
-                  }
-                ]
-                "###);
-            },
-        )
-        .await;
-}

crates/meilisearch/tests/vector/binary_quantized.rs

@@ -1,380 +0,0 @@
-use meili_snap::{json_string, snapshot};
-
-use crate::common::{GetAllDocumentsOptions, Server};
-use crate::json;
-use crate::vector::generate_default_user_provided_documents;
-
-#[actix_rt::test]
-async fn retrieve_binary_quantize_status_in_the_settings() {
-    let server = Server::new().await;
-    let index = server.index("doggo");
-    let (value, code) = server.set_features(json!({"vectorStore": true})).await;
-    snapshot!(code, @"200 OK");
-    snapshot!(value, @r###"
-    {
-      "vectorStore": true,
-      "metrics": false,
-      "logsRoute": false,
-      "editDocumentsByFunction": false,
-      "containsFilter": false
-    }
-    "###);
-
-    let (response, code) = index
-        .update_settings(json!({
-          "embedders": {
-              "manual": {
-                  "source": "userProvided",
-                  "dimensions": 3,
-              }
-          },
-        }))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response.uid()).await.succeeded();
-
-    let (settings, code) = index.settings().await;
-    snapshot!(code, @"200 OK");
-    snapshot!(settings["embedders"]["manual"], @r###"{"source":"userProvided","dimensions":3}"###);
-
-    let (response, code) = index
-        .update_settings(json!({
-          "embedders": {
-              "manual": {
-                  "source": "userProvided",
-                  "dimensions": 3,
-                  "binaryQuantized": false,
-              }
-          },
-        }))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response.uid()).await.succeeded();
-
-    let (settings, code) = index.settings().await;
-    snapshot!(code, @"200 OK");
-    snapshot!(settings["embedders"]["manual"], @r###"{"source":"userProvided","dimensions":3,"binaryQuantized":false}"###);
-
-    let (response, code) = index
-        .update_settings(json!({
-          "embedders": {
-              "manual": {
-                  "source": "userProvided",
-                  "dimensions": 3,
-                  "binaryQuantized": true,
-              }
-          },
-        }))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response.uid()).await.succeeded();
-
-    let (settings, code) = index.settings().await;
-    snapshot!(code, @"200 OK");
-    snapshot!(settings["embedders"]["manual"], @r###"{"source":"userProvided","dimensions":3,"binaryQuantized":true}"###);
-}
-
-#[actix_rt::test]
-async fn binary_quantize_before_sending_documents() {
-    let server = Server::new().await;
-    let index = server.index("doggo");
-    let (value, code) = server.set_features(json!({"vectorStore": true})).await;
-    snapshot!(code, @"200 OK");
-    snapshot!(value, @r###"
-    {
-      "vectorStore": true,
-      "metrics": false,
-      "logsRoute": false,
-      "editDocumentsByFunction": false,
-      "containsFilter": false
-    }
-    "###);
-
-    let (response, code) = index
-        .update_settings(json!({
-          "embedders": {
-              "manual": {
-                  "source": "userProvided",
-                  "dimensions": 3,
-                  "binaryQuantized": true,
-              }
-          },
-        }))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response.uid()).await.succeeded();
-
-    let documents = json!([
-      {"id": 0, "name": "kefir", "_vectors": { "manual": [-1.2, -2.3, 3.2] }},
-      {"id": 1, "name": "echo", "_vectors": { "manual": [2.5, 1.5, -130] }},
-    ]);
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    index.wait_task(value.uid()).await.succeeded();
-
-    // Make sure the documents are binary quantized
-    let (documents, _code) = index
-        .get_all_documents(GetAllDocumentsOptions { retrieve_vectors: true, ..Default::default() })
-        .await;
-    snapshot!(json_string!(documents), @r###"
-    {
-      "results": [
-        {
-          "id": 0,
-          "name": "kefir",
-          "_vectors": {
-            "manual": {
-              "embeddings": [
-                [
-                  -1.0,
-                  -1.0,
-                  1.0
-                ]
-              ],
-              "regenerate": false
-            }
-          }
-        },
-        {
-          "id": 1,
-          "name": "echo",
-          "_vectors": {
-            "manual": {
-              "embeddings": [
-                [
-                  1.0,
-                  1.0,
-                  -1.0
-                ]
-              ],
-              "regenerate": false
-            }
-          }
-        }
-      ],
-      "offset": 0,
-      "limit": 20,
-      "total": 2
-    }
-    "###);
-}
-
-#[actix_rt::test]
-async fn binary_quantize_after_sending_documents() {
-    let server = Server::new().await;
-    let index = server.index("doggo");
-    let (value, code) = server.set_features(json!({"vectorStore": true})).await;
-    snapshot!(code, @"200 OK");
-    snapshot!(value, @r###"
-    {
-      "vectorStore": true,
-      "metrics": false,
-      "logsRoute": false,
-      "editDocumentsByFunction": false,
-      "containsFilter": false
-    }
-    "###);
-
-    let (response, code) = index
-        .update_settings(json!({
-          "embedders": {
-              "manual": {
-                  "source": "userProvided",
-                  "dimensions": 3,
-              }
-          },
-        }))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response.uid()).await.succeeded();
-
-    let documents = json!([
-      {"id": 0, "name": "kefir", "_vectors": { "manual": [-1.2, -2.3, 3.2] }},
-      {"id": 1, "name": "echo", "_vectors": { "manual": [2.5, 1.5, -130] }},
-    ]);
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    index.wait_task(value.uid()).await.succeeded();
-
-    let (response, code) = index
-        .update_settings(json!({
-          "embedders": {
-              "manual": {
-                  "source": "userProvided",
-                  "dimensions": 3,
-                  "binaryQuantized": true,
-              }
-          },
-        }))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response.uid()).await.succeeded();
-
-    // Make sure the documents are binary quantized
-    let (documents, _code) = index
-        .get_all_documents(GetAllDocumentsOptions { retrieve_vectors: true, ..Default::default() })
-        .await;
-    snapshot!(json_string!(documents), @r###"
-    {
-      "results": [
-        {
-          "id": 0,
-          "name": "kefir",
-          "_vectors": {
-            "manual": {
-              "embeddings": [
-                [
-                  -1.0,
-                  -1.0,
-                  1.0
-                ]
-              ],
-              "regenerate": false
-            }
-          }
-        },
-        {
-          "id": 1,
-          "name": "echo",
-          "_vectors": {
-            "manual": {
-              "embeddings": [
-                [
-                  1.0,
-                  1.0,
-                  -1.0
-                ]
-              ],
-              "regenerate": false
-            }
-          }
-        }
-      ],
-      "offset": 0,
-      "limit": 20,
-      "total": 2
-    }
-    "###);
-}
-
-#[actix_rt::test]
-async fn try_to_disable_binary_quantization() {
-    let server = Server::new().await;
-    let index = server.index("doggo");
-    let (value, code) = server.set_features(json!({"vectorStore": true})).await;
-    snapshot!(code, @"200 OK");
-    snapshot!(value, @r###"
-    {
-      "vectorStore": true,
-      "metrics": false,
-      "logsRoute": false,
-      "editDocumentsByFunction": false,
-      "containsFilter": false
-    }
-    "###);
-
-    let (response, code) = index
-        .update_settings(json!({
-          "embedders": {
-              "manual": {
-                  "source": "userProvided",
-                  "dimensions": 3,
-                  "binaryQuantized": true,
-              }
-          },
-        }))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response.uid()).await.succeeded();
-
-    let (response, code) = index
-        .update_settings(json!({
-          "embedders": {
-              "manual": {
-                  "source": "userProvided",
-                  "dimensions": 3,
-                  "binaryQuantized": false,
-              }
-          },
-        }))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    let ret = server.wait_task(response.uid()).await;
-    snapshot!(ret, @r###"
-    {
-      "uid": "[uid]",
-      "indexUid": "doggo",
-      "status": "failed",
-      "type": "settingsUpdate",
-      "canceledBy": null,
-      "details": {
-        "embedders": {
-          "manual": {
-            "source": "userProvided",
-            "dimensions": 3,
-            "binaryQuantized": false
-          }
-        }
-      },
-      "error": {
-        "message": "`.embedders.manual.binaryQuantized`: Cannot disable the binary quantization.\n - Note: Binary quantization is a lossy operation that cannot be reverted.\n - Hint: Add a new embedder that is non-quantized and regenerate the vectors.",
-        "code": "invalid_settings_embedders",
-        "type": "invalid_request",
-        "link": "https://docs.meilisearch.com/errors#invalid_settings_embedders"
-      },
-      "duration": "[duration]",
-      "enqueuedAt": "[date]",
-      "startedAt": "[date]",
-      "finishedAt": "[date]"
-    }
-    "###);
-}
-
-#[actix_rt::test]
-async fn binary_quantize_clear_documents() {
-    let server = Server::new().await;
-    let index = generate_default_user_provided_documents(&server).await;
-
-    let (response, code) = index
-        .update_settings(json!({
-          "embedders": {
-              "manual": {
-                  "binaryQuantized": true,
-              }
-          },
-        }))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response.uid()).await.succeeded();
-
-    let (value, _code) = index.clear_all_documents().await;
-    index.wait_task(value.uid()).await.succeeded();
-
-    // Make sure the documents DB has been cleared
-    let (documents, _code) = index
-        .get_all_documents(GetAllDocumentsOptions { retrieve_vectors: true, ..Default::default() })
-        .await;
-    snapshot!(json_string!(documents), @r###"
-    {
-      "results": [],
-      "offset": 0,
-      "limit": 20,
-      "total": 0
-    }
-    "###);
-
-    // Make sure the arroy DB has been cleared
-    let (documents, _code) =
-        index.search_post(json!({ "hybrid": { "embedder": "manual" }, "vector": [1, 1, 1] })).await;
-    snapshot!(documents, @r###"
-    {
-      "hits": [],
-      "query": "",
-      "processingTimeMs": "[duration]",
-      "limit": 20,
-      "offset": 0,
-      "estimatedTotalHits": 0,
-      "semanticHitCount": 0
-    }
-    "###);
-}

crates/meilisearch/tests/vector/mod.rs

@@ -1,734 +0,0 @@
-mod binary_quantized;
-mod openai;
-mod rest;
-mod settings;
-
-use std::str::FromStr;
-
-use meili_snap::{json_string, snapshot};
-use meilisearch::option::MaxThreads;
-
-use crate::common::index::Index;
-use crate::common::{default_settings, GetAllDocumentsOptions, Server};
-use crate::json;
-
-async fn get_server_vector() -> Server {
-    let server = Server::new().await;
-    let (value, code) = server.set_features(json!({"vectorStore": true})).await;
-    snapshot!(code, @"200 OK");
-    snapshot!(value, @r###"
-  {
-    "vectorStore": true,
-    "metrics": false,
-    "logsRoute": false,
-    "editDocumentsByFunction": false,
-    "containsFilter": false
-  }
-  "###);
-    server
-}
-
-#[actix_rt::test]
-async fn add_remove_user_provided() {
-    let server = Server::new().await;
-    let index = server.index("doggo");
-    let (value, code) = server.set_features(json!({"vectorStore": true})).await;
-    snapshot!(code, @"200 OK");
-    snapshot!(value, @r###"
-    {
-      "vectorStore": true,
-      "metrics": false,
-      "logsRoute": false,
-      "editDocumentsByFunction": false,
-      "containsFilter": false
-    }
-    "###);
-
-    let (response, code) = index
-        .update_settings(json!({
-          "embedders": {
-              "manual": {
-                  "source": "userProvided",
-                  "dimensions": 3,
-              }
-          },
-        }))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response.uid()).await;
-
-    let documents = json!([
-      {"id": 0, "name": "kefir", "_vectors": { "manual": [0, 0, 0] }},
-      {"id": 1, "name": "echo", "_vectors": { "manual": [1, 1, 1] }},
-    ]);
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    index.wait_task(value.uid()).await;
-
-    let (documents, _code) = index
-        .get_all_documents(GetAllDocumentsOptions { retrieve_vectors: true, ..Default::default() })
-        .await;
-    snapshot!(json_string!(documents), @r###"
-    {
-      "results": [
-        {
-          "id": 0,
-          "name": "kefir",
-          "_vectors": {
-            "manual": {
-              "embeddings": [
-                [
-                  0.0,
-                  0.0,
-                  0.0
-                ]
-              ],
-              "regenerate": false
-            }
-          }
-        },
-        {
-          "id": 1,
-          "name": "echo",
-          "_vectors": {
-            "manual": {
-              "embeddings": [
-                [
-                  1.0,
-                  1.0,
-                  1.0
-                ]
-              ],
-              "regenerate": false
-            }
-          }
-        }
-      ],
-      "offset": 0,
-      "limit": 20,
-      "total": 2
-    }
-    "###);
-
-    let documents = json!([
-      {"id": 0, "name": "kefir", "_vectors": { "manual": [10, 10, 10] }},
-      {"id": 1, "name": "echo", "_vectors": { "manual": null }},
-    ]);
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    index.wait_task(value.uid()).await;
-
-    let (documents, _code) = index
-        .get_all_documents(GetAllDocumentsOptions { retrieve_vectors: true, ..Default::default() })
-        .await;
-    snapshot!(json_string!(documents), @r###"
-    {
-      "results": [
-        {
-          "id": 0,
-          "name": "kefir",
-          "_vectors": {
-            "manual": {
-              "embeddings": [
-                [
-                  10.0,
-                  10.0,
-                  10.0
-                ]
-              ],
-              "regenerate": false
-            }
-          }
-        },
-        {
-          "id": 1,
-          "name": "echo",
-          "_vectors": {
-            "manual": {
-              "embeddings": [],
-              "regenerate": false
-            }
-          }
-        }
-      ],
-      "offset": 0,
-      "limit": 20,
-      "total": 2
-    }
-    "###);
-
-    let (value, code) = index.delete_document(0).await;
-    snapshot!(code, @"202 Accepted");
-    index.wait_task(value.uid()).await;
-
-    let (documents, _code) = index
-        .get_all_documents(GetAllDocumentsOptions { retrieve_vectors: true, ..Default::default() })
-        .await;
-    snapshot!(json_string!(documents), @r###"
-    {
-      "results": [
-        {
-          "id": 1,
-          "name": "echo",
-          "_vectors": {
-            "manual": {
-              "embeddings": [],
-              "regenerate": false
-            }
-          }
-        }
-      ],
-      "offset": 0,
-      "limit": 20,
-      "total": 1
-    }
-    "###);
-}
-
-async fn generate_default_user_provided_documents(server: &Server) -> Index {
-    let index = server.index("doggo");
-    let (value, code) = server.set_features(json!({"vectorStore": true})).await;
-    snapshot!(code, @"200 OK");
-    snapshot!(value, @r###"
-    {
-      "vectorStore": true,
-      "metrics": false,
-      "logsRoute": false,
-      "editDocumentsByFunction": false,
-      "containsFilter": false
-    }
-    "###);
-
-    let (response, code) = index
-        .update_settings(json!({
-          "embedders": {
-              "manual": {
-                  "source": "userProvided",
-                  "dimensions": 3,
-              }
-          },
-        }))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    server.wait_task(response.uid()).await;
-
-    let documents = json!([
-      {"id": 0, "name": "kefir", "_vectors": { "manual": [0, 0, 0] }},
-      {"id": 1, "name": "echo", "_vectors": { "manual": [1, 1, 1] }},
-      {"id": 2, "name": "billou", "_vectors": { "manual": [[2, 2, 2], [2, 2, 3]] }},
-      {"id": 3, "name": "intel", "_vectors": { "manual": { "regenerate": false, "embeddings": [3, 3, 3] }}},
-      {"id": 4, "name": "max", "_vectors": { "manual": { "regenerate": false, "embeddings": [[4, 4, 4], [4, 4, 5]] }}},
-    ]);
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    index.wait_task(value.uid()).await;
-
-    index
-}
-
-#[actix_rt::test]
-async fn user_provided_embeddings_error() {
-    let server = Server::new().await;
-    let index = generate_default_user_provided_documents(&server).await;
-
-    // First case, we forget to specify the `regenerate`
-    let documents =
-        json!({"id": 0, "name": "kefir", "_vectors": { "manual": { "embeddings": [0, 0, 0] }}});
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    let task = index.wait_task(value.uid()).await;
-    snapshot!(task, @r###"
-    {
-      "uid": "[uid]",
-      "indexUid": "doggo",
-      "status": "failed",
-      "type": "documentAdditionOrUpdate",
-      "canceledBy": null,
-      "details": {
-        "receivedDocuments": 1,
-        "indexedDocuments": 0
-      },
-      "error": {
-        "message": "Bad embedder configuration in the document with id: `\"0\"`. Missing field `regenerate` inside `.manual`",
-        "code": "invalid_vectors_type",
-        "type": "invalid_request",
-        "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
-      },
-      "duration": "[duration]",
-      "enqueuedAt": "[date]",
-      "startedAt": "[date]",
-      "finishedAt": "[date]"
-    }
-    "###);
-
-    // Second case, we don't specify anything
-    let documents = json!({"id": 0, "name": "kefir", "_vectors": { "manual": {}}});
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    let task = index.wait_task(value.uid()).await;
-    snapshot!(task, @r###"
-    {
-      "uid": "[uid]",
-      "indexUid": "doggo",
-      "status": "failed",
-      "type": "documentAdditionOrUpdate",
-      "canceledBy": null,
-      "details": {
-        "receivedDocuments": 1,
-        "indexedDocuments": 0
-      },
-      "error": {
-        "message": "Bad embedder configuration in the document with id: `\"0\"`. Missing field `regenerate` inside `.manual`",
-        "code": "invalid_vectors_type",
-        "type": "invalid_request",
-        "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
-      },
-      "duration": "[duration]",
-      "enqueuedAt": "[date]",
-      "startedAt": "[date]",
-      "finishedAt": "[date]"
-    }
-    "###);
-
-    // Third case, we specify something wrong in place of regenerate
-    let documents =
-        json!({"id": 0, "name": "kefir", "_vectors": { "manual": { "regenerate": "yes please" }}});
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    let task = index.wait_task(value.uid()).await;
-    snapshot!(task, @r###"
-    {
-      "uid": "[uid]",
-      "indexUid": "doggo",
-      "status": "failed",
-      "type": "documentAdditionOrUpdate",
-      "canceledBy": null,
-      "details": {
-        "receivedDocuments": 1,
-        "indexedDocuments": 0
-      },
-      "error": {
-        "message": "Bad embedder configuration in the document with id: `\"0\"`. Invalid value type at `.manual.regenerate`: expected a boolean, but found a string: `\"yes please\"`",
-        "code": "invalid_vectors_type",
-        "type": "invalid_request",
-        "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
-      },
-      "duration": "[duration]",
-      "enqueuedAt": "[date]",
-      "startedAt": "[date]",
-      "finishedAt": "[date]"
-    }
-    "###);
-
-    let documents =
-        json!({"id": 0, "name": "kefir", "_vectors": { "manual": { "embeddings": true }}});
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    let task = index.wait_task(value.uid()).await;
-    snapshot!(task, @r###"
-    {
-      "uid": "[uid]",
-      "indexUid": "doggo",
-      "status": "failed",
-      "type": "documentAdditionOrUpdate",
-      "canceledBy": null,
-      "details": {
-        "receivedDocuments": 1,
-        "indexedDocuments": 0
-      },
-      "error": {
-        "message": "Bad embedder configuration in the document with id: `\"0\"`. Invalid value type at `.manual.embeddings`: expected null or an array, but found a boolean: `true`",
-        "code": "invalid_vectors_type",
-        "type": "invalid_request",
-        "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
-      },
-      "duration": "[duration]",
-      "enqueuedAt": "[date]",
-      "startedAt": "[date]",
-      "finishedAt": "[date]"
-    }
-    "###);
-
-    let documents =
-        json!({"id": 0, "name": "kefir", "_vectors": { "manual": { "embeddings": [true] }}});
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    let task = index.wait_task(value.uid()).await;
-    snapshot!(task, @r###"
-    {
-      "uid": "[uid]",
-      "indexUid": "doggo",
-      "status": "failed",
-      "type": "documentAdditionOrUpdate",
-      "canceledBy": null,
-      "details": {
-        "receivedDocuments": 1,
-        "indexedDocuments": 0
-      },
-      "error": {
-        "message": "Bad embedder configuration in the document with id: `\"0\"`. Invalid value type at `.manual.embeddings[0]`: expected a number or an array, but found a boolean: `true`",
-        "code": "invalid_vectors_type",
-        "type": "invalid_request",
-        "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
-      },
-      "duration": "[duration]",
-      "enqueuedAt": "[date]",
-      "startedAt": "[date]",
-      "finishedAt": "[date]"
-    }
-    "###);
-
-    let documents =
-        json!({"id": 0, "name": "kefir", "_vectors": { "manual": { "embeddings": [[true]] }}});
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    let task = index.wait_task(value.uid()).await;
-    snapshot!(task, @r###"
-    {
-      "uid": "[uid]",
-      "indexUid": "doggo",
-      "status": "failed",
-      "type": "documentAdditionOrUpdate",
-      "canceledBy": null,
-      "details": {
-        "receivedDocuments": 1,
-        "indexedDocuments": 0
-      },
-      "error": {
-        "message": "Bad embedder configuration in the document with id: `\"0\"`. Invalid value type at `.manual.embeddings[0][0]`: expected a number, but found a boolean: `true`",
-        "code": "invalid_vectors_type",
-        "type": "invalid_request",
-        "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
-      },
-      "duration": "[duration]",
-      "enqueuedAt": "[date]",
-      "startedAt": "[date]",
-      "finishedAt": "[date]"
-    }
-    "###);
-
-    let documents = json!({"id": 0, "name": "kefir", "_vectors": { "manual": { "embeddings": [23, 0.1, -12], "regenerate": true }}});
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    let task = index.wait_task(value.uid()).await;
-    snapshot!(task["status"], @r###""succeeded""###);
-
-    let documents =
-        json!({"id": 0, "name": "kefir", "_vectors": { "manual": { "regenerate": false }}});
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    let task = index.wait_task(value.uid()).await;
-    snapshot!(task["status"], @r###""succeeded""###);
-
-    let documents = json!({"id": 0, "name": "kefir", "_vectors": { "manual": { "regenerate": false, "embeddings": [0.1, [0.2, 0.3]] }}});
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    let task = index.wait_task(value.uid()).await;
-    snapshot!(task, @r###"
-    {
-      "uid": "[uid]",
-      "indexUid": "doggo",
-      "status": "failed",
-      "type": "documentAdditionOrUpdate",
-      "canceledBy": null,
-      "details": {
-        "receivedDocuments": 1,
-        "indexedDocuments": 0
-      },
-      "error": {
-        "message": "Bad embedder configuration in the document with id: `\"0\"`. Invalid value type at `.manual.embeddings[1]`: expected a number, but found an array: `[0.2,0.3]`",
-        "code": "invalid_vectors_type",
-        "type": "invalid_request",
-        "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
-      },
-      "duration": "[duration]",
-      "enqueuedAt": "[date]",
-      "startedAt": "[date]",
-      "finishedAt": "[date]"
-    }
-    "###);
-
-    let documents = json!({"id": 0, "name": "kefir", "_vectors": { "manual": { "regenerate": false, "embeddings": [[0.1, 0.2], 0.3] }}});
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    let task = index.wait_task(value.uid()).await;
-    snapshot!(task, @r###"
-    {
-      "uid": "[uid]",
-      "indexUid": "doggo",
-      "status": "failed",
-      "type": "documentAdditionOrUpdate",
-      "canceledBy": null,
-      "details": {
-        "receivedDocuments": 1,
-        "indexedDocuments": 0
-      },
-      "error": {
-        "message": "Bad embedder configuration in the document with id: `\"0\"`. Invalid value type at `.manual.embeddings[1]`: expected an array, but found a number: `0.3`",
-        "code": "invalid_vectors_type",
-        "type": "invalid_request",
-        "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
-      },
-      "duration": "[duration]",
-      "enqueuedAt": "[date]",
-      "startedAt": "[date]",
-      "finishedAt": "[date]"
-    }
-    "###);
-
-    let documents = json!({"id": 0, "name": "kefir", "_vectors": { "manual": { "regenerate": false, "embeddings": [[0.1, true], 0.3] }}});
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    let task = index.wait_task(value.uid()).await;
-    snapshot!(task, @r###"
-    {
-      "uid": "[uid]",
-      "indexUid": "doggo",
-      "status": "failed",
-      "type": "documentAdditionOrUpdate",
-      "canceledBy": null,
-      "details": {
-        "receivedDocuments": 1,
-        "indexedDocuments": 0
-      },
-      "error": {
-        "message": "Bad embedder configuration in the document with id: `\"0\"`. Invalid value type at `.manual.embeddings[0][1]`: expected a number, but found a boolean: `true`",
-        "code": "invalid_vectors_type",
-        "type": "invalid_request",
-        "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
-      },
-      "duration": "[duration]",
-      "enqueuedAt": "[date]",
-      "startedAt": "[date]",
-      "finishedAt": "[date]"
-    }
-    "###);
-}
-
-#[actix_rt::test]
-async fn user_provided_vectors_error() {
-    let temp = tempfile::tempdir().unwrap();
-    let mut options = default_settings(temp.path());
-    // If we have more than one indexing thread the error messages below may become inconsistent
-    options.indexer_options.max_indexing_threads = MaxThreads::from_str("1").unwrap();
-    let server = Server::new_with_options(options).await.unwrap();
-
-    let index = generate_default_user_provided_documents(&server).await;
-
-    // First case, we forget to specify `_vectors`
-    let documents = json!([{"id": 40, "name": "kefir"}, {"id": 41, "name": "intel"}, {"id": 42, "name": "max"}, {"id": 43, "name": "venus"}, {"id": 44, "name": "eva"}]);
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    let task = index.wait_task(value.uid()).await;
-    snapshot!(task, @r###"
-    {
-      "uid": "[uid]",
-      "indexUid": "doggo",
-      "status": "failed",
-      "type": "documentAdditionOrUpdate",
-      "canceledBy": null,
-      "details": {
-        "receivedDocuments": 5,
-        "indexedDocuments": 0
-      },
-      "error": {
-        "message": "While embedding documents for embedder `manual`: no vectors provided for document \"40\" and at least 4 other document(s)\n- Note: `manual` has `source: userProvided`, so documents must provide embeddings as an array in `_vectors.manual`.\n- Hint: opt-out for a document with `_vectors.manual: null`",
-        "code": "vector_embedding_error",
-        "type": "invalid_request",
-        "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
-      },
-      "duration": "[duration]",
-      "enqueuedAt": "[date]",
-      "startedAt": "[date]",
-      "finishedAt": "[date]"
-    }
-    "###);
-
-    // Second case, we provide `_vectors` with a typo
-    let documents = json!({"id": 42, "name": "kefir", "_vector": { "manaul": [0, 0, 0] }});
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    let task = index.wait_task(value.uid()).await;
-    snapshot!(task, @r###"
-    {
-      "uid": "[uid]",
-      "indexUid": "doggo",
-      "status": "failed",
-      "type": "documentAdditionOrUpdate",
-      "canceledBy": null,
-      "details": {
-        "receivedDocuments": 1,
-        "indexedDocuments": 0
-      },
-      "error": {
-        "message": "While embedding documents for embedder `manual`: no vectors provided for document \"42\"\n- Note: `manual` has `source: userProvided`, so documents must provide embeddings as an array in `_vectors.manual`.\n- Hint: try replacing `_vector` by `_vectors` in 1 document(s).",
-        "code": "vector_embedding_error",
-        "type": "invalid_request",
-        "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
-      },
-      "duration": "[duration]",
-      "enqueuedAt": "[date]",
-      "startedAt": "[date]",
-      "finishedAt": "[date]"
-    }
-    "###);
-
-    // Third case, we specify the embedder with a typo
-    let documents = json!({"id": 42, "name": "kefir", "_vectors": { "manaul": [0, 0, 0] }});
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    let task = index.wait_task(value.uid()).await;
-    snapshot!(task, @r###"
-    {
-      "uid": "[uid]",
-      "indexUid": "doggo",
-      "status": "failed",
-      "type": "documentAdditionOrUpdate",
-      "canceledBy": null,
-      "details": {
-        "receivedDocuments": 1,
-        "indexedDocuments": 0
-      },
-      "error": {
-        "message": "While embedding documents for embedder `manual`: no vectors provided for document \"42\"\n- Note: `manual` has `source: userProvided`, so documents must provide embeddings as an array in `_vectors.manual`.\n- Hint: try replacing `_vectors.manaul` by `_vectors.manual` in 1 document(s).",
-        "code": "vector_embedding_error",
-        "type": "invalid_request",
-        "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
-      },
-      "duration": "[duration]",
-      "enqueuedAt": "[date]",
-      "startedAt": "[date]",
-      "finishedAt": "[date]"
-    }
-    "###);
-}
-
-#[actix_rt::test]
-async fn clear_documents() {
-    let server = Server::new().await;
-    let index = generate_default_user_provided_documents(&server).await;
-
-    let (value, _code) = index.clear_all_documents().await;
-    index.wait_task(value.uid()).await;
-
-    // Make sure the documents DB has been cleared
-    let (documents, _code) = index
-        .get_all_documents(GetAllDocumentsOptions { retrieve_vectors: true, ..Default::default() })
-        .await;
-    snapshot!(json_string!(documents), @r###"
-    {
-      "results": [],
-      "offset": 0,
-      "limit": 20,
-      "total": 0
-    }
-    "###);
-
-    // Make sure the arroy DB has been cleared
-    let (documents, _code) =
-        index.search_post(json!({ "vector": [1, 1, 1], "hybrid": {"embedder": "manual"} })).await;
-    snapshot!(documents, @r###"
-    {
-      "hits": [],
-      "query": "",
-      "processingTimeMs": "[duration]",
-      "limit": 20,
-      "offset": 0,
-      "estimatedTotalHits": 0,
-      "semanticHitCount": 0
-    }
-    "###);
-}
-
-#[actix_rt::test]
-async fn add_remove_one_vector_4588() {
-    // https://github.com/meilisearch/meilisearch/issues/4588
-    let server = Server::new().await;
-    let index = server.index("doggo");
-    let (value, code) = server.set_features(json!({"vectorStore": true})).await;
-    snapshot!(code, @"200 OK");
-    snapshot!(value, @r###"
-    {
-      "vectorStore": true,
-      "metrics": false,
-      "logsRoute": false,
-      "editDocumentsByFunction": false,
-      "containsFilter": false
-    }
-    "###);
-
-    let (response, code) = index
-        .update_settings(json!({
-          "embedders": {
-              "manual": {
-                  "source": "userProvided",
-                  "dimensions": 3,
-              }
-          },
-        }))
-        .await;
-    snapshot!(code, @"202 Accepted");
-    let task = server.wait_task(response.uid()).await;
-    snapshot!(task, name: "settings-processed");
-
-    let documents = json!([
-      {"id": 0, "name": "kefir", "_vectors": { "manual": [0, 0, 0] }},
-    ]);
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    let task = index.wait_task(value.uid()).await;
-    snapshot!(task, name: "document-added");
-
-    let documents = json!([
-      {"id": 0, "name": "kefir", "_vectors": { "manual": null }},
-    ]);
-    let (value, code) = index.add_documents(documents, None).await;
-    snapshot!(code, @"202 Accepted");
-    let task = index.wait_task(value.uid()).await;
-    snapshot!(task, name: "document-deleted");
-
-    let (documents, _code) = index
-        .search_post(
-            json!({"vector": [1, 1, 1], "hybrid": {"semanticRatio": 1.0, "embedder": "manual"} }),
-        )
-        .await;
-    snapshot!(documents, @r###"
-    {
-      "hits": [
-        {
-          "id": 0,
-          "name": "kefir"
-        }
-      ],
-      "query": "",
-      "processingTimeMs": "[duration]",
-      "limit": 20,
-      "offset": 0,
-      "estimatedTotalHits": 1,
-      "semanticHitCount": 1
-    }
-    "###);
-
-    let (documents, _code) = index
-        .get_all_documents(GetAllDocumentsOptions { retrieve_vectors: true, ..Default::default() })
-        .await;
-    snapshot!(json_string!(documents), @r###"
-    {
-      "results": [
-        {
-          "id": 0,
-          "name": "kefir",
-          "_vectors": {
-            "manual": {
-              "embeddings": [],
-              "regenerate": false
-            }
-          }
-        }
-      ],
-      "offset": 0,
-      "limit": 20,
-      "total": 1
-    }
-    "###);
-}