Add test tryinmg to reproduce bug

4822: HuggingFace: Clearer error message when a model is not supported r=Kerollmops a=dureuill

# Pull Request

## Related issue
Context: <https://github.com/meilisearch/meilisearch/discussions/4820>

## What does this PR do?
- Improve error message when a model configuration cannot be loaded and its "architectures" field does not contain "BertModel"

Co-authored-by: Louis Dureuil <louis@meilisearch.com>

.github/workflows/bench-manual.yml

@@ -18,11 +18,9 @@ jobs:
         timeout-minutes: 180 # 3h
         steps:
             - uses: actions/checkout@v3
-            - uses: actions-rs/toolchain@v1
+            - uses: helix-editor/rust-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

@@ -35,12 +35,17 @@ jobs:
             fetch-depth: 0 # fetch full history to be able to get main commit sha
             ref: ${{ steps.comment-branch.outputs.head_ref }}
 
-        - uses: actions-rs/toolchain@v1
+        - uses: helix-editor/rust-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 }})" -- ${{ steps.command.outputs.command-arguments }}
+            cargo xtask bench --api-key "${{ 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

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

@@ -12,11 +12,9 @@ jobs:
         timeout-minutes: 180 # 3h
         steps:
           - uses: actions/checkout@v3
-          - uses: actions-rs/toolchain@v1
+          - uses: helix-editor/rust-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

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

.github/workflows/benchmarks-pr.yml

@@ -13,11 +13,9 @@ jobs:
     runs-on: benchmarks
     timeout-minutes: 4320 # 72h
     steps:
-      - uses: actions-rs/toolchain@v1
+      - uses: helix-editor/rust-toolchain@v1
         with:
           profile: minimal
-          toolchain: stable
-          override: true
 
       - name: Check for Command
         id: command

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

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

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

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

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

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

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

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

.github/workflows/flaky-tests.yml

@@ -1,4 +1,5 @@
 name: Look for flaky tests
+
 on:
   workflow_dispatch:
   schedule:
@@ -8,18 +9,15 @@ jobs:
   flaky:
     runs-on: ubuntu-latest
     container:
-      # Use ubuntu-18.04 to compile with glibc 2.27, which are the production expectations
-      image: ubuntu:18.04
+      # Use ubuntu-20.04 to compile with glibc 2.28
+      image: ubuntu:20.04
     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: actions-rs/toolchain@v1
-      with:
-        toolchain: stable
-        override: true
+    - uses: helix-editor/rust-toolchain@v1
     - name: Install cargo-flaky
       run: cargo install cargo-flaky
     - name: Run cargo flaky in the dumps

.github/workflows/fuzzer-indexing.yml

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

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

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

.github/workflows/publish-binaries.yml

@@ -37,18 +37,15 @@ jobs:
     runs-on: ubuntu-latest
     needs: check-version
     container:
-      # Use ubuntu-18.04 to compile with glibc 2.27
-      image: ubuntu:18.04
+      # Use ubuntu-20.04 to compile with glibc 2.28
+      image: ubuntu:20.04
     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: actions-rs/toolchain@v1
-      with:
-        toolchain: stable
-        override: true
+    - uses: helix-editor/rust-toolchain@v1
     - name: Build
       run: cargo build --release --locked
     # No need to upload binaries for dry run (cron)
@@ -78,10 +75,7 @@ jobs:
             asset_name: meilisearch-windows-amd64.exe
     steps:
     - uses: actions/checkout@v3
-    - uses: actions-rs/toolchain@v1
-      with:
-        toolchain: stable
-        override: true
+    - uses: helix-editor/rust-toolchain@v1
     - name: Build
       run: cargo build --release --locked
     # No need to upload binaries for dry run (cron)
@@ -107,12 +101,10 @@ jobs:
       - name: Checkout repository
         uses: actions/checkout@v3
       - name: Installing Rust toolchain
-        uses: actions-rs/toolchain@v1
+        uses: helix-editor/rust-toolchain@v1
         with:
-          toolchain: stable
           profile: minimal
           target: ${{ matrix.target }}
-          override: true
       - name: Cargo build
         uses: actions-rs/cargo@v1
         with:
@@ -132,9 +124,11 @@ jobs:
     name: Publish binary for aarch64
     runs-on: ubuntu-latest
     needs: check-version
+    env:
+      DEBIAN_FRONTEND: noninteractive
     container:
-      # Use ubuntu-18.04 to compile with glibc 2.27
-      image: ubuntu:18.04
+      # Use ubuntu-20.04 to compile with glibc 2.28
+      image: ubuntu:20.04
     strategy:
       matrix:
         include:
@@ -154,12 +148,10 @@ jobs:
           add-apt-repository "deb [arch=$(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: actions-rs/toolchain@v1
+        uses: helix-editor/rust-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
@@ -170,6 +162,9 @@ 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

@@ -80,10 +80,11 @@ 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@v5
+        uses: docker/build-push-action@v6
         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-18.04
+    name: Tests on ubuntu-20.04
     runs-on: ubuntu-latest
     container:
-      # Use ubuntu-18.04 to compile with glibc 2.27, which are the production expectations
-      image: ubuntu:18.04
+      # Use ubuntu-20.04 to compile with glibc 2.28
+      image: ubuntu:20.04
     steps:
       - uses: actions/checkout@v3
       - name: Install needed dependencies
@@ -31,10 +31,7 @@ jobs:
           apt-get update && apt-get install -y curl
           apt-get install build-essential -y
       - name: Setup test with Rust stable
-        uses: actions-rs/toolchain@v1
-        with:
-          toolchain: stable
-          override: true
+        uses: helix-editor/rust-toolchain@v1
       - name: Cache dependencies
         uses: Swatinem/rust-cache@v2.7.1
       - name: Run cargo check without any default features
@@ -59,10 +56,7 @@ jobs:
       - uses: actions/checkout@v3
       - name: Cache dependencies
         uses: Swatinem/rust-cache@v2.7.1
-      - uses: actions-rs/toolchain@v1
-        with:
-          toolchain: stable
-          override: true
+      - uses: helix-editor/rust-toolchain@v1
       - name: Run cargo check without any default features
         uses: actions-rs/cargo@v1
         with:
@@ -78,8 +72,8 @@ jobs:
     name: Tests almost all features
     runs-on: ubuntu-latest
     container:
-      # Use ubuntu-18.04 to compile with glibc 2.27, which are the production expectations
-      image: ubuntu:18.04
+      # Use ubuntu-20.04 to compile with glibc 2.28
+      image: ubuntu:20.04
     if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
     steps:
       - uses: actions/checkout@v3
@@ -87,10 +81,7 @@ jobs:
         run: |
           apt-get update
           apt-get install --assume-yes build-essential curl
-      - uses: actions-rs/toolchain@v1
-        with:
-          toolchain: stable
-          override: true
+      - uses: helix-editor/rust-toolchain@v1
       - name: Run cargo build with almost all features
         run: |
           cargo build --workspace --locked --release --features "$(cargo xtask list-features --exclude-feature cuda)"
@@ -102,7 +93,7 @@ jobs:
     name: Test disabled tokenization
     runs-on: ubuntu-latest
     container:
-      image: ubuntu:18.04
+      image: ubuntu:20.04
     if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
     steps:
       - uses: actions/checkout@v3
@@ -110,13 +101,10 @@ jobs:
         run: |
           apt-get update
           apt-get install --assume-yes build-essential curl
-      - uses: actions-rs/toolchain@v1
-        with:
-          toolchain: stable
-          override: true
+      - uses: helix-editor/rust-toolchain@v1
       - 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 -vqz lindera; then
+          if cargo tree -f '{p} {f}' -e normal --no-default-features | grep -qz lindera; then
             echo "lindera has been found in the sources and it shouldn't"
             exit 1
           fi
@@ -129,18 +117,15 @@ jobs:
     name: Run tests in debug
     runs-on: ubuntu-latest
     container:
-      # Use ubuntu-18.04 to compile with glibc 2.27, which are the production expectations
-      image: ubuntu:18.04
+      # Use ubuntu-20.04 to compile with glibc 2.28
+      image: ubuntu:20.04
     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: actions-rs/toolchain@v1
-        with:
-          toolchain: stable
-          override: true
+      - uses: helix-editor/rust-toolchain@v1
       - name: Cache dependencies
         uses: Swatinem/rust-cache@v2.7.1
       - name: Run tests in debug
@@ -154,11 +139,9 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v3
-      - uses: actions-rs/toolchain@v1
+      - uses: helix-editor/rust-toolchain@v1
         with:
           profile: minimal
-          toolchain: 1.75.0
-          override: true
           components: clippy
       - name: Cache dependencies
         uses: Swatinem/rust-cache@v2.7.1
@@ -173,10 +156,10 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v3
-      - uses: actions-rs/toolchain@v1
+      - uses: helix-editor/rust-toolchain@v1
         with:
           profile: minimal
-          toolchain: nightly
+          toolchain: nightly-2024-07-09
           override: true
           components: rustfmt
       - name: Cache dependencies

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

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

BENCHMARKS.md

@@ -109,6 +109,12 @@ 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.
@@ -187,8 +193,8 @@ They are JSON files with the following structure (comments are not actually supp
   },
   // Core of the workload.
   // A list of commands to run sequentially.
-  // A command is a request to the Meilisearch instance that is executed while the profiling runs.
-  "commands": [
+  // Optional: A precommand is a request to the Meilisearch instance that is executed before the profiling runs.
+  "precommands": [
     {
       // Meilisearch route to call. `http://localhost:7700/` will be prepended.
       "route": "indexes/movies/settings",
@@ -224,8 +230,11 @@ 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": "DontWait"
-    },
+      "synchronous": "WaitForTask"
+    }
+  ],
+  // A command is a request to the Meilisearch instance that is executed while the profiling runs.
+  "commands": [
     {
       "route": "indexes/movies/documents",
       "method": "POST",

CONTRIBUTING.md

@@ -52,6 +52,20 @@ 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.
@@ -63,7 +77,7 @@ 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

@@ -22,7 +22,7 @@ members = [
 ]
 
 [workspace.package]
-version = "1.8.0"
+version = "1.10.0"
 authors = [
     "Quentin de Quelen <quentin@dequelen.me>",
     "Clément Renault <clement@meilisearch.com>",

Dockerfile

@@ -1,7 +1,7 @@
 # Compile
-FROM    rust:1.75.0-alpine3.18 AS compiler
+FROM    rust:1.79.0-alpine3.20 AS compiler
 
-RUN     apk add -q --update-cache --no-cache build-base openssl-dev
+RUN     apk add -q --no-cache build-base openssl-dev
 
 WORKDIR /
 
@@ -20,13 +20,12 @@ RUN     set -eux; \
         cargo build --release -p meilisearch -p meilitool
 
 # Run
-FROM    alpine:3.16
+FROM    alpine:3.20
 
 ENV     MEILI_HTTP_ADDR 0.0.0.0:7700
 ENV     MEILI_SERVER_PROVIDER docker
 
-RUN     apk update --quiet \
-        && apk add -q --no-cache libgcc tini curl
+RUN     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

@@ -1,9 +1,6 @@
 <p align="center">
-  <a href="https://www.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=logo#gh-light-mode-only" target="_blank">
-    <img src="assets/meilisearch-logo-light.svg?sanitize=true#gh-light-mode-only">
-  </a>
-  <a href="https://www.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=logo#gh-dark-mode-only" target="_blank">
-    <img src="assets/meilisearch-logo-dark.svg?sanitize=true#gh-dark-mode-only">
+  <a href="https://www.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=logo" target="_blank">
+    <img src="assets/meilisearch-logo-kawaii.png">
   </a>
 </p>
 
@@ -25,7 +22,7 @@
 
 <p align="center">⚡ A lightning-fast search engine that fits effortlessly into your apps, websites, and workflow 🔍</p>
 
-Meilisearch helps you shape a delightful search experience in a snap, offering features that work out-of-the-box to speed up your workflow.
+[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.
 
 <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">
@@ -36,11 +33,18 @@ Meilisearch helps you shape a delightful search experience in a snap, offering f
   </a>
 </p>
 
-🔥 [**Try it!**](https://where2watch.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demo-link) 🔥
+## 🖥 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).
 
 ## ✨ Features
-
-- **Search-as-you-type:** find search results in less than 50 milliseconds
+- **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/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
@@ -55,15 +59,15 @@ Meilisearch helps you shape a delightful search experience in a snap, offering f
 
 ## 📖 Documentation
 
-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).
+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).
 
 ## 🚀 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 [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.
+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.
 
-## ⚡ 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). No credit card 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). Additional features include analytics & monitoring in many regions around the world. No credit card is required.
 
 ## 🧰 SDKs & integration tools
 
@@ -83,15 +87,15 @@ Finally, for more in-depth information, refer to our articles explaining fundame
 
 ## 📊 Telemetry
 
-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.
+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.
 
-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.
+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.
 
 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), 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)
+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)
 
 🗞 [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.
 
@@ -105,11 +109,11 @@ Thank you for your support!
 
 ## 👩‍💻 Contributing
 
-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).
+Meilisearch is, and will always be, open-source! If you want to contribute to the project, please look at [our contribution guidelines](CONTRIBUTING.md).
 
 ## 📦 Versioning
 
-Meilisearch releases and their associated binaries are available [in this GitHub page](https://github.com/meilisearch/meilisearch/releases).
+Meilisearch releases and their associated binaries are available on the project's [releases 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 = "1.0.79"
+anyhow = "1.0.86"
 csv = "1.3.0"
 milli = { path = "../milli" }
-mimalloc = { version = "0.1.39", default-features = false }
-serde_json = { version = "1.0.111", features = ["preserve_order"] }
+mimalloc = { version = "0.1.43", default-features = false }
+serde_json = { version = "1.0.120", features = ["preserve_order"] }
 
 [dev-dependencies]
 criterion = { version = "0.5.1", features = ["html_reports"] }
 rand = "0.8.5"
 rand_chacha = "0.3.1"
-roaring = "0.10.2"
+roaring = "0.10.6"
 
 [build-dependencies]
-anyhow = "1.0.79"
-bytes = "1.5.0"
+anyhow = "1.0.86"
+bytes = "1.6.0"
 convert_case = "0.6.0"
-flate2 = "1.0.28"
-reqwest = { version = "0.11.23", features = ["blocking", "rustls-tls"], default-features = false }
+flate2 = "1.0.30"
+reqwest = { version = "0.12.5", features = ["blocking", "rustls-tls"], default-features = false }
 
 [features]
 default = ["milli/all-tokenizations"]

bors.toml

@@ -1,5 +1,5 @@
 status = [
-    'Tests on ubuntu-18.04',
+    'Tests on ubuntu-20.04',
     'Tests on macos-12',
     'Tests on windows-2022',
     'Run Clippy',

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 = "0.3.34", features = ["parsing"] }
+time = { version = "0.3.36", features = ["parsing"] }
 
 [build-dependencies]
-anyhow = "1.0.80"
-vergen-git2 = "1.0.0-beta.2"
+anyhow = "1.0.86"
+vergen-git2 = "1.0.0"

build-info/build.rs

@@ -5,6 +5,13 @@ 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.

dump/Cargo.toml

@@ -11,22 +11,21 @@ readme.workspace = true
 license.workspace = true
 
 [dependencies]
-anyhow = "1.0.79"
-flate2 = "1.0.28"
-http = "0.2.11"
-meilisearch-auth = { path = "../meilisearch-auth" }
+anyhow = "1.0.86"
+flate2 = "1.0.30"
+http = "1.1.0"
 meilisearch-types = { path = "../meilisearch-types" }
 once_cell = "1.19.0"
-regex = "1.10.2"
-roaring = { version = "0.10.2", features = ["serde"] }
-serde = { version = "1.0.195", features = ["derive"] }
-serde_json = { version = "1.0.111", features = ["preserve_order"] }
-tar = "0.4.40"
-tempfile = "3.9.0"
-thiserror = "1.0.56"
-time = { version = "0.3.31", features = ["serde-well-known", "formatting", "parsing", "macros"] }
+regex = "1.10.5"
+roaring = { version = "0.10.6", features = ["serde"] }
+serde = { version = "1.0.204", features = ["derive"] }
+serde_json = { version = "1.0.120", features = ["preserve_order"] }
+tar = "0.4.41"
+tempfile = "3.10.1"
+thiserror = "1.0.61"
+time = { version = "0.3.36", features = ["serde-well-known", "formatting", "parsing", "macros"] }
 tracing = "0.1.40"
-uuid = { version = "1.6.1", features = ["serde", "v4"] }
+uuid = { version = "1.10.0", features = ["serde", "v4"] }
 
 [dev-dependencies]
 big_s = "1.0.2"

dump/src/lib.rs

@@ -104,6 +104,11 @@ pub enum KindDump {
     DocumentDeletionByFilter {
         filter: serde_json::Value,
     },
+    DocumentEdition {
+        filter: Option<serde_json::Value>,
+        context: Option<serde_json::Map<String, serde_json::Value>>,
+        function: String,
+    },
     Settings {
         settings: Box<meilisearch_types::settings::Settings<Unchecked>>,
         is_deletion: bool,
@@ -172,6 +177,9 @@ impl From<KindWithContent> for KindDump {
             KindWithContent::DocumentDeletionByFilter { filter_expr, .. } => {
                 KindDump::DocumentDeletionByFilter { filter: filter_expr }
             }
+            KindWithContent::DocumentEdition { filter_expr, context, function, .. } => {
+                KindDump::DocumentEdition { filter: filter_expr, context, function }
+            }
             KindWithContent::DocumentClear { .. } => KindDump::DocumentClear,
             KindWithContent::SettingsUpdate {
                 new_settings,

dump/src/reader/compat/v2_to_v3.rs

@@ -425,7 +425,7 @@ pub(crate) mod test {
         let mut dump = v2::V2Reader::open(dir).unwrap().to_v3();
 
         // top level infos
-        insta::assert_display_snapshot!(dump.date().unwrap(), @"2022-10-09 20:27:59.904096267 +00:00:00");
+        insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-09 20:27:59.904096267 +00:00:00");
 
         // tasks
         let tasks = dump.tasks().collect::<Result<Vec<_>>>().unwrap();

dump/src/reader/compat/v3_to_v4.rs

@@ -358,7 +358,7 @@ pub(crate) mod test {
         let mut dump = v3::V3Reader::open(dir).unwrap().to_v4();
 
         // top level infos
-        insta::assert_display_snapshot!(dump.date().unwrap(), @"2022-10-07 11:39:03.709153554 +00:00:00");
+        insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-07 11:39:03.709153554 +00:00:00");
 
         // tasks
         let tasks = dump.tasks().collect::<Result<Vec<_>>>().unwrap();

dump/src/reader/compat/v4_to_v5.rs

@@ -394,8 +394,8 @@ pub(crate) mod test {
         let mut dump = v4::V4Reader::open(dir).unwrap().to_v5();
 
         // top level infos
-        insta::assert_display_snapshot!(dump.date().unwrap(), @"2022-10-06 12:53:49.131989609 +00:00:00");
-        insta::assert_display_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d");
+        insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-06 12:53:49.131989609 +00:00:00");
+        insta::assert_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d");
 
         // tasks
         let tasks = dump.tasks().collect::<Result<Vec<_>>>().unwrap();

dump/src/reader/compat/v5_to_v6.rs

@@ -442,8 +442,8 @@ pub(crate) mod test {
         let mut dump = v5::V5Reader::open(dir).unwrap().to_v6();
 
         // top level infos
-        insta::assert_display_snapshot!(dump.date().unwrap(), @"2022-10-04 15:55:10.344982459 +00:00:00");
-        insta::assert_display_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d");
+        insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-04 15:55:10.344982459 +00:00:00");
+        insta::assert_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d");
 
         // tasks
         let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();

dump/src/reader/mod.rs

@@ -197,13 +197,147 @@ pub(crate) mod test {
     use super::*;
     use crate::reader::v6::RuntimeTogglableFeatures;
 
+    #[test]
+    fn import_dump_v6_with_vectors() {
+        // dump containing two indexes
+        //
+        // "vector", configured with an embedder
+        // contains:
+        // - one document with an overriden vector,
+        // - one document with a natural vector
+        // - one document with a _vectors map containing one additional embedder name and a natural vector
+        // - one document with a _vectors map containing one additional embedder name and an overriden vector
+        //
+        // "novector", no embedder
+        // contains:
+        // - a document without vector
+        // - a document with a random _vectors field
+        let dump = File::open("tests/assets/v6-with-vectors.dump").unwrap();
+        let mut dump = DumpReader::open(dump).unwrap();
+
+        // top level infos
+        insta::assert_snapshot!(dump.date().unwrap(), @"2024-05-16 15:51:34.151044 +00:00:00");
+        insta::assert_debug_snapshot!(dump.instance_uid().unwrap(), @"None");
+
+        // tasks
+        let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
+        meili_snap::snapshot_hash!(meili_snap::json_string!(tasks), @"278f63325ef06ca04d01df98d8207b94");
+        assert_eq!(update_files.len(), 10);
+        assert!(update_files[0].is_none()); // the dump creation
+        assert!(update_files[1].is_none());
+        assert!(update_files[2].is_none());
+        assert!(update_files[3].is_none());
+        assert!(update_files[4].is_none());
+        assert!(update_files[5].is_none());
+        assert!(update_files[6].is_none());
+        assert!(update_files[7].is_none());
+        assert!(update_files[8].is_none());
+        assert!(update_files[9].is_none());
+
+        // indexes
+        let mut indexes = dump.indexes().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        // the index are not ordered in any way by default
+        indexes.sort_by_key(|index| index.metadata().uid.to_string());
+
+        let mut vector_index = indexes.pop().unwrap();
+        let mut novector_index = indexes.pop().unwrap();
+        assert!(indexes.is_empty());
+
+        // vector
+
+        insta::assert_json_snapshot!(vector_index.metadata(), @r###"
+        {
+          "uid": "vector",
+          "primaryKey": "id",
+          "createdAt": "2024-05-16T15:33:17.240962Z",
+          "updatedAt": "2024-05-16T15:40:55.723052Z"
+        }
+        "###);
+
+        {
+            let documents: Result<Vec<_>> = vector_index.documents().unwrap().collect();
+            let mut documents = documents.unwrap();
+            assert_eq!(documents.len(), 4);
+
+            documents.sort_by_key(|doc| doc.get("id").unwrap().to_string());
+
+            {
+                let document = documents.pop().unwrap();
+                insta::assert_json_snapshot!(document);
+            }
+
+            {
+                let document = documents.pop().unwrap();
+                insta::assert_json_snapshot!(document);
+            }
+
+            {
+                let document = documents.pop().unwrap();
+                insta::assert_json_snapshot!(document);
+            }
+
+            {
+                let document = documents.pop().unwrap();
+                insta::assert_json_snapshot!(document);
+            }
+        }
+
+        // novector
+
+        insta::assert_json_snapshot!(novector_index.metadata(), @r###"
+        {
+          "uid": "novector",
+          "primaryKey": "id",
+          "createdAt": "2024-05-16T15:33:03.568055Z",
+          "updatedAt": "2024-05-16T15:33:07.530217Z"
+        }
+        "###);
+
+        insta::assert_json_snapshot!(novector_index.settings().unwrap().embedders, @"null");
+
+        {
+            let documents: Result<Vec<_>> = novector_index.documents().unwrap().collect();
+            let mut documents = documents.unwrap();
+            assert_eq!(documents.len(), 2);
+
+            documents.sort_by_key(|doc| doc.get("id").unwrap().to_string());
+
+            {
+                let document = documents.pop().unwrap();
+                insta::assert_json_snapshot!(document, @r###"
+                {
+                  "id": "e1",
+                  "other": "random1",
+                  "_vectors": "toto"
+                }
+                "###);
+            }
+
+            {
+                let document = documents.pop().unwrap();
+                insta::assert_json_snapshot!(document, @r###"
+                {
+                  "id": "e0",
+                  "other": "random0"
+                }
+                "###);
+            }
+        }
+
+        assert_eq!(
+            dump.features().unwrap().unwrap(),
+            RuntimeTogglableFeatures { vector_store: true, ..Default::default() }
+        );
+    }
+
     #[test]
     fn import_dump_v6_experimental() {
         let dump = File::open("tests/assets/v6-with-experimental.dump").unwrap();
         let mut dump = DumpReader::open(dump).unwrap();
 
         // top level infos
-        insta::assert_display_snapshot!(dump.date().unwrap(), @"2023-07-06 7:10:27.21958 +00:00:00");
+        insta::assert_snapshot!(dump.date().unwrap(), @"2023-07-06 7:10:27.21958 +00:00:00");
         insta::assert_debug_snapshot!(dump.instance_uid().unwrap(), @"None");
 
         // tasks
@@ -249,8 +383,8 @@ pub(crate) mod test {
         let mut dump = DumpReader::open(dump).unwrap();
 
         // top level infos
-        insta::assert_display_snapshot!(dump.date().unwrap(), @"2022-10-04 15:55:10.344982459 +00:00:00");
-        insta::assert_display_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d");
+        insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-04 15:55:10.344982459 +00:00:00");
+        insta::assert_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d");
 
         // tasks
         let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
@@ -329,8 +463,8 @@ pub(crate) mod test {
         let mut dump = DumpReader::open(dump).unwrap();
 
         // top level infos
-        insta::assert_display_snapshot!(dump.date().unwrap(), @"2022-10-06 12:53:49.131989609 +00:00:00");
-        insta::assert_display_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d");
+        insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-06 12:53:49.131989609 +00:00:00");
+        insta::assert_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d");
 
         // tasks
         let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
@@ -406,7 +540,7 @@ pub(crate) mod test {
         let mut dump = DumpReader::open(dump).unwrap();
 
         // top level infos
-        insta::assert_display_snapshot!(dump.date().unwrap(), @"2022-10-07 11:39:03.709153554 +00:00:00");
+        insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-07 11:39:03.709153554 +00:00:00");
         assert_eq!(dump.instance_uid().unwrap(), None);
 
         // tasks
@@ -499,7 +633,7 @@ pub(crate) mod test {
         let mut dump = DumpReader::open(dump).unwrap();
 
         // top level infos
-        insta::assert_display_snapshot!(dump.date().unwrap(), @"2022-10-09 20:27:59.904096267 +00:00:00");
+        insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-09 20:27:59.904096267 +00:00:00");
         assert_eq!(dump.instance_uid().unwrap(), None);
 
         // tasks
@@ -592,7 +726,7 @@ pub(crate) mod test {
         let mut dump = DumpReader::open(dump).unwrap();
 
         // top level infos
-        insta::assert_display_snapshot!(dump.date().unwrap(), @"2023-01-30 16:26:09.247261 +00:00:00");
+        insta::assert_snapshot!(dump.date().unwrap(), @"2023-01-30 16:26:09.247261 +00:00:00");
         assert_eq!(dump.instance_uid().unwrap(), None);
 
         // tasks

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

@@ -0,0 +1,783 @@
+---
+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
+    ]
+  }
+}

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

@@ -0,0 +1,786 @@
+---
+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
+    }
+  }
+}

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

@@ -0,0 +1,785 @@
+---
+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
+    }
+  }
+}

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

@@ -0,0 +1,780 @@
+---
+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
+    ]
+  }
+}

dump/src/reader/v2/mod.rs

@@ -252,7 +252,7 @@ pub(crate) mod test {
         let mut dump = V2Reader::open(dir).unwrap();
 
         // top level infos
-        insta::assert_display_snapshot!(dump.date().unwrap(), @"2022-10-09 20:27:59.904096267 +00:00:00");
+        insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-09 20:27:59.904096267 +00:00:00");
 
         // tasks
         let tasks = dump.tasks().collect::<Result<Vec<_>>>().unwrap();
@@ -349,7 +349,7 @@ pub(crate) mod test {
         let mut dump = V2Reader::open(dir).unwrap();
 
         // top level infos
-        insta::assert_display_snapshot!(dump.date().unwrap(), @"2023-01-30 16:26:09.247261 +00:00:00");
+        insta::assert_snapshot!(dump.date().unwrap(), @"2023-01-30 16:26:09.247261 +00:00:00");
 
         // tasks
         let tasks = dump.tasks().collect::<Result<Vec<_>>>().unwrap();

dump/src/reader/v3/mod.rs

@@ -267,7 +267,7 @@ pub(crate) mod test {
         let mut dump = V3Reader::open(dir).unwrap();
 
         // top level infos
-        insta::assert_display_snapshot!(dump.date().unwrap(), @"2022-10-07 11:39:03.709153554 +00:00:00");
+        insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-07 11:39:03.709153554 +00:00:00");
 
         // tasks
         let tasks = dump.tasks().collect::<Result<Vec<_>>>().unwrap();

dump/src/reader/v3/settings.rs

@@ -152,6 +152,7 @@ impl Settings<Unchecked> {
 }
 
 #[derive(Debug, Clone, Deserialize)]
+#[allow(dead_code)] // otherwise rustc complains that the fields go unused
 #[cfg_attr(test, derive(serde::Serialize))]
 #[serde(deny_unknown_fields)]
 #[serde(rename_all = "camelCase")]

dump/src/reader/v4/mod.rs

@@ -262,8 +262,8 @@ pub(crate) mod test {
         let mut dump = V4Reader::open(dir).unwrap();
 
         // top level infos
-        insta::assert_display_snapshot!(dump.date().unwrap(), @"2022-10-06 12:53:49.131989609 +00:00:00");
-        insta::assert_display_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d");
+        insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-06 12:53:49.131989609 +00:00:00");
+        insta::assert_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d");
 
         // tasks
         let tasks = dump.tasks().collect::<Result<Vec<_>>>().unwrap();

dump/src/reader/v4/settings.rs

@@ -182,6 +182,7 @@ impl Settings<Unchecked> {
     }
 }
 
+#[allow(dead_code)] // otherwise rustc complains that the fields go unused
 #[derive(Debug, Clone, Deserialize)]
 #[cfg_attr(test, derive(serde::Serialize))]
 #[serde(deny_unknown_fields)]

dump/src/reader/v5/mod.rs

@@ -299,8 +299,8 @@ pub(crate) mod test {
         let mut dump = V5Reader::open(dir).unwrap();
 
         // top level infos
-        insta::assert_display_snapshot!(dump.date().unwrap(), @"2022-10-04 15:55:10.344982459 +00:00:00");
-        insta::assert_display_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d");
+        insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-04 15:55:10.344982459 +00:00:00");
+        insta::assert_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d");
 
         // tasks
         let tasks = dump.tasks().collect::<Result<Vec<_>>>().unwrap();

dump/src/reader/v5/tasks.rs

@@ -200,6 +200,7 @@ impl std::ops::Deref for IndexUid {
     }
 }
 
+#[allow(dead_code)] // otherwise rustc complains that the fields go unused
 #[derive(Debug)]
 #[cfg_attr(test, derive(serde::Serialize))]
 #[cfg_attr(test, serde(rename_all = "camelCase"))]

dump/src/writer.rs

@@ -281,7 +281,7 @@ pub(crate) mod test {
         let dump_path = dump.path();
 
         // ==== checking global file hierarchy (we want to be sure there isn't too many files or too few)
-        insta::assert_display_snapshot!(create_directory_hierarchy(dump_path), @r###"
+        insta::assert_snapshot!(create_directory_hierarchy(dump_path), @r###"
         .
         ├---- indexes/
         │    └---- doggos/

file-store/Cargo.toml

@@ -11,10 +11,7 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-tempfile = "3.9.0"
-thiserror = "1.0.56"
+tempfile = "3.10.1"
+thiserror = "1.0.61"
 tracing = "0.1.40"
-uuid = { version = "1.6.1", features = ["serde", "v4"] }
-
-[dev-dependencies]
-faux = "0.1.10"
+uuid = { version = "1.10.0", features = ["serde", "v4"] }

filter-parser/Cargo.toml

@@ -14,7 +14,7 @@ license.workspace = true
 [dependencies]
 nom = "7.1.3"
 nom_locate = "4.2.0"
-unescaper = "0.1.3"
+unescaper = "0.1.5"
 
 [dev-dependencies]
-insta = "1.34.0"
+insta = "1.39.0"

filter-parser/src/condition.rs

@@ -26,6 +26,7 @@ pub enum Condition<'a> {
     LowerThan(Token<'a>),
     LowerThanOrEqual(Token<'a>),
     Between { from: Token<'a>, to: Token<'a> },
+    Contains { keyword: Token<'a>, word: Token<'a> },
 }
 
 /// condition      = value ("==" | ">" ...) value
@@ -92,6 +93,34 @@ pub fn parse_not_exists(input: Span) -> IResult<FilterCondition> {
     Ok((input, FilterCondition::Not(Box::new(FilterCondition::Condition { fid: key, op: Exists }))))
 }
 
+/// contains        = value "CONTAINS" value
+pub fn parse_contains(input: Span) -> IResult<FilterCondition> {
+    let (input, (fid, contains, value)) =
+        tuple((parse_value, tag("CONTAINS"), cut(parse_value)))(input)?;
+    Ok((
+        input,
+        FilterCondition::Condition {
+            fid,
+            op: Contains { keyword: Token { span: contains, value: None }, word: value },
+        },
+    ))
+}
+
+/// contains        = value "NOT" WS+ "CONTAINS" value
+pub fn parse_not_contains(input: Span) -> IResult<FilterCondition> {
+    let keyword = tuple((tag("NOT"), multispace1, tag("CONTAINS")));
+    let (input, (fid, (_not, _spaces, contains), value)) =
+        tuple((parse_value, keyword, cut(parse_value)))(input)?;
+
+    Ok((
+        input,
+        FilterCondition::Not(Box::new(FilterCondition::Condition {
+            fid,
+            op: Contains { keyword: Token { span: contains, value: None }, word: value },
+        })),
+    ))
+}
+
 /// to             = value value "TO" WS+ value
 pub fn parse_to(input: Span) -> IResult<FilterCondition> {
     let (input, (key, from, _, _, to)) =

filter-parser/src/error.rs

@@ -146,7 +146,7 @@ impl<'a> Display for Error<'a> {
             }
             ErrorKind::InvalidPrimary => {
                 let text = if input.trim().is_empty() { "but instead got nothing.".to_string() } else { format!("at `{}`.", escaped_input) };
-                writeln!(f, "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` {}", text)?
+                writeln!(f, "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` {}", text)?
             }
             ErrorKind::InvalidEscapedNumber => {
                 writeln!(f, "Found an invalid escaped sequence number: `{}`.", escaped_input)?

filter-parser/src/lib.rs

@@ -48,8 +48,8 @@ use std::fmt::Debug;
 
 pub use condition::{parse_condition, parse_to, Condition};
 use condition::{
-    parse_exists, parse_is_empty, parse_is_not_empty, parse_is_not_null, parse_is_null,
-    parse_not_exists,
+    parse_contains, parse_exists, parse_is_empty, parse_is_not_empty, parse_is_not_null,
+    parse_is_null, parse_not_contains, parse_not_exists,
 };
 use error::{cut_with_err, ExpectedValueKind, NomErrorExt};
 pub use error::{Error, ErrorKind};
@@ -147,7 +147,37 @@ pub enum FilterCondition<'a> {
     GeoBoundingBox { top_right_point: [Token<'a>; 2], bottom_left_point: [Token<'a>; 2] },
 }
 
+pub enum TraversedElement<'a> {
+    FilterCondition(&'a FilterCondition<'a>),
+    Condition(&'a Condition<'a>),
+}
+
 impl<'a> FilterCondition<'a> {
+    pub fn use_contains_operator(&self) -> Option<&Token> {
+        match self {
+            FilterCondition::Condition { fid: _, op } => match op {
+                Condition::GreaterThan(_)
+                | Condition::GreaterThanOrEqual(_)
+                | Condition::Equal(_)
+                | Condition::NotEqual(_)
+                | Condition::Null
+                | Condition::Empty
+                | Condition::Exists
+                | Condition::LowerThan(_)
+                | Condition::LowerThanOrEqual(_)
+                | Condition::Between { .. } => None,
+                Condition::Contains { keyword, word: _ } => Some(keyword),
+            },
+            FilterCondition::Not(this) => this.use_contains_operator(),
+            FilterCondition::Or(seq) | FilterCondition::And(seq) => {
+                seq.iter().find_map(|filter| filter.use_contains_operator())
+            }
+            FilterCondition::GeoLowerThan { .. }
+            | FilterCondition::GeoBoundingBox { .. }
+            | FilterCondition::In { .. } => None,
+        }
+    }
+
     /// Returns the first token found at the specified depth, `None` if no token at this depth.
     pub fn token_at_depth(&self, depth: usize) -> Option<&Token> {
         match self {
@@ -452,6 +482,8 @@ fn parse_primary(input: Span, depth: usize) -> IResult<FilterCondition> {
         parse_exists,
         parse_not_exists,
         parse_to,
+        parse_contains,
+        parse_not_contains,
         // the next lines are only for error handling and are written at the end to have the less possible performance impact
         parse_geo,
         parse_geo_distance,
@@ -534,6 +566,7 @@ impl<'a> std::fmt::Display for Condition<'a> {
             Condition::LowerThan(token) => write!(f, "< {token}"),
             Condition::LowerThanOrEqual(token) => write!(f, "<= {token}"),
             Condition::Between { from, to } => write!(f, "{from} TO {to}"),
+            Condition::Contains { word, keyword: _ } => write!(f, "CONTAINS {word}"),
         }
     }
 }
@@ -558,127 +591,135 @@ pub mod tests {
         unsafe { Span::new_from_raw_offset(offset, lines as u32, value, "") }.into()
     }
 
+    #[track_caller]
     fn p(s: &str) -> impl std::fmt::Display + '_ {
         Fc::parse(s).unwrap().unwrap()
     }
 
     #[test]
     fn parse_escaped() {
-        insta::assert_display_snapshot!(p(r"title = 'foo\\'"), @r#"{title} = {foo\}"#);
-        insta::assert_display_snapshot!(p(r"title = 'foo\\\\'"), @r#"{title} = {foo\\}"#);
-        insta::assert_display_snapshot!(p(r"title = 'foo\\\\\\'"), @r#"{title} = {foo\\\}"#);
-        insta::assert_display_snapshot!(p(r"title = 'foo\\\\\\\\'"), @r#"{title} = {foo\\\\}"#);
+        insta::assert_snapshot!(p(r"title = 'foo\\'"), @r#"{title} = {foo\}"#);
+        insta::assert_snapshot!(p(r"title = 'foo\\\\'"), @r#"{title} = {foo\\}"#);
+        insta::assert_snapshot!(p(r"title = 'foo\\\\\\'"), @r#"{title} = {foo\\\}"#);
+        insta::assert_snapshot!(p(r"title = 'foo\\\\\\\\'"), @r#"{title} = {foo\\\\}"#);
         // but it also works with other sequences
-        insta::assert_display_snapshot!(p(r#"title = 'foo\x20\n\t\"\'"'"#), @"{title} = {foo \n\t\"\'\"}");
+        insta::assert_snapshot!(p(r#"title = 'foo\x20\n\t\"\'"'"#), @"{title} = {foo \n\t\"\'\"}");
     }
 
     #[test]
     fn parse() {
         // Test equal
-        insta::assert_display_snapshot!(p("channel = Ponce"), @"{channel} = {Ponce}");
-        insta::assert_display_snapshot!(p("subscribers = 12"), @"{subscribers} = {12}");
-        insta::assert_display_snapshot!(p("channel = 'Mister Mv'"), @"{channel} = {Mister Mv}");
-        insta::assert_display_snapshot!(p("channel = \"Mister Mv\""), @"{channel} = {Mister Mv}");
-        insta::assert_display_snapshot!(p("'dog race' = Borzoi"), @"{dog race} = {Borzoi}");
-        insta::assert_display_snapshot!(p("\"dog race\" = Chusky"), @"{dog race} = {Chusky}");
-        insta::assert_display_snapshot!(p("\"dog race\" = \"Bernese Mountain\""), @"{dog race} = {Bernese Mountain}");
-        insta::assert_display_snapshot!(p("'dog race' = 'Bernese Mountain'"), @"{dog race} = {Bernese Mountain}");
-        insta::assert_display_snapshot!(p("\"dog race\" = 'Bernese Mountain'"), @"{dog race} = {Bernese Mountain}");
+        insta::assert_snapshot!(p("channel = Ponce"), @"{channel} = {Ponce}");
+        insta::assert_snapshot!(p("subscribers = 12"), @"{subscribers} = {12}");
+        insta::assert_snapshot!(p("channel = 'Mister Mv'"), @"{channel} = {Mister Mv}");
+        insta::assert_snapshot!(p("channel = \"Mister Mv\""), @"{channel} = {Mister Mv}");
+        insta::assert_snapshot!(p("'dog race' = Borzoi"), @"{dog race} = {Borzoi}");
+        insta::assert_snapshot!(p("\"dog race\" = Chusky"), @"{dog race} = {Chusky}");
+        insta::assert_snapshot!(p("\"dog race\" = \"Bernese Mountain\""), @"{dog race} = {Bernese Mountain}");
+        insta::assert_snapshot!(p("'dog race' = 'Bernese Mountain'"), @"{dog race} = {Bernese Mountain}");
+        insta::assert_snapshot!(p("\"dog race\" = 'Bernese Mountain'"), @"{dog race} = {Bernese Mountain}");
 
         // Test IN
-        insta::assert_display_snapshot!(p("colour IN[]"), @"{colour} IN[]");
-        insta::assert_display_snapshot!(p("colour IN[green]"), @"{colour} IN[{green}, ]");
-        insta::assert_display_snapshot!(p("colour IN[green,]"), @"{colour} IN[{green}, ]");
-        insta::assert_display_snapshot!(p("colour NOT IN[green,blue]"), @"NOT ({colour} IN[{green}, {blue}, ])");
-        insta::assert_display_snapshot!(p(" colour IN [  green , blue , ]"), @"{colour} IN[{green}, {blue}, ]");
+        insta::assert_snapshot!(p("colour IN[]"), @"{colour} IN[]");
+        insta::assert_snapshot!(p("colour IN[green]"), @"{colour} IN[{green}, ]");
+        insta::assert_snapshot!(p("colour IN[green,]"), @"{colour} IN[{green}, ]");
+        insta::assert_snapshot!(p("colour NOT IN[green,blue]"), @"NOT ({colour} IN[{green}, {blue}, ])");
+        insta::assert_snapshot!(p(" colour IN [  green , blue , ]"), @"{colour} IN[{green}, {blue}, ]");
 
         // Test IN + OR/AND/()
-        insta::assert_display_snapshot!(p(" colour IN [green, blue]  AND color = green "), @"AND[{colour} IN[{green}, {blue}, ], {color} = {green}, ]");
-        insta::assert_display_snapshot!(p("NOT (colour IN [green, blue])  AND color = green "), @"AND[NOT ({colour} IN[{green}, {blue}, ]), {color} = {green}, ]");
-        insta::assert_display_snapshot!(p("x = 1 OR NOT (colour IN [green, blue]  OR color = green) "), @"OR[{x} = {1}, NOT (OR[{colour} IN[{green}, {blue}, ], {color} = {green}, ]), ]");
+        insta::assert_snapshot!(p(" colour IN [green, blue]  AND color = green "), @"AND[{colour} IN[{green}, {blue}, ], {color} = {green}, ]");
+        insta::assert_snapshot!(p("NOT (colour IN [green, blue])  AND color = green "), @"AND[NOT ({colour} IN[{green}, {blue}, ]), {color} = {green}, ]");
+        insta::assert_snapshot!(p("x = 1 OR NOT (colour IN [green, blue]  OR color = green) "), @"OR[{x} = {1}, NOT (OR[{colour} IN[{green}, {blue}, ], {color} = {green}, ]), ]");
 
         // Test whitespace start/end
-        insta::assert_display_snapshot!(p(" colour = green "), @"{colour} = {green}");
-        insta::assert_display_snapshot!(p(" (colour = green OR colour = red) "), @"OR[{colour} = {green}, {colour} = {red}, ]");
-        insta::assert_display_snapshot!(p(" colour IN [green, blue]  AND color = green "), @"AND[{colour} IN[{green}, {blue}, ], {color} = {green}, ]");
-        insta::assert_display_snapshot!(p(" colour NOT  IN [green, blue] "), @"NOT ({colour} IN[{green}, {blue}, ])");
-        insta::assert_display_snapshot!(p(" colour IN [green, blue] "), @"{colour} IN[{green}, {blue}, ]");
+        insta::assert_snapshot!(p(" colour = green "), @"{colour} = {green}");
+        insta::assert_snapshot!(p(" (colour = green OR colour = red) "), @"OR[{colour} = {green}, {colour} = {red}, ]");
+        insta::assert_snapshot!(p(" colour IN [green, blue]  AND color = green "), @"AND[{colour} IN[{green}, {blue}, ], {color} = {green}, ]");
+        insta::assert_snapshot!(p(" colour NOT  IN [green, blue] "), @"NOT ({colour} IN[{green}, {blue}, ])");
+        insta::assert_snapshot!(p(" colour IN [green, blue] "), @"{colour} IN[{green}, {blue}, ]");
 
         // Test conditions
-        insta::assert_display_snapshot!(p("channel != ponce"), @"{channel} != {ponce}");
-        insta::assert_display_snapshot!(p("NOT channel = ponce"), @"NOT ({channel} = {ponce})");
-        insta::assert_display_snapshot!(p("subscribers < 1000"), @"{subscribers} < {1000}");
-        insta::assert_display_snapshot!(p("subscribers > 1000"), @"{subscribers} > {1000}");
-        insta::assert_display_snapshot!(p("subscribers <= 1000"), @"{subscribers} <= {1000}");
-        insta::assert_display_snapshot!(p("subscribers >= 1000"), @"{subscribers} >= {1000}");
-        insta::assert_display_snapshot!(p("subscribers <= 1000"), @"{subscribers} <= {1000}");
-        insta::assert_display_snapshot!(p("subscribers 100 TO 1000"), @"{subscribers} {100} TO {1000}");
+        insta::assert_snapshot!(p("channel != ponce"), @"{channel} != {ponce}");
+        insta::assert_snapshot!(p("NOT channel = ponce"), @"NOT ({channel} = {ponce})");
+        insta::assert_snapshot!(p("subscribers < 1000"), @"{subscribers} < {1000}");
+        insta::assert_snapshot!(p("subscribers > 1000"), @"{subscribers} > {1000}");
+        insta::assert_snapshot!(p("subscribers <= 1000"), @"{subscribers} <= {1000}");
+        insta::assert_snapshot!(p("subscribers >= 1000"), @"{subscribers} >= {1000}");
+        insta::assert_snapshot!(p("subscribers <= 1000"), @"{subscribers} <= {1000}");
+        insta::assert_snapshot!(p("subscribers 100 TO 1000"), @"{subscribers} {100} TO {1000}");
 
         // Test NOT
-        insta::assert_display_snapshot!(p("NOT subscribers < 1000"), @"NOT ({subscribers} < {1000})");
-        insta::assert_display_snapshot!(p("NOT subscribers 100 TO 1000"), @"NOT ({subscribers} {100} TO {1000})");
+        insta::assert_snapshot!(p("NOT subscribers < 1000"), @"NOT ({subscribers} < {1000})");
+        insta::assert_snapshot!(p("NOT subscribers 100 TO 1000"), @"NOT ({subscribers} {100} TO {1000})");
 
         // Test NULL + NOT NULL
-        insta::assert_display_snapshot!(p("subscribers IS NULL"), @"{subscribers} IS NULL");
-        insta::assert_display_snapshot!(p("NOT subscribers IS NULL"), @"NOT ({subscribers} IS NULL)");
-        insta::assert_display_snapshot!(p("subscribers IS NOT NULL"), @"NOT ({subscribers} IS NULL)");
-        insta::assert_display_snapshot!(p("NOT subscribers IS NOT NULL"), @"{subscribers} IS NULL");
-        insta::assert_display_snapshot!(p("subscribers  IS   NOT   NULL"), @"NOT ({subscribers} IS NULL)");
+        insta::assert_snapshot!(p("subscribers IS NULL"), @"{subscribers} IS NULL");
+        insta::assert_snapshot!(p("NOT subscribers IS NULL"), @"NOT ({subscribers} IS NULL)");
+        insta::assert_snapshot!(p("subscribers IS NOT NULL"), @"NOT ({subscribers} IS NULL)");
+        insta::assert_snapshot!(p("NOT subscribers IS NOT NULL"), @"{subscribers} IS NULL");
+        insta::assert_snapshot!(p("subscribers  IS   NOT   NULL"), @"NOT ({subscribers} IS NULL)");
 
         // Test EMPTY + NOT EMPTY
-        insta::assert_display_snapshot!(p("subscribers IS EMPTY"), @"{subscribers} IS EMPTY");
-        insta::assert_display_snapshot!(p("NOT subscribers IS EMPTY"), @"NOT ({subscribers} IS EMPTY)");
-        insta::assert_display_snapshot!(p("subscribers IS NOT EMPTY"), @"NOT ({subscribers} IS EMPTY)");
-        insta::assert_display_snapshot!(p("NOT subscribers IS NOT EMPTY"), @"{subscribers} IS EMPTY");
-        insta::assert_display_snapshot!(p("subscribers  IS   NOT   EMPTY"), @"NOT ({subscribers} IS EMPTY)");
+        insta::assert_snapshot!(p("subscribers IS EMPTY"), @"{subscribers} IS EMPTY");
+        insta::assert_snapshot!(p("NOT subscribers IS EMPTY"), @"NOT ({subscribers} IS EMPTY)");
+        insta::assert_snapshot!(p("subscribers IS NOT EMPTY"), @"NOT ({subscribers} IS EMPTY)");
+        insta::assert_snapshot!(p("NOT subscribers IS NOT EMPTY"), @"{subscribers} IS EMPTY");
+        insta::assert_snapshot!(p("subscribers  IS   NOT   EMPTY"), @"NOT ({subscribers} IS EMPTY)");
 
         // Test EXISTS + NOT EXITS
-        insta::assert_display_snapshot!(p("subscribers EXISTS"), @"{subscribers} EXISTS");
-        insta::assert_display_snapshot!(p("NOT subscribers EXISTS"), @"NOT ({subscribers} EXISTS)");
-        insta::assert_display_snapshot!(p("subscribers NOT EXISTS"), @"NOT ({subscribers} EXISTS)");
-        insta::assert_display_snapshot!(p("NOT subscribers NOT EXISTS"), @"{subscribers} EXISTS");
-        insta::assert_display_snapshot!(p("subscribers NOT   EXISTS"), @"NOT ({subscribers} EXISTS)");
+        insta::assert_snapshot!(p("subscribers EXISTS"), @"{subscribers} EXISTS");
+        insta::assert_snapshot!(p("NOT subscribers EXISTS"), @"NOT ({subscribers} EXISTS)");
+        insta::assert_snapshot!(p("subscribers NOT EXISTS"), @"NOT ({subscribers} EXISTS)");
+        insta::assert_snapshot!(p("NOT subscribers NOT EXISTS"), @"{subscribers} EXISTS");
+        insta::assert_snapshot!(p("subscribers NOT   EXISTS"), @"NOT ({subscribers} EXISTS)");
+
+        // Test CONTAINS + NOT CONTAINS
+        insta::assert_snapshot!(p("subscribers CONTAINS 'hello'"), @"{subscribers} CONTAINS {hello}");
+        insta::assert_snapshot!(p("NOT subscribers CONTAINS 'hello'"), @"NOT ({subscribers} CONTAINS {hello})");
+        insta::assert_snapshot!(p("subscribers NOT CONTAINS hello"), @"NOT ({subscribers} CONTAINS {hello})");
+        insta::assert_snapshot!(p("NOT subscribers NOT CONTAINS 'hello'"), @"{subscribers} CONTAINS {hello}");
+        insta::assert_snapshot!(p("subscribers NOT   CONTAINS 'hello'"), @"NOT ({subscribers} CONTAINS {hello})");
 
         // Test nested NOT
-        insta::assert_display_snapshot!(p("NOT NOT NOT NOT x = 5"), @"{x} = {5}");
-        insta::assert_display_snapshot!(p("NOT NOT (NOT NOT x = 5)"), @"{x} = {5}");
+        insta::assert_snapshot!(p("NOT NOT NOT NOT x = 5"), @"{x} = {5}");
+        insta::assert_snapshot!(p("NOT NOT (NOT NOT x = 5)"), @"{x} = {5}");
 
         // Test geo radius
-        insta::assert_display_snapshot!(p("_geoRadius(12, 13, 14)"), @"_geoRadius({12}, {13}, {14})");
-        insta::assert_display_snapshot!(p("NOT _geoRadius(12, 13, 14)"), @"NOT (_geoRadius({12}, {13}, {14}))");
-        insta::assert_display_snapshot!(p("_geoRadius(12,13,14)"), @"_geoRadius({12}, {13}, {14})");
+        insta::assert_snapshot!(p("_geoRadius(12, 13, 14)"), @"_geoRadius({12}, {13}, {14})");
+        insta::assert_snapshot!(p("NOT _geoRadius(12, 13, 14)"), @"NOT (_geoRadius({12}, {13}, {14}))");
+        insta::assert_snapshot!(p("_geoRadius(12,13,14)"), @"_geoRadius({12}, {13}, {14})");
 
         // Test geo bounding box
-        insta::assert_display_snapshot!(p("_geoBoundingBox([12, 13], [14, 15])"), @"_geoBoundingBox([{12}, {13}], [{14}, {15}])");
-        insta::assert_display_snapshot!(p("NOT _geoBoundingBox([12, 13], [14, 15])"), @"NOT (_geoBoundingBox([{12}, {13}], [{14}, {15}]))");
-        insta::assert_display_snapshot!(p("_geoBoundingBox([12,13],[14,15])"), @"_geoBoundingBox([{12}, {13}], [{14}, {15}])");
+        insta::assert_snapshot!(p("_geoBoundingBox([12, 13], [14, 15])"), @"_geoBoundingBox([{12}, {13}], [{14}, {15}])");
+        insta::assert_snapshot!(p("NOT _geoBoundingBox([12, 13], [14, 15])"), @"NOT (_geoBoundingBox([{12}, {13}], [{14}, {15}]))");
+        insta::assert_snapshot!(p("_geoBoundingBox([12,13],[14,15])"), @"_geoBoundingBox([{12}, {13}], [{14}, {15}])");
 
         // Test OR + AND
-        insta::assert_display_snapshot!(p("channel = ponce AND 'dog race' != 'bernese mountain'"), @"AND[{channel} = {ponce}, {dog race} != {bernese mountain}, ]");
-        insta::assert_display_snapshot!(p("channel = ponce OR 'dog race' != 'bernese mountain'"), @"OR[{channel} = {ponce}, {dog race} != {bernese mountain}, ]");
-        insta::assert_display_snapshot!(p("channel = ponce AND 'dog race' != 'bernese mountain' OR subscribers > 1000"), @"OR[AND[{channel} = {ponce}, {dog race} != {bernese mountain}, ], {subscribers} > {1000}, ]");
-        insta::assert_display_snapshot!(
+        insta::assert_snapshot!(p("channel = ponce AND 'dog race' != 'bernese mountain'"), @"AND[{channel} = {ponce}, {dog race} != {bernese mountain}, ]");
+        insta::assert_snapshot!(p("channel = ponce OR 'dog race' != 'bernese mountain'"), @"OR[{channel} = {ponce}, {dog race} != {bernese mountain}, ]");
+        insta::assert_snapshot!(p("channel = ponce AND 'dog race' != 'bernese mountain' OR subscribers > 1000"), @"OR[AND[{channel} = {ponce}, {dog race} != {bernese mountain}, ], {subscribers} > {1000}, ]");
+        insta::assert_snapshot!(
         p("channel = ponce AND 'dog race' != 'bernese mountain' OR subscribers > 1000 OR colour = red OR colour = blue AND size = 7"),
         @"OR[AND[{channel} = {ponce}, {dog race} != {bernese mountain}, ], {subscribers} > {1000}, {colour} = {red}, AND[{colour} = {blue}, {size} = {7}, ], ]"
         );
 
         // Test parentheses
-        insta::assert_display_snapshot!(p("channel = ponce AND ( 'dog race' != 'bernese mountain' OR subscribers > 1000 )"), @"AND[{channel} = {ponce}, OR[{dog race} != {bernese mountain}, {subscribers} > {1000}, ], ]");
-        insta::assert_display_snapshot!(p("(channel = ponce AND 'dog race' != 'bernese mountain' OR subscribers > 1000) AND _geoRadius(12, 13, 14)"), @"AND[OR[AND[{channel} = {ponce}, {dog race} != {bernese mountain}, ], {subscribers} > {1000}, ], _geoRadius({12}, {13}, {14}), ]");
+        insta::assert_snapshot!(p("channel = ponce AND ( 'dog race' != 'bernese mountain' OR subscribers > 1000 )"), @"AND[{channel} = {ponce}, OR[{dog race} != {bernese mountain}, {subscribers} > {1000}, ], ]");
+        insta::assert_snapshot!(p("(channel = ponce AND 'dog race' != 'bernese mountain' OR subscribers > 1000) AND _geoRadius(12, 13, 14)"), @"AND[OR[AND[{channel} = {ponce}, {dog race} != {bernese mountain}, ], {subscribers} > {1000}, ], _geoRadius({12}, {13}, {14}), ]");
 
         // Test recursion
         // This is the most that is allowed
-        insta::assert_display_snapshot!(
+        insta::assert_snapshot!(
             p("(((((((((((((((((((((((((((((((((((((((((((((((((x = 1)))))))))))))))))))))))))))))))))))))))))))))))))"),
             @"{x} = {1}"
         );
-        insta::assert_display_snapshot!(
+        insta::assert_snapshot!(
             p("NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT x = 1"),
             @"NOT ({x} = {1})"
         );
 
         // Confusing keywords
-        insta::assert_display_snapshot!(p(r#"NOT "OR" EXISTS AND "EXISTS" NOT EXISTS"#), @"AND[NOT ({OR} EXISTS), NOT ({EXISTS} EXISTS), ]");
+        insta::assert_snapshot!(p(r#"NOT "OR" EXISTS AND "EXISTS" NOT EXISTS"#), @"AND[NOT ({OR} EXISTS), NOT ({EXISTS} EXISTS), ]");
     }
 
     #[test]
@@ -689,182 +730,182 @@ pub mod tests {
             Fc::parse(s).unwrap_err().to_string()
         }
 
-        insta::assert_display_snapshot!(p("channel = Ponce = 12"), @r###"
+        insta::assert_snapshot!(p("channel = Ponce = 12"), @r###"
         Found unexpected characters at the end of the filter: `= 12`. You probably forgot an `OR` or an `AND` rule.
         17:21 channel = Ponce = 12
         "###);
 
-        insta::assert_display_snapshot!(p("channel =    "), @r###"
+        insta::assert_snapshot!(p("channel =    "), @r###"
         Was expecting a value but instead got nothing.
         14:14 channel =
         "###);
 
-        insta::assert_display_snapshot!(p("channel = 🐻"), @r###"
+        insta::assert_snapshot!(p("channel = 🐻"), @r###"
         Was expecting a value but instead got `🐻`.
         11:12 channel = 🐻
         "###);
 
-        insta::assert_display_snapshot!(p("channel = 🐻 AND followers < 100"), @r###"
+        insta::assert_snapshot!(p("channel = 🐻 AND followers < 100"), @r###"
         Was expecting a value but instead got `🐻`.
         11:12 channel = 🐻 AND followers < 100
         "###);
 
-        insta::assert_display_snapshot!(p("'OR'"), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `\'OR\'`.
+        insta::assert_snapshot!(p("'OR'"), @r###"
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `\'OR\'`.
         1:5 'OR'
         "###);
 
-        insta::assert_display_snapshot!(p("OR"), @r###"
+        insta::assert_snapshot!(p("OR"), @r###"
         Was expecting a value but instead got `OR`, which is a reserved keyword. To use `OR` as a field name or a value, surround it by quotes.
         1:3 OR
         "###);
 
-        insta::assert_display_snapshot!(p("channel Ponce"), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `channel Ponce`.
+        insta::assert_snapshot!(p("channel Ponce"), @r###"
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `channel Ponce`.
         1:14 channel Ponce
         "###);
 
-        insta::assert_display_snapshot!(p("channel = Ponce OR"), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` but instead got nothing.
+        insta::assert_snapshot!(p("channel = Ponce OR"), @r###"
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` but instead got nothing.
         19:19 channel = Ponce OR
         "###);
 
-        insta::assert_display_snapshot!(p("_geoRadius"), @r###"
+        insta::assert_snapshot!(p("_geoRadius"), @r###"
         The `_geoRadius` filter expects three arguments: `_geoRadius(latitude, longitude, radius)`.
         1:11 _geoRadius
         "###);
 
-        insta::assert_display_snapshot!(p("_geoRadius = 12"), @r###"
+        insta::assert_snapshot!(p("_geoRadius = 12"), @r###"
         The `_geoRadius` filter expects three arguments: `_geoRadius(latitude, longitude, radius)`.
         1:16 _geoRadius = 12
         "###);
 
-        insta::assert_display_snapshot!(p("_geoBoundingBox"), @r###"
+        insta::assert_snapshot!(p("_geoBoundingBox"), @r###"
         The `_geoBoundingBox` filter expects two pairs of arguments: `_geoBoundingBox([latitude, longitude], [latitude, longitude])`.
         1:16 _geoBoundingBox
         "###);
 
-        insta::assert_display_snapshot!(p("_geoBoundingBox = 12"), @r###"
+        insta::assert_snapshot!(p("_geoBoundingBox = 12"), @r###"
         The `_geoBoundingBox` filter expects two pairs of arguments: `_geoBoundingBox([latitude, longitude], [latitude, longitude])`.
         1:21 _geoBoundingBox = 12
         "###);
 
-        insta::assert_display_snapshot!(p("_geoBoundingBox(1.0, 1.0)"), @r###"
+        insta::assert_snapshot!(p("_geoBoundingBox(1.0, 1.0)"), @r###"
         The `_geoBoundingBox` filter expects two pairs of arguments: `_geoBoundingBox([latitude, longitude], [latitude, longitude])`.
         1:26 _geoBoundingBox(1.0, 1.0)
         "###);
 
-        insta::assert_display_snapshot!(p("_geoPoint(12, 13, 14)"), @r###"
+        insta::assert_snapshot!(p("_geoPoint(12, 13, 14)"), @r###"
         `_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.
         1:22 _geoPoint(12, 13, 14)
         "###);
 
-        insta::assert_display_snapshot!(p("position <= _geoPoint(12, 13, 14)"), @r###"
+        insta::assert_snapshot!(p("position <= _geoPoint(12, 13, 14)"), @r###"
         `_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.
         13:34 position <= _geoPoint(12, 13, 14)
         "###);
 
-        insta::assert_display_snapshot!(p("_geoDistance(12, 13, 14)"), @r###"
+        insta::assert_snapshot!(p("_geoDistance(12, 13, 14)"), @r###"
         `_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.
         1:25 _geoDistance(12, 13, 14)
         "###);
 
-        insta::assert_display_snapshot!(p("position <= _geoDistance(12, 13, 14)"), @r###"
+        insta::assert_snapshot!(p("position <= _geoDistance(12, 13, 14)"), @r###"
         `_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.
         13:37 position <= _geoDistance(12, 13, 14)
         "###);
 
-        insta::assert_display_snapshot!(p("_geo(12, 13, 14)"), @r###"
+        insta::assert_snapshot!(p("_geo(12, 13, 14)"), @r###"
         `_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.
         1:17 _geo(12, 13, 14)
         "###);
 
-        insta::assert_display_snapshot!(p("position <= _geo(12, 13, 14)"), @r###"
+        insta::assert_snapshot!(p("position <= _geo(12, 13, 14)"), @r###"
         `_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.
         13:29 position <= _geo(12, 13, 14)
         "###);
 
-        insta::assert_display_snapshot!(p("position <= _geoRadius(12, 13, 14)"), @r###"
+        insta::assert_snapshot!(p("position <= _geoRadius(12, 13, 14)"), @r###"
         The `_geoRadius` filter is an operation and can't be used as a value.
         13:35 position <= _geoRadius(12, 13, 14)
         "###);
 
-        insta::assert_display_snapshot!(p("channel = 'ponce"), @r###"
+        insta::assert_snapshot!(p("channel = 'ponce"), @r###"
         Expression `\'ponce` is missing the following closing delimiter: `'`.
         11:17 channel = 'ponce
         "###);
 
-        insta::assert_display_snapshot!(p("channel = \"ponce"), @r###"
+        insta::assert_snapshot!(p("channel = \"ponce"), @r###"
         Expression `\"ponce` is missing the following closing delimiter: `"`.
         11:17 channel = "ponce
         "###);
 
-        insta::assert_display_snapshot!(p("channel = mv OR (followers >= 1000"), @r###"
+        insta::assert_snapshot!(p("channel = mv OR (followers >= 1000"), @r###"
         Expression `(followers >= 1000` is missing the following closing delimiter: `)`.
         17:35 channel = mv OR (followers >= 1000
         "###);
 
-        insta::assert_display_snapshot!(p("channel = mv OR followers >= 1000)"), @r###"
+        insta::assert_snapshot!(p("channel = mv OR followers >= 1000)"), @r###"
         Found unexpected characters at the end of the filter: `)`. You probably forgot an `OR` or an `AND` rule.
         34:35 channel = mv OR followers >= 1000)
         "###);
 
-        insta::assert_display_snapshot!(p("colour NOT EXIST"), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `colour NOT EXIST`.
+        insta::assert_snapshot!(p("colour NOT EXIST"), @r###"
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `colour NOT EXIST`.
         1:17 colour NOT EXIST
         "###);
 
-        insta::assert_display_snapshot!(p("subscribers 100 TO1000"), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `subscribers 100 TO1000`.
+        insta::assert_snapshot!(p("subscribers 100 TO1000"), @r###"
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `subscribers 100 TO1000`.
         1:23 subscribers 100 TO1000
         "###);
 
-        insta::assert_display_snapshot!(p("channel = ponce ORdog != 'bernese mountain'"), @r###"
+        insta::assert_snapshot!(p("channel = ponce ORdog != 'bernese mountain'"), @r###"
         Found unexpected characters at the end of the filter: `ORdog != \'bernese mountain\'`. You probably forgot an `OR` or an `AND` rule.
         17:44 channel = ponce ORdog != 'bernese mountain'
         "###);
 
-        insta::assert_display_snapshot!(p("colour IN blue, green]"), @r###"
+        insta::assert_snapshot!(p("colour IN blue, green]"), @r###"
         Expected `[` after `IN` keyword.
         11:23 colour IN blue, green]
         "###);
 
-        insta::assert_display_snapshot!(p("colour IN [blue, green, 'blue' > 2]"), @r###"
+        insta::assert_snapshot!(p("colour IN [blue, green, 'blue' > 2]"), @r###"
         Expected only comma-separated field names inside `IN[..]` but instead found `> 2]`.
         32:36 colour IN [blue, green, 'blue' > 2]
         "###);
 
-        insta::assert_display_snapshot!(p("colour IN [blue, green, AND]"), @r###"
+        insta::assert_snapshot!(p("colour IN [blue, green, AND]"), @r###"
         Expected only comma-separated field names inside `IN[..]` but instead found `AND]`.
         25:29 colour IN [blue, green, AND]
         "###);
 
-        insta::assert_display_snapshot!(p("colour IN [blue, green"), @r###"
+        insta::assert_snapshot!(p("colour IN [blue, green"), @r###"
         Expected matching `]` after the list of field names given to `IN[`
         23:23 colour IN [blue, green
         "###);
 
-        insta::assert_display_snapshot!(p("colour IN ['blue, green"), @r###"
+        insta::assert_snapshot!(p("colour IN ['blue, green"), @r###"
         Expression `\'blue, green` is missing the following closing delimiter: `'`.
         12:24 colour IN ['blue, green
         "###);
 
-        insta::assert_display_snapshot!(p("x = EXISTS"), @r###"
+        insta::assert_snapshot!(p("x = EXISTS"), @r###"
         Was expecting a value but instead got `EXISTS`, which is a reserved keyword. To use `EXISTS` as a field name or a value, surround it by quotes.
         5:11 x = EXISTS
         "###);
 
-        insta::assert_display_snapshot!(p("AND = 8"), @r###"
+        insta::assert_snapshot!(p("AND = 8"), @r###"
         Was expecting a value but instead got `AND`, which is a reserved keyword. To use `AND` as a field name or a value, surround it by quotes.
         1:4 AND = 8
         "###);
 
-        insta::assert_display_snapshot!(p("((((((((((((((((((((((((((((((((((((((((((((((((((x = 1))))))))))))))))))))))))))))))))))))))))))))))))))"), @r###"
+        insta::assert_snapshot!(p("((((((((((((((((((((((((((((((((((((((((((((((((((x = 1))))))))))))))))))))))))))))))))))))))))))))))))))"), @r###"
         The filter exceeded the maximum depth limit. Try rewriting the filter so that it contains fewer nested conditions.
         51:106 ((((((((((((((((((((((((((((((((((((((((((((((((((x = 1))))))))))))))))))))))))))))))))))))))))))))))))))
         "###);
 
-        insta::assert_display_snapshot!(
+        insta::assert_snapshot!(
             p("NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT NOT x = 1"),
             @r###"
         The filter exceeded the maximum depth limit. Try rewriting the filter so that it contains fewer nested conditions.
@@ -872,41 +913,41 @@ pub mod tests {
         "###
         );
 
-        insta::assert_display_snapshot!(p(r#"NOT OR EXISTS AND EXISTS NOT EXISTS"#), @r###"
+        insta::assert_snapshot!(p(r#"NOT OR EXISTS AND EXISTS NOT EXISTS"#), @r###"
         Was expecting a value but instead got `OR`, which is a reserved keyword. To use `OR` as a field name or a value, surround it by quotes.
         5:7 NOT OR EXISTS AND EXISTS NOT EXISTS
         "###);
 
-        insta::assert_display_snapshot!(p(r#"value NULL"#), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `value NULL`.
+        insta::assert_snapshot!(p(r#"value NULL"#), @r###"
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `value NULL`.
         1:11 value NULL
         "###);
-        insta::assert_display_snapshot!(p(r#"value NOT NULL"#), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `value NOT NULL`.
+        insta::assert_snapshot!(p(r#"value NOT NULL"#), @r###"
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `value NOT NULL`.
         1:15 value NOT NULL
         "###);
-        insta::assert_display_snapshot!(p(r#"value EMPTY"#), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `value EMPTY`.
+        insta::assert_snapshot!(p(r#"value EMPTY"#), @r###"
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `value EMPTY`.
         1:12 value EMPTY
         "###);
-        insta::assert_display_snapshot!(p(r#"value NOT EMPTY"#), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `value NOT EMPTY`.
+        insta::assert_snapshot!(p(r#"value NOT EMPTY"#), @r###"
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `value NOT EMPTY`.
         1:16 value NOT EMPTY
         "###);
-        insta::assert_display_snapshot!(p(r#"value IS"#), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `value IS`.
+        insta::assert_snapshot!(p(r#"value IS"#), @r###"
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `value IS`.
         1:9 value IS
         "###);
-        insta::assert_display_snapshot!(p(r#"value IS NOT"#), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `value IS NOT`.
+        insta::assert_snapshot!(p(r#"value IS NOT"#), @r###"
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `value IS NOT`.
         1:13 value IS NOT
         "###);
-        insta::assert_display_snapshot!(p(r#"value IS EXISTS"#), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `value IS EXISTS`.
+        insta::assert_snapshot!(p(r#"value IS EXISTS"#), @r###"
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `value IS EXISTS`.
         1:16 value IS EXISTS
         "###);
-        insta::assert_display_snapshot!(p(r#"value IS NOT EXISTS"#), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `value IS NOT EXISTS`.
+        insta::assert_snapshot!(p(r#"value IS NOT EXISTS"#), @r###"
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `value IS NOT EXISTS`.
         1:20 value IS NOT EXISTS
         "###);
     }

filter-parser/src/value.rs

@@ -211,6 +211,7 @@ fn is_keyword(s: &str) -> bool {
             | "IS"
             | "NULL"
             | "EMPTY"
+            | "CONTAINS"
             | "_geoRadius"
             | "_geoBoundingBox"
     )

fuzzers/Cargo.toml

@@ -12,9 +12,9 @@ license.workspace = true
 
 [dependencies]
 arbitrary = { version = "1.3.2", features = ["derive"] }
-clap = { version = "4.4.17", features = ["derive"] }
-fastrand = "2.0.1"
+clap = { version = "4.5.9", features = ["derive"] }
+fastrand = "2.1.0"
 milli = { path = "../milli" }
-serde = { version = "1.0.195", features = ["derive"] }
-serde_json = { version = "1.0.111", features = ["preserve_order"] }
-tempfile = "3.9.0"
+serde = { version = "1.0.204", features = ["derive"] }
+serde_json = { version = "1.0.120", features = ["preserve_order"] }
+tempfile = "3.10.1"

index-scheduler/Cargo.toml

@@ -11,37 +11,38 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-anyhow = "1.0.79"
+anyhow = "1.0.86"
 bincode = "1.3.3"
 csv = "1.3.0"
-derive_builder = "0.12.0"
+derive_builder = "0.20.0"
 dump = { path = "../dump" }
-enum-iterator = "1.5.0"
+enum-iterator = "2.1.0"
 file-store = { path = "../file-store" }
-flate2 = "1.0.28"
+flate2 = "1.0.30"
 meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
-page_size = "0.5.0"
-puffin = { version = "0.16.0", features = ["serialization"] }
-rayon = "1.8.1"
-roaring = { version = "0.10.2", features = ["serde"] }
-serde = { version = "1.0.195", features = ["derive"] }
-serde_json = { version = "1.0.111", features = ["preserve_order"] }
+page_size = "0.6.0"
+rayon = "1.10.0"
+roaring = { version = "0.10.6", features = ["serde"] }
+serde = { version = "1.0.204", features = ["derive"] }
+serde_json = { version = "1.0.120", features = ["preserve_order"] }
 synchronoise = "1.0.1"
-tempfile = "3.9.0"
-thiserror = "1.0.56"
-time = { version = "0.3.31", features = [
+tempfile = "3.10.1"
+thiserror = "1.0.61"
+time = { version = "0.3.36", features = [
     "serde-well-known",
     "formatting",
     "parsing",
     "macros",
 ] }
 tracing = "0.1.40"
-ureq = "2.9.7"
-uuid = { version = "1.6.1", features = ["serde", "v4"] }
+ureq = "2.10.0"
+uuid = { version = "1.10.0", features = ["serde", "v4"] }
 
 [dev-dependencies]
+arroy = "0.4.0"
 big_s = "1.0.2"
 crossbeam = "0.8.4"
-insta = { version = "1.34.0", features = ["json", "redactions"] }
+insta = { version = "1.39.0", features = ["json", "redactions"] }
+maplit = "1.0.2"
 meili-snap = { path = "../meili-snap" }

index-scheduler/src/autobatcher.rs

@@ -24,6 +24,7 @@ enum AutobatchKind {
         allow_index_creation: bool,
         primary_key: Option<String>,
     },
+    DocumentEdition,
     DocumentDeletion,
     DocumentDeletionByFilter,
     DocumentClear,
@@ -63,6 +64,7 @@ impl From<KindWithContent> for AutobatchKind {
                 primary_key,
                 ..
             } => AutobatchKind::DocumentImport { method, allow_index_creation, primary_key },
+            KindWithContent::DocumentEdition { .. } => AutobatchKind::DocumentEdition,
             KindWithContent::DocumentDeletion { .. } => AutobatchKind::DocumentDeletion,
             KindWithContent::DocumentClear { .. } => AutobatchKind::DocumentClear,
             KindWithContent::DocumentDeletionByFilter { .. } => {
@@ -98,6 +100,9 @@ pub enum BatchKind {
         primary_key: Option<String>,
         operation_ids: Vec<TaskId>,
     },
+    DocumentEdition {
+        id: TaskId,
+    },
     DocumentDeletion {
         deletion_ids: Vec<TaskId>,
     },
@@ -199,6 +204,7 @@ impl BatchKind {
                 }),
                 allow_index_creation,
             ),
+            K::DocumentEdition => (Break(BatchKind::DocumentEdition { id: task_id }), false),
             K::DocumentDeletion => {
                 (Continue(BatchKind::DocumentDeletion { deletion_ids: vec![task_id] }), false)
             }
@@ -222,7 +228,7 @@ impl BatchKind {
 
         match (self, kind) {
             // We don't batch any of these operations
-            (this, K::IndexCreation | K::IndexUpdate | K::IndexSwap | K::DocumentDeletionByFilter) => Break(this),
+            (this, K::IndexCreation | K::IndexUpdate | K::IndexSwap | K::DocumentEdition | K::DocumentDeletionByFilter) => Break(this),
             // We must not batch tasks that don't have the same index creation rights if the index doesn't already exists.
             (this, kind) if !index_already_exists && this.allow_index_creation() == Some(false) && kind.allow_index_creation() == Some(true) => {
                 Break(this)
@@ -519,6 +525,7 @@ impl BatchKind {
                 | BatchKind::IndexDeletion { .. }
                 | BatchKind::IndexUpdate { .. }
                 | BatchKind::IndexSwap { .. }
+                | BatchKind::DocumentEdition { .. }
                 | BatchKind::DocumentDeletionByFilter { .. },
                 _,
             ) => {

index-scheduler/src/batch.rs

@@ -31,7 +31,10 @@ use meilisearch_types::milli::heed::CompactionOption;
 use meilisearch_types::milli::update::{
     IndexDocumentsConfig, IndexDocumentsMethod, IndexerConfig, Settings as MilliSettings,
 };
-use meilisearch_types::milli::{self, Filter};
+use meilisearch_types::milli::vector::parsed_vectors::{
+    ExplicitVectors, VectorOrArrayOfVectors, RESERVED_VECTORS_FIELD_NAME,
+};
+use meilisearch_types::milli::{self, Filter, Object};
 use meilisearch_types::settings::{apply_settings_to_builder, Settings, Unchecked};
 use meilisearch_types::tasks::{Details, IndexSwap, Kind, KindWithContent, Status, Task};
 use meilisearch_types::{compression, Index, VERSION_FILE_NAME};
@@ -103,6 +106,10 @@ pub(crate) enum IndexOperation {
         operations: Vec<DocumentOperation>,
         tasks: Vec<Task>,
     },
+    DocumentEdition {
+        index_uid: String,
+        task: Task,
+    },
     IndexDocumentDeletionByFilter {
         index_uid: String,
         task: Task,
@@ -161,7 +168,8 @@ impl Batch {
                 | IndexOperation::DocumentClear { tasks, .. } => {
                     RoaringBitmap::from_iter(tasks.iter().map(|task| task.uid))
                 }
-                IndexOperation::IndexDocumentDeletionByFilter { task, .. } => {
+                IndexOperation::DocumentEdition { task, .. }
+                | IndexOperation::IndexDocumentDeletionByFilter { task, .. } => {
                     RoaringBitmap::from_sorted_iter(std::iter::once(task.uid)).unwrap()
                 }
                 IndexOperation::SettingsAndDocumentOperation {
@@ -225,6 +233,7 @@ impl IndexOperation {
     pub fn index_uid(&self) -> &str {
         match self {
             IndexOperation::DocumentOperation { index_uid, .. }
+            | IndexOperation::DocumentEdition { index_uid, .. }
             | IndexOperation::IndexDocumentDeletionByFilter { index_uid, .. }
             | IndexOperation::DocumentClear { index_uid, .. }
             | IndexOperation::Settings { index_uid, .. }
@@ -240,6 +249,9 @@ impl fmt::Display for IndexOperation {
             IndexOperation::DocumentOperation { .. } => {
                 f.write_str("IndexOperation::DocumentOperation")
             }
+            IndexOperation::DocumentEdition { .. } => {
+                f.write_str("IndexOperation::DocumentEdition")
+            }
             IndexOperation::IndexDocumentDeletionByFilter { .. } => {
                 f.write_str("IndexOperation::IndexDocumentDeletionByFilter")
             }
@@ -292,6 +304,21 @@ impl IndexScheduler {
                     _ => unreachable!(),
                 }
             }
+            BatchKind::DocumentEdition { id } => {
+                let task = self.get_task(rtxn, id)?.ok_or(Error::CorruptedTaskQueue)?;
+                match &task.kind {
+                    KindWithContent::DocumentEdition { index_uid, .. } => {
+                        Ok(Some(Batch::IndexOperation {
+                            op: IndexOperation::DocumentEdition {
+                                index_uid: index_uid.clone(),
+                                task,
+                            },
+                            must_create_index: false,
+                        }))
+                    }
+                    _ => unreachable!(),
+                }
+            }
             BatchKind::DocumentOperation { method, operation_ids, .. } => {
                 let tasks = self.get_existing_tasks(rtxn, operation_ids)?;
                 let primary_key = tasks
@@ -526,8 +553,6 @@ impl IndexScheduler {
         #[cfg(test)]
         self.maybe_fail(crate::tests::FailureLocation::InsideCreateBatch)?;
 
-        puffin::profile_function!();
-
         let enqueued = &self.get_status(rtxn, Status::Enqueued)?;
         let to_cancel = self.get_kind(rtxn, Kind::TaskCancelation)? & enqueued;
 
@@ -636,8 +661,6 @@ impl IndexScheduler {
             self.breakpoint(crate::Breakpoint::InsideProcessBatch);
         }
 
-        puffin::profile_function!(batch.to_string());
-
         match batch {
             Batch::TaskCancelation { mut task, previous_started_at, previous_processing_tasks } => {
                 // 1. Retrieve the tasks that matched the query at enqueue-time.
@@ -785,10 +808,12 @@ impl IndexScheduler {
                 let dst = temp_snapshot_dir.path().join("auth");
                 fs::create_dir_all(&dst)?;
                 // TODO We can't use the open_auth_store_env function here but we should
-                let auth = milli::heed::EnvOpenOptions::new()
-                    .map_size(1024 * 1024 * 1024) // 1 GiB
-                    .max_dbs(2)
-                    .open(&self.auth_path)?;
+                let auth = unsafe {
+                    milli::heed::EnvOpenOptions::new()
+                        .map_size(1024 * 1024 * 1024) // 1 GiB
+                        .max_dbs(2)
+                        .open(&self.auth_path)
+                }?;
                 auth.copy_to_file(dst.join("data.mdb"), CompactionOption::Enabled)?;
 
                 // 5. Copy and tarball the flat snapshot
@@ -908,14 +933,67 @@ impl IndexScheduler {
 
                     let fields_ids_map = index.fields_ids_map(&rtxn)?;
                     let all_fields: Vec<_> = fields_ids_map.iter().map(|(id, _)| id).collect();
+                    let embedding_configs = index.embedding_configs(&rtxn)?;
 
                     // 3.1. Dump the documents
                     for ret in index.all_documents(&rtxn)? {
                         if self.must_stop_processing.get() {
                             return Err(Error::AbortedTask);
                         }
-                        let (_id, doc) = ret?;
-                        let document = milli::obkv_to_json(&all_fields, &fields_ids_map, doc)?;
+
+                        let (id, doc) = ret?;
+
+                        let mut document = milli::obkv_to_json(&all_fields, &fields_ids_map, doc)?;
+
+                        'inject_vectors: {
+                            let embeddings = index.embeddings(&rtxn, id)?;
+
+                            if embeddings.is_empty() {
+                                break 'inject_vectors;
+                            }
+
+                            let vectors = document
+                                .entry(RESERVED_VECTORS_FIELD_NAME.to_owned())
+                                .or_insert(serde_json::Value::Object(Default::default()));
+
+                            let serde_json::Value::Object(vectors) = vectors else {
+                                return Err(milli::Error::UserError(
+                                    milli::UserError::InvalidVectorsMapType {
+                                        document_id: {
+                                            if let Ok(Some(Ok(index))) = index
+                                                .external_id_of(&rtxn, std::iter::once(id))
+                                                .map(|it| it.into_iter().next())
+                                            {
+                                                index
+                                            } else {
+                                                format!("internal docid={id}")
+                                            }
+                                        },
+                                        value: vectors.clone(),
+                                    },
+                                )
+                                .into());
+                            };
+
+                            for (embedder_name, embeddings) in embeddings {
+                                let user_provided = embedding_configs
+                                    .iter()
+                                    .find(|conf| conf.name == embedder_name)
+                                    .is_some_and(|conf| conf.user_provided.contains(id));
+
+                                let embeddings = ExplicitVectors {
+                                    embeddings: Some(
+                                        VectorOrArrayOfVectors::from_array_of_vectors(embeddings),
+                                    ),
+                                    regenerate: !user_provided,
+                                };
+                                vectors.insert(
+                                    embedder_name,
+                                    serde_json::to_value(embeddings).unwrap(),
+                                );
+                            }
+                        }
+
                         index_dumper.push_document(&document)?;
                     }
 
@@ -1174,8 +1252,6 @@ impl IndexScheduler {
         index: &'i Index,
         operation: IndexOperation,
     ) -> Result<Vec<Task>> {
-        puffin::profile_function!();
-
         match operation {
             IndexOperation::DocumentClear { mut tasks, .. } => {
                 let count = milli::update::ClearDocuments::new(index_wtxn, index).execute()?;
@@ -1205,6 +1281,7 @@ impl IndexScheduler {
                 operations,
                 mut tasks,
             } => {
+                let started_processing_at = std::time::Instant::now();
                 let mut primary_key_has_been_set = false;
                 let must_stop_processing = self.must_stop_processing.clone();
                 let indexer_config = self.index_mapper.indexer_config();
@@ -1319,7 +1396,7 @@ impl IndexScheduler {
 
                 if !tasks.iter().all(|res| res.error.is_some()) {
                     let addition = builder.execute()?;
-                    tracing::info!(indexing_result = ?addition, "document indexing done");
+                    tracing::info!(indexing_result = ?addition, processed_in = ?started_processing_at.elapsed(), "document indexing done");
                 } else if primary_key_has_been_set {
                     // Everything failed but we've set a primary key.
                     // We need to remove it.
@@ -1334,6 +1411,64 @@ impl IndexScheduler {
 
                 Ok(tasks)
             }
+            IndexOperation::DocumentEdition { mut task, .. } => {
+                let (filter, context, function) =
+                    if let KindWithContent::DocumentEdition {
+                        filter_expr, context, function, ..
+                    } = &task.kind
+                    {
+                        (filter_expr, context, function)
+                    } else {
+                        unreachable!()
+                    };
+                let result_count = edit_documents_by_function(
+                    index_wtxn,
+                    filter,
+                    context.clone(),
+                    function,
+                    self.index_mapper.indexer_config(),
+                    self.must_stop_processing.clone(),
+                    index,
+                );
+                let (original_filter, context, function) = if let Some(Details::DocumentEdition {
+                    original_filter,
+                    context,
+                    function,
+                    ..
+                }) = task.details
+                {
+                    (original_filter, context, function)
+                } else {
+                    // In the case of a `documentDeleteByFilter` the details MUST be set
+                    unreachable!();
+                };
+
+                match result_count {
+                    Ok((deleted_documents, edited_documents)) => {
+                        task.status = Status::Succeeded;
+                        task.details = Some(Details::DocumentEdition {
+                            original_filter,
+                            context,
+                            function,
+                            deleted_documents: Some(deleted_documents),
+                            edited_documents: Some(edited_documents),
+                        });
+                    }
+                    Err(e) => {
+                        task.status = Status::Failed;
+                        task.details = Some(Details::DocumentEdition {
+                            original_filter,
+                            context,
+                            function,
+                            deleted_documents: Some(0),
+                            edited_documents: Some(0),
+                        });
+                        task.error = Some(e.into());
+                    }
+                }
+
+                Ok(vec![task])
+            }
             IndexOperation::IndexDocumentDeletionByFilter { mut task, index_uid: _ } => {
                 let filter =
                     if let KindWithContent::DocumentDeletionByFilter { filter_expr, .. } =
@@ -1622,3 +1757,44 @@ fn delete_document_by_filter<'a>(
         0
     })
 }
+
+fn edit_documents_by_function<'a>(
+    wtxn: &mut RwTxn<'a>,
+    filter: &Option<serde_json::Value>,
+    context: Option<Object>,
+    code: &str,
+    indexer_config: &IndexerConfig,
+    must_stop_processing: MustStopProcessing,
+    index: &'a Index,
+) -> Result<(u64, u64)> {
+    let candidates = match filter.as_ref().map(Filter::from_json) {
+        Some(Ok(Some(filter))) => filter.evaluate(wtxn, index).map_err(|err| match err {
+            milli::Error::UserError(milli::UserError::InvalidFilter(_)) => {
+                Error::from(err).with_custom_error_code(Code::InvalidDocumentFilter)
+            }
+            e => e.into(),
+        })?,
+        None | Some(Ok(None)) => index.documents_ids(wtxn)?,
+        Some(Err(e)) => return Err(e.into()),
+    };
+
+    let config = IndexDocumentsConfig {
+        update_method: IndexDocumentsMethod::ReplaceDocuments,
+        ..Default::default()
+    };
+
+    let mut builder = milli::update::IndexDocuments::new(
+        wtxn,
+        index,
+        indexer_config,
+        config,
+        |indexing_step| tracing::debug!(update = ?indexing_step),
+        || must_stop_processing.get(),
+    )?;
+
+    let (new_builder, count) = builder.edit_documents(&candidates, context, code)?;
+    builder = new_builder;
+
+    let _ = builder.execute()?;
+    Ok(count.unwrap())
+}

index-scheduler/src/features.rs

@@ -69,14 +69,27 @@ impl RoFeatures {
         }
     }
 
-    pub fn check_puffin(&self) -> Result<()> {
-        if self.runtime.export_puffin_reports {
+    pub fn check_edit_documents_by_function(&self, disabled_action: &'static str) -> Result<()> {
+        if self.runtime.edit_documents_by_function {
             Ok(())
         } else {
             Err(FeatureNotEnabledError {
-                disabled_action: "Outputting Puffin reports to disk",
-                feature: "export puffin reports",
-                issue_link: "https://github.com/meilisearch/product/discussions/693",
+                disabled_action,
+                feature: "edit documents by function",
+                issue_link: "https://github.com/orgs/meilisearch/discussions/762",
+            }
+            .into())
+        }
+    }
+
+    pub fn check_contains_filter(&self) -> Result<()> {
+        if self.runtime.contains_filter {
+            Ok(())
+        } else {
+            Err(FeatureNotEnabledError {
+                disabled_action: "Using `CONTAINS` in a filter",
+                feature: "contains filter",
+                issue_link: "https://github.com/orgs/meilisearch/discussions/763",
             }
             .into())
         }
@@ -92,9 +105,11 @@ impl FeatureData {
         let txn = env.read_txn()?;
         let persisted_features: RuntimeTogglableFeatures =
             runtime_features_db.get(&txn, EXPERIMENTAL_FEATURES)?.unwrap_or_default();
+        let InstanceTogglableFeatures { metrics, logs_route, contains_filter } = instance_features;
         let runtime = Arc::new(RwLock::new(RuntimeTogglableFeatures {
-            metrics: instance_features.metrics || persisted_features.metrics,
-            logs_route: instance_features.logs_route || persisted_features.logs_route,
+            metrics: metrics || persisted_features.metrics,
+            logs_route: logs_route || persisted_features.logs_route,
+            contains_filter: contains_filter || persisted_features.contains_filter,
             ..persisted_features
         }));
 

index-scheduler/src/insta_snapshot.rs

@@ -32,7 +32,6 @@ pub fn snapshot_index_scheduler(scheduler: &IndexScheduler) -> String {
         features: _,
         max_number_of_tasks: _,
         max_number_of_batched_tasks: _,
-        puffin_frame: _,
         wake_up: _,
         dumps_path: _,
         snapshots_path: _,
@@ -178,6 +177,17 @@ fn snapshot_details(d: &Details) -> String {
         } => {
             format!("{{ received_documents: {received_documents}, indexed_documents: {indexed_documents:?} }}")
         }
+        Details::DocumentEdition {
+            deleted_documents,
+            edited_documents,
+            original_filter,
+            context,
+            function,
+        } => {
+            format!(
+                "{{ deleted_documents: {deleted_documents:?}, edited_documents: {edited_documents:?}, context: {context:?}, function: {function:?}, original_filter: {original_filter:?} }}"
+            )
+        }
         Details::SettingsUpdate { settings } => {
             format!("{{ settings: {settings:?} }}")
         }

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

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

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

@@ -0,0 +1,20 @@
+---
+source: index-scheduler/src/lib.rs
+expression: task.details
+---
+{
+  "embedders": {
+    "A_fakerest": {
+      "source": "rest",
+      "apiKey": "MyXXXX...",
+      "dimensions": 384,
+      "url": "http://localhost:7777"
+    },
+    "B_small_hf": {
+      "source": "huggingFace",
+      "model": "sentence-transformers/all-MiniLM-L6-v2",
+      "revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
+      "documentTemplate": "{{doc.doggo}} the {{doc.breed}} best doggo"
+    }
+  }
+}

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

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

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

@@ -0,0 +1,23 @@
+---
+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",
+    "query": null,
+    "input_field": [
+      "input"
+    ],
+    "path_to_embeddings": [
+      "data"
+    ],
+    "embedding_object": [
+      "embedding"
+    ],
+    "input_type": "text"
+  }
+}

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

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

index-scheduler/src/snapshots/index_scheduler__tests__import_vectors.snap

@@ -0,0 +1,20 @@
+---
+source: index-scheduler/src/lib.rs
+expression: task.details
+---
+{
+  "embedders": {
+    "A_fakerest": {
+      "source": "rest",
+      "apiKey": "MyXXXX...",
+      "dimensions": 384,
+      "url": "http://localhost:7777"
+    },
+    "B_small_hf": {
+      "source": "huggingFace",
+      "model": "sentence-transformers/all-MiniLM-L6-v2",
+      "revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
+      "documentTemplate": "{{doc.doggo}} the {{doc.breed}} best doggo"
+    }
+  }
+}

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

@@ -0,0 +1,49 @@
+---
+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), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: 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, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: 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), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: 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, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: 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:
+
+----------------------------------------------------------------------
+

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

@@ -0,0 +1,48 @@
+---
+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), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: 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, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: 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), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: 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, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: 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
+
+----------------------------------------------------------------------
+

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

@@ -0,0 +1,45 @@
+---
+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), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: 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, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: 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), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: 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, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: 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:
+
+----------------------------------------------------------------------
+

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

@@ -0,0 +1,44 @@
+---
+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), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: 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, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: 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), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: 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, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: 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
+
+----------------------------------------------------------------------
+

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

@@ -0,0 +1,36 @@
+---
+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), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: 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, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: 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), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: 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, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: 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:
+
+----------------------------------------------------------------------
+

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

@@ -0,0 +1,40 @@
+---
+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), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: 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, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: 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), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: 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, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: 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:
+
+----------------------------------------------------------------------
+

index-scheduler/src/utils.rs

@@ -238,6 +238,7 @@ pub fn swap_index_uid_in_task(task: &mut Task, swap: (&str, &str)) {
     let mut index_uids = vec![];
     match &mut task.kind {
         K::DocumentAdditionOrUpdate { index_uid, .. } => index_uids.push(index_uid),
+        K::DocumentEdition { index_uid, .. } => index_uids.push(index_uid),
         K::DocumentDeletion { index_uid, .. } => index_uids.push(index_uid),
         K::DocumentDeletionByFilter { index_uid, .. } => index_uids.push(index_uid),
         K::DocumentClear { index_uid } => index_uids.push(index_uid),
@@ -272,9 +273,9 @@ pub fn swap_index_uid_in_task(task: &mut Task, swap: (&str, &str)) {
     }
     for index_uid in index_uids {
         if index_uid == swap.0 {
-            *index_uid = swap.1.to_owned();
+            swap.1.clone_into(index_uid);
         } else if index_uid == swap.1 {
-            *index_uid = swap.0.to_owned();
+            swap.0.clone_into(index_uid);
         }
     }
 }
@@ -408,7 +409,26 @@ impl IndexScheduler {
                                 match status {
                                     Status::Succeeded => assert!(indexed_documents <= received_documents),
                                     Status::Failed | Status::Canceled => assert_eq!(indexed_documents, 0),
-                                    status => panic!("DocumentAddition can't have an indexed_document set if it's {}", status),
+                                    status => panic!("DocumentAddition can't have an indexed_documents set if it's {}", status),
+                                }
+                            }
+                            None => {
+                                assert!(matches!(status, Status::Enqueued | Status::Processing))
+                            }
+                        }
+                    }
+                    Details::DocumentEdition { edited_documents, .. } => {
+                        assert_eq!(kind.as_kind(), Kind::DocumentEdition);
+                        match edited_documents {
+                            Some(edited_documents) => {
+                                assert!(matches!(
+                                    status,
+                                    Status::Succeeded | Status::Failed | Status::Canceled
+                                ));
+                                match status {
+                                    Status::Succeeded => (),
+                                    Status::Failed | Status::Canceled => assert_eq!(edited_documents, 0),
+                                    status => panic!("DocumentEdition can't have an edited_documents set if it's {}", status),
                                 }
                             }
                             None => {

meili-snap/Cargo.toml

@@ -11,6 +11,6 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-insta = { version = "^1.34.0", features = ["json", "redactions"] }
+insta = { version = "^1.39.0", features = ["json", "redactions"] }
 md5 = "0.7.0"
 once_cell = "1.19"

meilisearch-auth/Cargo.toml

@@ -11,16 +11,16 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-base64 = "0.21.7"
-enum-iterator = "1.5.0"
+base64 = "0.22.1"
+enum-iterator = "2.1.0"
 hmac = "0.12.1"
 maplit = "1.0.2"
 meilisearch-types = { path = "../meilisearch-types" }
 rand = "0.8.5"
-roaring = { version = "0.10.2", features = ["serde"] }
-serde = { version = "1.0.195", features = ["derive"] }
-serde_json = { version = "1.0.111", features = ["preserve_order"] }
+roaring = { version = "0.10.6", features = ["serde"] }
+serde = { version = "1.0.204", features = ["derive"] }
+serde_json = { version = "1.0.120", features = ["preserve_order"] }
 sha2 = "0.10.8"
-thiserror = "1.0.56"
-time = { version = "0.3.31", features = ["serde-well-known", "formatting", "parsing", "macros"] }
-uuid = { version = "1.6.1", features = ["serde", "v4"] }
+thiserror = "1.0.61"
+time = { version = "0.3.36", features = ["serde-well-known", "formatting", "parsing", "macros"] }
+uuid = { version = "1.10.0", features = ["serde", "v4"] }

meilisearch-auth/src/lib.rs

@@ -188,6 +188,12 @@ impl AuthFilter {
         self.allow_index_creation && self.is_index_authorized(index)
     }
 
+    #[inline]
+    /// Return true if a tenant token was used to generate the search rules.
+    pub fn is_tenant_token(&self) -> bool {
+        self.search_rules.is_some()
+    }
+
     pub fn with_allowed_indexes(allowed_indexes: HashSet<IndexUidPattern>) -> Self {
         Self {
             search_rules: None,
@@ -205,6 +211,7 @@ impl AuthFilter {
                 .unwrap_or(true)
     }
 
+    /// Check if the index is authorized by the API key and the tenant token.
     pub fn is_index_authorized(&self, index: &str) -> bool {
         self.key_authorized_indexes.is_index_authorized(index)
             && self
@@ -214,6 +221,44 @@ impl AuthFilter {
                 .unwrap_or(true)
     }
 
+    /// Only check if the index is authorized by the API key
+    pub fn api_key_is_index_authorized(&self, index: &str) -> bool {
+        self.key_authorized_indexes.is_index_authorized(index)
+    }
+
+    /// Only check if the index is authorized by the tenant token
+    pub fn tenant_token_is_index_authorized(&self, index: &str) -> bool {
+        self.search_rules
+            .as_ref()
+            .map(|search_rules| search_rules.is_index_authorized(index))
+            .unwrap_or(true)
+    }
+
+    /// Return the list of authorized indexes by the tenant token if any
+    pub fn tenant_token_list_index_authorized(&self) -> Vec<String> {
+        match self.search_rules {
+            Some(ref search_rules) => {
+                let mut indexes: Vec<_> = match search_rules {
+                    SearchRules::Set(set) => set.iter().map(|s| s.to_string()).collect(),
+                    SearchRules::Map(map) => map.keys().map(|s| s.to_string()).collect(),
+                };
+                indexes.sort_unstable();
+                indexes
+            }
+            None => Vec::new(),
+        }
+    }
+
+    /// Return the list of authorized indexes by the api key if any
+    pub fn api_key_list_index_authorized(&self) -> Vec<String> {
+        let mut indexes: Vec<_> = match self.key_authorized_indexes {
+            SearchRules::Set(ref set) => set.iter().map(|s| s.to_string()).collect(),
+            SearchRules::Map(ref map) => map.keys().map(|s| s.to_string()).collect(),
+        };
+        indexes.sort_unstable();
+        indexes
+    }
+
     pub fn get_index_search_rules(&self, index: &str) -> Option<IndexSearchRules> {
         if !self.is_index_authorized(index) {
             return None;

meilisearch-auth/src/store.rs

@@ -49,7 +49,7 @@ pub fn open_auth_store_env(path: &Path) -> milli::heed::Result<milli::heed::Env>
     let mut options = EnvOpenOptions::new();
     options.map_size(AUTH_STORE_SIZE); // 1GB
     options.max_dbs(2);
-    options.open(path)
+    unsafe { options.open(path) }
 }
 
 impl HeedAuthStore {

meilisearch-types/Cargo.toml

@@ -11,31 +11,36 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-actix-web = { version = "4.5.1", default-features = false }
-anyhow = "1.0.79"
+actix-web = { version = "4.8.0", default-features = false }
+anyhow = "1.0.86"
 convert_case = "0.6.0"
 csv = "1.3.0"
-deserr = { version = "0.6.1", features = ["actix-web"] }
-either = { version = "1.9.0", features = ["serde"] }
-enum-iterator = "1.5.0"
+deserr = { version = "0.6.2", features = ["actix-web"] }
+either = { version = "1.13.0", features = ["serde"] }
+enum-iterator = "2.1.0"
 file-store = { path = "../file-store" }
-flate2 = "1.0.28"
+flate2 = "1.0.30"
 fst = "0.4.7"
-memmap2 = "0.7.1"
+memmap2 = "0.9.4"
 milli = { path = "../milli" }
-roaring = { version = "0.10.2", features = ["serde"] }
-serde = { version = "1.0.195", features = ["derive"] }
+roaring = { version = "0.10.6", features = ["serde"] }
+serde = { version = "1.0.204", features = ["derive"] }
 serde-cs = "0.2.4"
-serde_json = "1.0.111"
-tar = "0.4.40"
-tempfile = "3.9.0"
-thiserror = "1.0.56"
-time = { version = "0.3.31", features = ["serde-well-known", "formatting", "parsing", "macros"] }
-tokio = "1.35"
-uuid = { version = "1.6.1", features = ["serde", "v4"] }
+serde_json = "1.0.120"
+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 = "1.38"
+uuid = { version = "1.10.0", features = ["serde", "v4"] }
 
 [dev-dependencies]
-insta = "1.34.0"
+insta = "1.39.0"
 meili-snap = { path = "../meili-snap" }
 
 [features]
@@ -49,6 +54,8 @@ chinese-pinyin = ["milli/chinese-pinyin"]
 hebrew = ["milli/hebrew"]
 # japanese specialized tokenization
 japanese = ["milli/japanese"]
+# korean specialized tokenization
+korean = ["milli/korean"]
 # thai specialized tokenization
 thai = ["milli/thai"]
 # allow greek specialized tokenization

meilisearch-types/src/deserr/mod.rs

@@ -155,6 +155,10 @@ make_missing_field_convenience_builder!(
     MissingFacetSearchFacetName,
     missing_facet_search_facet_name
 );
+make_missing_field_convenience_builder!(
+    MissingDocumentEditionFunction,
+    missing_document_edition_function
+);
 
 // Integrate a sub-error into a [`DeserrError`] by taking its error message but using
 // the default error code (C) from `Self`
@@ -188,4 +192,8 @@ merge_with_error_impl_take_error_message!(ParseOffsetDateTimeError);
 merge_with_error_impl_take_error_message!(ParseTaskKindError);
 merge_with_error_impl_take_error_message!(ParseTaskStatusError);
 merge_with_error_impl_take_error_message!(IndexUidFormatError);
+merge_with_error_impl_take_error_message!(InvalidMultiSearchWeight);
 merge_with_error_impl_take_error_message!(InvalidSearchSemanticRatio);
+merge_with_error_impl_take_error_message!(InvalidSearchRankingScoreThreshold);
+merge_with_error_impl_take_error_message!(InvalidSimilarRankingScoreThreshold);
+merge_with_error_impl_take_error_message!(InvalidSimilarId);

meilisearch-types/src/error.rs

@@ -222,7 +222,9 @@ InvalidApiKeyUid                      , InvalidRequest       , BAD_REQUEST ;
 InvalidContentType                    , InvalidRequest       , UNSUPPORTED_MEDIA_TYPE ;
 InvalidDocumentCsvDelimiter           , InvalidRequest       , BAD_REQUEST ;
 InvalidDocumentFields                 , InvalidRequest       , BAD_REQUEST ;
+InvalidDocumentRetrieveVectors        , InvalidRequest       , BAD_REQUEST ;
 MissingDocumentFilter                 , InvalidRequest       , BAD_REQUEST ;
+MissingDocumentEditionFunction        , InvalidRequest       , BAD_REQUEST ;
 InvalidDocumentFilter                 , InvalidRequest       , BAD_REQUEST ;
 InvalidDocumentGeoField               , InvalidRequest       , BAD_REQUEST ;
 InvalidVectorDimensions               , InvalidRequest       , BAD_REQUEST ;
@@ -236,21 +238,35 @@ InvalidIndexLimit                     , InvalidRequest       , BAD_REQUEST ;
 InvalidIndexOffset                    , InvalidRequest       , BAD_REQUEST ;
 InvalidIndexPrimaryKey                , InvalidRequest       , BAD_REQUEST ;
 InvalidIndexUid                       , InvalidRequest       , BAD_REQUEST ;
+InvalidMultiSearchFederated           , InvalidRequest       , BAD_REQUEST ;
+InvalidMultiSearchFederationOptions   , InvalidRequest       , BAD_REQUEST ;
+InvalidMultiSearchQueryPagination     , InvalidRequest       , BAD_REQUEST ;
+InvalidMultiSearchQueryRankingRules   , InvalidRequest       , BAD_REQUEST ;
+InvalidMultiSearchWeight              , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchAttributesToSearchOn     , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchAttributesToCrop         , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchAttributesToHighlight    , InvalidRequest       , BAD_REQUEST ;
+InvalidSimilarAttributesToRetrieve    , InvalidRequest       , BAD_REQUEST ;
+InvalidSimilarRetrieveVectors         , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchAttributesToRetrieve     , InvalidRequest       , BAD_REQUEST ;
+InvalidSearchRankingScoreThreshold    , InvalidRequest       , BAD_REQUEST ;
+InvalidSimilarRankingScoreThreshold   , InvalidRequest       , BAD_REQUEST ;
+InvalidSearchRetrieveVectors          , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchCropLength               , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchCropMarker               , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchFacets                   , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchSemanticRatio            , InvalidRequest       , BAD_REQUEST ;
 InvalidFacetSearchFacetName           , InvalidRequest       , BAD_REQUEST ;
+InvalidSimilarId                      , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchFilter                   , InvalidRequest       , BAD_REQUEST ;
+InvalidSimilarFilter                  , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchHighlightPostTag         , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchHighlightPreTag          , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchHitsPerPage              , InvalidRequest       , BAD_REQUEST ;
+InvalidSimilarLimit                   , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchLimit                    , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchMatchingStrategy         , InvalidRequest       , BAD_REQUEST ;
+InvalidSimilarOffset                  , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchOffset                   , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchPage                     , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchQ                        , InvalidRequest       , BAD_REQUEST ;
@@ -259,15 +275,18 @@ InvalidFacetSearchName                , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchVector                   , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchShowMatchesPosition      , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchShowRankingScore         , InvalidRequest       , BAD_REQUEST ;
+InvalidSimilarShowRankingScore        , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchShowRankingScoreDetails  , InvalidRequest       , BAD_REQUEST ;
+InvalidSimilarShowRankingScoreDetails , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchSort                     , InvalidRequest       , BAD_REQUEST ;
+InvalidSearchDistinct                 , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsDisplayedAttributes    , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsDistinctAttribute      , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsProximityPrecision     , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsFaceting               , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsFilterableAttributes   , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsPagination             , InvalidRequest       , BAD_REQUEST ;
-InvalidSettingsSearchCutoffMs           , InvalidRequest       , BAD_REQUEST ;
+InvalidSettingsSearchCutoffMs         , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsEmbedders              , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsRankingRules           , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsSearchableAttributes   , InvalidRequest       , BAD_REQUEST ;
@@ -322,7 +341,11 @@ UnretrievableErrorCode                , InvalidRequest       , BAD_REQUEST ;
 UnsupportedMediaType                  , InvalidRequest       , UNSUPPORTED_MEDIA_TYPE ;
 
 // Experimental features
-VectorEmbeddingError                  , InvalidRequest       , BAD_REQUEST
+VectorEmbeddingError                  , InvalidRequest       , BAD_REQUEST ;
+NotFoundSimilarId                     , InvalidRequest       , BAD_REQUEST ;
+InvalidDocumentEditionContext         , InvalidRequest       , BAD_REQUEST ;
+InvalidDocumentEditionFunctionFilter  , InvalidRequest       , BAD_REQUEST ;
+EditDocumentsByFunctionError          , InvalidRequest       , BAD_REQUEST
 }
 
 impl ErrorCode for JoinError {
@@ -371,6 +394,7 @@ impl ErrorCode for milli::Error {
                         Code::IndexPrimaryKeyMultipleCandidatesFound
                     }
                     UserError::PrimaryKeyCannotBeChanged(_) => Code::IndexPrimaryKeyAlreadyExists,
+                    UserError::InvalidDistinctAttribute { .. } => Code::InvalidSearchDistinct,
                     UserError::SortRankingRuleMissing => Code::InvalidSearchSort,
                     UserError::InvalidFacetsDistribution { .. } => Code::InvalidSearchFacets,
                     UserError::InvalidSortableAttribute { .. } => Code::InvalidSearchSort,
@@ -383,15 +407,23 @@ impl ErrorCode for milli::Error {
                     UserError::CriterionError(_) => Code::InvalidSettingsRankingRules,
                     UserError::InvalidGeoField { .. } => Code::InvalidDocumentGeoField,
                     UserError::InvalidVectorDimensions { .. } => Code::InvalidVectorDimensions,
-                    UserError::InvalidVectorsMapType { .. } => Code::InvalidVectorsType,
-                    UserError::InvalidVectorsType { .. } => Code::InvalidVectorsType,
+                    UserError::InvalidVectorsMapType { .. }
+                    | UserError::InvalidVectorsEmbedderConf { .. } => Code::InvalidVectorsType,
                     UserError::TooManyVectors(_, _) => Code::TooManyVectors,
                     UserError::SortError(_) => Code::InvalidSearchSort,
                     UserError::InvalidMinTypoWordLenSetting(_, _) => {
                         Code::InvalidSettingsTypoTolerance
                     }
                     UserError::InvalidEmbedder(_) => Code::InvalidEmbedder,
-                    UserError::VectorEmbeddingError(_) => Code::VectorEmbeddingError,
+                    UserError::VectorEmbeddingError(_) | UserError::DocumentEmbeddingError(_) => {
+                        Code::VectorEmbeddingError
+                    }
+                    UserError::DocumentEditionCannotModifyPrimaryKey
+                    | UserError::DocumentEditionDocumentMustBeObject
+                    | UserError::DocumentEditionRuntimeError(_)
+                    | UserError::DocumentEditionCompilationError(_) => {
+                        Code::EditDocumentsByFunctionError
+                    }
                 }
             }
         }
@@ -423,7 +455,6 @@ impl ErrorCode for HeedError {
             HeedError::Mdb(_)
             | HeedError::Encoding(_)
             | HeedError::Decoding(_)
-            | HeedError::InvalidDatabaseTyping
             | HeedError::DatabaseClosing
             | HeedError::BadOpenOptions { .. } => Code::Internal,
         }
@@ -488,6 +519,38 @@ impl fmt::Display for deserr_codes::InvalidSearchSemanticRatio {
     }
 }
 
+impl fmt::Display for deserr_codes::InvalidMultiSearchWeight {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        write!(f, "the value of `weight` is invalid, expected a positive float (>= 0.0).")
+    }
+}
+
+impl fmt::Display for deserr_codes::InvalidSimilarId {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        write!(
+            f,
+            "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 (_)."
+        )
+    }
+}
+
+impl fmt::Display for deserr_codes::InvalidSearchRankingScoreThreshold {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        write!(
+            f,
+            "the value of `rankingScoreThreshold` is invalid, expected a float between `0.0` and `1.0`."
+        )
+    }
+}
+
+impl fmt::Display for deserr_codes::InvalidSimilarRankingScoreThreshold {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        deserr_codes::InvalidSearchRankingScoreThreshold.fmt(f)
+    }
+}
+
 #[macro_export]
 macro_rules! internal_error {
     ($target:ty : $($other:path), *) => {

meilisearch-types/src/features.rs

@@ -6,11 +6,13 @@ pub struct RuntimeTogglableFeatures {
     pub vector_store: bool,
     pub metrics: bool,
     pub logs_route: bool,
-    pub export_puffin_reports: bool,
+    pub edit_documents_by_function: bool,
+    pub contains_filter: bool,
 }
 
 #[derive(Default, Debug, Clone, Copy)]
 pub struct InstanceTogglableFeatures {
     pub metrics: bool,
     pub logs_route: bool,
+    pub contains_filter: bool,
 }

meilisearch-types/src/settings.rs

@@ -8,6 +8,7 @@ use std::str::FromStr;
 
 use deserr::{DeserializeError, Deserr, ErrorKind, MergeWithError, ValuePointerRef};
 use fst::IntoStreamer;
+use milli::index::IndexEmbeddingConfig;
 use milli::proximity::ProximityPrecision;
 use milli::update::Setting;
 use milli::{Criterion, CriterionError, Index, DEFAULT_VALUES_PER_FACET};
@@ -672,7 +673,7 @@ pub fn settings(
     let embedders: BTreeMap<_, _> = index
         .embedding_configs(rtxn)?
         .into_iter()
-        .map(|(name, config)| (name, Setting::Set(config.into())))
+        .map(|IndexEmbeddingConfig { name, config, .. }| (name, Setting::Set(config.into())))
         .collect();
     let embedders = if embedders.is_empty() { Setting::NotSet } else { Setting::Set(embedders) };
 

meilisearch-types/src/task_view.rs

@@ -1,3 +1,4 @@
+use milli::Object;
 use serde::Serialize;
 use time::{Duration, OffsetDateTime};
 
@@ -54,6 +55,8 @@ pub struct DetailsView {
     #[serde(skip_serializing_if = "Option::is_none")]
     pub indexed_documents: Option<Option<u64>>,
     #[serde(skip_serializing_if = "Option::is_none")]
+    pub edited_documents: Option<Option<u64>>,
+    #[serde(skip_serializing_if = "Option::is_none")]
     pub primary_key: Option<Option<String>>,
     #[serde(skip_serializing_if = "Option::is_none")]
     pub provided_ids: Option<usize>,
@@ -70,6 +73,10 @@ pub struct DetailsView {
     #[serde(skip_serializing_if = "Option::is_none")]
     pub dump_uid: Option<Option<String>>,
     #[serde(skip_serializing_if = "Option::is_none")]
+    pub context: Option<Option<Object>>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub function: Option<String>,
+    #[serde(skip_serializing_if = "Option::is_none")]
     #[serde(flatten)]
     pub settings: Option<Box<Settings<Unchecked>>>,
     #[serde(skip_serializing_if = "Option::is_none")]
@@ -86,6 +93,20 @@ impl From<Details> for DetailsView {
                     ..DetailsView::default()
                 }
             }
+            Details::DocumentEdition {
+                deleted_documents,
+                edited_documents,
+                original_filter,
+                context,
+                function,
+            } => DetailsView {
+                deleted_documents: Some(deleted_documents),
+                edited_documents: Some(edited_documents),
+                original_filter: Some(original_filter),
+                context: Some(context),
+                function: Some(function),
+                ..DetailsView::default()
+            },
             Details::SettingsUpdate { mut settings } => {
                 settings.hide_secrets();
                 DetailsView { settings: Some(settings), ..DetailsView::default() }

meilisearch-types/src/tasks.rs

@@ -5,6 +5,7 @@ use std::str::FromStr;
 
 use enum_iterator::Sequence;
 use milli::update::IndexDocumentsMethod;
+use milli::Object;
 use roaring::RoaringBitmap;
 use serde::{Deserialize, Serialize, Serializer};
 use time::{Duration, OffsetDateTime};
@@ -48,6 +49,7 @@ impl Task {
             | TaskDeletion { .. }
             | IndexSwap { .. } => None,
             DocumentAdditionOrUpdate { index_uid, .. }
+            | DocumentEdition { index_uid, .. }
             | DocumentDeletion { index_uid, .. }
             | DocumentDeletionByFilter { index_uid, .. }
             | DocumentClear { index_uid }
@@ -67,7 +69,8 @@ impl Task {
     pub fn content_uuid(&self) -> Option<Uuid> {
         match self.kind {
             KindWithContent::DocumentAdditionOrUpdate { content_file, .. } => Some(content_file),
-            KindWithContent::DocumentDeletion { .. }
+            KindWithContent::DocumentEdition { .. }
+            | KindWithContent::DocumentDeletion { .. }
             | KindWithContent::DocumentDeletionByFilter { .. }
             | KindWithContent::DocumentClear { .. }
             | KindWithContent::SettingsUpdate { .. }
@@ -102,6 +105,12 @@ pub enum KindWithContent {
         index_uid: String,
         filter_expr: serde_json::Value,
     },
+    DocumentEdition {
+        index_uid: String,
+        filter_expr: Option<serde_json::Value>,
+        context: Option<milli::Object>,
+        function: String,
+    },
     DocumentClear {
         index_uid: String,
     },
@@ -150,6 +159,7 @@ impl KindWithContent {
     pub fn as_kind(&self) -> Kind {
         match self {
             KindWithContent::DocumentAdditionOrUpdate { .. } => Kind::DocumentAdditionOrUpdate,
+            KindWithContent::DocumentEdition { .. } => Kind::DocumentEdition,
             KindWithContent::DocumentDeletion { .. } => Kind::DocumentDeletion,
             KindWithContent::DocumentDeletionByFilter { .. } => Kind::DocumentDeletion,
             KindWithContent::DocumentClear { .. } => Kind::DocumentDeletion,
@@ -174,6 +184,7 @@ impl KindWithContent {
             | TaskCancelation { .. }
             | TaskDeletion { .. } => vec![],
             DocumentAdditionOrUpdate { index_uid, .. }
+            | DocumentEdition { index_uid, .. }
             | DocumentDeletion { index_uid, .. }
             | DocumentDeletionByFilter { index_uid, .. }
             | DocumentClear { index_uid }
@@ -202,6 +213,15 @@ impl KindWithContent {
                     indexed_documents: None,
                 })
             }
+            KindWithContent::DocumentEdition { index_uid: _, filter_expr, context, function } => {
+                Some(Details::DocumentEdition {
+                    deleted_documents: None,
+                    edited_documents: None,
+                    original_filter: filter_expr.as_ref().map(|v| v.to_string()),
+                    context: context.clone(),
+                    function: function.clone(),
+                })
+            }
             KindWithContent::DocumentDeletion { index_uid: _, documents_ids } => {
                 Some(Details::DocumentDeletion {
                     provided_ids: documents_ids.len(),
@@ -250,6 +270,15 @@ impl KindWithContent {
                     indexed_documents: Some(0),
                 })
             }
+            KindWithContent::DocumentEdition { index_uid: _, filter_expr, context, function } => {
+                Some(Details::DocumentEdition {
+                    deleted_documents: Some(0),
+                    edited_documents: Some(0),
+                    original_filter: filter_expr.as_ref().map(|v| v.to_string()),
+                    context: context.clone(),
+                    function: function.clone(),
+                })
+            }
             KindWithContent::DocumentDeletion { index_uid: _, documents_ids } => {
                 Some(Details::DocumentDeletion {
                     provided_ids: documents_ids.len(),
@@ -301,6 +330,7 @@ impl From<&KindWithContent> for Option<Details> {
                     indexed_documents: None,
                 })
             }
+            KindWithContent::DocumentEdition { .. } => None,
             KindWithContent::DocumentDeletion { .. } => None,
             KindWithContent::DocumentDeletionByFilter { .. } => None,
             KindWithContent::DocumentClear { .. } => None,
@@ -394,6 +424,7 @@ impl std::error::Error for ParseTaskStatusError {}
 #[serde(rename_all = "camelCase")]
 pub enum Kind {
     DocumentAdditionOrUpdate,
+    DocumentEdition,
     DocumentDeletion,
     SettingsUpdate,
     IndexCreation,
@@ -410,6 +441,7 @@ impl Kind {
     pub fn related_to_one_index(&self) -> bool {
         match self {
             Kind::DocumentAdditionOrUpdate
+            | Kind::DocumentEdition
             | Kind::DocumentDeletion
             | Kind::SettingsUpdate
             | Kind::IndexCreation
@@ -427,6 +459,7 @@ impl Display for Kind {
     fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
         match self {
             Kind::DocumentAdditionOrUpdate => write!(f, "documentAdditionOrUpdate"),
+            Kind::DocumentEdition => write!(f, "documentEdition"),
             Kind::DocumentDeletion => write!(f, "documentDeletion"),
             Kind::SettingsUpdate => write!(f, "settingsUpdate"),
             Kind::IndexCreation => write!(f, "indexCreation"),
@@ -454,6 +487,8 @@ impl FromStr for Kind {
             Ok(Kind::IndexDeletion)
         } else if kind.eq_ignore_ascii_case("documentAdditionOrUpdate") {
             Ok(Kind::DocumentAdditionOrUpdate)
+        } else if kind.eq_ignore_ascii_case("documentEdition") {
+            Ok(Kind::DocumentEdition)
         } else if kind.eq_ignore_ascii_case("documentDeletion") {
             Ok(Kind::DocumentDeletion)
         } else if kind.eq_ignore_ascii_case("settingsUpdate") {
@@ -495,16 +530,50 @@ impl std::error::Error for ParseTaskKindError {}
 
 #[derive(Debug, PartialEq, Eq, Clone, Serialize, Deserialize)]
 pub enum Details {
-    DocumentAdditionOrUpdate { received_documents: u64, indexed_documents: Option<u64> },
-    SettingsUpdate { settings: Box<Settings<Unchecked>> },
-    IndexInfo { primary_key: Option<String> },
-    DocumentDeletion { provided_ids: usize, deleted_documents: Option<u64> },
-    DocumentDeletionByFilter { original_filter: String, deleted_documents: Option<u64> },
-    ClearAll { deleted_documents: Option<u64> },
-    TaskCancelation { matched_tasks: u64, canceled_tasks: Option<u64>, original_filter: String },
-    TaskDeletion { matched_tasks: u64, deleted_tasks: Option<u64>, original_filter: String },
-    Dump { dump_uid: Option<String> },
-    IndexSwap { swaps: Vec<IndexSwap> },
+    DocumentAdditionOrUpdate {
+        received_documents: u64,
+        indexed_documents: Option<u64>,
+    },
+    SettingsUpdate {
+        settings: Box<Settings<Unchecked>>,
+    },
+    IndexInfo {
+        primary_key: Option<String>,
+    },
+    DocumentDeletion {
+        provided_ids: usize,
+        deleted_documents: Option<u64>,
+    },
+    DocumentDeletionByFilter {
+        original_filter: String,
+        deleted_documents: Option<u64>,
+    },
+    DocumentEdition {
+        deleted_documents: Option<u64>,
+        edited_documents: Option<u64>,
+        original_filter: Option<String>,
+        context: Option<Object>,
+        function: String,
+    },
+    ClearAll {
+        deleted_documents: Option<u64>,
+    },
+    TaskCancelation {
+        matched_tasks: u64,
+        canceled_tasks: Option<u64>,
+        original_filter: String,
+    },
+    TaskDeletion {
+        matched_tasks: u64,
+        deleted_tasks: Option<u64>,
+        original_filter: String,
+    },
+    Dump {
+        dump_uid: Option<String>,
+    },
+    IndexSwap {
+        swaps: Vec<IndexSwap>,
+    },
 }
 
 impl Details {
@@ -514,6 +583,7 @@ impl Details {
             Self::DocumentAdditionOrUpdate { indexed_documents, .. } => {
                 *indexed_documents = Some(0)
             }
+            Self::DocumentEdition { edited_documents, .. } => *edited_documents = Some(0),
             Self::DocumentDeletion { deleted_documents, .. } => *deleted_documents = Some(0),
             Self::DocumentDeletionByFilter { deleted_documents, .. } => {
                 *deleted_documents = Some(0)

meilisearch/Cargo.toml

@@ -14,131 +14,125 @@ default-run = "meilisearch"
 
 [dependencies]
 actix-cors = "0.7.0"
-actix-http = { version = "3.6.0", default-features = false, features = [
+actix-http = { version = "3.8.0", default-features = false, features = [
     "compress-brotli",
     "compress-gzip",
-    "rustls-0_21",
+    "rustls-0_23",
 ] }
 actix-utils = "3.0.1"
-actix-web = { version = "4.5.1", default-features = false, features = [
+actix-web = { version = "4.8.0", default-features = false, features = [
     "macros",
     "compress-brotli",
     "compress-gzip",
     "cookies",
-    "rustls-0_21",
+    "rustls-0_23",
 ] }
-actix-web-static-files = { git = "https://github.com/kilork/actix-web-static-files.git", rev = "2d3b6160", optional = true }
-anyhow = { version = "1.0.79", features = ["backtrace"] }
-async-stream = "0.3.5"
-async-trait = "0.1.77"
-bstr = "1.9.0"
-byte-unit = { version = "4.0.19", default-features = false, features = [
+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 = "1.5.0"
-clap = { version = "4.4.17", features = ["derive", "env"] }
-crossbeam-channel = "0.5.11"
-deserr = { version = "0.6.1", features = ["actix-web"] }
+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 = "1.9.0"
+either = "1.13.0"
 file-store = { path = "../file-store" }
-flate2 = "1.0.28"
+flate2 = "1.0.30"
 fst = "0.4.7"
 futures = "0.3.30"
 futures-util = "0.3.30"
-http = "0.2.11"
 index-scheduler = { path = "../index-scheduler" }
-indexmap = { version = "2.1.0", features = ["serde"] }
-is-terminal = "0.4.10"
-itertools = "0.11.0"
-jsonwebtoken = "9.2.0"
-lazy_static = "1.4.0"
+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 = "0.1.39", default-features = false }
+mimalloc = { version = "0.1.43", default-features = false }
 mime = "0.3.17"
 num_cpus = "1.16.0"
-obkv = "0.2.1"
+obkv = "0.2.2"
 once_cell = "1.19.0"
-ordered-float = "4.2.0"
-parking_lot = "0.12.1"
+ordered-float = "4.2.1"
+parking_lot = "0.12.3"
 permissive-json-pointer = { path = "../permissive-json-pointer" }
-pin-project-lite = "0.2.13"
+pin-project-lite = "0.2.14"
 platform-dirs = "0.3.0"
-prometheus = { version = "0.13.3", features = ["process"] }
-puffin = { version = "0.16.0", features = ["serialization"] }
+prometheus = { version = "0.13.4", features = ["process"] }
 rand = "0.8.5"
-rayon = "1.8.0"
-regex = "1.10.2"
-reqwest = { version = "0.11.23", features = [
+rayon = "1.10.0"
+regex = "1.10.5"
+reqwest = { version = "0.12.5", features = [
     "rustls-tls",
     "json",
 ], default-features = false }
-rustls = "0.21.12"
-rustls-pemfile = "1.0.2"
-segment = { version = "0.2.3", optional = true }
-serde = { version = "1.0.195", features = ["derive"] }
-serde_json = { version = "1.0.111", features = ["preserve_order"] }
+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", optional = true }
+serde = { version = "1.0.204", features = ["derive"] }
+serde_json = { version = "1.0.120", features = ["preserve_order"] }
 sha2 = "0.10.8"
-siphasher = "1.0.0"
+siphasher = "1.0.1"
 slice-group-by = "0.3.1"
-static-files = { version = "0.2.3", optional = true }
-sysinfo = "0.30.5"
-tar = "0.4.40"
-tempfile = "3.9.0"
-thiserror = "1.0.56"
-time = { version = "0.3.31", features = [
+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 = "1.35.1", features = ["full"] }
-tokio-stream = "0.1.14"
-toml = "0.8.8"
-uuid = { version = "1.6.1", features = ["serde", "v4"] }
-walkdir = "2.4.0"
-yaup = "0.2.1"
+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 = "2.5.0", features = ["serde"] }
+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 = "0.7.9"
+tracing-actix-web = "0.7.11"
 build-info = { version = "1.7.0", path = "../build-info" }
+roaring = "0.10.2"
 
 [dev-dependencies]
-actix-rt = "2.9.0"
-assert-json-diff = "2.0.2"
-brotli = "3.4.0"
-insta = "1.34.0"
+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"
-yaup = "0.2.1"
+yaup = "0.3.1"
 
 [build-dependencies]
-anyhow = { version = "1.0.79", optional = true }
-cargo_toml = { version = "0.18.0", optional = true }
+anyhow = { version = "1.0.86", optional = true }
+cargo_toml = { version = "0.20.3", optional = true }
 hex = { version = "0.4.3", optional = true }
-reqwest = { version = "0.11.23", features = [
+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 = "0.2.3", optional = true }
-tempfile = { version = "3.9.0", optional = true }
-zip = { version = "0.6.6", 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 = ["analytics", "meilisearch-types/all-tokenizations", "mini-dashboard"]
 analytics = ["segment"]
 mini-dashboard = [
-    "actix-web-static-files",
     "static-files",
     "anyhow",
     "cargo_toml",
@@ -152,6 +146,7 @@ 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"]
@@ -159,5 +154,5 @@ vietnamese = ["meilisearch-types/vietnamese"]
 swedish-recomposition = ["meilisearch-types/swedish-recomposition"]
 
 [package.metadata.mini-dashboard]
-assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.2.13/build.zip"
-sha1 = "e20cc9b390003c6c844f4b8bcc5c5013191a77ff"
+assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.2.14/build.zip"
+sha1 = "592d1b5a3459d621d0aae1dded8fe3154f5c38fe"

meilisearch/src/analytics/mock_analytics.rs

@@ -6,7 +6,7 @@ use meilisearch_types::InstanceUid;
 use serde_json::Value;
 
 use super::{find_user_id, Analytics, DocumentDeletionKind, DocumentFetchKind};
-use crate::routes::indexes::documents::UpdateDocumentsQuery;
+use crate::routes::indexes::documents::{DocumentEditionByFunction, UpdateDocumentsQuery};
 use crate::Opt;
 
 pub struct MockAnalytics {
@@ -25,12 +25,24 @@ impl SearchAggregator {
     pub fn succeed(&mut self, _: &dyn Any) {}
 }
 
+#[derive(Default)]
+pub struct SimilarAggregator;
+
+#[allow(dead_code)]
+impl SimilarAggregator {
+    pub fn from_query(_: &dyn Any, _: &dyn Any) -> Self {
+        Self
+    }
+
+    pub fn succeed(&mut self, _: &dyn Any) {}
+}
+
 #[derive(Default)]
 pub struct MultiSearchAggregator;
 
 #[allow(dead_code)]
 impl MultiSearchAggregator {
-    pub fn from_queries(_: &dyn Any, _: &dyn Any) -> Self {
+    pub fn from_federated_search(_: &dyn Any, _: &dyn Any) -> Self {
         Self
     }
 
@@ -66,6 +78,8 @@ impl Analytics for MockAnalytics {
     fn publish(&self, _event_name: String, _send: Value, _request: Option<&HttpRequest>) {}
     fn get_search(&self, _aggregate: super::SearchAggregator) {}
     fn post_search(&self, _aggregate: super::SearchAggregator) {}
+    fn get_similar(&self, _aggregate: super::SimilarAggregator) {}
+    fn post_similar(&self, _aggregate: super::SimilarAggregator) {}
     fn post_multi_search(&self, _aggregate: super::MultiSearchAggregator) {}
     fn post_facet_search(&self, _aggregate: super::FacetSearchAggregator) {}
     fn add_documents(
@@ -83,6 +97,13 @@ impl Analytics for MockAnalytics {
         _request: &HttpRequest,
     ) {
     }
+    fn update_documents_by_function(
+        &self,
+        _documents_query: &DocumentEditionByFunction,
+        _index_creation: bool,
+        _request: &HttpRequest,
+    ) {
+    }
     fn get_fetch_documents(&self, _documents_query: &DocumentFetchKind, _request: &HttpRequest) {}
     fn post_fetch_documents(&self, _documents_query: &DocumentFetchKind, _request: &HttpRequest) {}
 }

meilisearch/src/analytics/mod.rs

@@ -13,7 +13,7 @@ use once_cell::sync::Lazy;
 use platform_dirs::AppDirs;
 use serde_json::Value;
 
-use crate::routes::indexes::documents::UpdateDocumentsQuery;
+use crate::routes::indexes::documents::{DocumentEditionByFunction, UpdateDocumentsQuery};
 
 // if the analytics feature is disabled
 // the `SegmentAnalytics` point to the mock instead of the real analytics
@@ -22,6 +22,8 @@ pub type SegmentAnalytics = mock_analytics::MockAnalytics;
 #[cfg(not(feature = "analytics"))]
 pub type SearchAggregator = mock_analytics::SearchAggregator;
 #[cfg(not(feature = "analytics"))]
+pub type SimilarAggregator = mock_analytics::SimilarAggregator;
+#[cfg(not(feature = "analytics"))]
 pub type MultiSearchAggregator = mock_analytics::MultiSearchAggregator;
 #[cfg(not(feature = "analytics"))]
 pub type FacetSearchAggregator = mock_analytics::FacetSearchAggregator;
@@ -32,6 +34,8 @@ pub type SegmentAnalytics = segment_analytics::SegmentAnalytics;
 #[cfg(feature = "analytics")]
 pub type SearchAggregator = segment_analytics::SearchAggregator;
 #[cfg(feature = "analytics")]
+pub type SimilarAggregator = segment_analytics::SimilarAggregator;
+#[cfg(feature = "analytics")]
 pub type MultiSearchAggregator = segment_analytics::MultiSearchAggregator;
 #[cfg(feature = "analytics")]
 pub type FacetSearchAggregator = segment_analytics::FacetSearchAggregator;
@@ -70,8 +74,8 @@ pub enum DocumentDeletionKind {
 
 #[derive(Copy, Clone, Debug, PartialEq, Eq)]
 pub enum DocumentFetchKind {
-    PerDocumentId,
-    Normal { with_filter: bool, limit: usize, offset: usize },
+    PerDocumentId { retrieve_vectors: bool },
+    Normal { with_filter: bool, limit: usize, offset: usize, retrieve_vectors: bool },
 }
 
 pub trait Analytics: Sync + Send {
@@ -86,13 +90,19 @@ pub trait Analytics: Sync + Send {
     /// This method should be called to aggregate a post search
     fn post_search(&self, aggregate: SearchAggregator);
 
+    /// This method should be called to aggregate a get similar request
+    fn get_similar(&self, aggregate: SimilarAggregator);
+
+    /// This method should be called to aggregate a post similar request
+    fn post_similar(&self, aggregate: SimilarAggregator);
+
     /// This method should be called to aggregate a post array of searches
     fn post_multi_search(&self, aggregate: MultiSearchAggregator);
 
     /// This method should be called to aggregate post facet values searches
     fn post_facet_search(&self, aggregate: FacetSearchAggregator);
 
-    // this method should be called to aggregate a add documents request
+    // this method should be called to aggregate an add documents request
     fn add_documents(
         &self,
         documents_query: &UpdateDocumentsQuery,
@@ -109,11 +119,19 @@ pub trait Analytics: Sync + Send {
     // this method should be called to aggregate a add documents request
     fn delete_documents(&self, kind: DocumentDeletionKind, request: &HttpRequest);
 
-    // this method should be called to batch a update documents request
+    // this method should be called to batch an update documents request
     fn update_documents(
         &self,
         documents_query: &UpdateDocumentsQuery,
         index_creation: bool,
         request: &HttpRequest,
     );
+
+    // this method should be called to batch an update documents by function request
+    fn update_documents_by_function(
+        &self,
+        documents_query: &DocumentEditionByFunction,
+        index_creation: bool,
+        request: &HttpRequest,
+    );
 }

meilisearch/src/analytics/segment_analytics.rs

@@ -5,10 +5,9 @@ use std::path::{Path, PathBuf};
 use std::sync::Arc;
 use std::time::{Duration, Instant};
 
-use actix_web::http::header::USER_AGENT;
+use actix_web::http::header::{CONTENT_TYPE, USER_AGENT};
 use actix_web::HttpRequest;
 use byte_unit::Byte;
-use http::header::CONTENT_TYPE;
 use index_scheduler::IndexScheduler;
 use meilisearch_auth::{AuthController, AuthFilter};
 use meilisearch_types::InstanceUid;
@@ -31,13 +30,14 @@ use crate::analytics::Analytics;
 use crate::option::{
     default_http_addr, IndexerOpts, LogMode, MaxMemory, MaxThreads, ScheduleSnapshot,
 };
-use crate::routes::indexes::documents::UpdateDocumentsQuery;
+use crate::routes::indexes::documents::{DocumentEditionByFunction, UpdateDocumentsQuery};
 use crate::routes::indexes::facet_search::FacetSearchQuery;
 use crate::routes::{create_all_stats, Stats};
 use crate::search::{
-    FacetSearchResult, MatchingStrategy, SearchQuery, SearchQueryWithIndex, SearchResult,
-    DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG,
-    DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT, DEFAULT_SEMANTIC_RATIO,
+    FacetSearchResult, FederatedSearch, MatchingStrategy, SearchQuery, SearchQueryWithIndex,
+    SearchResult, SimilarQuery, SimilarResult, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER,
+    DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT,
+    DEFAULT_SEMANTIC_RATIO,
 };
 use crate::Opt;
 
@@ -73,11 +73,14 @@ pub enum AnalyticsMsg {
     BatchMessage(Track),
     AggregateGetSearch(SearchAggregator),
     AggregatePostSearch(SearchAggregator),
+    AggregateGetSimilar(SimilarAggregator),
+    AggregatePostSimilar(SimilarAggregator),
     AggregatePostMultiSearch(MultiSearchAggregator),
     AggregatePostFacetSearch(FacetSearchAggregator),
     AggregateAddDocuments(DocumentsAggregator),
     AggregateDeleteDocuments(DocumentsDeletionAggregator),
     AggregateUpdateDocuments(DocumentsAggregator),
+    AggregateEditDocumentsByFunction(EditDocumentsByFunctionAggregator),
     AggregateGetFetchDocuments(DocumentsFetchAggregator),
     AggregatePostFetchDocuments(DocumentsFetchAggregator),
 }
@@ -147,8 +150,11 @@ impl SegmentAnalytics {
             add_documents_aggregator: DocumentsAggregator::default(),
             delete_documents_aggregator: DocumentsDeletionAggregator::default(),
             update_documents_aggregator: DocumentsAggregator::default(),
+            edit_documents_by_function_aggregator: EditDocumentsByFunctionAggregator::default(),
             get_fetch_documents_aggregator: DocumentsFetchAggregator::default(),
             post_fetch_documents_aggregator: DocumentsFetchAggregator::default(),
+            get_similar_aggregator: SimilarAggregator::default(),
+            post_similar_aggregator: SimilarAggregator::default(),
         });
         tokio::spawn(segment.run(index_scheduler.clone(), auth_controller.clone()));
 
@@ -184,6 +190,14 @@ impl super::Analytics for SegmentAnalytics {
         let _ = self.sender.try_send(AnalyticsMsg::AggregatePostSearch(aggregate));
     }
 
+    fn get_similar(&self, aggregate: SimilarAggregator) {
+        let _ = self.sender.try_send(AnalyticsMsg::AggregateGetSimilar(aggregate));
+    }
+
+    fn post_similar(&self, aggregate: SimilarAggregator) {
+        let _ = self.sender.try_send(AnalyticsMsg::AggregatePostSimilar(aggregate));
+    }
+
     fn post_facet_search(&self, aggregate: FacetSearchAggregator) {
         let _ = self.sender.try_send(AnalyticsMsg::AggregatePostFacetSearch(aggregate));
     }
@@ -217,6 +231,17 @@ impl super::Analytics for SegmentAnalytics {
         let _ = self.sender.try_send(AnalyticsMsg::AggregateUpdateDocuments(aggregate));
     }
 
+    fn update_documents_by_function(
+        &self,
+        documents_query: &DocumentEditionByFunction,
+        index_creation: bool,
+        request: &HttpRequest,
+    ) {
+        let aggregate =
+            EditDocumentsByFunctionAggregator::from_query(documents_query, index_creation, request);
+        let _ = self.sender.try_send(AnalyticsMsg::AggregateEditDocumentsByFunction(aggregate));
+    }
+
     fn get_fetch_documents(&self, documents_query: &DocumentFetchKind, request: &HttpRequest) {
         let aggregate = DocumentsFetchAggregator::from_query(documents_query, request);
         let _ = self.sender.try_send(AnalyticsMsg::AggregateGetFetchDocuments(aggregate));
@@ -236,6 +261,7 @@ impl super::Analytics for SegmentAnalytics {
 #[derive(Debug, Clone, Serialize)]
 struct Infos {
     env: String,
+    experimental_contains_filter: bool,
     experimental_enable_metrics: bool,
     experimental_search_queue_size: usize,
     experimental_logs_mode: LogMode,
@@ -278,6 +304,7 @@ impl From<Opt> for Infos {
         // Thus we must not insert `..` at the end.
         let Opt {
             db_path,
+            experimental_contains_filter,
             experimental_enable_metrics,
             experimental_search_queue_size,
             experimental_logs_mode,
@@ -328,6 +355,7 @@ impl From<Opt> for Infos {
         // We consider information sensible if it contains a path, an address, or a key.
         Self {
             env,
+            experimental_contains_filter,
             experimental_enable_metrics,
             experimental_search_queue_size,
             experimental_logs_mode,
@@ -377,8 +405,11 @@ pub struct Segment {
     add_documents_aggregator: DocumentsAggregator,
     delete_documents_aggregator: DocumentsDeletionAggregator,
     update_documents_aggregator: DocumentsAggregator,
+    edit_documents_by_function_aggregator: EditDocumentsByFunctionAggregator,
     get_fetch_documents_aggregator: DocumentsFetchAggregator,
     post_fetch_documents_aggregator: DocumentsFetchAggregator,
+    get_similar_aggregator: SimilarAggregator,
+    post_similar_aggregator: SimilarAggregator,
 }
 
 impl Segment {
@@ -439,8 +470,11 @@ impl Segment {
                         Some(AnalyticsMsg::AggregateAddDocuments(agreg)) => self.add_documents_aggregator.aggregate(agreg),
                         Some(AnalyticsMsg::AggregateDeleteDocuments(agreg)) => self.delete_documents_aggregator.aggregate(agreg),
                         Some(AnalyticsMsg::AggregateUpdateDocuments(agreg)) => self.update_documents_aggregator.aggregate(agreg),
+                        Some(AnalyticsMsg::AggregateEditDocumentsByFunction(agreg)) => self.edit_documents_by_function_aggregator.aggregate(agreg),
                         Some(AnalyticsMsg::AggregateGetFetchDocuments(agreg)) => self.get_fetch_documents_aggregator.aggregate(agreg),
                         Some(AnalyticsMsg::AggregatePostFetchDocuments(agreg)) => self.post_fetch_documents_aggregator.aggregate(agreg),
+                        Some(AnalyticsMsg::AggregateGetSimilar(agreg)) => self.get_similar_aggregator.aggregate(agreg),
+                        Some(AnalyticsMsg::AggregatePostSimilar(agreg)) => self.post_similar_aggregator.aggregate(agreg),
                         None => (),
                     }
                 }
@@ -492,8 +526,11 @@ impl Segment {
             add_documents_aggregator,
             delete_documents_aggregator,
             update_documents_aggregator,
+            edit_documents_by_function_aggregator,
             get_fetch_documents_aggregator,
             post_fetch_documents_aggregator,
+            get_similar_aggregator,
+            post_similar_aggregator,
         } = self;
 
         if let Some(get_search) =
@@ -531,6 +568,11 @@ impl Segment {
         {
             let _ = self.batcher.push(update_documents).await;
         }
+        if let Some(edit_documents_by_function) = take(edit_documents_by_function_aggregator)
+            .into_event(user, "Documents Edited By Function")
+        {
+            let _ = self.batcher.push(edit_documents_by_function).await;
+        }
         if let Some(get_fetch_documents) =
             take(get_fetch_documents_aggregator).into_event(user, "Documents Fetched GET")
         {
@@ -541,6 +583,18 @@ impl Segment {
         {
             let _ = self.batcher.push(post_fetch_documents).await;
         }
+
+        if let Some(get_similar_documents) =
+            take(get_similar_aggregator).into_event(user, "Similar GET")
+        {
+            let _ = self.batcher.push(get_similar_documents).await;
+        }
+
+        if let Some(post_similar_documents) =
+            take(post_similar_aggregator).into_event(user, "Similar POST")
+        {
+            let _ = self.batcher.push(post_similar_documents).await;
+        }
         let _ = self.batcher.flush().await;
     }
 }
@@ -566,6 +620,9 @@ pub struct SearchAggregator {
     // 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,
@@ -591,6 +648,7 @@ pub struct SearchAggregator {
     // Whether a non-default embedder was specified
     embedder: 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>,
@@ -617,6 +675,7 @@ pub struct SearchAggregator {
     // scoring
     show_ranking_score: bool,
     show_ranking_score_details: bool,
+    ranking_score_threshold: bool,
 }
 
 impl SearchAggregator {
@@ -630,6 +689,7 @@ impl SearchAggregator {
             page,
             hits_per_page,
             attributes_to_retrieve: _,
+            retrieve_vectors,
             attributes_to_crop: _,
             crop_length,
             attributes_to_highlight: _,
@@ -638,6 +698,7 @@ impl SearchAggregator {
             show_ranking_score_details,
             filter,
             sort,
+            distinct,
             facets: _,
             highlight_pre_tag,
             highlight_post_tag,
@@ -645,6 +706,7 @@ impl SearchAggregator {
             matching_strategy,
             attributes_to_search_on,
             hybrid,
+            ranking_score_threshold,
         } = query;
 
         let mut ret = Self::default();
@@ -659,6 +721,8 @@ impl SearchAggregator {
             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;
@@ -695,6 +759,7 @@ impl SearchAggregator {
         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);
@@ -717,6 +782,7 @@ impl SearchAggregator {
 
         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();
@@ -761,6 +827,7 @@ impl SearchAggregator {
             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,
@@ -769,6 +836,7 @@ impl SearchAggregator {
             attributes_to_search_on_total_number_of_uses,
             max_terms_number,
             max_vector_size,
+            retrieve_vectors,
             matching_strategy,
             max_limit,
             max_offset,
@@ -790,6 +858,7 @@ impl SearchAggregator {
             hybrid,
             total_degraded,
             total_used_negative_operator,
+            ranking_score_threshold,
         } = other;
 
         if self.timestamp.is_none() {
@@ -816,6 +885,9 @@ impl SearchAggregator {
         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;
@@ -838,6 +910,7 @@ impl SearchAggregator {
 
         // 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;
         self.embedder |= embedder;
@@ -873,6 +946,7 @@ impl SearchAggregator {
         // scoring
         self.show_ranking_score |= show_ranking_score;
         self.show_ranking_score_details |= show_ranking_score_details;
+        self.ranking_score_threshold |= ranking_score_threshold;
     }
 
     pub fn into_event(self, user: &User, event_name: &str) -> Option<Track> {
@@ -885,6 +959,7 @@ impl SearchAggregator {
             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,
@@ -893,6 +968,7 @@ impl SearchAggregator {
             attributes_to_search_on_total_number_of_uses,
             max_terms_number,
             max_vector_size,
+            retrieve_vectors,
             matching_strategy,
             max_limit,
             max_offset,
@@ -914,6 +990,7 @@ impl SearchAggregator {
             hybrid,
             total_degraded,
             total_used_negative_operator,
+            ranking_score_threshold,
         } = self;
 
         if total_received == 0 {
@@ -940,6 +1017,7 @@ impl SearchAggregator {
                     "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,
@@ -954,6 +1032,7 @@ impl SearchAggregator {
                 },
                 "vector": {
                     "max_vector_size": max_vector_size,
+                    "retrieve_vectors": retrieve_vectors,
                 },
                 "hybrid": {
                     "enabled": hybrid,
@@ -984,6 +1063,7 @@ impl SearchAggregator {
                 "scoring": {
                     "show_ranking_score": show_ranking_score,
                     "show_ranking_score_details": show_ranking_score_details,
+                    "ranking_score_threshold": ranking_score_threshold,
                 },
             });
 
@@ -1018,22 +1098,33 @@ pub struct MultiSearchAggregator {
     show_ranking_score: bool,
     show_ranking_score_details: bool,
 
+    // federation
+    use_federation: bool,
+
     // context
     user_agents: HashSet<String>,
 }
 
 impl MultiSearchAggregator {
-    pub fn from_queries(query: &[SearchQueryWithIndex], request: &HttpRequest) -> Self {
+    pub fn from_federated_search(
+        federated_search: &FederatedSearch,
+        request: &HttpRequest,
+    ) -> Self {
         let timestamp = Some(OffsetDateTime::now_utc());
 
         let user_agents = extract_user_agents(request).into_iter().collect();
 
-        let distinct_indexes: HashSet<_> = query
+        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: _,
@@ -1041,6 +1132,7 @@ impl MultiSearchAggregator {
                     page: _,
                     hits_per_page: _,
                     attributes_to_retrieve: _,
+                    retrieve_vectors: _,
                     attributes_to_crop: _,
                     crop_length: _,
                     attributes_to_highlight: _,
@@ -1049,6 +1141,7 @@ impl MultiSearchAggregator {
                     show_matches_position: _,
                     filter: _,
                     sort: _,
+                    distinct: _,
                     facets: _,
                     highlight_pre_tag: _,
                     highlight_post_tag: _,
@@ -1056,14 +1149,17 @@ impl MultiSearchAggregator {
                     matching_strategy: _,
                     attributes_to_search_on: _,
                     hybrid: _,
+                    ranking_score_threshold: _,
                 } = query;
 
                 index_uid.as_str()
             })
             .collect();
 
-        let show_ranking_score = query.iter().any(|query| query.show_ranking_score);
-        let show_ranking_score_details = query.iter().any(|query| query.show_ranking_score_details);
+        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 {
             timestamp,
@@ -1071,10 +1167,11 @@ impl MultiSearchAggregator {
             total_succeeded: 0,
             total_distinct_index_count: distinct_indexes.len(),
             total_single_index: if distinct_indexes.len() == 1 { 1 } else { 0 },
-            total_search_count: query.len(),
+            total_search_count: federated_search.queries.len(),
             show_ranking_score,
             show_ranking_score_details,
             user_agents,
+            use_federation,
         }
     }
 
@@ -1100,6 +1197,7 @@ impl MultiSearchAggregator {
         let show_ranking_score_details =
             this.show_ranking_score_details || other.show_ranking_score_details;
         let mut user_agents = this.user_agents;
+        let use_federation = this.use_federation || other.use_federation;
 
         for user_agent in other.user_agents.into_iter() {
             user_agents.insert(user_agent);
@@ -1116,6 +1214,7 @@ impl MultiSearchAggregator {
             user_agents,
             show_ranking_score,
             show_ranking_score_details,
+            use_federation,
             // do not add _ or ..Default::default() here
         };
 
@@ -1134,6 +1233,7 @@ impl MultiSearchAggregator {
             user_agents,
             show_ranking_score,
             show_ranking_score_details,
+            use_federation,
         } = self;
 
         if total_received == 0 {
@@ -1158,6 +1258,9 @@ impl MultiSearchAggregator {
                 "scoring": {
                     "show_ranking_score": show_ranking_score,
                     "show_ranking_score_details": show_ranking_score_details,
+                },
+                "federation": {
+                    "use_federation": use_federation,
                 }
             });
 
@@ -1203,6 +1306,7 @@ impl FacetSearchAggregator {
             matching_strategy,
             attributes_to_search_on,
             hybrid,
+            ranking_score_threshold,
         } = query;
 
         let mut ret = Self::default();
@@ -1217,7 +1321,8 @@ impl FacetSearchAggregator {
             || filter.is_some()
             || *matching_strategy != MatchingStrategy::default()
             || attributes_to_search_on.is_some()
-            || hybrid.is_some();
+            || hybrid.is_some()
+            || ranking_score_threshold.is_some();
 
         ret
     }
@@ -1404,6 +1509,75 @@ impl DocumentsAggregator {
     }
 }
 
+#[derive(Default)]
+pub struct EditDocumentsByFunctionAggregator {
+    timestamp: Option<OffsetDateTime>,
+
+    // Set to true if at least one request was filtered
+    filtered: bool,
+    // Set to true if at least one request contained a context
+    with_context: bool,
+
+    // context
+    user_agents: HashSet<String>,
+
+    index_creation: bool,
+}
+
+impl EditDocumentsByFunctionAggregator {
+    pub fn from_query(
+        documents_query: &DocumentEditionByFunction,
+        index_creation: bool,
+        request: &HttpRequest,
+    ) -> Self {
+        let DocumentEditionByFunction { filter, context, function: _ } = documents_query;
+
+        Self {
+            timestamp: Some(OffsetDateTime::now_utc()),
+            user_agents: extract_user_agents(request).into_iter().collect(),
+            filtered: filter.is_some(),
+            with_context: context.is_some(),
+            index_creation,
+        }
+    }
+
+    /// Aggregate one [DocumentsAggregator] into another.
+    pub fn aggregate(&mut self, other: Self) {
+        let Self { timestamp, user_agents, index_creation, filtered, with_context } = other;
+
+        if self.timestamp.is_none() {
+            self.timestamp = timestamp;
+        }
+
+        // we can't create a union because there is no `into_union` method
+        for user_agent in user_agents {
+            self.user_agents.insert(user_agent);
+        }
+        self.index_creation |= index_creation;
+        self.filtered |= filtered;
+        self.with_context |= with_context;
+    }
+
+    pub fn into_event(self, user: &User, event_name: &str) -> Option<Track> {
+        let Self { timestamp, user_agents, index_creation, filtered, with_context } = self;
+
+        let properties = json!({
+            "user-agent": user_agents,
+            "filtered": filtered,
+            "with_context": with_context,
+            "index_creation": index_creation,
+        });
+
+        Some(Track {
+            timestamp,
+            user: user.clone(),
+            event: event_name.to_string(),
+            properties,
+            ..Default::default()
+        })
+    }
+}
+
 #[derive(Default, Serialize)]
 pub struct DocumentsDeletionAggregator {
     #[serde(skip)]
@@ -1493,6 +1667,9 @@ pub struct DocumentsFetchAggregator {
     // if a filter was used
     per_filter: bool,
 
+    #[serde(rename = "vector.retrieve_vectors")]
+    retrieve_vectors: bool,
+
     // pagination
     #[serde(rename = "pagination.max_limit")]
     max_limit: usize,
@@ -1502,18 +1679,21 @@ pub struct DocumentsFetchAggregator {
 
 impl DocumentsFetchAggregator {
     pub fn from_query(query: &DocumentFetchKind, request: &HttpRequest) -> Self {
-        let (limit, offset) = match query {
-            DocumentFetchKind::PerDocumentId => (1, 0),
-            DocumentFetchKind::Normal { limit, offset, .. } => (*limit, *offset),
+        let (limit, offset, retrieve_vectors) = match query {
+            DocumentFetchKind::PerDocumentId { retrieve_vectors } => (1, 0, *retrieve_vectors),
+            DocumentFetchKind::Normal { limit, offset, retrieve_vectors, .. } => {
+                (*limit, *offset, *retrieve_vectors)
+            }
         };
         Self {
             timestamp: Some(OffsetDateTime::now_utc()),
             user_agents: extract_user_agents(request).into_iter().collect(),
             total_received: 1,
-            per_document_id: matches!(query, DocumentFetchKind::PerDocumentId),
+            per_document_id: matches!(query, DocumentFetchKind::PerDocumentId { .. }),
             per_filter: matches!(query, DocumentFetchKind::Normal { with_filter, .. } if *with_filter),
             max_limit: limit,
             max_offset: offset,
+            retrieve_vectors,
         }
     }
 
@@ -1527,6 +1707,7 @@ impl DocumentsFetchAggregator {
             per_filter,
             max_limit,
             max_offset,
+            retrieve_vectors,
         } = other;
 
         if self.timestamp.is_none() {
@@ -1542,6 +1723,8 @@ impl DocumentsFetchAggregator {
 
         self.max_limit = self.max_limit.max(max_limit);
         self.max_offset = self.max_offset.max(max_offset);
+
+        self.retrieve_vectors |= retrieve_vectors;
     }
 
     pub fn into_event(self, user: &User, event_name: &str) -> Option<Track> {
@@ -1558,3 +1741,251 @@ impl DocumentsFetchAggregator {
         })
     }
 }
+
+#[derive(Default)]
+pub struct SimilarAggregator {
+    timestamp: Option<OffsetDateTime>,
+
+    // context
+    user_agents: HashSet<String>,
+
+    // 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
+    embedder: bool,
+    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,
+}
+
+impl SimilarAggregator {
+    #[allow(clippy::field_reassign_with_default)]
+    pub fn from_query(query: &SimilarQuery, request: &HttpRequest) -> 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.timestamp = Some(OffsetDateTime::now_utc());
+
+        ret.total_received = 1;
+        ret.user_agents = extract_user_agents(request).into_iter().collect();
+
+        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.embedder = embedder.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);
+    }
+
+    /// Aggregate one [SimilarAggregator] into another.
+    pub fn aggregate(&mut self, mut other: Self) {
+        let Self {
+            timestamp,
+            user_agents,
+            total_received,
+            total_succeeded,
+            ref 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,
+            embedder,
+            ranking_score_threshold,
+            retrieve_vectors,
+        } = other;
+
+        if self.timestamp.is_none() {
+            self.timestamp = timestamp;
+        }
+
+        // context
+        for user_agent in user_agents.into_iter() {
+            self.user_agents.insert(user_agent);
+        }
+
+        // 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(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.embedder |= embedder;
+        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;
+    }
+
+    pub fn into_event(self, user: &User, event_name: &str) -> Option<Track> {
+        let Self {
+            timestamp,
+            user_agents,
+            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,
+            embedder,
+            ranking_score_threshold,
+            retrieve_vectors,
+        } = self;
+
+        if total_received == 0 {
+            None
+        } else {
+            // 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);
+
+            let properties = json!({
+                "user-agent": user_agents,
+                "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,
+                },
+                "hybrid": {
+                    "embedder": embedder,
+                },
+                "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,
+                },
+            });
+
+            Some(Track {
+                timestamp,
+                user: user.clone(),
+                event: event_name.to_string(),
+                properties,
+                ..Default::default()
+            })
+        }
+    }
+}

meilisearch/src/error.rs

@@ -1,6 +1,6 @@
 use actix_web as aweb;
 use aweb::error::{JsonPayloadError, QueryPayloadError};
-use byte_unit::Byte;
+use byte_unit::{Byte, UnitType};
 use meilisearch_types::document_formats::{DocumentFormatError, PayloadType};
 use meilisearch_types::error::{Code, ErrorCode, ResponseError};
 use meilisearch_types::index_uid::{IndexUid, IndexUidFormatError};
@@ -27,13 +27,17 @@ pub enum MeilisearchHttpError {
     EmptyFilter,
     #[error("Invalid syntax for the filter parameter: `expected {}, found: {1}`.", .0.join(", "))]
     InvalidExpression(&'static [&'static str], Value),
+    #[error("Using `federationOptions` is not allowed in a non-federated search.\n Hint: remove `federationOptions` from query #{0} or add `federation: {{}}` to the request.")]
+    FederationOptionsInNonFederatedRequest(usize),
+    #[error("Inside `.queries[{0}]`: Using pagination options is not allowed in federated queries.\n Hint: remove `{1}` from query #{0} or remove `federation: {{}}` from the request")]
+    PaginationInFederatedQuery(usize, &'static str),
     #[error("A {0} payload is missing.")]
     MissingPayload(PayloadType),
     #[error("Too many search requests running at the same time: {0}. Retry after 10s.")]
     TooManySearchRequests(usize),
     #[error("Internal error: Search limiter is down.")]
     SearchLimiterIsDown,
-    #[error("The provided payload reached the size limit. The maximum accepted payload size is {}.",  Byte::from_bytes(*.0 as u64).get_appropriate_unit(true))]
+    #[error("The provided payload reached the size limit. The maximum accepted payload size is {}.",  Byte::from_u64(*.0 as u64).get_appropriate_unit(UnitType::Binary))]
     PayloadTooLarge(usize),
     #[error("Two indexes must be given for each swap. The list `[{}]` contains {} indexes.",
         .0.iter().map(|uid| format!("\"{uid}\"")).collect::<Vec<_>>().join(", "), .0.len()
@@ -86,6 +90,12 @@ impl ErrorCode for MeilisearchHttpError {
             MeilisearchHttpError::DocumentFormat(e) => e.error_code(),
             MeilisearchHttpError::Join(_) => Code::Internal,
             MeilisearchHttpError::MissingSearchHybrid => Code::MissingSearchHybrid,
+            MeilisearchHttpError::FederationOptionsInNonFederatedRequest(_) => {
+                Code::InvalidMultiSearchFederationOptions
+            }
+            MeilisearchHttpError::PaginationInFederatedQuery(_, _) => {
+                Code::InvalidMultiSearchQueryPagination
+            }
         }
     }
 }
@@ -98,14 +108,29 @@ impl From<MeilisearchHttpError> for aweb::Error {
 
 impl From<aweb::error::PayloadError> for MeilisearchHttpError {
     fn from(error: aweb::error::PayloadError) -> Self {
-        MeilisearchHttpError::Payload(PayloadError::Payload(error))
+        match error {
+            aweb::error::PayloadError::Incomplete(_) => MeilisearchHttpError::Payload(
+                PayloadError::Payload(ActixPayloadError::IncompleteError),
+            ),
+            _ => MeilisearchHttpError::Payload(PayloadError::Payload(
+                ActixPayloadError::OtherError(error),
+            )),
+        }
     }
 }
 
+#[derive(Debug, thiserror::Error)]
+pub enum ActixPayloadError {
+    #[error("The provided payload is incomplete and cannot be parsed")]
+    IncompleteError,
+    #[error(transparent)]
+    OtherError(aweb::error::PayloadError),
+}
+
 #[derive(Debug, thiserror::Error)]
 pub enum PayloadError {
     #[error(transparent)]
-    Payload(aweb::error::PayloadError),
+    Payload(ActixPayloadError),
     #[error(transparent)]
     Json(JsonPayloadError),
     #[error(transparent)]
@@ -122,13 +147,15 @@ impl ErrorCode for PayloadError {
     fn error_code(&self) -> Code {
         match self {
             PayloadError::Payload(e) => match e {
-                aweb::error::PayloadError::Incomplete(_) => Code::Internal,
-                aweb::error::PayloadError::EncodingCorrupted => Code::Internal,
-                aweb::error::PayloadError::Overflow => Code::PayloadTooLarge,
-                aweb::error::PayloadError::UnknownLength => Code::Internal,
-                aweb::error::PayloadError::Http2Payload(_) => Code::Internal,
-                aweb::error::PayloadError::Io(_) => Code::Internal,
-                _ => todo!(),
+                ActixPayloadError::IncompleteError => Code::BadRequest,
+                ActixPayloadError::OtherError(error) => match error {
+                    aweb::error::PayloadError::EncodingCorrupted => Code::Internal,
+                    aweb::error::PayloadError::Overflow => Code::PayloadTooLarge,
+                    aweb::error::PayloadError::UnknownLength => Code::Internal,
+                    aweb::error::PayloadError::Http2Payload(_) => Code::Internal,
+                    aweb::error::PayloadError::Io(_) => Code::Internal,
+                    _ => todo!(),
+                },
             },
             PayloadError::Json(err) => match err {
                 JsonPayloadError::Overflow { .. } => Code::PayloadTooLarge,

meilisearch/src/extractors/authentication/mod.rs

@@ -12,6 +12,8 @@ use futures::Future;
 use meilisearch_auth::{AuthController, AuthFilter};
 use meilisearch_types::error::{Code, ResponseError};
 
+use self::policies::AuthError;
+
 pub struct GuardedData<P, D> {
     data: D,
     filters: AuthFilter,
@@ -35,12 +37,12 @@ impl<P, D> GuardedData<P, D> {
         let missing_master_key = auth.get_master_key().is_none();
 
         match Self::authenticate(auth, token, index).await? {
-            Some(filters) => match data {
+            Ok(filters) => match data {
                 Some(data) => Ok(Self { data, filters, _marker: PhantomData }),
                 None => Err(AuthenticationError::IrretrievableState.into()),
             },
-            None if missing_master_key => Err(AuthenticationError::MissingMasterKey.into()),
-            None => Err(AuthenticationError::InvalidToken.into()),
+            Err(_) if missing_master_key => Err(AuthenticationError::MissingMasterKey.into()),
+            Err(e) => Err(ResponseError::from_msg(e.to_string(), Code::InvalidApiKey)),
         }
     }
 
@@ -51,12 +53,12 @@ impl<P, D> GuardedData<P, D> {
         let missing_master_key = auth.get_master_key().is_none();
 
         match Self::authenticate(auth, String::new(), None).await? {
-            Some(filters) => match data {
+            Ok(filters) => match data {
                 Some(data) => Ok(Self { data, filters, _marker: PhantomData }),
                 None => Err(AuthenticationError::IrretrievableState.into()),
             },
-            None if missing_master_key => Err(AuthenticationError::MissingMasterKey.into()),
-            None => Err(AuthenticationError::MissingAuthorizationHeader.into()),
+            Err(_) if missing_master_key => Err(AuthenticationError::MissingMasterKey.into()),
+            Err(_) => Err(AuthenticationError::MissingAuthorizationHeader.into()),
         }
     }
 
@@ -64,7 +66,7 @@ impl<P, D> GuardedData<P, D> {
         auth: Data<AuthController>,
         token: String,
         index: Option<String>,
-    ) -> Result<Option<AuthFilter>, ResponseError>
+    ) -> Result<Result<AuthFilter, AuthError>, ResponseError>
     where
         P: Policy + 'static,
     {
@@ -127,13 +129,14 @@ pub trait Policy {
         auth: Data<AuthController>,
         token: &str,
         index: Option<&str>,
-    ) -> Option<AuthFilter>;
+    ) -> Result<AuthFilter, policies::AuthError>;
 }
 
 pub mod policies {
     use actix_web::web::Data;
     use jsonwebtoken::{decode, Algorithm, DecodingKey, Validation};
     use meilisearch_auth::{AuthController, AuthFilter, SearchRules};
+    use meilisearch_types::error::{Code, ErrorCode};
     // reexport actions in policies in order to be used in routes configuration.
     pub use meilisearch_types::keys::{actions, Action};
     use serde::{Deserialize, Serialize};
@@ -144,11 +147,53 @@ pub mod policies {
 
     enum TenantTokenOutcome {
         NotATenantToken,
-        Invalid,
-        Expired,
         Valid(Uuid, SearchRules),
     }
 
+    #[derive(thiserror::Error, Debug)]
+    pub enum AuthError {
+        #[error("Tenant token expired. Was valid up to `{exp}` and we're now `{now}`.")]
+        ExpiredTenantToken { exp: i64, now: i64 },
+        #[error("The provided API key is invalid.")]
+        InvalidApiKey,
+        #[error("The provided tenant token cannot acces the index `{index}`, allowed indexes are {allowed:?}.")]
+        TenantTokenAccessingnUnauthorizedIndex { index: String, allowed: Vec<String> },
+        #[error(
+            "The API key used to generate this tenant token cannot acces the index `{index}`."
+        )]
+        TenantTokenApiKeyAccessingnUnauthorizedIndex { index: String },
+        #[error(
+            "The API key cannot acces the index `{index}`, authorized indexes are {allowed:?}."
+        )]
+        ApiKeyAccessingnUnauthorizedIndex { index: String, allowed: Vec<String> },
+        #[error("The provided tenant token is invalid.")]
+        InvalidTenantToken,
+        #[error("Could not decode tenant token, {0}.")]
+        CouldNotDecodeTenantToken(jsonwebtoken::errors::Error),
+        #[error("Invalid action `{0}`.")]
+        InternalInvalidAction(u8),
+    }
+
+    impl From<jsonwebtoken::errors::Error> for AuthError {
+        fn from(error: jsonwebtoken::errors::Error) -> Self {
+            use jsonwebtoken::errors::ErrorKind;
+
+            match error.kind() {
+                ErrorKind::InvalidToken => AuthError::InvalidTenantToken,
+                _ => AuthError::CouldNotDecodeTenantToken(error),
+            }
+        }
+    }
+
+    impl ErrorCode for AuthError {
+        fn error_code(&self) -> Code {
+            match self {
+                AuthError::InternalInvalidAction(_) => Code::Internal,
+                _ => Code::InvalidApiKey,
+            }
+        }
+    }
+
     fn tenant_token_validation() -> Validation {
         let mut validation = Validation::default();
         validation.validate_exp = false;
@@ -158,15 +203,15 @@ pub mod policies {
     }
 
     /// Extracts the key id used to sign the payload, without performing any validation.
-    fn extract_key_id(token: &str) -> Option<Uuid> {
+    fn extract_key_id(token: &str) -> Result<Uuid, AuthError> {
         let mut validation = tenant_token_validation();
         validation.insecure_disable_signature_validation();
         let dummy_key = DecodingKey::from_secret(b"secret");
-        let token_data = decode::<Claims>(token, &dummy_key, &validation).ok()?;
+        let token_data = decode::<Claims>(token, &dummy_key, &validation)?;
 
         // get token fields without validating it.
         let Claims { api_key_uid, .. } = token_data.claims;
-        Some(api_key_uid)
+        Ok(api_key_uid)
     }
 
     fn is_keys_action(action: u8) -> bool {
@@ -187,76 +232,102 @@ pub mod policies {
             auth: Data<AuthController>,
             token: &str,
             index: Option<&str>,
-        ) -> Option<AuthFilter> {
+        ) -> Result<AuthFilter, AuthError> {
             // authenticate if token is the master key.
             // Without a master key, all routes are accessible except the key-related routes.
             if auth.get_master_key().map_or_else(|| !is_keys_action(A), |mk| mk == token) {
-                return Some(AuthFilter::default());
+                return Ok(AuthFilter::default());
             }
 
             let (key_uuid, search_rules) =
                 match ActionPolicy::<A>::authenticate_tenant_token(&auth, token) {
-                    TenantTokenOutcome::Valid(key_uuid, search_rules) => {
+                    Ok(TenantTokenOutcome::Valid(key_uuid, search_rules)) => {
                         (key_uuid, Some(search_rules))
                     }
-                    TenantTokenOutcome::Expired => return None,
-                    TenantTokenOutcome::Invalid => return None,
-                    TenantTokenOutcome::NotATenantToken => {
-                        (auth.get_optional_uid_from_encoded_key(token.as_bytes()).ok()??, None)
-                    }
+                    Ok(TenantTokenOutcome::NotATenantToken)
+                    | Err(AuthError::InvalidTenantToken) => (
+                        auth.get_optional_uid_from_encoded_key(token.as_bytes())
+                            .map_err(|_e| AuthError::InvalidApiKey)?
+                            .ok_or(AuthError::InvalidApiKey)?,
+                        None,
+                    ),
+                    Err(e) => return Err(e),
                 };
 
             // check that the indexes are allowed
-            let action = Action::from_repr(A)?;
-            let auth_filter = auth.get_key_filters(key_uuid, search_rules).ok()?;
-            if auth.is_key_authorized(key_uuid, action, index).unwrap_or(false)
-                && index.map(|index| auth_filter.is_index_authorized(index)).unwrap_or(true)
-            {
-                return Some(auth_filter);
+            let action = Action::from_repr(A).ok_or(AuthError::InternalInvalidAction(A))?;
+            let auth_filter = auth
+                .get_key_filters(key_uuid, search_rules)
+                .map_err(|_e| AuthError::InvalidApiKey)?;
+
+            // First check if the index is authorized in the tenant token, this is a public
+            // information, we can return a nice error message.
+            if let Some(index) = index {
+                if !auth_filter.tenant_token_is_index_authorized(index) {
+                    return Err(AuthError::TenantTokenAccessingnUnauthorizedIndex {
+                        index: index.to_string(),
+                        allowed: auth_filter.tenant_token_list_index_authorized(),
+                    });
+                }
+                if !auth_filter.api_key_is_index_authorized(index) {
+                    if auth_filter.is_tenant_token() {
+                        // If the error comes from a tenant token we cannot share the list
+                        // of authorized indexes in the API key. This is not public information.
+                        return Err(AuthError::TenantTokenApiKeyAccessingnUnauthorizedIndex {
+                            index: index.to_string(),
+                        });
+                    } else {
+                        // Otherwise we can share the list
+                        // of authorized indexes in the API key.
+                        return Err(AuthError::ApiKeyAccessingnUnauthorizedIndex {
+                            index: index.to_string(),
+                            allowed: auth_filter.api_key_list_index_authorized(),
+                        });
+                    }
+                }
+            }
+            if auth.is_key_authorized(key_uuid, action, index).unwrap_or(false) {
+                return Ok(auth_filter);
             }
 
-            None
+            Err(AuthError::InvalidApiKey)
         }
     }
 
     impl<const A: u8> ActionPolicy<A> {
-        fn authenticate_tenant_token(auth: &AuthController, token: &str) -> TenantTokenOutcome {
+        fn authenticate_tenant_token(
+            auth: &AuthController,
+            token: &str,
+        ) -> Result<TenantTokenOutcome, AuthError> {
             // Only search action can be accessed by a tenant token.
             if A != actions::SEARCH {
-                return TenantTokenOutcome::NotATenantToken;
+                return Ok(TenantTokenOutcome::NotATenantToken);
             }
 
-            let uid = if let Some(uid) = extract_key_id(token) {
-                uid
-            } else {
-                return TenantTokenOutcome::NotATenantToken;
-            };
+            let uid = extract_key_id(token)?;
 
             // Check if tenant token is valid.
             let key = if let Some(key) = auth.generate_key(uid) {
                 key
             } else {
-                return TenantTokenOutcome::Invalid;
+                return Err(AuthError::InvalidTenantToken);
             };
 
-            let data = if let Ok(data) = decode::<Claims>(
+            let data = decode::<Claims>(
                 token,
                 &DecodingKey::from_secret(key.as_bytes()),
                 &tenant_token_validation(),
-            ) {
-                data
-            } else {
-                return TenantTokenOutcome::Invalid;
-            };
+            )?;
 
             // Check if token is expired.
             if let Some(exp) = data.claims.exp {
-                if OffsetDateTime::now_utc().unix_timestamp() > exp {
-                    return TenantTokenOutcome::Expired;
+                let now = OffsetDateTime::now_utc().unix_timestamp();
+                if now > exp {
+                    return Err(AuthError::ExpiredTenantToken { exp, now });
                 }
             }
 
-            TenantTokenOutcome::Valid(uid, data.claims.search_rules)
+            Ok(TenantTokenOutcome::Valid(uid, data.claims.search_rules))
         }
     }
 

meilisearch/src/lib.rs

@@ -15,6 +15,7 @@ use std::fs::File;
 use std::io::{BufReader, BufWriter};
 use std::num::NonZeroUsize;
 use std::path::Path;
+use std::str::FromStr;
 use std::sync::Arc;
 use std::thread::{self, available_parallelism};
 use std::time::Duration;
@@ -23,13 +24,13 @@ use actix_cors::Cors;
 use actix_http::body::MessageBody;
 use actix_web::dev::{ServiceFactory, ServiceResponse};
 use actix_web::error::JsonPayloadError;
+use actix_web::http::header::{CONTENT_TYPE, USER_AGENT};
 use actix_web::web::Data;
 use actix_web::{web, HttpRequest};
 use analytics::Analytics;
 use anyhow::bail;
 use error::PayloadError;
 use extractors::payload::PayloadConfig;
-use http::header::CONTENT_TYPE;
 use index_scheduler::{IndexScheduler, IndexSchedulerOptions};
 use meilisearch_auth::AuthController;
 use meilisearch_types::milli::documents::{DocumentsBatchBuilder, DocumentsBatchReader};
@@ -167,7 +168,7 @@ impl tracing_actix_web::RootSpanBuilder for AwebTracingLogger {
         let conn_info = request.connection_info();
         let headers = request.headers();
         let user_agent = headers
-            .get(http::header::USER_AGENT)
+            .get(USER_AGENT)
             .map(|value| String::from_utf8_lossy(value.as_bytes()).into_owned())
             .unwrap_or_default();
         info_span!("HTTP request", method = %request.method(), host = conn_info.host(), route = %request.path(), query_parameters = %request.query_string(), %user_agent, status_code = Empty, error = Empty)
@@ -300,15 +301,15 @@ fn open_or_create_database_unchecked(
             dumps_path: opt.dump_dir.clone(),
             webhook_url: opt.task_webhook_url.as_ref().map(|url| url.to_string()),
             webhook_authorization_header: opt.task_webhook_authorization_header.clone(),
-            task_db_size: opt.max_task_db_size.get_bytes() as usize,
-            index_base_map_size: opt.max_index_size.get_bytes() as usize,
+            task_db_size: opt.max_task_db_size.as_u64() as usize,
+            index_base_map_size: opt.max_index_size.as_u64() as usize,
             enable_mdb_writemap: opt.experimental_reduce_indexing_memory_usage,
             indexer_config: (&opt.indexer_options).try_into()?,
             autobatching_enabled: true,
             cleanup_enabled: !opt.experimental_replication_parameters,
             max_number_of_tasks: 1_000_000,
             max_number_of_batched_tasks: opt.experimental_max_number_of_batched_tasks,
-            index_growth_amount: byte_unit::Byte::from_str("10GiB").unwrap().get_bytes() as usize,
+            index_growth_amount: byte_unit::Byte::from_str("10GiB").unwrap().as_u64() as usize,
             index_count: DEFAULT_INDEX_COUNT,
             instance_features,
         })?)
@@ -476,7 +477,7 @@ pub fn configure_data(
         opt.experimental_search_queue_size,
         available_parallelism().unwrap_or(NonZeroUsize::new(2).unwrap()),
     );
-    let http_payload_size_limit = opt.http_payload_size_limit.get_bytes() as usize;
+    let http_payload_size_limit = opt.http_payload_size_limit.as_u64() as usize;
     config
         .app_data(index_scheduler)
         .app_data(auth)

meilisearch/src/main.rs

@@ -151,7 +151,7 @@ async fn run_http(
     .keep_alive(KeepAlive::Os);
 
     if let Some(config) = opt_clone.get_ssl_config()? {
-        http_server.bind_rustls_021(opt_clone.http_addr, config)?.run().await?;
+        http_server.bind_rustls_0_23(opt_clone.http_addr, config)?.run().await?;
     } else {
         http_server.bind(&opt_clone.http_addr)?.run().await?;
     }

meilisearch/src/option.rs

@@ -9,16 +9,14 @@ use std::str::FromStr;
 use std::sync::Arc;
 use std::{env, fmt, fs};
 
-use byte_unit::{Byte, ByteError};
+use byte_unit::{Byte, ParseError, UnitType};
 use clap::Parser;
 use meilisearch_types::features::InstanceTogglableFeatures;
 use meilisearch_types::milli::update::IndexerConfig;
 use meilisearch_types::milli::ThreadPoolNoAbortBuilder;
-use rustls::server::{
-    AllowAnyAnonymousOrAuthenticatedClient, AllowAnyAuthenticatedClient, ServerSessionMemoryCache,
-};
+use rustls::server::{ServerSessionMemoryCache, WebPkiClientVerifier};
 use rustls::RootCertStore;
-use rustls_pemfile::{certs, pkcs8_private_keys, rsa_private_keys};
+use rustls_pemfile::{certs, rsa_private_keys};
 use serde::{Deserialize, Serialize};
 use sysinfo::{MemoryRefreshKind, RefreshKind, System};
 use url::Url;
@@ -54,6 +52,7 @@ const MEILI_LOG_LEVEL: &str = "MEILI_LOG_LEVEL";
 const MEILI_EXPERIMENTAL_LOGS_MODE: &str = "MEILI_EXPERIMENTAL_LOGS_MODE";
 const MEILI_EXPERIMENTAL_REPLICATION_PARAMETERS: &str = "MEILI_EXPERIMENTAL_REPLICATION_PARAMETERS";
 const MEILI_EXPERIMENTAL_ENABLE_LOGS_ROUTE: &str = "MEILI_EXPERIMENTAL_ENABLE_LOGS_ROUTE";
+const MEILI_EXPERIMENTAL_CONTAINS_FILTER: &str = "MEILI_EXPERIMENTAL_CONTAINS_FILTER";
 const MEILI_EXPERIMENTAL_ENABLE_METRICS: &str = "MEILI_EXPERIMENTAL_ENABLE_METRICS";
 const MEILI_EXPERIMENTAL_SEARCH_QUEUE_SIZE: &str = "MEILI_EXPERIMENTAL_SEARCH_QUEUE_SIZE";
 const MEILI_EXPERIMENTAL_REDUCE_INDEXING_MEMORY_USAGE: &str =
@@ -339,6 +338,13 @@ pub struct Opt {
     #[serde(default)]
     pub log_level: LogLevel,
 
+    /// Experimental contains filter feature. For more information, see: <https://github.com/orgs/meilisearch/discussions/763>
+    ///
+    /// Enables the experimental contains filter operator.
+    #[clap(long, env = MEILI_EXPERIMENTAL_CONTAINS_FILTER)]
+    #[serde(default)]
+    pub experimental_contains_filter: bool,
+
     /// Experimental metrics feature. For more information, see: <https://github.com/meilisearch/meilisearch/discussions/3518>
     ///
     /// Enables the Prometheus metrics on the `GET /metrics` endpoint.
@@ -483,6 +489,7 @@ impl Opt {
             config_file_path: _,
             #[cfg(feature = "analytics")]
             no_analytics,
+            experimental_contains_filter,
             experimental_enable_metrics,
             experimental_search_queue_size,
             experimental_logs_mode,
@@ -540,6 +547,10 @@ impl Opt {
 
         export_to_env_if_not_present(MEILI_DUMP_DIR, dump_dir);
         export_to_env_if_not_present(MEILI_LOG_LEVEL, log_level.to_string());
+        export_to_env_if_not_present(
+            MEILI_EXPERIMENTAL_CONTAINS_FILTER,
+            experimental_contains_filter.to_string(),
+        );
         export_to_env_if_not_present(
             MEILI_EXPERIMENTAL_ENABLE_METRICS,
             experimental_enable_metrics.to_string(),
@@ -569,23 +580,21 @@ impl Opt {
 
     pub fn get_ssl_config(&self) -> anyhow::Result<Option<rustls::ServerConfig>> {
         if let (Some(cert_path), Some(key_path)) = (&self.ssl_cert_path, &self.ssl_key_path) {
-            let config = rustls::ServerConfig::builder().with_safe_defaults();
+            let config = rustls::ServerConfig::builder();
 
             let config = match &self.ssl_auth_path {
                 Some(auth_path) => {
                     let roots = load_certs(auth_path.to_path_buf())?;
                     let mut client_auth_roots = RootCertStore::empty();
                     for root in roots {
-                        client_auth_roots.add(&root).unwrap();
+                        client_auth_roots.add(root).unwrap();
                     }
-                    if self.ssl_require_auth {
-                        let verifier = AllowAnyAuthenticatedClient::new(client_auth_roots);
-                        config.with_client_cert_verifier(Arc::from(verifier))
-                    } else {
-                        let verifier =
-                            AllowAnyAnonymousOrAuthenticatedClient::new(client_auth_roots);
-                        config.with_client_cert_verifier(Arc::from(verifier))
+                    let mut client_verifier =
+                        WebPkiClientVerifier::builder(client_auth_roots.into());
+                    if !self.ssl_require_auth {
+                        client_verifier = client_verifier.allow_unauthenticated();
                     }
+                    config.with_client_cert_verifier(client_verifier.build()?)
                 }
                 None => config.with_no_client_auth(),
             };
@@ -594,7 +603,7 @@ impl Opt {
             let privkey = load_private_key(key_path.to_path_buf())?;
             let ocsp = load_ocsp(&self.ssl_ocsp_path)?;
             let mut config = config
-                .with_single_cert_with_ocsp_and_sct(certs, privkey, ocsp, vec![])
+                .with_single_cert_with_ocsp(certs, privkey, ocsp)
                 .map_err(|_| anyhow::anyhow!("bad certificates/private key"))?;
 
             config.key_log = Arc::new(rustls::KeyLogFile::new());
@@ -604,7 +613,7 @@ impl Opt {
             }
 
             if self.ssl_tickets {
-                config.ticketer = rustls::Ticketer::new().unwrap();
+                config.ticketer = rustls::crypto::ring::Ticketer::new().unwrap();
             }
 
             Ok(Some(config))
@@ -617,6 +626,7 @@ impl Opt {
         InstanceTogglableFeatures {
             metrics: self.experimental_enable_metrics,
             logs_route: self.experimental_enable_logs_route,
+            contains_filter: self.experimental_contains_filter,
         }
     }
 }
@@ -674,7 +684,7 @@ impl TryFrom<&IndexerOpts> for IndexerConfig {
 
         Ok(Self {
             log_every_n: Some(DEFAULT_LOG_EVERY_N),
-            max_memory: other.max_indexing_memory.map(|b| b.get_bytes() as usize),
+            max_memory: other.max_indexing_memory.map(|b| b.as_u64() as usize),
             thread_pool: Some(thread_pool),
             max_positions_per_attributes: None,
             skip_index_budget: other.skip_index_budget,
@@ -688,23 +698,25 @@ impl TryFrom<&IndexerOpts> for IndexerConfig {
 pub struct MaxMemory(Option<Byte>);
 
 impl FromStr for MaxMemory {
-    type Err = ByteError;
+    type Err = ParseError;
 
-    fn from_str(s: &str) -> Result<MaxMemory, ByteError> {
+    fn from_str(s: &str) -> Result<MaxMemory, Self::Err> {
         Byte::from_str(s).map(Some).map(MaxMemory)
     }
 }
 
 impl Default for MaxMemory {
     fn default() -> MaxMemory {
-        MaxMemory(total_memory_bytes().map(|bytes| bytes * 2 / 3).map(Byte::from_bytes))
+        MaxMemory(total_memory_bytes().map(|bytes| bytes * 2 / 3).map(Byte::from_u64))
     }
 }
 
 impl fmt::Display for MaxMemory {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         match self.0 {
-            Some(memory) => write!(f, "{}", memory.get_appropriate_unit(true)),
+            Some(memory) => {
+                write!(f, "{}", memory.get_appropriate_unit(UnitType::Binary))
+            }
             None => f.write_str("unknown"),
         }
     }
@@ -767,21 +779,26 @@ impl Deref for MaxThreads {
     }
 }
 
-fn load_certs(filename: PathBuf) -> anyhow::Result<Vec<rustls::Certificate>> {
+fn load_certs(
+    filename: PathBuf,
+) -> anyhow::Result<Vec<rustls::pki_types::CertificateDer<'static>>> {
     let certfile =
         fs::File::open(filename).map_err(|_| anyhow::anyhow!("cannot open certificate file"))?;
     let mut reader = BufReader::new(certfile);
     certs(&mut reader)
-        .map(|certs| certs.into_iter().map(rustls::Certificate).collect())
+        .collect::<Result<Vec<_>, _>>()
         .map_err(|_| anyhow::anyhow!("cannot read certificate file"))
 }
 
-fn load_private_key(filename: PathBuf) -> anyhow::Result<rustls::PrivateKey> {
+fn load_private_key(
+    filename: PathBuf,
+) -> anyhow::Result<rustls::pki_types::PrivateKeyDer<'static>> {
     let rsa_keys = {
         let keyfile = fs::File::open(filename.clone())
             .map_err(|_| anyhow::anyhow!("cannot open private key file"))?;
         let mut reader = BufReader::new(keyfile);
         rsa_private_keys(&mut reader)
+            .collect::<Result<Vec<_>, _>>()
             .map_err(|_| anyhow::anyhow!("file contains invalid rsa private key"))?
     };
 
@@ -789,19 +806,21 @@ fn load_private_key(filename: PathBuf) -> anyhow::Result<rustls::PrivateKey> {
         let keyfile = fs::File::open(filename)
             .map_err(|_| anyhow::anyhow!("cannot open private key file"))?;
         let mut reader = BufReader::new(keyfile);
-        pkcs8_private_keys(&mut reader).map_err(|_| {
-            anyhow::anyhow!(
-                "file contains invalid pkcs8 private key (encrypted keys not supported)"
-            )
-        })?
+        rustls_pemfile::pkcs8_private_keys(&mut reader).collect::<Result<Vec<_>, _>>().map_err(
+            |_| {
+                anyhow::anyhow!(
+                    "file contains invalid pkcs8 private key (encrypted keys not supported)"
+                )
+            },
+        )?
     };
 
     // prefer to load pkcs8 keys
     if !pkcs8_keys.is_empty() {
-        Ok(rustls::PrivateKey(pkcs8_keys[0].clone()))
+        Ok(rustls::pki_types::PrivateKeyDer::Pkcs8(pkcs8_keys[0].clone_key()))
     } else {
         assert!(!rsa_keys.is_empty());
-        Ok(rustls::PrivateKey(rsa_keys[0].clone()))
+        Ok(rustls::pki_types::PrivateKeyDer::Pkcs1(rsa_keys[0].clone_key()))
     }
 }
 
@@ -844,11 +863,11 @@ fn default_env() -> String {
 }
 
 fn default_max_index_size() -> Byte {
-    Byte::from_bytes(INDEX_SIZE)
+    Byte::from_u64(INDEX_SIZE)
 }
 
 fn default_max_task_db_size() -> Byte {
-    Byte::from_bytes(TASK_DB_SIZE)
+    Byte::from_u64(TASK_DB_SIZE)
 }
 
 fn default_http_payload_size_limit() -> Byte {

meilisearch/src/routes/features.rs

@@ -48,7 +48,9 @@ pub struct RuntimeTogglableFeatures {
     #[deserr(default)]
     pub logs_route: Option<bool>,
     #[deserr(default)]
-    pub export_puffin_reports: Option<bool>,
+    pub edit_documents_by_function: Option<bool>,
+    #[deserr(default)]
+    pub contains_filter: Option<bool>,
 }
 
 async fn patch_features(
@@ -68,10 +70,11 @@ async fn patch_features(
         vector_store: new_features.0.vector_store.unwrap_or(old_features.vector_store),
         metrics: new_features.0.metrics.unwrap_or(old_features.metrics),
         logs_route: new_features.0.logs_route.unwrap_or(old_features.logs_route),
-        export_puffin_reports: new_features
+        edit_documents_by_function: new_features
             .0
-            .export_puffin_reports
-            .unwrap_or(old_features.export_puffin_reports),
+            .edit_documents_by_function
+            .unwrap_or(old_features.edit_documents_by_function),
+        contains_filter: new_features.0.contains_filter.unwrap_or(old_features.contains_filter),
     };
 
     // explicitly destructure for analytics rather than using the `Serialize` implementation, because
@@ -81,7 +84,8 @@ async fn patch_features(
         vector_store,
         metrics,
         logs_route,
-        export_puffin_reports,
+        edit_documents_by_function,
+        contains_filter,
     } = new_features;
 
     analytics.publish(
@@ -90,7 +94,8 @@ async fn patch_features(
             "vector_store": vector_store,
             "metrics": metrics,
             "logs_route": logs_route,
-            "export_puffin_reports": export_puffin_reports,
+            "edit_documents_by_function": edit_documents_by_function,
+            "contains_filter": contains_filter,
         }),
         Some(&req),
     );

meilisearch/src/routes/indexes/documents.rs

@@ -7,7 +7,7 @@ use bstr::ByteSlice as _;
 use deserr::actix_web::{AwebJson, AwebQueryParameter};
 use deserr::Deserr;
 use futures::StreamExt;
-use index_scheduler::{IndexScheduler, TaskId};
+use index_scheduler::{IndexScheduler, RoFeatures, TaskId};
 use meilisearch_types::deserr::query_params::Param;
 use meilisearch_types::deserr::{DeserrJsonError, DeserrQueryParamError};
 use meilisearch_types::document_formats::{read_csv, read_json, read_ndjson, PayloadType};
@@ -16,6 +16,7 @@ use meilisearch_types::error::{Code, ResponseError};
 use meilisearch_types::heed::RoTxn;
 use meilisearch_types::index_uid::IndexUid;
 use meilisearch_types::milli::update::IndexDocumentsMethod;
+use meilisearch_types::milli::vector::parsed_vectors::ExplicitVectors;
 use meilisearch_types::milli::DocumentId;
 use meilisearch_types::star_or::OptionStarOrList;
 use meilisearch_types::tasks::KindWithContent;
@@ -39,7 +40,7 @@ use crate::extractors::sequential_extractor::SeqHandler;
 use crate::routes::{
     get_task_id, is_dry_run, PaginationView, SummarizedTaskView, PAGINATION_DEFAULT_LIMIT,
 };
-use crate::search::parse_filter;
+use crate::search::{parse_filter, RetrieveVectors};
 use crate::Opt;
 
 static ACCEPTED_CONTENT_TYPE: Lazy<Vec<String>> = Lazy::new(|| {
@@ -81,6 +82,7 @@ pub fn configure(cfg: &mut web::ServiceConfig) {
         web::resource("/delete-batch").route(web::post().to(SeqHandler(delete_documents_batch))),
     )
     .service(web::resource("/delete").route(web::post().to(SeqHandler(delete_documents_by_filter))))
+    .service(web::resource("/edit").route(web::post().to(SeqHandler(edit_documents_by_function))))
     .service(web::resource("/fetch").route(web::post().to(SeqHandler(documents_by_query_post))))
     .service(
         web::resource("/{document_id}")
@@ -94,6 +96,8 @@ pub fn configure(cfg: &mut web::ServiceConfig) {
 pub struct GetDocument {
     #[deserr(default, error = DeserrQueryParamError<InvalidDocumentFields>)]
     fields: OptionStarOrList<String>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidDocumentRetrieveVectors>)]
+    retrieve_vectors: Param<bool>,
 }
 
 pub async fn get_document(
@@ -107,13 +111,20 @@ pub async fn get_document(
     debug!(parameters = ?params, "Get document");
     let index_uid = IndexUid::try_from(index_uid)?;
 
-    analytics.get_fetch_documents(&DocumentFetchKind::PerDocumentId, &req);
-
-    let GetDocument { fields } = params.into_inner();
+    let GetDocument { fields, retrieve_vectors: param_retrieve_vectors } = params.into_inner();
     let attributes_to_retrieve = fields.merge_star_and_none();
 
+    let features = index_scheduler.features();
+    let retrieve_vectors = RetrieveVectors::new(param_retrieve_vectors.0, features)?;
+
+    analytics.get_fetch_documents(
+        &DocumentFetchKind::PerDocumentId { retrieve_vectors: param_retrieve_vectors.0 },
+        &req,
+    );
+
     let index = index_scheduler.index(&index_uid)?;
-    let document = retrieve_document(&index, &document_id, attributes_to_retrieve)?;
+    let document =
+        retrieve_document(&index, &document_id, attributes_to_retrieve, retrieve_vectors)?;
     debug!(returns = ?document, "Get document");
     Ok(HttpResponse::Ok().json(document))
 }
@@ -153,6 +164,8 @@ pub struct BrowseQueryGet {
     limit: Param<usize>,
     #[deserr(default, error = DeserrQueryParamError<InvalidDocumentFields>)]
     fields: OptionStarOrList<String>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidDocumentRetrieveVectors>)]
+    retrieve_vectors: Param<bool>,
     #[deserr(default, error = DeserrQueryParamError<InvalidDocumentFilter>)]
     filter: Option<String>,
 }
@@ -166,6 +179,8 @@ pub struct BrowseQuery {
     limit: usize,
     #[deserr(default, error = DeserrJsonError<InvalidDocumentFields>)]
     fields: Option<Vec<String>>,
+    #[deserr(default, error = DeserrJsonError<InvalidDocumentRetrieveVectors>)]
+    retrieve_vectors: bool,
     #[deserr(default, error = DeserrJsonError<InvalidDocumentFilter>)]
     filter: Option<Value>,
 }
@@ -185,6 +200,7 @@ pub async fn documents_by_query_post(
             with_filter: body.filter.is_some(),
             limit: body.limit,
             offset: body.offset,
+            retrieve_vectors: body.retrieve_vectors,
         },
         &req,
     );
@@ -201,7 +217,7 @@ pub async fn get_documents(
 ) -> Result<HttpResponse, ResponseError> {
     debug!(parameters = ?params, "Get documents GET");
 
-    let BrowseQueryGet { limit, offset, fields, filter } = params.into_inner();
+    let BrowseQueryGet { limit, offset, fields, retrieve_vectors, filter } = params.into_inner();
 
     let filter = match filter {
         Some(f) => match serde_json::from_str(&f) {
@@ -215,6 +231,7 @@ pub async fn get_documents(
         offset: offset.0,
         limit: limit.0,
         fields: fields.merge_star_and_none(),
+        retrieve_vectors: retrieve_vectors.0,
         filter,
     };
 
@@ -223,6 +240,7 @@ pub async fn get_documents(
             with_filter: query.filter.is_some(),
             limit: query.limit,
             offset: query.offset,
+            retrieve_vectors: query.retrieve_vectors,
         },
         &req,
     );
@@ -236,10 +254,21 @@ fn documents_by_query(
     query: BrowseQuery,
 ) -> Result<HttpResponse, ResponseError> {
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
-    let BrowseQuery { offset, limit, fields, filter } = query;
+    let BrowseQuery { offset, limit, fields, retrieve_vectors, filter } = query;
+
+    let features = index_scheduler.features();
+    let retrieve_vectors = RetrieveVectors::new(retrieve_vectors, features)?;
 
     let index = index_scheduler.index(&index_uid)?;
-    let (total, documents) = retrieve_documents(&index, offset, limit, filter, fields)?;
+    let (total, documents) = retrieve_documents(
+        &index,
+        offset,
+        limit,
+        filter,
+        fields,
+        retrieve_vectors,
+        index_scheduler.features(),
+    )?;
 
     let ret = PaginationView::new(offset, limit, total as usize, documents);
 
@@ -283,7 +312,11 @@ pub async fn replace_documents(
     debug!(parameters = ?params, "Replace documents");
     let params = params.into_inner();
 
-    analytics.add_documents(&params, index_scheduler.index(&index_uid).is_err(), &req);
+    analytics.add_documents(
+        &params,
+        index_scheduler.index_exists(&index_uid).map_or(true, |x| !x),
+        &req,
+    );
 
     let allow_index_creation = index_scheduler.filters().allow_index_creation(&index_uid);
     let uid = get_task_id(&req, &opt)?;
@@ -320,7 +353,11 @@ pub async fn update_documents(
     let params = params.into_inner();
     debug!(parameters = ?params, "Update documents");
 
-    analytics.update_documents(&params, index_scheduler.index(&index_uid).is_err(), &req);
+    analytics.add_documents(
+        &params,
+        index_scheduler.index_exists(&index_uid).map_or(true, |x| !x),
+        &req,
+    );
 
     let allow_index_creation = index_scheduler.filters().allow_index_creation(&index_uid);
     let uid = get_task_id(&req, &opt)?;
@@ -535,11 +572,9 @@ pub async fn delete_documents_by_filter(
     analytics.delete_documents(DocumentDeletionKind::PerFilter, &req);
 
     // we ensure the filter is well formed before enqueuing it
-    || -> Result<_, ResponseError> {
-        Ok(crate::search::parse_filter(&filter)?.ok_or(MeilisearchHttpError::EmptyFilter)?)
-    }()
-    // and whatever was the error, the error code should always be an InvalidDocumentFilter
-    .map_err(|err| ResponseError::from_msg(err.message, Code::InvalidDocumentFilter))?;
+    crate::search::parse_filter(&filter, Code::InvalidDocumentFilter, index_scheduler.features())?
+        .ok_or(MeilisearchHttpError::EmptyFilter)?;
+
     let task = KindWithContent::DocumentDeletionByFilter { index_uid, filter_expr: filter };
 
     let uid = get_task_id(&req, &opt)?;
@@ -553,6 +588,83 @@ pub async fn delete_documents_by_filter(
     Ok(HttpResponse::Accepted().json(task))
 }
 
+#[derive(Debug, Deserr)]
+#[deserr(error = DeserrJsonError, rename_all = camelCase, deny_unknown_fields)]
+pub struct DocumentEditionByFunction {
+    #[deserr(default, error = DeserrJsonError<InvalidDocumentFilter>)]
+    pub filter: Option<Value>,
+    #[deserr(default, error = DeserrJsonError<InvalidDocumentEditionContext>)]
+    pub context: Option<Value>,
+    #[deserr(error = DeserrJsonError<InvalidDocumentEditionFunctionFilter>, missing_field_error = DeserrJsonError::missing_document_edition_function)]
+    pub function: String,
+}
+
+pub async fn edit_documents_by_function(
+    index_scheduler: GuardedData<ActionPolicy<{ actions::DOCUMENTS_ALL }>, Data<IndexScheduler>>,
+    index_uid: web::Path<String>,
+    params: AwebJson<DocumentEditionByFunction, DeserrJsonError>,
+    req: HttpRequest,
+    opt: web::Data<Opt>,
+    analytics: web::Data<dyn Analytics>,
+) -> Result<HttpResponse, ResponseError> {
+    debug!(parameters = ?params, "Edit documents by function");
+
+    index_scheduler
+        .features()
+        .check_edit_documents_by_function("Using the documents edit route")?;
+
+    let index_uid = IndexUid::try_from(index_uid.into_inner())?;
+    let index_uid = index_uid.into_inner();
+    let params = params.into_inner();
+
+    analytics.update_documents_by_function(
+        &params,
+        index_scheduler.index(&index_uid).is_err(),
+        &req,
+    );
+
+    let DocumentEditionByFunction { filter, context, function } = params;
+    let engine = milli::rhai::Engine::new();
+    if let Err(e) = engine.compile(&function) {
+        return Err(ResponseError::from_msg(e.to_string(), Code::BadRequest));
+    }
+
+    if let Some(ref filter) = filter {
+        // we ensure the filter is well formed before enqueuing it
+        crate::search::parse_filter(
+            filter,
+            Code::InvalidDocumentFilter,
+            index_scheduler.features(),
+        )?
+        .ok_or(MeilisearchHttpError::EmptyFilter)?;
+    }
+    let task = KindWithContent::DocumentEdition {
+        index_uid,
+        filter_expr: filter,
+        context: match context {
+            Some(Value::Object(m)) => Some(m),
+            None => None,
+            _ => {
+                return Err(ResponseError::from_msg(
+                    "The context must be an object".to_string(),
+                    Code::InvalidDocumentEditionContext,
+                ))
+            }
+        },
+        function,
+    };
+
+    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, "Edit documents by function");
+    Ok(HttpResponse::Accepted().json(task))
+}
+
 pub async fn clear_all_documents(
     index_scheduler: GuardedData<ActionPolicy<{ actions::DOCUMENTS_DELETE }>, Data<IndexScheduler>>,
     index_uid: web::Path<String>,
@@ -579,13 +691,46 @@ fn some_documents<'a, 't: 'a>(
     index: &'a Index,
     rtxn: &'t RoTxn,
     doc_ids: impl IntoIterator<Item = DocumentId> + 'a,
+    retrieve_vectors: RetrieveVectors,
 ) -> Result<impl Iterator<Item = Result<Document, ResponseError>> + 'a, ResponseError> {
     let fields_ids_map = index.fields_ids_map(rtxn)?;
     let all_fields: Vec<_> = fields_ids_map.iter().map(|(id, _)| id).collect();
+    let embedding_configs = index.embedding_configs(rtxn)?;
 
     Ok(index.iter_documents(rtxn, doc_ids)?.map(move |ret| {
-        ret.map_err(ResponseError::from).and_then(|(_key, document)| -> Result<_, ResponseError> {
-            Ok(milli::obkv_to_json(&all_fields, &fields_ids_map, document)?)
+        ret.map_err(ResponseError::from).and_then(|(key, document)| -> Result<_, ResponseError> {
+            let mut document = milli::obkv_to_json(&all_fields, &fields_ids_map, document)?;
+            match retrieve_vectors {
+                RetrieveVectors::Ignore => {}
+                RetrieveVectors::Hide => {
+                    document.remove("_vectors");
+                }
+                RetrieveVectors::Retrieve => {
+                    // Clippy is simply wrong
+                    #[allow(clippy::manual_unwrap_or_default)]
+                    let mut vectors = match document.remove("_vectors") {
+                        Some(Value::Object(map)) => map,
+                        _ => Default::default(),
+                    };
+                    for (name, vector) in index.embeddings(rtxn, key)? {
+                        let user_provided = embedding_configs
+                            .iter()
+                            .find(|conf| conf.name == name)
+                            .is_some_and(|conf| conf.user_provided.contains(key));
+                        let embeddings = ExplicitVectors {
+                            embeddings: Some(vector.into()),
+                            regenerate: !user_provided,
+                        };
+                        vectors.insert(
+                            name,
+                            serde_json::to_value(embeddings).map_err(MeilisearchHttpError::from)?,
+                        );
+                    }
+                    document.insert("_vectors".into(), vectors.into());
+                }
+            }
+
+            Ok(document)
         })
     }))
 }
@@ -596,12 +741,13 @@ fn retrieve_documents<S: AsRef<str>>(
     limit: usize,
     filter: Option<Value>,
     attributes_to_retrieve: Option<Vec<S>>,
+    retrieve_vectors: RetrieveVectors,
+    features: RoFeatures,
 ) -> Result<(u64, Vec<Document>), ResponseError> {
     let rtxn = index.read_txn()?;
     let filter = &filter;
     let filter = if let Some(filter) = filter {
-        parse_filter(filter)
-            .map_err(|err| ResponseError::from_msg(err.to_string(), Code::InvalidDocumentFilter))?
+        parse_filter(filter, Code::InvalidDocumentFilter, features)?
     } else {
         None
     };
@@ -620,53 +766,57 @@ fn retrieve_documents<S: AsRef<str>>(
     let (it, number_of_documents) = {
         let number_of_documents = candidates.len();
         (
-            some_documents(index, &rtxn, candidates.into_iter().skip(offset).take(limit))?,
+            some_documents(
+                index,
+                &rtxn,
+                candidates.into_iter().skip(offset).take(limit),
+                retrieve_vectors,
+            )?,
             number_of_documents,
         )
     };
 
-    let documents: Result<Vec<_>, ResponseError> = it
+    let documents: Vec<_> = it
         .map(|document| {
             Ok(match &attributes_to_retrieve {
                 Some(attributes_to_retrieve) => permissive_json_pointer::select_values(
                     &document?,
-                    attributes_to_retrieve.iter().map(|s| s.as_ref()),
+                    attributes_to_retrieve.iter().map(|s| s.as_ref()).chain(
+                        (retrieve_vectors == RetrieveVectors::Retrieve).then_some("_vectors"),
+                    ),
                 ),
                 None => document?,
             })
         })
-        .collect();
+        .collect::<Result<_, ResponseError>>()?;
 
-    Ok((number_of_documents, documents?))
+    Ok((number_of_documents, documents))
 }
 
 fn retrieve_document<S: AsRef<str>>(
     index: &Index,
     doc_id: &str,
     attributes_to_retrieve: Option<Vec<S>>,
+    retrieve_vectors: RetrieveVectors,
 ) -> Result<Document, ResponseError> {
     let txn = index.read_txn()?;
 
-    let fields_ids_map = index.fields_ids_map(&txn)?;
-    let all_fields: Vec<_> = fields_ids_map.iter().map(|(id, _)| id).collect();
-
     let internal_id = index
         .external_documents_ids()
         .get(&txn, doc_id)?
         .ok_or_else(|| MeilisearchHttpError::DocumentNotFound(doc_id.to_string()))?;
 
-    let document = index
-        .documents(&txn, std::iter::once(internal_id))?
-        .into_iter()
+    let document = some_documents(index, &txn, Some(internal_id), retrieve_vectors)?
         .next()
-        .map(|(_, d)| d)
-        .ok_or_else(|| MeilisearchHttpError::DocumentNotFound(doc_id.to_string()))?;
+        .ok_or_else(|| MeilisearchHttpError::DocumentNotFound(doc_id.to_string()))??;
 
-    let document = meilisearch_types::milli::obkv_to_json(&all_fields, &fields_ids_map, document)?;
     let document = match &attributes_to_retrieve {
         Some(attributes_to_retrieve) => permissive_json_pointer::select_values(
             &document,
-            attributes_to_retrieve.iter().map(|s| s.as_ref()),
+            attributes_to_retrieve
+                .iter()
+                .map(|s| s.as_ref())
+                .chain((retrieve_vectors == RetrieveVectors::Retrieve).then_some("_vectors")),
         ),
         None => document,
     };

meilisearch/src/routes/indexes/facet_search.rs

@@ -14,8 +14,8 @@ 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, HybridQuery, MatchingStrategy, SearchQuery,
-    DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG,
+    add_search_rules, perform_facet_search, 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;
@@ -46,6 +46,8 @@ pub struct FacetSearchQuery {
     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>,
 }
 
 pub async fn search(
@@ -69,7 +71,7 @@ pub async fn search(
 
     // Tenant token search_rules.
     if let Some(search_rules) = index_scheduler.filters().get_index_search_rules(&index_uid) {
-        add_search_rules(&mut search_query, search_rules);
+        add_search_rules(&mut search_query.filter, search_rules);
     }
 
     let index = index_scheduler.index(&index_uid)?;
@@ -77,7 +79,14 @@ pub async fn search(
     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)
+        perform_facet_search(
+            &index,
+            search_query,
+            facet_query,
+            facet_name,
+            search_kind,
+            index_scheduler.features(),
+        )
     })
     .await?;
 
@@ -103,6 +112,7 @@ impl From<FacetSearchQuery> for SearchQuery {
             matching_strategy,
             attributes_to_search_on,
             hybrid,
+            ranking_score_threshold,
         } = value;
 
         SearchQuery {
@@ -112,6 +122,7 @@ impl From<FacetSearchQuery> for SearchQuery {
             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,
@@ -120,6 +131,7 @@ impl From<FacetSearchQuery> for SearchQuery {
             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(),
@@ -128,6 +140,7 @@ impl From<FacetSearchQuery> for SearchQuery {
             vector,
             attributes_to_search_on,
             hybrid,
+            ranking_score_threshold,
         }
     }
 }

meilisearch/src/routes/indexes/mod.rs

@@ -29,6 +29,7 @@ pub mod documents;
 pub mod facet_search;
 pub mod search;
 pub mod settings;
+pub mod similar;
 
 pub fn configure(cfg: &mut web::ServiceConfig) {
     cfg.service(
@@ -48,6 +49,7 @@ pub fn configure(cfg: &mut web::ServiceConfig) {
             .service(web::scope("/documents").configure(documents::configure))
             .service(web::scope("/search").configure(search::configure))
             .service(web::scope("/facet-search").configure(facet_search::configure))
+            .service(web::scope("/similar").configure(similar::configure))
             .service(web::scope("/settings").configure(settings::configure)),
     );
 }

meilisearch/src/routes/indexes/search.rs

@@ -19,9 +19,10 @@ use crate::extractors::authentication::GuardedData;
 use crate::extractors::sequential_extractor::SeqHandler;
 use crate::metrics::MEILISEARCH_DEGRADED_SEARCH_REQUESTS;
 use crate::search::{
-    add_search_rules, perform_search, HybridQuery, MatchingStrategy, SearchKind, SearchQuery,
-    SemanticRatio, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG,
-    DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET, DEFAULT_SEMANTIC_RATIO,
+    add_search_rules, perform_search, HybridQuery, MatchingStrategy, RankingScoreThreshold,
+    RetrieveVectors, SearchKind, SearchQuery, SemanticRatio, DEFAULT_CROP_LENGTH,
+    DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG,
+    DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET, DEFAULT_SEMANTIC_RATIO,
 };
 use crate::search_queue::SearchQueue;
 
@@ -50,6 +51,8 @@ pub struct SearchQueryGet {
     hits_per_page: Option<Param<usize>>,
     #[deserr(default, error = DeserrQueryParamError<InvalidSearchAttributesToRetrieve>)]
     attributes_to_retrieve: Option<CS<String>>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidSearchRetrieveVectors>)]
+    retrieve_vectors: Param<bool>,
     #[deserr(default, error = DeserrQueryParamError<InvalidSearchAttributesToCrop>)]
     attributes_to_crop: Option<CS<String>>,
     #[deserr(default = Param(DEFAULT_CROP_LENGTH()), error = DeserrQueryParamError<InvalidSearchCropLength>)]
@@ -60,6 +63,8 @@ pub struct SearchQueryGet {
     filter: Option<String>,
     #[deserr(default, error = DeserrQueryParamError<InvalidSearchSort>)]
     sort: Option<String>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidSearchDistinct>)]
+    distinct: Option<String>,
     #[deserr(default, error = DeserrQueryParamError<InvalidSearchShowMatchesPosition>)]
     show_matches_position: Param<bool>,
     #[deserr(default, error = DeserrQueryParamError<InvalidSearchShowRankingScore>)]
@@ -82,6 +87,21 @@ pub struct SearchQueryGet {
     pub hybrid_embedder: Option<String>,
     #[deserr(default, error = DeserrQueryParamError<InvalidSearchSemanticRatio>)]
     pub hybrid_semantic_ratio: Option<SemanticRatioGet>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidSearchRankingScoreThreshold>)]
+    pub ranking_score_threshold: Option<RankingScoreThresholdGet>,
+}
+
+#[derive(Debug, Clone, Copy, PartialEq, deserr::Deserr)]
+#[deserr(try_from(String) = TryFrom::try_from -> InvalidSearchRankingScoreThreshold)]
+pub struct RankingScoreThresholdGet(RankingScoreThreshold);
+
+impl std::convert::TryFrom<String> for RankingScoreThresholdGet {
+    type Error = InvalidSearchRankingScoreThreshold;
+
+    fn try_from(s: String) -> Result<Self, Self::Error> {
+        let f: f64 = s.parse().map_err(|_| InvalidSearchRankingScoreThreshold)?;
+        Ok(RankingScoreThresholdGet(RankingScoreThreshold::try_from(f)?))
+    }
 }
 
 #[derive(Debug, Clone, Copy, Default, PartialEq, deserr::Deserr)]
@@ -137,11 +157,13 @@ impl From<SearchQueryGet> for SearchQuery {
             page: other.page.as_deref().copied(),
             hits_per_page: other.hits_per_page.as_deref().copied(),
             attributes_to_retrieve: other.attributes_to_retrieve.map(|o| o.into_iter().collect()),
+            retrieve_vectors: other.retrieve_vectors.0,
             attributes_to_crop: other.attributes_to_crop.map(|o| o.into_iter().collect()),
             crop_length: other.crop_length.0,
             attributes_to_highlight: other.attributes_to_highlight.map(|o| o.into_iter().collect()),
             filter,
             sort: other.sort.map(|attr| fix_sort_query_parameters(&attr)),
+            distinct: other.distinct,
             show_matches_position: other.show_matches_position.0,
             show_ranking_score: other.show_ranking_score.0,
             show_ranking_score_details: other.show_ranking_score_details.0,
@@ -152,6 +174,7 @@ impl From<SearchQueryGet> for SearchQuery {
             matching_strategy: other.matching_strategy,
             attributes_to_search_on: other.attributes_to_search_on.map(|o| o.into_iter().collect()),
             hybrid,
+            ranking_score_threshold: other.ranking_score_threshold.map(|o| o.0),
         }
     }
 }
@@ -196,7 +219,7 @@ pub async fn search_with_url_query(
 
     // Tenant token search_rules.
     if let Some(search_rules) = index_scheduler.filters().get_index_search_rules(&index_uid) {
-        add_search_rules(&mut query, search_rules);
+        add_search_rules(&mut query.filter, search_rules);
     }
 
     let mut aggregate = SearchAggregator::from_query(&query, &req);
@@ -205,10 +228,12 @@ pub async fn search_with_url_query(
     let features = index_scheduler.features();
 
     let search_kind = search_kind(&query, index_scheduler.get_ref(), &index, features)?;
-
+    let retrieve_vector = RetrieveVectors::new(query.retrieve_vectors, features)?;
     let _permit = search_queue.try_get_search_permit().await?;
-    let search_result =
-        tokio::task::spawn_blocking(move || perform_search(&index, query, search_kind)).await?;
+    let search_result = tokio::task::spawn_blocking(move || {
+        perform_search(&index, query, search_kind, retrieve_vector, index_scheduler.features())
+    })
+    .await?;
     if let Ok(ref search_result) = search_result {
         aggregate.succeed(search_result);
     }
@@ -235,7 +260,7 @@ pub async fn search_with_post(
 
     // Tenant token search_rules.
     if let Some(search_rules) = index_scheduler.filters().get_index_search_rules(&index_uid) {
-        add_search_rules(&mut query, search_rules);
+        add_search_rules(&mut query.filter, search_rules);
     }
 
     let mut aggregate = SearchAggregator::from_query(&query, &req);
@@ -245,10 +270,13 @@ pub async fn search_with_post(
     let features = index_scheduler.features();
 
     let search_kind = search_kind(&query, index_scheduler.get_ref(), &index, features)?;
+    let retrieve_vectors = RetrieveVectors::new(query.retrieve_vectors, features)?;
 
     let _permit = search_queue.try_get_search_permit().await?;
-    let search_result =
-        tokio::task::spawn_blocking(move || perform_search(&index, query, search_kind)).await?;
+    let search_result = tokio::task::spawn_blocking(move || {
+        perform_search(&index, query, search_kind, retrieve_vectors, index_scheduler.features())
+    })
+    .await?;
     if let Ok(ref search_result) = search_result {
         aggregate.succeed(search_result);
         if search_result.degraded {
@@ -270,11 +298,10 @@ pub fn search_kind(
     features: RoFeatures,
 ) -> Result<SearchKind, ResponseError> {
     if query.vector.is_some() {
-        features.check_vector("Passing `vector` as a query parameter")?;
+        features.check_vector("Passing `vector` as a parameter")?;
     }
-
     if query.hybrid.is_some() {
-        features.check_vector("Passing `hybrid` as a query parameter")?;
+        features.check_vector("Passing `hybrid` as a parameter")?;
     }
 
     // regardless of anything, always do a keyword search when we don't have a vector and the query is whitespace or missing