Merge #4881

4881: Infer locales from index settings r=curquiza a=ManyTheFish

# Pull Request

## Related issue
Fixes #4828
Fixes #4816
## What does this PR do?
- Add some test using `AttributesToSearchOn`
- Make the search infer the language based on the index settings when the `locales` filed is not precise


CI is now working:
https://github.com/meilisearch/meilisearch/actions/runs/10490050545/job/29055955667



Co-authored-by: ManyTheFish <many@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: dtolnay/rust-toolchain@1.79
               with:
                 profile: minimal
-                toolchain: stable
-                override: true
 
             - name: Run benchmarks - workload ${WORKLOAD_NAME} - branch ${{ github.ref }} - commit ${{ github.sha }}
               run: |

.github/workflows/bench-pr.yml

@@ -16,6 +16,37 @@ jobs:
       runs-on: benchmarks
       timeout-minutes: 180 # 3h
       steps:
+        - name: Check permissions
+          id: permission
+          env:
+            PR_AUTHOR: ${{github.event.issue.user.login }}
+            COMMENT_AUTHOR: ${{github.event.comment.user.login }}
+            REPOSITORY: ${{github.repository}}
+            PR_ID: ${{github.event.issue.number}}
+          run: |
+            PR_REPOSITORY=$(gh api /repos/"$REPOSITORY"/pulls/"$PR_ID" --jq .head.repo.full_name)
+            if $(gh api /repos/"$REPOSITORY"/collaborators/"$PR_AUTHOR"/permission --jq .user.permissions.push)
+            then
+              echo "::notice title=Authentication success::PR author authenticated"
+            else
+              echo "::error title=Authentication error::PR author doesn't have push permission on this repository"
+              exit 1
+            fi
+            if $(gh api /repos/"$REPOSITORY"/collaborators/"$COMMENT_AUTHOR"/permission --jq .user.permissions.push)
+            then
+              echo "::notice title=Authentication success::Comment author authenticated"
+            else
+              echo "::error title=Authentication error::Comment author doesn't have push permission on this repository"
+              exit 1
+            fi
+            if [ "$PR_REPOSITORY" = "$REPOSITORY" ]
+            then
+              echo "::notice title=Authentication success::PR started from main repository"
+            else
+              echo "::error title=Authentication error::PR started from a fork"
+              exit 1
+            fi
+
         - name: Check for Command
           id: command
           uses: xt0rted/slash-command-action@v2
@@ -35,11 +66,9 @@ 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: dtolnay/rust-toolchain@1.79
           with:
             profile: minimal
-            toolchain: stable
-            override: true
 
         - name: Run benchmarks on PR ${{ github.event.issue.id }}
           run: |

.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: dtolnay/rust-toolchain@1.79
             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: dtolnay/rust-toolchain@1.79
         with:
           profile: minimal
-          toolchain: stable
-          override: true
 
       # Set variables
       - name: Set current branch name

.github/workflows/benchmarks-pr.yml

@@ -13,11 +13,40 @@ jobs:
     runs-on: benchmarks
     timeout-minutes: 4320 # 72h
     steps:
-      - uses: actions-rs/toolchain@v1
+      - name: Check permissions
+        id: permission
+        env:
+          PR_AUTHOR: ${{github.event.issue.user.login }}
+          COMMENT_AUTHOR: ${{github.event.comment.user.login }}
+          REPOSITORY: ${{github.repository}}
+          PR_ID: ${{github.event.issue.number}}
+        run: |
+          PR_REPOSITORY=$(gh api /repos/"$REPOSITORY"/pulls/"$PR_ID" --jq .head.repo.full_name)
+          if $(gh api /repos/"$REPOSITORY"/collaborators/"$PR_AUTHOR"/permission --jq .user.permissions.push)
+          then
+            echo "::notice title=Authentication success::PR author authenticated"
+          else
+            echo "::error title=Authentication error::PR author doesn't have push permission on this repository"
+            exit 1
+          fi
+          if $(gh api /repos/"$REPOSITORY"/collaborators/"$COMMENT_AUTHOR"/permission --jq .user.permissions.push)
+          then
+            echo "::notice title=Authentication success::Comment author authenticated"
+          else
+            echo "::error title=Authentication error::Comment author doesn't have push permission on this repository"
+            exit 1
+          fi
+          if [ "$PR_REPOSITORY" = "$REPOSITORY" ]
+          then
+            echo "::notice title=Authentication success::PR started from main repository"
+          else
+            echo "::error title=Authentication error::PR started from a fork"
+            exit 1
+          fi
+
+      - uses: dtolnay/rust-toolchain@1.79
         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: dtolnay/rust-toolchain@1.79
         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: dtolnay/rust-toolchain@1.79
         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: dtolnay/rust-toolchain@1.79
         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: dtolnay/rust-toolchain@1.79
         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: dtolnay/rust-toolchain@1.79
     - 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: dtolnay/rust-toolchain@1.79
         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: dtolnay/rust-toolchain@1.79
     - 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: dtolnay/rust-toolchain@1.79
     - 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: dtolnay/rust-toolchain@1.79
     - 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: dtolnay/rust-toolchain@1.79
         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: dtolnay/rust-toolchain@1.79
         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: dtolnay/rust-toolchain@1.79
       - 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: dtolnay/rust-toolchain@1.79
       - 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: dtolnay/rust-toolchain@1.79
       - 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
@@ -110,10 +101,7 @@ jobs:
         run: |
           apt-get update
           apt-get install --assume-yes build-essential curl
-      - uses: actions-rs/toolchain@v1
-        with:
-          toolchain: stable
-          override: true
+      - uses: dtolnay/rust-toolchain@1.79
       - name: Run cargo tree without default features and check lindera is not present
         run: |
           if cargo tree -f '{p} {f}' -e normal --no-default-features | grep -qz lindera; then
@@ -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: dtolnay/rust-toolchain@1.79
       - 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: dtolnay/rust-toolchain@1.79
         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: dtolnay/rust-toolchain@1.79
         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: dtolnay/rust-toolchain@1.79
         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.

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 = "1.9.0"
+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](https://www.meilisearch.com) 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 @@
   </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
-- **Hybrid search:** Combine the best of both [semantic](https://www.meilisearch.com/docs/learn/experimental/vector_search) & 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
+- **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
@@ -59,7 +63,7 @@ You can consult Meilisearch's documentation at [meilisearch.com/docs](https://ww
 
 ## 🚀 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
 
@@ -83,7 +87,7 @@ 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). Remember to include your `Instance UID` in the message, as this helps us quickly find and delete your data.
 
@@ -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,
@@ -278,6 +286,7 @@ pub(crate) mod test {
             pagination: Setting::NotSet,
             embedders: Setting::NotSet,
             search_cutoff_ms: Setting::NotSet,
+            localized_attributes: Setting::NotSet,
             _kind: std::marker::PhantomData,
         };
         settings.check()

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

@@ -379,6 +379,7 @@ impl<T> From<v5::Settings<T>> for v6::Settings<v6::Unchecked> {
                 v5::Setting::NotSet => v6::Setting::NotSet,
             },
             embedders: v6::Setting::NotSet,
+            localized_attributes: v6::Setting::NotSet,
             search_cutoff_ms: v6::Setting::NotSet,
             _kind: std::marker::PhantomData,
         }
@@ -442,8 +443,8 @@ 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

@@ -216,7 +216,7 @@ pub(crate) mod test {
         let mut dump = DumpReader::open(dump).unwrap();
 
         // top level infos
-        insta::assert_display_snapshot!(dump.date().unwrap(), @"2024-05-16 15:51:34.151044 +00:00:00");
+        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
@@ -337,7 +337,7 @@ pub(crate) mod test {
         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
@@ -383,8 +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();
@@ -463,8 +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();
@@ -540,7 +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
@@ -633,7 +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
@@ -726,7 +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/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/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/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/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

@@ -11,38 +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"
-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

@@ -34,7 +34,7 @@ use meilisearch_types::milli::update::{
 use meilisearch_types::milli::vector::parsed_vectors::{
     ExplicitVectors, VectorOrArrayOfVectors, RESERVED_VECTORS_FIELD_NAME,
 };
-use meilisearch_types::milli::{self, Filter};
+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};
@@ -106,6 +106,10 @@ pub(crate) enum IndexOperation {
         operations: Vec<DocumentOperation>,
         tasks: Vec<Task>,
     },
+    DocumentEdition {
+        index_uid: String,
+        task: Task,
+    },
     IndexDocumentDeletionByFilter {
         index_uid: String,
         task: Task,
@@ -164,7 +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 {
@@ -228,6 +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, .. }
@@ -243,6 +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")
             }
@@ -295,6 +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
@@ -1257,6 +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();
@@ -1371,7 +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.
@@ -1386,6 +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, .. } =
@@ -1674,3 +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

@@ -68,6 +68,32 @@ impl RoFeatures {
             .into())
         }
     }
+
+    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,
+                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())
+        }
+    }
 }
 
 impl FeatureData {
@@ -79,9 +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/index_mapper/mod.rs

@@ -108,8 +108,10 @@ pub struct IndexStats {
     /// Association of every field name with the number of times it occurs in the documents.
     pub field_distribution: FieldDistribution,
     /// Creation date of the index.
+    #[serde(with = "time::serde::rfc3339")]
     pub created_at: OffsetDateTime,
     /// Date of the last update of the index.
+    #[serde(with = "time::serde::rfc3339")]
     pub updated_at: OffsetDateTime,
 }
 

index-scheduler/src/insta_snapshot.rs

@@ -177,6 +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/lib.rs

@@ -662,7 +662,11 @@ impl IndexScheduler {
         let rtxn = self.env.read_txn()?;
         self.index_mapper.index(&rtxn, name)
     }
-
+    /// Return the boolean referring if index exists.
+    pub fn index_exists(&self, name: &str) -> Result<bool> {
+        let rtxn = self.env.read_txn()?;
+        self.index_mapper.index_exists(&rtxn, name)
+    }
     /// Return the name of all indexes without opening them.
     pub fn index_names(&self) -> Result<Vec<String>> {
         let rtxn = self.env.read_txn()?;
@@ -1603,6 +1607,14 @@ impl<'a> Dump<'a> {
                         index_uid: task.index_uid.ok_or(Error::CorruptedDump)?,
                     }
                 }
+                KindDump::DocumentEdition { filter, context, function } => {
+                    KindWithContent::DocumentEdition {
+                        index_uid: task.index_uid.ok_or(Error::CorruptedDump)?,
+                        filter_expr: filter,
+                        context,
+                        function,
+                    }
+                }
                 KindDump::DocumentClear => KindWithContent::DocumentClear {
                     index_uid: task.index_uid.ok_or(Error::CorruptedDump)?,
                 },
@@ -1811,7 +1823,7 @@ mod tests {
                 task_db_size: 1000 * 1000, // 1 MB, we don't use MiB on purpose.
                 index_base_map_size: 1000 * 1000, // 1 MB, we don't use MiB on purpose.
                 enable_mdb_writemap: false,
-                index_growth_amount: 1000 * 1000, // 1 MB
+                index_growth_amount: 1000 * 1000 * 1000 * 1000, // 1 TB
                 index_count: 5,
                 indexer_config,
                 autobatching_enabled: true,
@@ -3035,6 +3047,8 @@ mod tests {
             api_key: Setting::Set(S("My super secret")),
             url: Setting::Set(S("http://localhost:7777")),
             dimensions: Setting::Set(4),
+            request: Setting::Set(serde_json::json!("{{text}}")),
+            response: Setting::Set(serde_json::json!("{{embedding}}")),
             ..Default::default()
         };
         embedders.insert(S("default"), Setting::Set(embedding_settings));
@@ -3787,15 +3801,15 @@ mod tests {
         ]);
         snapshot!(snapshot_index_scheduler(&index_scheduler), name: "after_processing_the_10_tasks");
 
-        // The index should not exists.
-        snapshot!(format!("{}", index_scheduler.index("doggos").map(|_| ()).unwrap_err()), @"Index `doggos` not found.");
+        // The index should not exist.
+        snapshot!(matches!(index_scheduler.index_exists("doggos"), Ok(true)), @"false");
     }
 
     #[test]
     fn test_document_addition_cant_create_index_without_index_without_autobatching() {
         // We're going to execute multiple document addition that don't have
         // the right to create an index while there is no index currently.
-        // Since the autobatching is disabled, every tasks should be processed
+        // Since the auto-batching is disabled, every task should be processed
         // sequentially and throw an IndexDoesNotExists.
         let (index_scheduler, mut handle) = IndexScheduler::test(false, vec![]);
 
@@ -3837,8 +3851,8 @@ mod tests {
         handle.advance_n_failed_batches(5);
         snapshot!(snapshot_index_scheduler(&index_scheduler), name: "all_tasks_processed");
 
-        // The index should not exists.
-        snapshot!(format!("{}", index_scheduler.index("doggos").map(|_| ()).unwrap_err()), @"Index `doggos` not found.");
+        // The index should not exist.
+        snapshot!(matches!(index_scheduler.index_exists("doggos"), Ok(true)), @"false");
     }
 
     #[test]
@@ -4744,6 +4758,7 @@ mod tests {
           "types": {
             "documentAdditionOrUpdate": 0,
             "documentDeletion": 0,
+            "documentEdition": 0,
             "dumpCreation": 0,
             "indexCreation": 3,
             "indexDeletion": 0,
@@ -4775,6 +4790,7 @@ mod tests {
           "types": {
             "documentAdditionOrUpdate": 0,
             "documentDeletion": 0,
+            "documentEdition": 0,
             "dumpCreation": 0,
             "indexCreation": 3,
             "indexDeletion": 0,
@@ -4813,6 +4829,7 @@ mod tests {
           "types": {
             "documentAdditionOrUpdate": 0,
             "documentDeletion": 0,
+            "documentEdition": 0,
             "dumpCreation": 0,
             "indexCreation": 3,
             "indexDeletion": 0,
@@ -4852,6 +4869,7 @@ mod tests {
           "types": {
             "documentAdditionOrUpdate": 0,
             "documentDeletion": 0,
+            "documentEdition": 0,
             "dumpCreation": 0,
             "indexCreation": 3,
             "indexDeletion": 0,
@@ -4990,6 +5008,8 @@ mod tests {
             api_key: Setting::Set(S("My super secret")),
             url: Setting::Set(S("http://localhost:7777")),
             dimensions: Setting::Set(384),
+            request: Setting::Set(serde_json::json!("{{text}}")),
+            response: Setting::Set(serde_json::json!("{{embedding}}")),
             ..Default::default()
         };
         embedders.insert(S("A_fakerest"), Setting::Set(embedding_settings));

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

@@ -8,7 +8,9 @@ expression: task.details
       "source": "rest",
       "apiKey": "MyXXXX...",
       "dimensions": 384,
-      "url": "http://localhost:7777"
+      "url": "http://localhost:7777",
+      "request": "{{text}}",
+      "response": "{{embedding}}"
     },
     "B_small_hf": {
       "source": "huggingFace",

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

@@ -8,16 +8,8 @@ expression: fakerest_config.embedder_options
     "distribution": null,
     "dimensions": 384,
     "url": "http://localhost:7777",
-    "query": null,
-    "input_field": [
-      "input"
-    ],
-    "path_to_embeddings": [
-      "data"
-    ],
-    "embedding_object": [
-      "embedding"
-    ],
-    "input_type": "text"
+    "request": "{{text}}",
+    "response": "{{embedding}}",
+    "headers": {}
   }
 }

index-scheduler/src/snapshots/index_scheduler__tests__import_vectors.snap

@@ -8,7 +8,9 @@ expression: task.details
       "source": "rest",
       "apiKey": "MyXXXX...",
       "dimensions": 384,
-      "url": "http://localhost:7777"
+      "url": "http://localhost:7777",
+      "request": "{{text}}",
+      "response": "{{embedding}}"
     },
     "B_small_hf": {
       "source": "huggingFace",

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

@@ -8,7 +8,9 @@ expression: task.details
       "source": "rest",
       "apiKey": "MyXXXX...",
       "dimensions": 4,
-      "url": "http://localhost:7777"
+      "url": "http://localhost:7777",
+      "request": "{{text}}",
+      "response": "{{embedding}}"
     }
   }
 }

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

@@ -1,6 +1,6 @@
 ---
 source: index-scheduler/src/lib.rs
-expression: embedding_config.embedder_options
+expression: config.embedder_options
 ---
 {
   "Rest": {
@@ -8,16 +8,8 @@ expression: embedding_config.embedder_options
     "distribution": null,
     "dimensions": 4,
     "url": "http://localhost:7777",
-    "query": null,
-    "input_field": [
-      "input"
-    ],
-    "path_to_embeddings": [
-      "data"
-    ],
-    "embedding_object": [
-      "embedding"
-    ],
-    "input_type": "text"
+    "request": "{{text}}",
+    "response": "{{embedding}}",
+    "headers": {}
   }
 }

index-scheduler/src/snapshots/index_scheduler__tests__settings_update.snap

@@ -8,7 +8,9 @@ expression: task.details
       "source": "rest",
       "apiKey": "MyXXXX...",
       "dimensions": 4,
-      "url": "http://localhost:7777"
+      "url": "http://localhost:7777",
+      "request": "{{text}}",
+      "response": "{{embedding}}"
     }
   }
 }

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

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
 []
 ----------------------------------------------------------------------
 ### 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 }}
+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"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 1 {uid: 1, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
 2 {uid: 2, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: None, method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
 ----------------------------------------------------------------------
@@ -46,4 +46,3 @@ doggos: { number_of_documents: 1, field_distribution: {"_vectors": 1, "breed": 1
 ### File Store:
 
 ----------------------------------------------------------------------
-

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

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
 []
 ----------------------------------------------------------------------
 ### 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 }}
+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"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 1 {uid: 1, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
 2 {uid: 2, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: None, method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
 ----------------------------------------------------------------------
@@ -45,4 +45,3 @@ doggos: { number_of_documents: 1, field_distribution: {"_vectors": 1, "breed": 1
 00000000-0000-0000-0000-000000000001
 
 ----------------------------------------------------------------------
-

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

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
 []
 ----------------------------------------------------------------------
 ### 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 }}
+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"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 1 {uid: 1, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:
@@ -42,4 +42,3 @@ doggos: { number_of_documents: 1, field_distribution: {"_vectors": 1, "breed": 1
 ### File Store:
 
 ----------------------------------------------------------------------
-

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

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
 []
 ----------------------------------------------------------------------
 ### 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 }}
+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"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 1 {uid: 1, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:
@@ -41,4 +41,3 @@ doggos: { number_of_documents: 0, field_distribution: {} }
 00000000-0000-0000-0000-000000000000
 
 ----------------------------------------------------------------------
-

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

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
 []
 ----------------------------------------------------------------------
 ### 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 }}
+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"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued [0,]
@@ -33,4 +33,3 @@ doggos [0,]
 ### File Store:
 
 ----------------------------------------------------------------------
-

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

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
 []
 ----------------------------------------------------------------------
 ### 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 }}
+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"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued []
@@ -37,4 +37,3 @@ doggos: { number_of_documents: 0, field_distribution: {} }
 ### File Store:
 
 ----------------------------------------------------------------------
-

index-scheduler/src/snapshots/lib.rs/test_settings_update/after_registering_settings_task.snap

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
 []
 ----------------------------------------------------------------------
 ### 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({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), 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 })}), 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({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), 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 })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+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({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued [0,]
@@ -33,4 +33,3 @@ doggos [0,]
 ### File Store:
 
 ----------------------------------------------------------------------
-

index-scheduler/src/snapshots/lib.rs/test_settings_update/settings_update_processed.snap

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
 []
 ----------------------------------------------------------------------
 ### 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({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), 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 })}), 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({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), 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 })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+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({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued []
@@ -37,4 +37,3 @@ doggos: { number_of_documents: 0, field_distribution: {} }
 ### 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),
@@ -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-types/Cargo.toml

@@ -11,36 +11,36 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-actix-web = { version = "4.6.0", 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_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 = "1.35"
-uuid = { version = "1.6.1", features = ["serde", "v4"] }
+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]
@@ -54,6 +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`
@@ -188,6 +192,7 @@ 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);

meilisearch-types/src/error.rs

@@ -224,6 +224,7 @@ 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 ;
@@ -237,6 +238,11 @@ 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 ;
@@ -250,6 +256,7 @@ InvalidSearchCropLength               , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchCropMarker               , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchFacets                   , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchSemanticRatio            , InvalidRequest       , BAD_REQUEST ;
+InvalidSearchLocales                  , InvalidRequest       , BAD_REQUEST ;
 InvalidFacetSearchFacetName           , InvalidRequest       , BAD_REQUEST ;
 InvalidSimilarId                      , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchFilter                   , InvalidRequest       , BAD_REQUEST ;
@@ -291,6 +298,7 @@ InvalidSettingsSeparatorTokens        , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsDictionary             , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsSynonyms               , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsTypoTolerance          , InvalidRequest       , BAD_REQUEST ;
+InvalidSettingsLocalizedAttributes    , InvalidRequest       , BAD_REQUEST ;
 InvalidState                          , Internal             , INTERNAL_SERVER_ERROR ;
 InvalidStoreFile                      , Internal             , INTERNAL_SERVER_ERROR ;
 InvalidSwapDuplicateIndexFound        , InvalidRequest       , BAD_REQUEST ;
@@ -336,7 +344,10 @@ UnsupportedMediaType                  , InvalidRequest       , UNSUPPORTED_MEDIA
 
 // Experimental features
 VectorEmbeddingError                  , InvalidRequest       , BAD_REQUEST ;
-NotFoundSimilarId                     , InvalidRequest       , BAD_REQUEST
+NotFoundSimilarId                     , InvalidRequest       , BAD_REQUEST ;
+InvalidDocumentEditionContext         , InvalidRequest       , BAD_REQUEST ;
+InvalidDocumentEditionFunctionFilter  , InvalidRequest       , BAD_REQUEST ;
+EditDocumentsByFunctionError          , InvalidRequest       , BAD_REQUEST
 }
 
 impl ErrorCode for JoinError {
@@ -406,7 +417,15 @@ impl ErrorCode for milli::Error {
                         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
+                    }
                 }
             }
         }
@@ -502,6 +521,12 @@ 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!(

meilisearch-types/src/features.rs

@@ -6,10 +6,13 @@ pub struct RuntimeTogglableFeatures {
     pub vector_store: bool,
     pub metrics: bool,
     pub logs_route: 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/lib.rs

@@ -7,6 +7,7 @@ pub mod features;
 pub mod index_uid;
 pub mod index_uid_pattern;
 pub mod keys;
+pub mod locales;
 pub mod settings;
 pub mod star_or;
 pub mod task_view;

meilisearch-types/src/locales.rs

@@ -0,0 +1,157 @@
+use deserr::Deserr;
+use milli::LocalizedAttributesRule;
+use serde::{Deserialize, Serialize};
+use serde_json::json;
+
+/// Generate a Locale enum and its From and Into implementations for milli::tokenizer::Language.
+///
+/// this enum implements `Deserr` in order to be used in the API.
+macro_rules! make_locale {
+
+    ($($language:tt), +) => {
+        #[derive(Debug, Copy, Clone, PartialEq, Eq, Deserr, Serialize, Deserialize, Ord, PartialOrd)]
+        #[deserr(rename_all = camelCase)]
+        #[serde(rename_all = "camelCase")]
+        pub enum Locale {
+            $($language),+,
+        }
+
+        impl From<milli::tokenizer::Language> for Locale {
+            fn from(other: milli::tokenizer::Language) -> Locale {
+                match other {
+                    $(milli::tokenizer::Language::$language => Locale::$language), +
+                }
+            }
+        }
+
+        impl From<Locale> for milli::tokenizer::Language {
+            fn from(other: Locale) -> milli::tokenizer::Language {
+                match other {
+                    $(Locale::$language => milli::tokenizer::Language::$language), +,
+                }
+            }
+        }
+
+        #[derive(Debug)]
+        pub struct LocaleFormatError {
+            pub invalid_locale: String,
+        }
+
+        impl std::fmt::Display for LocaleFormatError {
+            fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+                let valid_locales = [$(Locale::$language),+].iter().map(|l| format!("`{}`", json!(l).as_str().unwrap())).collect::<Vec<_>>().join(", ");
+                write!(f, "Unsupported locale `{}`, expected one of {}", self.invalid_locale, valid_locales)
+            }
+        }
+    };
+}
+
+make_locale! {
+    Epo,
+    Eng,
+    Rus,
+    Cmn,
+    Spa,
+    Por,
+    Ita,
+    Ben,
+    Fra,
+    Deu,
+    Ukr,
+    Kat,
+    Ara,
+    Hin,
+    Jpn,
+    Heb,
+    Yid,
+    Pol,
+    Amh,
+    Jav,
+    Kor,
+    Nob,
+    Dan,
+    Swe,
+    Fin,
+    Tur,
+    Nld,
+    Hun,
+    Ces,
+    Ell,
+    Bul,
+    Bel,
+    Mar,
+    Kan,
+    Ron,
+    Slv,
+    Hrv,
+    Srp,
+    Mkd,
+    Lit,
+    Lav,
+    Est,
+    Tam,
+    Vie,
+    Urd,
+    Tha,
+    Guj,
+    Uzb,
+    Pan,
+    Aze,
+    Ind,
+    Tel,
+    Pes,
+    Mal,
+    Ori,
+    Mya,
+    Nep,
+    Sin,
+    Khm,
+    Tuk,
+    Aka,
+    Zul,
+    Sna,
+    Afr,
+    Lat,
+    Slk,
+    Cat,
+    Tgl,
+    Hye
+}
+
+impl std::error::Error for LocaleFormatError {}
+
+impl std::str::FromStr for Locale {
+    type Err = LocaleFormatError;
+
+    fn from_str(s: &str) -> Result<Self, Self::Err> {
+        milli::tokenizer::Language::from_code(s)
+            .map(Self::from)
+            .ok_or(LocaleFormatError { invalid_locale: s.to_string() })
+    }
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Deserr, Serialize, Deserialize)]
+#[deserr(rename_all = camelCase)]
+#[serde(rename_all = "camelCase")]
+pub struct LocalizedAttributesRuleView {
+    pub attribute_patterns: Vec<String>,
+    pub locales: Vec<Locale>,
+}
+
+impl From<LocalizedAttributesRule> for LocalizedAttributesRuleView {
+    fn from(rule: LocalizedAttributesRule) -> Self {
+        Self {
+            attribute_patterns: rule.attribute_patterns,
+            locales: rule.locales.into_iter().map(|l| l.into()).collect(),
+        }
+    }
+}
+
+impl From<LocalizedAttributesRuleView> for LocalizedAttributesRule {
+    fn from(view: LocalizedAttributesRuleView) -> Self {
+        Self {
+            attribute_patterns: view.attribute_patterns,
+            locales: view.locales.into_iter().map(|l| l.into()).collect(),
+        }
+    }
+}

meilisearch-types/src/settings.rs

@@ -17,6 +17,7 @@ use serde::{Deserialize, Serialize, Serializer};
 use crate::deserr::DeserrJsonError;
 use crate::error::deserr_codes::*;
 use crate::facet_values_sort::FacetValuesSort;
+use crate::locales::LocalizedAttributesRuleView;
 
 /// The maximum number of results that the engine
 /// will be able to return in one search call.
@@ -198,6 +199,9 @@ pub struct Settings<T> {
     #[serde(default, skip_serializing_if = "Setting::is_not_set")]
     #[deserr(default, error = DeserrJsonError<InvalidSettingsSearchCutoffMs>)]
     pub search_cutoff_ms: Setting<u64>,
+    #[serde(default, skip_serializing_if = "Setting::is_not_set")]
+    #[deserr(default, error = DeserrJsonError<InvalidSettingsLocalizedAttributes>)]
+    pub localized_attributes: Setting<Vec<LocalizedAttributesRuleView>>,
 
     #[serde(skip)]
     #[deserr(skip)]
@@ -261,6 +265,7 @@ impl Settings<Checked> {
             pagination: Setting::Reset,
             embedders: Setting::Reset,
             search_cutoff_ms: Setting::Reset,
+            localized_attributes: Setting::Reset,
             _kind: PhantomData,
         }
     }
@@ -284,7 +289,8 @@ impl Settings<Checked> {
             pagination,
             embedders,
             search_cutoff_ms,
-            ..
+            localized_attributes: localized_attributes_rules,
+            _kind,
         } = self;
 
         Settings {
@@ -305,6 +311,7 @@ impl Settings<Checked> {
             pagination,
             embedders,
             search_cutoff_ms,
+            localized_attributes: localized_attributes_rules,
             _kind: PhantomData,
         }
     }
@@ -352,6 +359,7 @@ impl Settings<Unchecked> {
             pagination: self.pagination,
             embedders: self.embedders,
             search_cutoff_ms: self.search_cutoff_ms,
+            localized_attributes: self.localized_attributes,
             _kind: PhantomData,
         }
     }
@@ -402,6 +410,7 @@ pub fn apply_settings_to_builder(
         pagination,
         embedders,
         search_cutoff_ms,
+        localized_attributes: localized_attributes_rules,
         _kind,
     } = settings;
 
@@ -485,6 +494,13 @@ pub fn apply_settings_to_builder(
         Setting::NotSet => (),
     }
 
+    match localized_attributes_rules {
+        Setting::Set(ref rules) => builder
+            .set_localized_attributes_rules(rules.iter().cloned().map(|r| r.into()).collect()),
+        Setting::Reset => builder.reset_localized_attributes_rules(),
+        Setting::NotSet => (),
+    }
+
     match typo_tolerance {
         Setting::Set(ref value) => {
             match value.enabled {
@@ -679,6 +695,8 @@ pub fn settings(
 
     let search_cutoff_ms = index.search_cutoff(rtxn)?;
 
+    let localized_attributes_rules = index.localized_attributes_rules(rtxn)?;
+
     let mut settings = Settings {
         displayed_attributes: match displayed_attributes {
             Some(attrs) => Setting::Set(attrs),
@@ -711,6 +729,10 @@ pub fn settings(
             Some(cutoff) => Setting::Set(cutoff),
             None => Setting::Reset,
         },
+        localized_attributes: match localized_attributes_rules {
+            Some(rules) => Setting::Set(rules.into_iter().map(|r| r.into()).collect()),
+            None => Setting::Reset,
+        },
         _kind: PhantomData,
     };
 
@@ -902,6 +924,7 @@ pub(crate) mod test {
             faceting: Setting::NotSet,
             pagination: Setting::NotSet,
             embedders: Setting::NotSet,
+            localized_attributes: Setting::NotSet,
             search_cutoff_ms: Setting::NotSet,
             _kind: PhantomData::<Unchecked>,
         };
@@ -930,6 +953,7 @@ pub(crate) mod test {
             faceting: Setting::NotSet,
             pagination: Setting::NotSet,
             embedders: Setting::NotSet,
+            localized_attributes: Setting::NotSet,
             search_cutoff_ms: Setting::NotSet,
             _kind: PhantomData::<Unchecked>,
         };

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

@@ -14,130 +14,126 @@ default-run = "meilisearch"
 
 [dependencies]
 actix-cors = "0.7.0"
-actix-http = { version = "3.7.0", 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 = "4.6.0", 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 = { version = "4.0.1", 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"] }
+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 = "0.7.10"
+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"
+actix-rt = "2.10.0"
 brotli = "6.0.0"
-insta = "1.34.0"
+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"
+wiremock = "0.6.0"
+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",
@@ -151,6 +147,7 @@ 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"]

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 {
@@ -42,7 +42,7 @@ 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
     }
 
@@ -97,6 +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
@@ -102,7 +102,7 @@ pub trait Analytics: Sync + Send {
     /// 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,
@@ -119,11 +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

@@ -1,16 +1,16 @@
-use std::collections::{BinaryHeap, HashMap, HashSet};
+use std::collections::{BTreeSet, BinaryHeap, HashMap, HashSet};
 use std::fs;
 use std::mem::take;
 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::locales::Locale;
 use meilisearch_types::InstanceUid;
 use once_cell::sync::Lazy;
 use regex::Regex;
@@ -31,12 +31,12 @@ 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,
-    SimilarQuery, SimilarResult, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER,
+    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,
 };
@@ -81,6 +81,7 @@ pub enum AnalyticsMsg {
     AggregateAddDocuments(DocumentsAggregator),
     AggregateDeleteDocuments(DocumentsDeletionAggregator),
     AggregateUpdateDocuments(DocumentsAggregator),
+    AggregateEditDocumentsByFunction(EditDocumentsByFunctionAggregator),
     AggregateGetFetchDocuments(DocumentsFetchAggregator),
     AggregatePostFetchDocuments(DocumentsFetchAggregator),
 }
@@ -150,6 +151,7 @@ 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(),
@@ -230,6 +232,17 @@ 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));
@@ -249,6 +262,7 @@ 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,
@@ -291,6 +305,7 @@ 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,
@@ -341,6 +356,7 @@ 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,
@@ -390,6 +406,7 @@ 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,
@@ -454,6 +471,7 @@ 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),
@@ -509,6 +527,7 @@ 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,
@@ -550,6 +569,11 @@ 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")
         {
@@ -630,6 +654,9 @@ pub struct SearchAggregator {
     // every time a search is done, we increment the counter linked to the used settings
     matching_strategy: HashMap<String, usize>,
 
+    // List of the unique Locales passed as parameter
+    locales: BTreeSet<Locale>,
+
     // pagination
     max_limit: usize,
     max_offset: usize,
@@ -684,6 +711,7 @@ impl SearchAggregator {
             attributes_to_search_on,
             hybrid,
             ranking_score_threshold,
+            locales,
         } = query;
 
         let mut ret = Self::default();
@@ -751,6 +779,10 @@ impl SearchAggregator {
 
         ret.matching_strategy.insert(format!("{:?}", matching_strategy), 1);
 
+        if let Some(locales) = locales {
+            ret.locales = locales.iter().copied().collect();
+        }
+
         ret.highlight_pre_tag = *highlight_pre_tag != DEFAULT_HIGHLIGHT_PRE_TAG();
         ret.highlight_post_tag = *highlight_post_tag != DEFAULT_HIGHLIGHT_POST_TAG();
         ret.crop_marker = *crop_marker != DEFAULT_CROP_MARKER();
@@ -836,6 +868,7 @@ impl SearchAggregator {
             total_degraded,
             total_used_negative_operator,
             ranking_score_threshold,
+            ref mut locales,
         } = other;
 
         if self.timestamp.is_none() {
@@ -924,6 +957,9 @@ impl SearchAggregator {
         self.show_ranking_score |= show_ranking_score;
         self.show_ranking_score_details |= show_ranking_score_details;
         self.ranking_score_threshold |= ranking_score_threshold;
+
+        // locales
+        self.locales.append(locales);
     }
 
     pub fn into_event(self, user: &User, event_name: &str) -> Option<Track> {
@@ -968,6 +1004,7 @@ impl SearchAggregator {
             total_degraded,
             total_used_negative_operator,
             ranking_score_threshold,
+            locales,
         } = self;
 
         if total_received == 0 {
@@ -1037,6 +1074,7 @@ impl SearchAggregator {
                 "matching_strategy": {
                     "most_used_strategy": matching_strategy.iter().max_by_key(|(_, v)| *v).map(|(k, _)| json!(k)).unwrap_or_else(|| json!(null)),
                 },
+                "locales": locales,
                 "scoring": {
                     "show_ranking_score": show_ranking_score,
                     "show_ranking_score_details": show_ranking_score_details,
@@ -1075,22 +1113,33 @@ 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: _,
@@ -1116,14 +1165,17 @@ impl MultiSearchAggregator {
                     attributes_to_search_on: _,
                     hybrid: _,
                     ranking_score_threshold: _,
+                    locales: _,
                 } = 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,
@@ -1131,10 +1183,11 @@ 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,
         }
     }
 
@@ -1160,6 +1213,7 @@ 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);
@@ -1176,6 +1230,7 @@ impl MultiSearchAggregator {
             user_agents,
             show_ranking_score,
             show_ranking_score_details,
+            use_federation,
             // do not add _ or ..Default::default() here
         };
 
@@ -1194,6 +1249,7 @@ impl MultiSearchAggregator {
             user_agents,
             show_ranking_score,
             show_ranking_score_details,
+            use_federation,
         } = self;
 
         if total_received == 0 {
@@ -1218,6 +1274,9 @@ impl MultiSearchAggregator {
                 "scoring": {
                     "show_ranking_score": show_ranking_score,
                     "show_ranking_score_details": show_ranking_score_details,
+                },
+                "federation": {
+                    "use_federation": use_federation,
                 }
             });
 
@@ -1264,6 +1323,7 @@ impl FacetSearchAggregator {
             attributes_to_search_on,
             hybrid,
             ranking_score_threshold,
+            locales,
         } = query;
 
         let mut ret = Self::default();
@@ -1279,7 +1339,8 @@ impl FacetSearchAggregator {
             || *matching_strategy != MatchingStrategy::default()
             || attributes_to_search_on.is_some()
             || hybrid.is_some()
-            || ranking_score_threshold.is_some();
+            || ranking_score_threshold.is_some()
+            || locales.is_some();
 
         ret
     }
@@ -1466,6 +1527,75 @@ 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)]

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

@@ -72,6 +72,19 @@ fn on_panic(info: &std::panic::PanicInfo) {
 
 #[actix_web::main]
 async fn main() -> anyhow::Result<()> {
+    try_main().await.inspect_err(|error| {
+        tracing::error!(%error);
+        let mut current = error.source();
+        let mut depth = 0;
+        while let Some(source) = current {
+            tracing::info!(%source, depth, "Error caused by");
+            current = source.source();
+            depth += 1;
+        }
+    })
+}
+
+async fn try_main() -> anyhow::Result<()> {
     let (opt, config_read_from) = Opt::try_build()?;
 
     std::panic::set_hook(Box::new(on_panic));
@@ -151,7 +164,7 @@ 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

@@ -47,6 +47,10 @@ pub struct RuntimeTogglableFeatures {
     pub metrics: Option<bool>,
     #[deserr(default)]
     pub logs_route: Option<bool>,
+    #[deserr(default)]
+    pub edit_documents_by_function: Option<bool>,
+    #[deserr(default)]
+    pub contains_filter: Option<bool>,
 }
 
 async fn patch_features(
@@ -66,13 +70,23 @@ 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),
+        edit_documents_by_function: new_features
+            .0
+            .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
     // the it renames to camelCase, which we don't want for analytics.
     // **Do not** ignore fields with `..` or `_` here, because we want to add them in the future.
-    let meilisearch_types::features::RuntimeTogglableFeatures { vector_store, metrics, logs_route } =
-        new_features;
+    let meilisearch_types::features::RuntimeTogglableFeatures {
+        vector_store,
+        metrics,
+        logs_route,
+        edit_documents_by_function,
+        contains_filter,
+    } = new_features;
 
     analytics.publish(
         "Experimental features Updated".to_string(),
@@ -80,6 +94,8 @@ async fn patch_features(
             "vector_store": vector_store,
             "metrics": metrics,
             "logs_route": logs_route,
+            "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};
@@ -82,6 +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}")
@@ -259,8 +260,15 @@ fn documents_by_query(
     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, retrieve_vectors)?;
+    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);
 
@@ -304,7 +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)?;
@@ -341,7 +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)?;
@@ -556,11 +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)?;
@@ -574,6 +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>,
@@ -615,6 +706,8 @@ fn some_documents<'a, 't: 'a>(
                     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(),
@@ -649,12 +742,12 @@ fn retrieve_documents<S: AsRef<str>>(
     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
     };

meilisearch/src/routes/indexes/facet_search.rs

@@ -6,6 +6,7 @@ use meilisearch_types::deserr::DeserrJsonError;
 use meilisearch_types::error::deserr_codes::*;
 use meilisearch_types::error::ResponseError;
 use meilisearch_types::index_uid::IndexUid;
+use meilisearch_types::locales::Locale;
 use serde_json::Value;
 use tracing::debug;
 
@@ -48,6 +49,8 @@ pub struct FacetSearchQuery {
     pub attributes_to_search_on: Option<Vec<String>>,
     #[deserr(default, error = DeserrJsonError<InvalidSearchRankingScoreThreshold>, default)]
     pub ranking_score_threshold: Option<RankingScoreThreshold>,
+    #[deserr(default, error = DeserrJsonError<InvalidSearchLocales>, default)]
+    pub locales: Option<Vec<Locale>>,
 }
 
 pub async fn search(
@@ -67,6 +70,7 @@ pub async fn search(
 
     let facet_query = query.facet_query.clone();
     let facet_name = query.facet_name.clone();
+    let locales = query.locales.clone().map(|l| l.into_iter().map(Into::into).collect());
     let mut search_query = SearchQuery::from(query);
 
     // Tenant token search_rules.
@@ -79,7 +83,15 @@ 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(),
+            locales,
+        )
     })
     .await?;
 
@@ -106,6 +118,7 @@ impl From<FacetSearchQuery> for SearchQuery {
             attributes_to_search_on,
             hybrid,
             ranking_score_threshold,
+            locales,
         } = value;
 
         SearchQuery {
@@ -134,6 +147,7 @@ impl From<FacetSearchQuery> for SearchQuery {
             attributes_to_search_on,
             hybrid,
             ranking_score_threshold,
+            locales,
         }
     }
 }

meilisearch/src/routes/indexes/search.rs

@@ -7,6 +7,7 @@ use meilisearch_types::deserr::{DeserrJsonError, DeserrQueryParamError};
 use meilisearch_types::error::deserr_codes::*;
 use meilisearch_types::error::ResponseError;
 use meilisearch_types::index_uid::IndexUid;
+use meilisearch_types::locales::Locale;
 use meilisearch_types::milli;
 use meilisearch_types::serde_cs::vec::CS;
 use serde_json::Value;
@@ -89,6 +90,8 @@ pub struct SearchQueryGet {
     pub hybrid_semantic_ratio: Option<SemanticRatioGet>,
     #[deserr(default, error = DeserrQueryParamError<InvalidSearchRankingScoreThreshold>)]
     pub ranking_score_threshold: Option<RankingScoreThresholdGet>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidSearchLocales>)]
+    pub locales: Option<CS<Locale>>,
 }
 
 #[derive(Debug, Clone, Copy, PartialEq, deserr::Deserr)]
@@ -175,6 +178,7 @@ impl From<SearchQueryGet> for SearchQuery {
             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),
+            locales: other.locales.map(|o| o.into_iter().collect()),
         }
     }
 }
@@ -231,7 +235,7 @@ pub async fn search_with_url_query(
     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, retrieve_vector)
+        perform_search(&index, query, search_kind, retrieve_vector, index_scheduler.features())
     })
     .await?;
     if let Ok(ref search_result) = search_result {
@@ -274,7 +278,7 @@ pub async fn search_with_post(
 
     let _permit = search_queue.try_get_search_permit().await?;
     let search_result = tokio::task::spawn_blocking(move || {
-        perform_search(&index, query, search_kind, retrieve_vectors)
+        perform_search(&index, query, search_kind, retrieve_vectors, index_scheduler.features())
     })
     .await?;
     if let Ok(ref search_result) = search_result {

meilisearch/src/routes/indexes/settings.rs

@@ -474,6 +474,28 @@ make_setting_route!(
     }
 );
 
+make_setting_route!(
+    "/localized-attributes",
+    put,
+    Vec<meilisearch_types::locales::LocalizedAttributesRuleView>,
+    meilisearch_types::deserr::DeserrJsonError<
+        meilisearch_types::error::deserr_codes::InvalidSettingsLocalizedAttributes,
+    >,
+    localized_attributes,
+    "localizedAttributes",
+    analytics,
+    |rules: &Option<Vec<meilisearch_types::locales::LocalizedAttributesRuleView>>, req: &HttpRequest| {
+        use serde_json::json;
+        analytics.publish(
+            "LocalizedAttributesRules Updated".to_string(),
+            json!({
+                "locales": rules.as_ref().map(|rules| rules.iter().flat_map(|rule| rule.locales.iter().cloned()).collect::<std::collections::BTreeSet<_>>())
+            }),
+            Some(req),
+        );
+    }
+);
+
 make_setting_route!(
     "/ranking-rules",
     put,
@@ -660,6 +682,7 @@ generate_configure!(
     filterable_attributes,
     sortable_attributes,
     displayed_attributes,
+    localized_attributes,
     searchable_attributes,
     distinct_attribute,
     proximity_precision,
@@ -786,6 +809,7 @@ pub async fn update_all(
             },
             "embedders": crate::routes::indexes::settings::embedder_analytics(new_settings.embedders.as_ref().set()),
             "search_cutoff_ms": new_settings.search_cutoff_ms.as_ref().set(),
+            "locales": new_settings.localized_attributes.as_ref().set().map(|rules| rules.iter().flat_map(|rule| rule.locales.iter().cloned()).collect::<std::collections::BTreeSet<_>>()),
         }),
         Some(&req),
     );

meilisearch/src/routes/indexes/similar.rs

@@ -106,7 +106,14 @@ async fn similar(
         SearchKind::embedder(&index_scheduler, &index, query.embedder.as_deref(), None)?;
 
     tokio::task::spawn_blocking(move || {
-        perform_similar(&index, query, embedder_name, embedder, retrieve_vectors)
+        perform_similar(
+            &index,
+            query,
+            embedder_name,
+            embedder,
+            retrieve_vectors,
+            index_scheduler.features(),
+        )
     })
     .await?
 }

meilisearch/src/routes/multi_search.rs

@@ -10,12 +10,14 @@ use serde::Serialize;
 use tracing::debug;
 
 use crate::analytics::{Analytics, MultiSearchAggregator};
+use crate::error::MeilisearchHttpError;
 use crate::extractors::authentication::policies::ActionPolicy;
 use crate::extractors::authentication::{AuthenticationError, GuardedData};
 use crate::extractors::sequential_extractor::SeqHandler;
 use crate::routes::indexes::search::search_kind;
 use crate::search::{
-    add_search_rules, perform_search, RetrieveVectors, SearchQueryWithIndex, SearchResultWithIndex,
+    add_search_rules, perform_federated_search, perform_search, FederatedSearch, RetrieveVectors,
+    SearchQueryWithIndex, SearchResultWithIndex,
 };
 use crate::search_queue::SearchQueue;
 
@@ -28,85 +30,44 @@ struct SearchResults {
     results: Vec<SearchResultWithIndex>,
 }
 
-#[derive(Debug, deserr::Deserr)]
-#[deserr(error = DeserrJsonError, rename_all = camelCase, deny_unknown_fields)]
-pub struct SearchQueries {
-    queries: Vec<SearchQueryWithIndex>,
-}
-
 pub async fn multi_search_with_post(
     index_scheduler: GuardedData<ActionPolicy<{ actions::SEARCH }>, Data<IndexScheduler>>,
     search_queue: Data<SearchQueue>,
-    params: AwebJson<SearchQueries, DeserrJsonError>,
+    params: AwebJson<FederatedSearch, DeserrJsonError>,
     req: HttpRequest,
     analytics: web::Data<dyn Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
-    let queries = params.into_inner().queries;
-
-    let mut multi_aggregate = MultiSearchAggregator::from_queries(&queries, &req);
-    let features = index_scheduler.features();
-
     // Since we don't want to process half of the search requests and then get a permit refused
     // we're going to get one permit for the whole duration of the multi-search request.
     let _permit = search_queue.try_get_search_permit().await?;
 
-    // Explicitly expect a `(ResponseError, usize)` for the error type rather than `ResponseError` only,
-    // so that `?` doesn't work if it doesn't use `with_index`, ensuring that it is not forgotten in case of code
-    // changes.
-    let search_results: Result<_, (ResponseError, usize)> = async {
-        let mut search_results = Vec::with_capacity(queries.len());
-        for (query_index, (index_uid, mut query)) in
-            queries.into_iter().map(SearchQueryWithIndex::into_index_query).enumerate()
-        {
-            debug!(on_index = query_index, parameters = ?query, "Multi-search");
+    let federated_search = params.into_inner();
 
+    let mut multi_aggregate = MultiSearchAggregator::from_federated_search(&federated_search, &req);
+
+    let FederatedSearch { mut queries, federation } = federated_search;
+
+    let features = index_scheduler.features();
+
+    // regardless of federation, check authorization and apply search rules
+    let auth = 'check_authorization: {
+        for (query_index, federated_query) in queries.iter_mut().enumerate() {
+            let index_uid = federated_query.index_uid.as_str();
             // Check index from API key
-            if !index_scheduler.filters().is_index_authorized(&index_uid) {
-                return Err(AuthenticationError::InvalidToken).with_index(query_index);
+            if !index_scheduler.filters().is_index_authorized(index_uid) {
+                break 'check_authorization Err(AuthenticationError::InvalidToken)
+                    .with_index(query_index);
             }
             // Apply search rules from tenant token
-            if let Some(search_rules) = index_scheduler.filters().get_index_search_rules(&index_uid)
+            if let Some(search_rules) = index_scheduler.filters().get_index_search_rules(index_uid)
             {
-                add_search_rules(&mut query.filter, search_rules);
+                add_search_rules(&mut federated_query.filter, search_rules);
             }
-
-            let index = index_scheduler
-                .index(&index_uid)
-                .map_err(|err| {
-                    let mut err = ResponseError::from(err);
-                    // Patch the HTTP status code to 400 as it defaults to 404 for `index_not_found`, but
-                    // here the resource not found is not part of the URL.
-                    err.code = StatusCode::BAD_REQUEST;
-                    err
-                })
-                .with_index(query_index)?;
-
-            let search_kind = search_kind(&query, index_scheduler.get_ref(), &index, features)
-                .with_index(query_index)?;
-            let retrieve_vector =
-                RetrieveVectors::new(query.retrieve_vectors, features).with_index(query_index)?;
-
-            let search_result = tokio::task::spawn_blocking(move || {
-                perform_search(&index, query, search_kind, retrieve_vector)
-            })
-            .await
-            .with_index(query_index)?;
-
-            search_results.push(SearchResultWithIndex {
-                index_uid: index_uid.into_inner(),
-                result: search_result.with_index(query_index)?,
-            });
         }
-        Ok(search_results)
-    }
-    .await;
+        Ok(())
+    };
 
-    if search_results.is_ok() {
-        multi_aggregate.succeed();
-    }
-    analytics.post_multi_search(multi_aggregate);
-
-    let search_results = search_results.map_err(|(mut err, query_index)| {
+    auth.map_err(|(mut err, query_index)| {
         // Add the query index that failed as context for the error message.
         // We're doing it only here and not directly in the `WithIndex` trait so that the `with_index` function returns a different type
         // of result and we can benefit from static typing.
@@ -114,9 +75,95 @@ pub async fn multi_search_with_post(
         err
     })?;
 
-    debug!(returns = ?search_results, "Multi-search");
+    let response = match federation {
+        Some(federation) => {
+            let search_result = tokio::task::spawn_blocking(move || {
+                perform_federated_search(&index_scheduler, queries, federation, features)
+            })
+            .await;
 
-    Ok(HttpResponse::Ok().json(SearchResults { results: search_results }))
+            if let Ok(Ok(_)) = search_result {
+                multi_aggregate.succeed();
+            }
+
+            analytics.post_multi_search(multi_aggregate);
+            HttpResponse::Ok().json(search_result??)
+        }
+        None => {
+            // Explicitly expect a `(ResponseError, usize)` for the error type rather than `ResponseError` only,
+            // so that `?` doesn't work if it doesn't use `with_index`, ensuring that it is not forgotten in case of code
+            // changes.
+            let search_results: Result<_, (ResponseError, usize)> = async {
+                let mut search_results = Vec::with_capacity(queries.len());
+                for (query_index, (index_uid, query, federation_options)) in queries
+                    .into_iter()
+                    .map(SearchQueryWithIndex::into_index_query_federation)
+                    .enumerate()
+                {
+                    debug!(on_index = query_index, parameters = ?query, "Multi-search");
+
+                    if federation_options.is_some() {
+                        return Err((
+                            MeilisearchHttpError::FederationOptionsInNonFederatedRequest(
+                                query_index,
+                            )
+                            .into(),
+                            query_index,
+                        ));
+                    }
+
+                    let index = index_scheduler
+                        .index(&index_uid)
+                        .map_err(|err| {
+                            let mut err = ResponseError::from(err);
+                            // Patch the HTTP status code to 400 as it defaults to 404 for `index_not_found`, but
+                            // here the resource not found is not part of the URL.
+                            err.code = StatusCode::BAD_REQUEST;
+                            err
+                        })
+                        .with_index(query_index)?;
+
+                    let search_kind =
+                        search_kind(&query, index_scheduler.get_ref(), &index, features)
+                            .with_index(query_index)?;
+                    let retrieve_vector = RetrieveVectors::new(query.retrieve_vectors, features)
+                        .with_index(query_index)?;
+
+                    let search_result = tokio::task::spawn_blocking(move || {
+                        perform_search(&index, query, search_kind, retrieve_vector, features)
+                    })
+                    .await
+                    .with_index(query_index)?;
+
+                    search_results.push(SearchResultWithIndex {
+                        index_uid: index_uid.into_inner(),
+                        result: search_result.with_index(query_index)?,
+                    });
+                }
+                Ok(search_results)
+            }
+            .await;
+
+            if search_results.is_ok() {
+                multi_aggregate.succeed();
+            }
+            analytics.post_multi_search(multi_aggregate);
+
+            let search_results = search_results.map_err(|(mut err, query_index)| {
+                // Add the query index that failed as context for the error message.
+                // We're doing it only here and not directly in the `WithIndex` trait so that the `with_index` function returns a different type
+                // of result and we can benefit from static typing.
+                err.message = format!("Inside `.queries[{query_index}]`: {}", err.message);
+                err
+            })?;
+
+            debug!(returns = ?search_results, "Multi-search");
+
+            HttpResponse::Ok().json(SearchResults { results: search_results })
+        }
+    };
+
+    Ok(response)
 }
 
 /// Local `Result` extension trait to avoid `map_err` boilerplate.

meilisearch/src/routes/tasks.rs

@@ -591,7 +591,7 @@ mod tests {
             let err = deserr_query_params::<TaskDeletionOrCancelationQuery>(params).unwrap_err();
             snapshot!(meili_snap::json_string!(err), @r###"
             {
-              "message": "Invalid value in parameter `types`: `createIndex` is not a valid task type. Available types are `documentAdditionOrUpdate`, `documentDeletion`, `settingsUpdate`, `indexCreation`, `indexDeletion`, `indexUpdate`, `indexSwap`, `taskCancelation`, `taskDeletion`, `dumpCreation`, `snapshotCreation`.",
+              "message": "Invalid value in parameter `types`: `createIndex` is not a valid task type. Available types are `documentAdditionOrUpdate`, `documentEdition`, `documentDeletion`, `settingsUpdate`, `indexCreation`, `indexDeletion`, `indexUpdate`, `indexSwap`, `taskCancelation`, `taskDeletion`, `dumpCreation`, `snapshotCreation`.",
               "code": "invalid_task_types",
               "type": "invalid_request",
               "link": "https://docs.meilisearch.com/errors#invalid_task_types"

meilisearch/src/search/federated.rs

@@ -0,0 +1,623 @@
+use std::cmp::Ordering;
+use std::collections::BTreeMap;
+use std::fmt;
+use std::iter::Zip;
+use std::rc::Rc;
+use std::str::FromStr as _;
+use std::time::Duration;
+use std::vec::{IntoIter, Vec};
+
+use actix_http::StatusCode;
+use index_scheduler::{IndexScheduler, RoFeatures};
+use meilisearch_types::deserr::DeserrJsonError;
+use meilisearch_types::error::deserr_codes::{
+    InvalidMultiSearchWeight, InvalidSearchLimit, InvalidSearchOffset,
+};
+use meilisearch_types::error::ResponseError;
+use meilisearch_types::milli::score_details::{ScoreDetails, ScoreValue};
+use meilisearch_types::milli::{self, DocumentId, TimeBudget};
+use roaring::RoaringBitmap;
+use serde::Serialize;
+
+use super::ranking_rules::{self, RankingRules};
+use super::{
+    prepare_search, AttributesFormat, HitMaker, HitsInfo, RetrieveVectors, SearchHit, SearchKind,
+    SearchQuery, SearchQueryWithIndex,
+};
+use crate::error::MeilisearchHttpError;
+use crate::routes::indexes::search::search_kind;
+
+pub const DEFAULT_FEDERATED_WEIGHT: f64 = 1.0;
+
+#[derive(Debug, Default, Clone, Copy, PartialEq, deserr::Deserr)]
+#[deserr(error = DeserrJsonError, rename_all = camelCase, deny_unknown_fields)]
+pub struct FederationOptions {
+    #[deserr(default, error = DeserrJsonError<InvalidMultiSearchWeight>)]
+    pub weight: Weight,
+}
+
+#[derive(Debug, Clone, Copy, PartialEq, deserr::Deserr)]
+#[deserr(try_from(f64) = TryFrom::try_from -> InvalidMultiSearchWeight)]
+pub struct Weight(f64);
+
+impl Default for Weight {
+    fn default() -> Self {
+        Weight(DEFAULT_FEDERATED_WEIGHT)
+    }
+}
+
+impl std::convert::TryFrom<f64> for Weight {
+    type Error = InvalidMultiSearchWeight;
+
+    fn try_from(f: f64) -> Result<Self, Self::Error> {
+        if f < 0.0 {
+            Err(InvalidMultiSearchWeight)
+        } else {
+            Ok(Weight(f))
+        }
+    }
+}
+
+impl std::ops::Deref for Weight {
+    type Target = f64;
+
+    fn deref(&self) -> &Self::Target {
+        &self.0
+    }
+}
+
+#[derive(Debug, deserr::Deserr)]
+#[deserr(error = DeserrJsonError, rename_all = camelCase, deny_unknown_fields)]
+pub struct Federation {
+    #[deserr(default = super::DEFAULT_SEARCH_LIMIT(), error = DeserrJsonError<InvalidSearchLimit>)]
+    pub limit: usize,
+    #[deserr(default = super::DEFAULT_SEARCH_OFFSET(), error = DeserrJsonError<InvalidSearchOffset>)]
+    pub offset: usize,
+}
+
+#[derive(Debug, deserr::Deserr)]
+#[deserr(error = DeserrJsonError, rename_all = camelCase, deny_unknown_fields)]
+pub struct FederatedSearch {
+    pub queries: Vec<SearchQueryWithIndex>,
+    #[deserr(default)]
+    pub federation: Option<Federation>,
+}
+#[derive(Serialize, Clone, PartialEq)]
+#[serde(rename_all = "camelCase")]
+pub struct FederatedSearchResult {
+    pub hits: Vec<SearchHit>,
+    pub processing_time_ms: u128,
+    #[serde(flatten)]
+    pub hits_info: HitsInfo,
+
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub semantic_hit_count: Option<u32>,
+
+    // These fields are only used for analytics purposes
+    #[serde(skip)]
+    pub degraded: bool,
+    #[serde(skip)]
+    pub used_negative_operator: bool,
+}
+
+impl fmt::Debug for FederatedSearchResult {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        let FederatedSearchResult {
+            hits,
+            processing_time_ms,
+            hits_info,
+            semantic_hit_count,
+            degraded,
+            used_negative_operator,
+        } = self;
+
+        let mut debug = f.debug_struct("SearchResult");
+        // The most important thing when looking at a search result is the time it took to process
+        debug.field("processing_time_ms", &processing_time_ms);
+        debug.field("hits", &format!("[{} hits returned]", hits.len()));
+        debug.field("hits_info", &hits_info);
+        if *used_negative_operator {
+            debug.field("used_negative_operator", used_negative_operator);
+        }
+        if *degraded {
+            debug.field("degraded", degraded);
+        }
+        if let Some(semantic_hit_count) = semantic_hit_count {
+            debug.field("semantic_hit_count", &semantic_hit_count);
+        }
+
+        debug.finish()
+    }
+}
+
+struct WeightedScore<'a> {
+    details: &'a [ScoreDetails],
+    weight: f64,
+}
+
+impl<'a> WeightedScore<'a> {
+    pub fn new(details: &'a [ScoreDetails], weight: f64) -> Self {
+        Self { details, weight }
+    }
+
+    pub fn weighted_global_score(&self) -> f64 {
+        ScoreDetails::global_score(self.details.iter()) * self.weight
+    }
+
+    pub fn compare_weighted_global_scores(&self, other: &Self) -> Ordering {
+        self.weighted_global_score()
+            .partial_cmp(&other.weighted_global_score())
+            // both are numbers, possibly infinite
+            .unwrap()
+    }
+
+    pub fn compare(&self, other: &Self) -> Ordering {
+        let mut left_it = ScoreDetails::score_values(self.details.iter());
+        let mut right_it = ScoreDetails::score_values(other.details.iter());
+
+        loop {
+            let left = left_it.next();
+            let right = right_it.next();
+
+            match (left, right) {
+                (None, None) => return Ordering::Equal,
+                (None, Some(_)) => return Ordering::Less,
+                (Some(_), None) => return Ordering::Greater,
+                (Some(ScoreValue::Score(left)), Some(ScoreValue::Score(right))) => {
+                    let left = left * self.weight;
+                    let right = right * other.weight;
+                    if (left - right).abs() <= f64::EPSILON {
+                        continue;
+                    }
+                    return left.partial_cmp(&right).unwrap();
+                }
+                (Some(ScoreValue::Sort(left)), Some(ScoreValue::Sort(right))) => {
+                    match left.partial_cmp(right) {
+                        Some(Ordering::Equal) => continue,
+                        Some(order) => return order,
+                        None => return self.compare_weighted_global_scores(other),
+                    }
+                }
+                (Some(ScoreValue::GeoSort(left)), Some(ScoreValue::GeoSort(right))) => {
+                    match left.partial_cmp(right) {
+                        Some(Ordering::Equal) => continue,
+                        Some(order) => return order,
+                        None => {
+                            return self.compare_weighted_global_scores(other);
+                        }
+                    }
+                }
+                // not comparable details, use global
+                (Some(ScoreValue::Score(_)), Some(_))
+                | (Some(_), Some(ScoreValue::Score(_)))
+                | (Some(ScoreValue::GeoSort(_)), Some(ScoreValue::Sort(_)))
+                | (Some(ScoreValue::Sort(_)), Some(ScoreValue::GeoSort(_))) => {
+                    let left_count = left_it.count();
+                    let right_count = right_it.count();
+                    // compare how many remaining groups of rules each side has.
+                    // the group with the most remaining groups wins.
+                    return left_count
+                        .cmp(&right_count)
+                        // breaks ties with the global ranking score
+                        .then_with(|| self.compare_weighted_global_scores(other));
+                }
+            }
+        }
+    }
+}
+
+struct QueryByIndex {
+    query: SearchQuery,
+    federation_options: FederationOptions,
+    query_index: usize,
+}
+
+struct SearchResultByQuery<'a> {
+    documents_ids: Vec<DocumentId>,
+    document_scores: Vec<Vec<ScoreDetails>>,
+    federation_options: FederationOptions,
+    hit_maker: HitMaker<'a>,
+    query_index: usize,
+}
+
+struct SearchResultByQueryIter<'a> {
+    it: Zip<IntoIter<DocumentId>, IntoIter<Vec<ScoreDetails>>>,
+    federation_options: FederationOptions,
+    hit_maker: Rc<HitMaker<'a>>,
+    query_index: usize,
+}
+
+impl<'a> SearchResultByQueryIter<'a> {
+    fn new(
+        SearchResultByQuery {
+            documents_ids,
+            document_scores,
+            federation_options,
+            hit_maker,
+            query_index,
+        }: SearchResultByQuery<'a>,
+    ) -> Self {
+        let it = documents_ids.into_iter().zip(document_scores);
+        Self { it, federation_options, hit_maker: Rc::new(hit_maker), query_index }
+    }
+}
+
+struct SearchResultByQueryIterItem<'a> {
+    docid: DocumentId,
+    score: Vec<ScoreDetails>,
+    federation_options: FederationOptions,
+    hit_maker: Rc<HitMaker<'a>>,
+    query_index: usize,
+}
+
+fn merge_index_local_results(
+    results_by_query: Vec<SearchResultByQuery<'_>>,
+) -> impl Iterator<Item = SearchResultByQueryIterItem> + '_ {
+    itertools::kmerge_by(
+        results_by_query.into_iter().map(SearchResultByQueryIter::new),
+        |left: &SearchResultByQueryIterItem, right: &SearchResultByQueryIterItem| {
+            let left_score = WeightedScore::new(&left.score, *left.federation_options.weight);
+            let right_score = WeightedScore::new(&right.score, *right.federation_options.weight);
+
+            match left_score.compare(&right_score) {
+                // the biggest score goes first
+                Ordering::Greater => true,
+                // break ties using query index
+                Ordering::Equal => left.query_index < right.query_index,
+                Ordering::Less => false,
+            }
+        },
+    )
+}
+
+fn merge_index_global_results(
+    results_by_index: Vec<SearchResultByIndex>,
+) -> impl Iterator<Item = SearchHitByIndex> {
+    itertools::kmerge_by(
+        results_by_index.into_iter().map(|result_by_index| result_by_index.hits.into_iter()),
+        |left: &SearchHitByIndex, right: &SearchHitByIndex| {
+            let left_score = WeightedScore::new(&left.score, *left.federation_options.weight);
+            let right_score = WeightedScore::new(&right.score, *right.federation_options.weight);
+
+            match left_score.compare(&right_score) {
+                // the biggest score goes first
+                Ordering::Greater => true,
+                // break ties using query index
+                Ordering::Equal => left.query_index < right.query_index,
+                Ordering::Less => false,
+            }
+        },
+    )
+}
+
+impl<'a> Iterator for SearchResultByQueryIter<'a> {
+    type Item = SearchResultByQueryIterItem<'a>;
+
+    fn next(&mut self) -> Option<Self::Item> {
+        let (docid, score) = self.it.next()?;
+        Some(SearchResultByQueryIterItem {
+            docid,
+            score,
+            federation_options: self.federation_options,
+            hit_maker: Rc::clone(&self.hit_maker),
+            query_index: self.query_index,
+        })
+    }
+}
+
+struct SearchHitByIndex {
+    hit: SearchHit,
+    score: Vec<ScoreDetails>,
+    federation_options: FederationOptions,
+    query_index: usize,
+}
+
+struct SearchResultByIndex {
+    hits: Vec<SearchHitByIndex>,
+    candidates: RoaringBitmap,
+    degraded: bool,
+    used_negative_operator: bool,
+}
+
+pub fn perform_federated_search(
+    index_scheduler: &IndexScheduler,
+    queries: Vec<SearchQueryWithIndex>,
+    federation: Federation,
+    features: RoFeatures,
+) -> Result<FederatedSearchResult, ResponseError> {
+    let before_search = std::time::Instant::now();
+
+    // this implementation partition the queries by index to guarantee an important property:
+    // - all the queries to a particular index use the same read transaction.
+    // This is an important property, otherwise we cannot guarantee the self-consistency of the results.
+
+    // 1. partition queries by index
+    let mut queries_by_index: BTreeMap<String, Vec<QueryByIndex>> = Default::default();
+    for (query_index, federated_query) in queries.into_iter().enumerate() {
+        if let Some(pagination_field) = federated_query.has_pagination() {
+            return Err(MeilisearchHttpError::PaginationInFederatedQuery(
+                query_index,
+                pagination_field,
+            )
+            .into());
+        }
+
+        let (index_uid, query, federation_options) = federated_query.into_index_query_federation();
+
+        queries_by_index.entry(index_uid.into_inner()).or_default().push(QueryByIndex {
+            query,
+            federation_options: federation_options.unwrap_or_default(),
+            query_index,
+        })
+    }
+
+    // 2. perform queries, merge and make hits index by index
+    let required_hit_count = federation.limit + federation.offset;
+    // In step (2), semantic_hit_count will be set to Some(0) if any search kind uses semantic
+    // Then in step (3), we'll update its value if there is any semantic search
+    let mut semantic_hit_count = None;
+    let mut results_by_index = Vec::with_capacity(queries_by_index.len());
+    let mut previous_query_data: Option<(RankingRules, usize, String)> = None;
+
+    for (index_uid, queries) in queries_by_index {
+        let index = match index_scheduler.index(&index_uid) {
+            Ok(index) => index,
+            Err(err) => {
+                let mut err = ResponseError::from(err);
+                // Patch the HTTP status code to 400 as it defaults to 404 for `index_not_found`, but
+                // here the resource not found is not part of the URL.
+                err.code = StatusCode::BAD_REQUEST;
+                if let Some(query) = queries.first() {
+                    err.message =
+                        format!("Inside `.queries[{}]`: {}", query.query_index, err.message);
+                }
+                return Err(err);
+            }
+        };
+
+        // Important: this is the only transaction we'll use for this index during this federated search
+        let rtxn = index.read_txn()?;
+
+        let criteria = index.criteria(&rtxn)?;
+
+        let dictionary = index.dictionary(&rtxn)?;
+        let dictionary: Option<Vec<_>> =
+            dictionary.as_ref().map(|x| x.iter().map(String::as_str).collect());
+        let separators = index.allowed_separators(&rtxn)?;
+        let separators: Option<Vec<_>> =
+            separators.as_ref().map(|x| x.iter().map(String::as_str).collect());
+
+        // each query gets its individual cutoff
+        let cutoff = index.search_cutoff(&rtxn)?;
+
+        let mut degraded = false;
+        let mut used_negative_operator = false;
+        let mut candidates = RoaringBitmap::new();
+
+        // 2.1. Compute all candidates for each query in the index
+        let mut results_by_query = Vec::with_capacity(queries.len());
+
+        for QueryByIndex { query, federation_options, query_index } in queries {
+            // use an immediately invoked lambda to capture the result without returning from the function
+
+            let res: Result<(), ResponseError> = (|| {
+                let search_kind = search_kind(&query, index_scheduler, &index, features)?;
+
+                let canonicalization_kind = match (&search_kind, &query.q) {
+                    (SearchKind::SemanticOnly { .. }, _) => {
+                        ranking_rules::CanonicalizationKind::Vector
+                    }
+                    (_, Some(q)) if !q.is_empty() => ranking_rules::CanonicalizationKind::Keyword,
+                    _ => ranking_rules::CanonicalizationKind::Placeholder,
+                };
+
+                let sort = if let Some(sort) = &query.sort {
+                    let sorts: Vec<_> =
+                        match sort.iter().map(|s| milli::AscDesc::from_str(s)).collect() {
+                            Ok(sorts) => sorts,
+                            Err(asc_desc_error) => {
+                                return Err(milli::Error::from(milli::SortError::from(
+                                    asc_desc_error,
+                                ))
+                                .into())
+                            }
+                        };
+                    Some(sorts)
+                } else {
+                    None
+                };
+
+                let ranking_rules = ranking_rules::RankingRules::new(
+                    criteria.clone(),
+                    sort,
+                    query.matching_strategy.into(),
+                    canonicalization_kind,
+                );
+
+                if let Some((previous_ranking_rules, previous_query_index, previous_index_uid)) =
+                    previous_query_data.take()
+                {
+                    if let Err(error) = ranking_rules.is_compatible_with(&previous_ranking_rules) {
+                        return Err(error.to_response_error(
+                            &ranking_rules,
+                            &previous_ranking_rules,
+                            query_index,
+                            previous_query_index,
+                            &index_uid,
+                            &previous_index_uid,
+                        ));
+                    }
+                    previous_query_data = if previous_ranking_rules.constraint_count()
+                        > ranking_rules.constraint_count()
+                    {
+                        Some((previous_ranking_rules, previous_query_index, previous_index_uid))
+                    } else {
+                        Some((ranking_rules, query_index, index_uid.clone()))
+                    };
+                } else {
+                    previous_query_data = Some((ranking_rules, query_index, index_uid.clone()));
+                }
+
+                match search_kind {
+                    SearchKind::KeywordOnly => {}
+                    _ => semantic_hit_count = Some(0),
+                }
+
+                let retrieve_vectors = RetrieveVectors::new(query.retrieve_vectors, features)?;
+
+                let time_budget = match cutoff {
+                    Some(cutoff) => TimeBudget::new(Duration::from_millis(cutoff)),
+                    None => TimeBudget::default(),
+                };
+
+                let (mut search, _is_finite_pagination, _max_total_hits, _offset) =
+                    prepare_search(&index, &rtxn, &query, &search_kind, time_budget, features)?;
+
+                search.scoring_strategy(milli::score_details::ScoringStrategy::Detailed);
+                search.offset(0);
+                search.limit(required_hit_count);
+
+                let (result, _semantic_hit_count) = super::search_from_kind(search_kind, search)?;
+                let format = AttributesFormat {
+                    attributes_to_retrieve: query.attributes_to_retrieve,
+                    retrieve_vectors,
+                    attributes_to_highlight: query.attributes_to_highlight,
+                    attributes_to_crop: query.attributes_to_crop,
+                    crop_length: query.crop_length,
+                    crop_marker: query.crop_marker,
+                    highlight_pre_tag: query.highlight_pre_tag,
+                    highlight_post_tag: query.highlight_post_tag,
+                    show_matches_position: query.show_matches_position,
+                    sort: query.sort,
+                    show_ranking_score: query.show_ranking_score,
+                    show_ranking_score_details: query.show_ranking_score_details,
+                    locales: query.locales.map(|l| l.iter().copied().map(Into::into).collect()),
+                };
+
+                let milli::SearchResult {
+                    matching_words,
+                    candidates: query_candidates,
+                    documents_ids,
+                    document_scores,
+                    degraded: query_degraded,
+                    used_negative_operator: query_used_negative_operator,
+                } = result;
+
+                candidates |= query_candidates;
+                degraded |= query_degraded;
+                used_negative_operator |= query_used_negative_operator;
+
+                let tokenizer = HitMaker::tokenizer(dictionary.as_deref(), separators.as_deref());
+
+                let formatter_builder = HitMaker::formatter_builder(matching_words, tokenizer);
+
+                let hit_maker = HitMaker::new(&index, &rtxn, format, formatter_builder)?;
+
+                results_by_query.push(SearchResultByQuery {
+                    federation_options,
+                    hit_maker,
+                    query_index,
+                    documents_ids,
+                    document_scores,
+                });
+                Ok(())
+            })();
+
+            if let Err(mut error) = res {
+                error.message = format!("Inside `.queries[{query_index}]`: {}", error.message);
+                return Err(error);
+            }
+        }
+        // 2.2. merge inside index
+        let mut documents_seen = RoaringBitmap::new();
+        let merged_result: Result<Vec<_>, ResponseError> =
+            merge_index_local_results(results_by_query)
+                // skip documents we've already seen & mark that we saw the current document
+                .filter(|SearchResultByQueryIterItem { docid, .. }| documents_seen.insert(*docid))
+                .take(required_hit_count)
+                // 2.3 make hits
+                .map(
+                    |SearchResultByQueryIterItem {
+                         docid,
+                         score,
+                         federation_options,
+                         hit_maker,
+                         query_index,
+                     }| {
+                        let mut hit = hit_maker.make_hit(docid, &score)?;
+                        let weighted_score =
+                            ScoreDetails::global_score(score.iter()) * (*federation_options.weight);
+
+                        let _federation = serde_json::json!(
+                            {
+                                "indexUid": index_uid,
+                                "queriesPosition": query_index,
+                                "weightedRankingScore": weighted_score,
+                            }
+                        );
+                        hit.document.insert("_federation".to_string(), _federation);
+                        Ok(SearchHitByIndex { hit, score, federation_options, query_index })
+                    },
+                )
+                .collect();
+
+        let merged_result = merged_result?;
+        results_by_index.push(SearchResultByIndex {
+            hits: merged_result,
+            candidates,
+            degraded,
+            used_negative_operator,
+        });
+    }
+
+    // 3. merge hits and metadata across indexes
+    // 3.1 merge metadata
+    let (estimated_total_hits, degraded, used_negative_operator) = {
+        let mut estimated_total_hits = 0;
+        let mut degraded = false;
+        let mut used_negative_operator = false;
+
+        for SearchResultByIndex {
+            hits: _,
+            candidates,
+            degraded: degraded_by_index,
+            used_negative_operator: used_negative_operator_by_index,
+        } in &results_by_index
+        {
+            estimated_total_hits += candidates.len() as usize;
+            degraded |= *degraded_by_index;
+            used_negative_operator |= *used_negative_operator_by_index;
+        }
+
+        (estimated_total_hits, degraded, used_negative_operator)
+    };
+
+    // 3.2 merge hits
+    let merged_hits: Vec<_> = merge_index_global_results(results_by_index)
+        .skip(federation.offset)
+        .take(federation.limit)
+        .inspect(|hit| {
+            if let Some(semantic_hit_count) = &mut semantic_hit_count {
+                if hit.score.iter().any(|score| matches!(&score, ScoreDetails::Vector(_))) {
+                    *semantic_hit_count += 1;
+                }
+            }
+        })
+        .map(|hit| hit.hit)
+        .collect();
+
+    let search_result = FederatedSearchResult {
+        hits: merged_hits,
+        processing_time_ms: before_search.elapsed().as_millis(),
+        hits_info: HitsInfo::OffsetLimit {
+            limit: federation.limit,
+            offset: federation.offset,
+            estimated_total_hits,
+        },
+        semantic_hit_count,
+        degraded,
+        used_negative_operator,
+    };
+
+    Ok(search_result)
+}

meilisearch/src/search/mod.rs

@@ -7,6 +7,7 @@ use std::time::{Duration, Instant};
 
 use deserr::Deserr;
 use either::Either;
+use index_scheduler::RoFeatures;
 use indexmap::IndexMap;
 use meilisearch_auth::IndexSearchRules;
 use meilisearch_types::deserr::DeserrJsonError;
@@ -14,16 +15,17 @@ use meilisearch_types::error::deserr_codes::*;
 use meilisearch_types::error::{Code, ResponseError};
 use meilisearch_types::heed::RoTxn;
 use meilisearch_types::index_uid::IndexUid;
+use meilisearch_types::locales::Locale;
 use meilisearch_types::milli::score_details::{ScoreDetails, ScoringStrategy};
 use meilisearch_types::milli::vector::parsed_vectors::ExplicitVectors;
 use meilisearch_types::milli::vector::Embedder;
 use meilisearch_types::milli::{FacetValueHit, OrderBy, SearchForFacetValues, TimeBudget};
 use meilisearch_types::settings::DEFAULT_PAGINATION_MAX_TOTAL_HITS;
 use meilisearch_types::{milli, Document};
-use milli::tokenizer::TokenizerBuilder;
+use milli::tokenizer::{Language, TokenizerBuilder};
 use milli::{
-    AscDesc, FieldId, FieldsIdsMap, Filter, FormatOptions, Index, MatchBounds, MatcherBuilder,
-    SortError, TermsMatchingStrategy, DEFAULT_VALUES_PER_FACET,
+    AscDesc, FieldId, FieldsIdsMap, Filter, FormatOptions, Index, LocalizedAttributesRule,
+    MatchBounds, MatcherBuilder, SortError, TermsMatchingStrategy, DEFAULT_VALUES_PER_FACET,
 };
 use regex::Regex;
 use serde::Serialize;
@@ -31,6 +33,11 @@ use serde_json::{json, Value};
 
 use crate::error::MeilisearchHttpError;
 
+mod federated;
+pub use federated::{perform_federated_search, FederatedSearch, Federation, FederationOptions};
+
+mod ranking_rules;
+
 type MatchesPosition = BTreeMap<String, Vec<MatchBounds>>;
 
 pub const DEFAULT_SEARCH_OFFSET: fn() -> usize = || 0;
@@ -94,6 +101,8 @@ pub struct SearchQuery {
     pub attributes_to_search_on: Option<Vec<String>>,
     #[deserr(default, error = DeserrJsonError<InvalidSearchRankingScoreThreshold>, default)]
     pub ranking_score_threshold: Option<RankingScoreThreshold>,
+    #[deserr(default, error = DeserrJsonError<InvalidSearchLocales>, default)]
+    pub locales: Option<Vec<Locale>>,
 }
 
 #[derive(Debug, Clone, Copy, PartialEq, Deserr)]
@@ -163,6 +172,7 @@ impl fmt::Debug for SearchQuery {
             matching_strategy,
             attributes_to_search_on,
             ranking_score_threshold,
+            locales,
         } = self;
 
         let mut debug = f.debug_struct("SearchQuery");
@@ -244,6 +254,10 @@ impl fmt::Debug for SearchQuery {
             debug.field("ranking_score_threshold", &ranking_score_threshold);
         }
 
+        if let Some(locales) = locales {
+            debug.field("locales", &locales);
+        }
+
         debug.finish()
     }
 }
@@ -257,11 +271,13 @@ pub struct HybridQuery {
     pub embedder: Option<String>,
 }
 
+#[derive(Clone)]
 pub enum SearchKind {
     KeywordOnly,
     SemanticOnly { embedder_name: String, embedder: Arc<Embedder> },
     Hybrid { embedder_name: String, embedder: Arc<Embedder>, semantic_ratio: f32 },
 }
+
 impl SearchKind {
     pub(crate) fn semantic(
         index_scheduler: &index_scheduler::IndexScheduler,
@@ -358,7 +374,7 @@ impl SearchQuery {
     }
 }
 
-/// A `SearchQuery` + an index UID.
+/// A `SearchQuery` + an index UID and optional FederationOptions.
 // This struct contains the fields of `SearchQuery` inline.
 // This is because neither deserr nor serde support `flatten` when using `deny_unknown_fields.
 // The `From<SearchQueryWithIndex>` implementation ensures both structs remain up to date.
@@ -373,10 +389,10 @@ pub struct SearchQueryWithIndex {
     pub vector: Option<Vec<f32>>,
     #[deserr(default, error = DeserrJsonError<InvalidHybridQuery>)]
     pub hybrid: Option<HybridQuery>,
-    #[deserr(default = DEFAULT_SEARCH_OFFSET(), error = DeserrJsonError<InvalidSearchOffset>)]
-    pub offset: usize,
-    #[deserr(default = DEFAULT_SEARCH_LIMIT(), error = DeserrJsonError<InvalidSearchLimit>)]
-    pub limit: usize,
+    #[deserr(default, error = DeserrJsonError<InvalidSearchOffset>)]
+    pub offset: Option<usize>,
+    #[deserr(default, error = DeserrJsonError<InvalidSearchLimit>)]
+    pub limit: Option<usize>,
     #[deserr(default, error = DeserrJsonError<InvalidSearchPage>)]
     pub page: Option<usize>,
     #[deserr(default, error = DeserrJsonError<InvalidSearchHitsPerPage>)]
@@ -417,12 +433,35 @@ pub struct SearchQueryWithIndex {
     pub attributes_to_search_on: Option<Vec<String>>,
     #[deserr(default, error = DeserrJsonError<InvalidSearchRankingScoreThreshold>, default)]
     pub ranking_score_threshold: Option<RankingScoreThreshold>,
+    #[deserr(default, error = DeserrJsonError<InvalidSearchLocales>, default)]
+    pub locales: Option<Vec<Locale>>,
+
+    #[deserr(default)]
+    pub federation_options: Option<FederationOptions>,
 }
 
 impl SearchQueryWithIndex {
-    pub fn into_index_query(self) -> (IndexUid, SearchQuery) {
+    pub fn has_federation_options(&self) -> bool {
+        self.federation_options.is_some()
+    }
+    pub fn has_pagination(&self) -> Option<&'static str> {
+        if self.offset.is_some() {
+            Some("offset")
+        } else if self.limit.is_some() {
+            Some("limit")
+        } else if self.page.is_some() {
+            Some("page")
+        } else if self.hits_per_page.is_some() {
+            Some("hitsPerPage")
+        } else {
+            None
+        }
+    }
+
+    pub fn into_index_query_federation(self) -> (IndexUid, SearchQuery, Option<FederationOptions>) {
         let SearchQueryWithIndex {
             index_uid,
+            federation_options,
             q,
             vector,
             offset,
@@ -448,14 +487,15 @@ impl SearchQueryWithIndex {
             attributes_to_search_on,
             hybrid,
             ranking_score_threshold,
+            locales,
         } = self;
         (
             index_uid,
             SearchQuery {
                 q,
                 vector,
-                offset,
-                limit,
+                offset: offset.unwrap_or(DEFAULT_SEARCH_OFFSET()),
+                limit: limit.unwrap_or(DEFAULT_SEARCH_LIMIT()),
                 page,
                 hits_per_page,
                 attributes_to_retrieve,
@@ -477,9 +517,11 @@ impl SearchQueryWithIndex {
                 attributes_to_search_on,
                 hybrid,
                 ranking_score_threshold,
+                locales,
                 // do not use ..Default::default() here,
                 // rather add any missing field from `SearchQuery` to `SearchQueryWithIndex`
             },
+            federation_options,
         )
     }
 }
@@ -732,7 +774,8 @@ fn prepare_search<'t>(
     query: &'t SearchQuery,
     search_kind: &SearchKind,
     time_budget: TimeBudget,
-) -> Result<(milli::Search<'t>, bool, usize, usize), MeilisearchHttpError> {
+    features: RoFeatures,
+) -> Result<(milli::Search<'t>, bool, usize, usize), ResponseError> {
     let mut search = index.search(rtxn);
     search.time_budget(time_budget);
     if let Some(ranking_score_threshold) = query.ranking_score_threshold {
@@ -752,10 +795,15 @@ fn prepare_search<'t>(
         SearchKind::SemanticOnly { embedder_name, embedder } => {
             let vector = match query.vector.clone() {
                 Some(vector) => vector,
-                None => embedder
-                    .embed_one(query.q.clone().unwrap())
-                    .map_err(milli::vector::Error::from)
-                    .map_err(milli::Error::from)?,
+                None => {
+                    let span = tracing::trace_span!(target: "search::vector", "embed_one");
+                    let _entered = span.enter();
+
+                    embedder
+                        .embed_one(query.q.clone().unwrap())
+                        .map_err(milli::vector::Error::from)
+                        .map_err(milli::Error::from)?
+                }
             };
 
             search.semantic(embedder_name.clone(), embedder.clone(), Some(vector));
@@ -814,7 +862,7 @@ fn prepare_search<'t>(
     search.limit(limit);
 
     if let Some(ref filter) = query.filter {
-        if let Some(facets) = parse_filter(filter)? {
+        if let Some(facets) = parse_filter(filter, Code::InvalidSearchFilter, features)? {
             search.filter(facets);
         }
     }
@@ -830,6 +878,10 @@ fn prepare_search<'t>(
         search.sort_criteria(sort);
     }
 
+    if let Some(ref locales) = query.locales {
+        search.locales(locales.iter().copied().map(Into::into).collect());
+    }
+
     Ok((search, is_finite_pagination, max_total_hits, offset))
 }
 
@@ -838,7 +890,8 @@ pub fn perform_search(
     query: SearchQuery,
     search_kind: SearchKind,
     retrieve_vectors: RetrieveVectors,
-) -> Result<SearchResult, MeilisearchHttpError> {
+    features: RoFeatures,
+) -> Result<SearchResult, ResponseError> {
     let before_search = Instant::now();
     let rtxn = index.read_txn()?;
     let time_budget = match index.search_cutoff(&rtxn)? {
@@ -847,7 +900,7 @@ pub fn perform_search(
     };
 
     let (search, is_finite_pagination, max_total_hits, offset) =
-        prepare_search(index, &rtxn, &query, &search_kind, time_budget)?;
+        prepare_search(index, &rtxn, &query, &search_kind, time_budget, features)?;
 
     let (
         milli::SearchResult {
@@ -859,15 +912,7 @@ pub fn perform_search(
             used_negative_operator,
         },
         semantic_hit_count,
-    ) = match &search_kind {
-        SearchKind::KeywordOnly => (search.execute()?, None),
-        SearchKind::SemanticOnly { .. } => {
-            let results = search.execute()?;
-            let semantic_hit_count = results.document_scores.len() as u32;
-            (results, Some(semantic_hit_count))
-        }
-        SearchKind::Hybrid { semantic_ratio, .. } => search.execute_hybrid(*semantic_ratio)?,
-    };
+    ) = search_from_kind(search_kind, search)?;
 
     let SearchQuery {
         q,
@@ -888,6 +933,7 @@ pub fn perform_search(
         highlight_pre_tag,
         highlight_post_tag,
         crop_marker,
+        locales,
         // already used in prepare_search
         vector: _,
         hybrid: _,
@@ -912,10 +958,16 @@ pub fn perform_search(
         sort,
         show_ranking_score,
         show_ranking_score_details,
+        locales: locales.map(|l| l.iter().copied().map(Into::into).collect()),
     };
 
-    let documents =
-        make_hits(index, &rtxn, format, matching_words, documents_ids, document_scores)?;
+    let documents = make_hits(
+        index,
+        &rtxn,
+        format,
+        matching_words,
+        documents_ids.iter().copied().zip(document_scores.iter()),
+    )?;
 
     let number_of_hits = min(candidates.len() as usize, max_total_hits);
     let hits_info = if is_finite_pagination {
@@ -983,6 +1035,22 @@ pub fn perform_search(
     Ok(result)
 }
 
+pub fn search_from_kind(
+    search_kind: SearchKind,
+    search: milli::Search<'_>,
+) -> Result<(milli::SearchResult, Option<u32>), MeilisearchHttpError> {
+    let (milli_result, semantic_hit_count) = match &search_kind {
+        SearchKind::KeywordOnly => (search.execute()?, None),
+        SearchKind::SemanticOnly { .. } => {
+            let results = search.execute()?;
+            let semantic_hit_count = results.document_scores.len() as u32;
+            (results, Some(semantic_hit_count))
+        }
+        SearchKind::Hybrid { semantic_ratio, .. } => search.execute_hybrid(*semantic_ratio)?,
+    };
+    Ok((milli_result, semantic_hit_count))
+}
+
 struct AttributesFormat {
     attributes_to_retrieve: Option<BTreeSet<String>>,
     retrieve_vectors: RetrieveVectors,
@@ -996,6 +1064,7 @@ struct AttributesFormat {
     sort: Option<Vec<String>>,
     show_ranking_score: bool,
     show_ranking_score_details: bool,
+    locales: Option<Vec<Language>>,
 }
 
 #[derive(Debug, Clone, Copy, PartialEq, Eq)]
@@ -1028,129 +1097,189 @@ impl RetrieveVectors {
     }
 }
 
-fn make_hits(
-    index: &Index,
-    rtxn: &RoTxn<'_>,
-    format: AttributesFormat,
-    matching_words: milli::MatchingWords,
-    documents_ids: Vec<u32>,
-    document_scores: Vec<Vec<ScoreDetails>>,
-) -> Result<Vec<SearchHit>, MeilisearchHttpError> {
-    let fields_ids_map = index.fields_ids_map(rtxn).unwrap();
-    let displayed_ids =
-        index.displayed_fields_ids(rtxn)?.map(|fields| fields.into_iter().collect::<BTreeSet<_>>());
+struct HitMaker<'a> {
+    index: &'a Index,
+    rtxn: &'a RoTxn<'a>,
+    fields_ids_map: FieldsIdsMap,
+    displayed_ids: BTreeSet<FieldId>,
+    vectors_fid: Option<FieldId>,
+    retrieve_vectors: RetrieveVectors,
+    to_retrieve_ids: BTreeSet<FieldId>,
+    embedding_configs: Vec<milli::index::IndexEmbeddingConfig>,
+    formatter_builder: MatcherBuilder<'a>,
+    formatted_options: BTreeMap<FieldId, FormatOptions>,
+    show_ranking_score: bool,
+    show_ranking_score_details: bool,
+    sort: Option<Vec<String>>,
+    show_matches_position: bool,
+    locales: Option<Vec<Language>>,
+}
 
-    let vectors_fid = fields_ids_map.id(milli::vector::parsed_vectors::RESERVED_VECTORS_FIELD_NAME);
+impl<'a> HitMaker<'a> {
+    pub fn tokenizer<'b>(
+        dictionary: Option<&'b [&'b str]>,
+        separators: Option<&'b [&'b str]>,
+    ) -> milli::tokenizer::Tokenizer<'b> {
+        let mut tokenizer_builder = TokenizerBuilder::default();
+        tokenizer_builder.create_char_map(true);
 
-    let vectors_is_hidden = match (&displayed_ids, vectors_fid) {
-        // displayed_ids is a wildcard, so `_vectors` can be displayed regardless of its fid
-        (None, _) => false,
-        // displayed_ids is a finite list, and `_vectors` cannot be part of it because it is not an existing field
-        (Some(_), None) => true,
-        // displayed_ids is a finit list, so hide if `_vectors` is not part of it
-        (Some(map), Some(vectors_fid)) => map.contains(&vectors_fid),
-    };
+        if let Some(separators) = separators {
+            tokenizer_builder.separators(separators);
+        }
 
-    let retrieve_vectors = if let RetrieveVectors::Retrieve = format.retrieve_vectors {
-        if vectors_is_hidden {
-            RetrieveVectors::Hide
+        if let Some(dictionary) = dictionary {
+            tokenizer_builder.words_dict(dictionary);
+        }
+
+        tokenizer_builder.into_tokenizer()
+    }
+
+    pub fn formatter_builder(
+        matching_words: milli::MatchingWords,
+        tokenizer: milli::tokenizer::Tokenizer<'_>,
+    ) -> MatcherBuilder<'_> {
+        let formatter_builder = MatcherBuilder::new(matching_words, tokenizer);
+
+        formatter_builder
+    }
+
+    pub fn new(
+        index: &'a Index,
+        rtxn: &'a RoTxn<'a>,
+        format: AttributesFormat,
+        mut formatter_builder: MatcherBuilder<'a>,
+    ) -> Result<Self, MeilisearchHttpError> {
+        formatter_builder.crop_marker(format.crop_marker);
+        formatter_builder.highlight_prefix(format.highlight_pre_tag);
+        formatter_builder.highlight_suffix(format.highlight_post_tag);
+
+        let fields_ids_map = index.fields_ids_map(rtxn)?;
+        let displayed_ids = index
+            .displayed_fields_ids(rtxn)?
+            .map(|fields| fields.into_iter().collect::<BTreeSet<_>>());
+
+        let vectors_fid =
+            fields_ids_map.id(milli::vector::parsed_vectors::RESERVED_VECTORS_FIELD_NAME);
+
+        let vectors_is_hidden = match (&displayed_ids, vectors_fid) {
+            // displayed_ids is a wildcard, so `_vectors` can be displayed regardless of its fid
+            (None, _) => false,
+            // displayed_ids is a finite list, and `_vectors` cannot be part of it because it is not an existing field
+            (Some(_), None) => true,
+            // displayed_ids is a finit list, so hide if `_vectors` is not part of it
+            (Some(map), Some(vectors_fid)) => map.contains(&vectors_fid),
+        };
+
+        let displayed_ids =
+            displayed_ids.unwrap_or_else(|| fields_ids_map.iter().map(|(id, _)| id).collect());
+
+        let retrieve_vectors = if let RetrieveVectors::Retrieve = format.retrieve_vectors {
+            if vectors_is_hidden {
+                RetrieveVectors::Hide
+            } else {
+                RetrieveVectors::Retrieve
+            }
         } else {
-            RetrieveVectors::Retrieve
-        }
-    } else {
-        format.retrieve_vectors
-    };
+            format.retrieve_vectors
+        };
 
-    let displayed_ids =
-        displayed_ids.unwrap_or_else(|| fields_ids_map.iter().map(|(id, _)| id).collect());
-    let fids = |attrs: &BTreeSet<String>| {
-        let mut ids = BTreeSet::new();
-        for attr in attrs {
-            if attr == "*" {
-                ids.clone_from(&displayed_ids);
-                break;
+        let fids = |attrs: &BTreeSet<String>| {
+            let mut ids = BTreeSet::new();
+            for attr in attrs {
+                if attr == "*" {
+                    ids.clone_from(&displayed_ids);
+                    break;
+                }
+
+                if let Some(id) = fields_ids_map.id(attr) {
+                    ids.insert(id);
+                }
             }
+            ids
+        };
+        let to_retrieve_ids: BTreeSet<_> = format
+            .attributes_to_retrieve
+            .as_ref()
+            .map(fids)
+            .unwrap_or_else(|| displayed_ids.clone())
+            .intersection(&displayed_ids)
+            .cloned()
+            .collect();
 
-            if let Some(id) = fields_ids_map.id(attr) {
-                ids.insert(id);
-            }
-        }
-        ids
-    };
-    let to_retrieve_ids: BTreeSet<_> = format
-        .attributes_to_retrieve
-        .as_ref()
-        .map(fids)
-        .unwrap_or_else(|| displayed_ids.clone())
-        .intersection(&displayed_ids)
-        .cloned()
-        .collect();
+        let attr_to_highlight = format.attributes_to_highlight.unwrap_or_default();
+        let attr_to_crop = format.attributes_to_crop.unwrap_or_default();
+        let formatted_options = compute_formatted_options(
+            &attr_to_highlight,
+            &attr_to_crop,
+            format.crop_length,
+            &to_retrieve_ids,
+            &fields_ids_map,
+            &displayed_ids,
+        );
 
-    let attr_to_highlight = format.attributes_to_highlight.unwrap_or_default();
-    let attr_to_crop = format.attributes_to_crop.unwrap_or_default();
-    let formatted_options = compute_formatted_options(
-        &attr_to_highlight,
-        &attr_to_crop,
-        format.crop_length,
-        &to_retrieve_ids,
-        &fields_ids_map,
-        &displayed_ids,
-    );
-    let mut tokenizer_builder = TokenizerBuilder::default();
-    tokenizer_builder.create_char_map(true);
-    let script_lang_map = index.script_language(rtxn)?;
-    if !script_lang_map.is_empty() {
-        tokenizer_builder.allow_list(&script_lang_map);
+        let embedding_configs = index.embedding_configs(rtxn)?;
+
+        Ok(Self {
+            index,
+            rtxn,
+            fields_ids_map,
+            displayed_ids,
+            vectors_fid,
+            retrieve_vectors,
+            to_retrieve_ids,
+            embedding_configs,
+            formatter_builder,
+            formatted_options,
+            show_ranking_score: format.show_ranking_score,
+            show_ranking_score_details: format.show_ranking_score_details,
+            show_matches_position: format.show_matches_position,
+            sort: format.sort,
+            locales: format.locales,
+        })
     }
-    let separators = index.allowed_separators(rtxn)?;
-    let separators: Option<Vec<_>> =
-        separators.as_ref().map(|x| x.iter().map(String::as_str).collect());
-    if let Some(ref separators) = separators {
-        tokenizer_builder.separators(separators);
-    }
-    let dictionary = index.dictionary(rtxn)?;
-    let dictionary: Option<Vec<_>> =
-        dictionary.as_ref().map(|x| x.iter().map(String::as_str).collect());
-    if let Some(ref dictionary) = dictionary {
-        tokenizer_builder.words_dict(dictionary);
-    }
-    let mut formatter_builder = MatcherBuilder::new(matching_words, tokenizer_builder.build());
-    formatter_builder.crop_marker(format.crop_marker);
-    formatter_builder.highlight_prefix(format.highlight_pre_tag);
-    formatter_builder.highlight_suffix(format.highlight_post_tag);
-    let mut documents = Vec::new();
-    let embedding_configs = index.embedding_configs(rtxn)?;
-    let documents_iter = index.documents(rtxn, documents_ids)?;
-    for ((id, obkv), score) in documents_iter.into_iter().zip(document_scores.into_iter()) {
+
+    pub fn make_hit(
+        &self,
+        id: u32,
+        score: &[ScoreDetails],
+    ) -> Result<SearchHit, MeilisearchHttpError> {
+        let (_, obkv) =
+            self.index.iter_documents(self.rtxn, std::iter::once(id))?.next().unwrap()?;
+
         // First generate a document with all the displayed fields
-        let displayed_document = make_document(&displayed_ids, &fields_ids_map, obkv)?;
+        let displayed_document = make_document(&self.displayed_ids, &self.fields_ids_map, obkv)?;
 
         let add_vectors_fid =
-            vectors_fid.filter(|_fid| retrieve_vectors == RetrieveVectors::Retrieve);
+            self.vectors_fid.filter(|_fid| self.retrieve_vectors == RetrieveVectors::Retrieve);
 
         // select the attributes to retrieve
-        let attributes_to_retrieve = to_retrieve_ids
+        let attributes_to_retrieve = self
+            .to_retrieve_ids
             .iter()
             // skip the vectors_fid if RetrieveVectors::Hide
-            .filter(|fid| match vectors_fid {
+            .filter(|fid| match self.vectors_fid {
                 Some(vectors_fid) => {
-                    !(retrieve_vectors == RetrieveVectors::Hide && **fid == vectors_fid)
+                    !(self.retrieve_vectors == RetrieveVectors::Hide && **fid == vectors_fid)
                 }
                 None => true,
             })
             // need to retrieve the existing `_vectors` field if the `RetrieveVectors::Retrieve`
             .chain(add_vectors_fid.iter())
-            .map(|&fid| fields_ids_map.name(fid).expect("Missing field name"));
+            .map(|&fid| self.fields_ids_map.name(fid).expect("Missing field name"));
+
         let mut document =
             permissive_json_pointer::select_values(&displayed_document, attributes_to_retrieve);
 
-        if retrieve_vectors == RetrieveVectors::Retrieve {
+        if self.retrieve_vectors == RetrieveVectors::Retrieve {
+            // Clippy is 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, id)? {
-                let user_provided = embedding_configs
+            for (name, vector) in self.index.embeddings(self.rtxn, id)? {
+                let user_provided = self
+                    .embedding_configs
                     .iter()
                     .find(|conf| conf.name == name)
                     .is_some_and(|conf| conf.user_provided.contains(id));
@@ -1161,23 +1290,28 @@ fn make_hits(
             document.insert("_vectors".into(), vectors.into());
         }
 
+        let localized_attributes =
+            self.index.localized_attributes_rules(self.rtxn)?.unwrap_or_default();
+
         let (matches_position, formatted) = format_fields(
             &displayed_document,
-            &fields_ids_map,
-            &formatter_builder,
-            &formatted_options,
-            format.show_matches_position,
-            &displayed_ids,
+            &self.fields_ids_map,
+            &self.formatter_builder,
+            &self.formatted_options,
+            self.show_matches_position,
+            &self.displayed_ids,
+            self.locales.as_deref(),
+            &localized_attributes,
         )?;
 
-        if let Some(sort) = format.sort.as_ref() {
+        if let Some(sort) = self.sort.as_ref() {
             insert_geo_distance(sort, &mut document);
         }
 
         let ranking_score =
-            format.show_ranking_score.then(|| ScoreDetails::global_score(score.iter()));
+            self.show_ranking_score.then(|| ScoreDetails::global_score(score.iter()));
         let ranking_score_details =
-            format.show_ranking_score_details.then(|| ScoreDetails::to_json_map(score.iter()));
+            self.show_ranking_score_details.then(|| ScoreDetails::to_json_map(score.iter()));
 
         let hit = SearchHit {
             document,
@@ -1186,7 +1320,35 @@ fn make_hits(
             ranking_score_details,
             ranking_score,
         };
-        documents.push(hit);
+
+        Ok(hit)
+    }
+}
+
+fn make_hits<'a>(
+    index: &Index,
+    rtxn: &RoTxn<'_>,
+    format: AttributesFormat,
+    matching_words: milli::MatchingWords,
+    documents_ids_scores: impl Iterator<Item = (u32, &'a Vec<ScoreDetails>)> + 'a,
+) -> Result<Vec<SearchHit>, MeilisearchHttpError> {
+    let mut documents = Vec::new();
+
+    let dictionary = index.dictionary(rtxn)?;
+    let dictionary: Option<Vec<_>> =
+        dictionary.as_ref().map(|x| x.iter().map(String::as_str).collect());
+    let separators = index.allowed_separators(rtxn)?;
+    let separators: Option<Vec<_>> =
+        separators.as_ref().map(|x| x.iter().map(String::as_str).collect());
+
+    let tokenizer = HitMaker::tokenizer(dictionary.as_deref(), separators.as_deref());
+
+    let formatter_builder = HitMaker::formatter_builder(matching_words, tokenizer);
+
+    let hit_maker = HitMaker::new(index, rtxn, format, formatter_builder)?;
+
+    for (id, score) in documents_ids_scores {
+        documents.push(hit_maker.make_hit(id, score)?);
     }
     Ok(documents)
 }
@@ -1197,7 +1359,9 @@ pub fn perform_facet_search(
     facet_query: Option<String>,
     facet_name: String,
     search_kind: SearchKind,
-) -> Result<FacetSearchResult, MeilisearchHttpError> {
+    features: RoFeatures,
+    locales: Option<Vec<Language>>,
+) -> Result<FacetSearchResult, ResponseError> {
     let before_search = Instant::now();
     let rtxn = index.read_txn()?;
     let time_budget = match index.search_cutoff(&rtxn)? {
@@ -1205,7 +1369,22 @@ pub fn perform_facet_search(
         None => TimeBudget::default(),
     };
 
-    let (search, _, _, _) = prepare_search(index, &rtxn, &search_query, &search_kind, time_budget)?;
+    // In the faceted search context, we want to use the intersection between the locales provided by the user
+    // and the locales of the facet string.
+    // If the facet string is not localized, we **ignore** the locales provided by the user because the facet data has no locale.
+    // If the user does not provide locales, we use the locales of the facet string.
+    let localized_attributes = index.localized_attributes_rules(&rtxn)?.unwrap_or_default();
+    let localized_attributes_locales =
+        localized_attributes.into_iter().find(|attr| attr.match_str(&facet_name));
+    let locales = localized_attributes_locales.map(|attr| {
+        attr.locales
+            .into_iter()
+            .filter(|locale| locales.as_ref().map_or(true, |locales| locales.contains(locale)))
+            .collect()
+    });
+
+    let (search, _, _, _) =
+        prepare_search(index, &rtxn, &search_query, &search_kind, time_budget, features)?;
     let mut facet_search = SearchForFacetValues::new(
         facet_name,
         search,
@@ -1218,6 +1397,10 @@ pub fn perform_facet_search(
         facet_search.max_values(max_facets as usize);
     }
 
+    if let Some(locales) = locales {
+        facet_search.locales(locales);
+    }
+
     Ok(FacetSearchResult {
         facet_hits: facet_search.execute()?,
         facet_query,
@@ -1231,6 +1414,7 @@ pub fn perform_similar(
     embedder_name: String,
     embedder: Arc<Embedder>,
     retrieve_vectors: RetrieveVectors,
+    features: RoFeatures,
 ) -> Result<SimilarResult, ResponseError> {
     let before_search = Instant::now();
     let rtxn = index.read_txn()?;
@@ -1261,10 +1445,7 @@ pub fn perform_similar(
         milli::Similar::new(internal_id, offset, limit, index, &rtxn, embedder_name, embedder);
 
     if let Some(ref filter) = query.filter {
-        if let Some(facets) = parse_filter(filter)
-            // inject InvalidSimilarFilter code
-            .map_err(|e| ResponseError::from_msg(e.to_string(), Code::InvalidSimilarFilter))?
-        {
+        if let Some(facets) = parse_filter(filter, Code::InvalidSimilarFilter, features)? {
             similar.filter(facets);
         }
     }
@@ -1300,9 +1481,16 @@ pub fn perform_similar(
         sort: None,
         show_ranking_score,
         show_ranking_score_details,
+        locales: None,
     };
 
-    let hits = make_hits(index, &rtxn, format, Default::default(), documents_ids, document_scores)?;
+    let hits = make_hits(
+        index,
+        &rtxn,
+        format,
+        Default::default(),
+        documents_ids.iter().copied().zip(document_scores.iter()),
+    )?;
 
     let max_total_hits = index
         .pagination_max_total_hits(&rtxn)
@@ -1331,13 +1519,23 @@ fn insert_geo_distance(sorts: &[String], document: &mut Document) {
         // TODO: TAMO: milli encountered an internal error, what do we want to do?
         let base = [capture_group[1].parse().unwrap(), capture_group[2].parse().unwrap()];
         let geo_point = &document.get("_geo").unwrap_or(&json!(null));
-        if let Some((lat, lng)) = geo_point["lat"].as_f64().zip(geo_point["lng"].as_f64()) {
+        if let Some((lat, lng)) =
+            extract_geo_value(&geo_point["lat"]).zip(extract_geo_value(&geo_point["lng"]))
+        {
             let distance = milli::distance_between_two_points(&base, &[lat, lng]);
             document.insert("_geoDistance".to_string(), json!(distance.round() as usize));
         }
     }
 }
 
+fn extract_geo_value(value: &Value) -> Option<f64> {
+    match value {
+        Value::Number(n) => n.as_f64(),
+        Value::String(s) => s.parse().ok(),
+        _ => None,
+    }
+}
+
 fn compute_formatted_options(
     attr_to_highlight: &HashSet<String>,
     attr_to_crop: &[String],
@@ -1465,13 +1663,16 @@ fn make_document(
     Ok(document)
 }
 
-fn format_fields<'a>(
+#[allow(clippy::too_many_arguments)]
+fn format_fields(
     document: &Document,
     field_ids_map: &FieldsIdsMap,
-    builder: &'a MatcherBuilder<'a>,
+    builder: &MatcherBuilder<'_>,
     formatted_options: &BTreeMap<FieldId, FormatOptions>,
     compute_matches: bool,
     displayable_ids: &BTreeSet<FieldId>,
+    locales: Option<&[Language]>,
+    localized_attributes: &[LocalizedAttributesRule],
 ) -> Result<(Option<MatchesPosition>, Document), MeilisearchHttpError> {
     let mut matches_position = compute_matches.then(BTreeMap::new);
     let mut document = document.clone();
@@ -1504,7 +1705,22 @@ fn format_fields<'a>(
             .reduce(|acc, option| acc.merge(option));
         let mut infos = Vec::new();
 
-        *value = format_value(std::mem::take(value), builder, format, &mut infos, compute_matches);
+        // if no locales has been provided, we try to find the locales in the localized_attributes.
+        let locales = locales.or_else(|| {
+            localized_attributes
+                .iter()
+                .find(|rule| rule.match_str(key))
+                .map(LocalizedAttributesRule::locales)
+        });
+
+        *value = format_value(
+            std::mem::take(value),
+            builder,
+            format,
+            &mut infos,
+            compute_matches,
+            locales,
+        );
 
         if let Some(matches) = matches_position.as_mut() {
             if !infos.is_empty() {
@@ -1523,16 +1739,17 @@ fn format_fields<'a>(
     Ok((matches_position, document))
 }
 
-fn format_value<'a>(
+fn format_value(
     value: Value,
-    builder: &'a MatcherBuilder<'a>,
+    builder: &MatcherBuilder<'_>,
     format_options: Option<FormatOptions>,
     infos: &mut Vec<MatchBounds>,
     compute_matches: bool,
+    locales: Option<&[Language]>,
 ) -> Value {
     match value {
         Value::String(old_string) => {
-            let mut matcher = builder.build(&old_string);
+            let mut matcher = builder.build(&old_string, locales);
             if compute_matches {
                 let matches = matcher.matches();
                 infos.extend_from_slice(&matches[..]);
@@ -1559,6 +1776,7 @@ fn format_value<'a>(
                         }),
                         infos,
                         compute_matches,
+                        locales,
                     )
                 })
                 .collect(),
@@ -1578,6 +1796,7 @@ fn format_value<'a>(
                             }),
                             infos,
                             compute_matches,
+                            locales,
                         ),
                     )
                 })
@@ -1586,7 +1805,7 @@ fn format_value<'a>(
         Value::Number(number) => {
             let s = number.to_string();
 
-            let mut matcher = builder.build(&s);
+            let mut matcher = builder.build(&s, locales);
             if compute_matches {
                 let matches = matcher.matches();
                 infos.extend_from_slice(&matches[..]);
@@ -1604,15 +1823,33 @@ fn format_value<'a>(
     }
 }
 
-pub(crate) fn parse_filter(facets: &Value) -> Result<Option<Filter>, MeilisearchHttpError> {
-    match facets {
-        Value::String(expr) => {
-            let condition = Filter::from_str(expr)?;
-            Ok(condition)
+pub(crate) fn parse_filter(
+    facets: &Value,
+    filter_parsing_error_code: Code,
+    features: RoFeatures,
+) -> Result<Option<Filter>, ResponseError> {
+    let filter = match facets {
+        Value::String(expr) => Filter::from_str(expr).map_err(|e| e.into()),
+        Value::Array(arr) => parse_filter_array(arr).map_err(|e| e.into()),
+        v => Err(MeilisearchHttpError::InvalidExpression(&["String", "Array"], v.clone()).into()),
+    };
+    let filter = filter.map_err(|err: ResponseError| {
+        ResponseError::from_msg(err.to_string(), filter_parsing_error_code)
+    })?;
+
+    if let Some(ref filter) = filter {
+        // If the contains operator is used while the contains filter features is not enabled, errors out
+        if let Some((token, error)) =
+            filter.use_contains_operator().zip(features.check_contains_filter().err())
+        {
+            return Err(ResponseError::from_msg(
+                token.as_external_error(error).to_string(),
+                Code::FeatureNotEnabled,
+            ));
         }
-        Value::Array(arr) => parse_filter_array(arr),
-        v => Err(MeilisearchHttpError::InvalidExpression(&["String", "Array"], v.clone())),
     }
+
+    Ok(filter)
 }
 
 fn parse_filter_array(arr: &[Value]) -> Result<Option<Filter>, MeilisearchHttpError> {
@@ -1711,4 +1948,54 @@ mod test {
         insert_geo_distance(sorters, &mut document);
         assert_eq!(document.get("_geoDistance"), None);
     }
+
+    #[test]
+    fn test_insert_geo_distance_with_coords_as_string() {
+        let value: Document = serde_json::from_str(
+            r#"{
+              "_geo": {
+                "lat": "50",
+                "lng": 3
+              }
+            }"#,
+        )
+        .unwrap();
+
+        let sorters = &["_geoPoint(50,3):desc".to_string()];
+        let mut document = value.clone();
+        insert_geo_distance(sorters, &mut document);
+        assert_eq!(document.get("_geoDistance"), Some(&json!(0)));
+
+        let value: Document = serde_json::from_str(
+            r#"{
+              "_geo": {
+                "lat": "50",
+                "lng": "3"
+              },
+              "id": "1"
+            }"#,
+        )
+        .unwrap();
+
+        let sorters = &["_geoPoint(50,3):desc".to_string()];
+        let mut document = value.clone();
+        insert_geo_distance(sorters, &mut document);
+        assert_eq!(document.get("_geoDistance"), Some(&json!(0)));
+
+        let value: Document = serde_json::from_str(
+            r#"{
+              "_geo": {
+                "lat": 50,
+                "lng": "3"
+              },
+              "id": "1"
+            }"#,
+        )
+        .unwrap();
+
+        let sorters = &["_geoPoint(50,3):desc".to_string()];
+        let mut document = value.clone();
+        insert_geo_distance(sorters, &mut document);
+        assert_eq!(document.get("_geoDistance"), Some(&json!(0)));
+    }
 }

meilisearch/src/search/ranking_rules.rs

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