make the task id u64

.github/ISSUE_TEMPLATE/sprint_issue.md

@@ -7,17 +7,19 @@ assignees: ''
 
 ---
 
-Related product team resources: [PRD]() (_internal only_)
+Related product team resources: [roadmap card]() (_internal only_) and [PRD]() (_internal only_)
 Related product discussion:
 Related spec: WIP
 
 ## Motivation
 
-<!---Copy/paste the information in PRD or briefly detail the product motivation. Ask product team if any hesitation.-->
+<!---Copy/paste the information in the roadmap resources or briefly detail the product motivation. Ask product team if any hesitation.-->
 
 ## Usage
 
-<!---Link to the public part of the PRD, or to the related product discussion for experimental features-->
+<!---Write a quick description of the usage if the usage has already been defined-->
+
+Refer to the final spec to know the details and the final decisions about the usage.
 
 ## TODO
 

.github/workflows/benchmarks-manual.yml

@@ -74,4 +74,4 @@ jobs:
           echo "${{ steps.file.outputs.basename }}.json has just been pushed."
           echo 'How to compare this benchmark with another one?'
           echo '  - Check the available files with: ./benchmarks/scripts/list.sh'
-          echo "  - Run the following command: ./benchmaks/scripts/compare.sh <file-to-compare-with> ${{ steps.file.outputs.basename }}.json"
+          echo "  - Run the following command: ./benchmaks/scipts/compare.sh <file-to-compare-with> ${{ steps.file.outputs.basename }}.json"

.github/workflows/benchmarks-pr.yml

@@ -1,98 +0,0 @@
-name: Benchmarks (PR)
-on: issue_comment
-permissions:
-  issues: write
-
-env:
-  GH_TOKEN: ${{ secrets.MEILI_BOT_GH_PAT }}
-
-jobs:
-  run-benchmarks-on-comment:
-    if: startsWith(github.event.comment.body, '/benchmark')
-    name: Run and upload benchmarks
-    runs-on: benchmarks
-    timeout-minutes: 4320 # 72h
-    steps:
-      - uses: actions-rs/toolchain@v1
-        with:
-          profile: minimal
-          toolchain: stable
-          override: true
-
-      - name: Check for Command
-        id: command
-        uses: xt0rted/slash-command-action@v2
-        with:
-          command: benchmark
-          reaction-type: "eyes"
-          repo-token: ${{ env.GH_TOKEN }}
-
-      - uses: xt0rted/pull-request-comment-branch@v2
-        id: comment-branch
-        with:
-          repo_token: ${{ env.GH_TOKEN }}
-
-      - uses: actions/checkout@v3
-        if: success()
-        with:
-          fetch-depth: 0 # fetch full history to be able to get main commit sha
-          ref: ${{ steps.comment-branch.outputs.head_ref }}
-
-      # Set variables
-      - name: Set current branch name
-        shell: bash
-        run: echo "name=$(git rev-parse --abbrev-ref HEAD)" >> $GITHUB_OUTPUT
-        id: current_branch
-      - name: Set normalized current branch name # Replace `/` by `_` in branch name to avoid issues when pushing to S3
-        shell: bash
-        run: echo "name=$(git rev-parse --abbrev-ref HEAD | tr '/' '_')" >> $GITHUB_OUTPUT
-        id: normalized_current_branch
-      - name: Set shorter commit SHA
-        shell: bash
-        run: echo "short=$(echo $GITHUB_SHA | cut -c1-8)" >> $GITHUB_OUTPUT
-        id: commit_sha
-      - name: Set file basename with format "dataset_branch_commitSHA"
-        shell: bash
-        run: echo "basename=$(echo ${{ steps.command.outputs.command-arguments }}_${{ steps.normalized_current_branch.outputs.name }}_${{ steps.commit_sha.outputs.short }})" >> $GITHUB_OUTPUT
-        id: file
-
-      # Run benchmarks
-      - name: Run benchmarks - Dataset ${{ steps.command.outputs.command-arguments }} - Branch ${{ steps.current_branch.outputs.name }} - Commit ${{ steps.commit_sha.outputs.short }}
-        run: |
-          cd benchmarks
-          cargo bench --bench ${{ steps.command.outputs.command-arguments }} -- --save-baseline ${{ steps.file.outputs.basename }}
-
-      # Generate critcmp files
-      - name: Install critcmp
-        uses: taiki-e/install-action@v2
-        with:
-          tool: critcmp
-      - name: Export cripcmp file
-        run: |
-          critcmp --export ${{ steps.file.outputs.basename }} > ${{ steps.file.outputs.basename }}.json
-
-      # Upload benchmarks
-      - name: Upload ${{ steps.file.outputs.basename }}.json to DO Spaces # DigitalOcean Spaces = S3
-        uses: BetaHuhn/do-spaces-action@v2
-        with:
-          access_key: ${{ secrets.DO_SPACES_ACCESS_KEY }}
-          secret_key: ${{ secrets.DO_SPACES_SECRET_KEY }}
-          space_name: ${{ secrets.DO_SPACES_SPACE_NAME }}
-          space_region: ${{ secrets.DO_SPACES_SPACE_REGION }}
-          source: ${{ steps.file.outputs.basename }}.json
-          out_dir: critcmp_results
-
-      # Compute the diff of the benchmarks and send a message on the GitHub PR
-      - name: Compute and send a message in the PR
-        env:
-          GITHUB_TOKEN: ${{ secrets.MEILI_BOT_GH_PAT }}
-        run: |
-          set -x
-          export base_ref=$(git merge-base origin/main ${{ steps.comment-branch.outputs.head_ref }} | head -c8)
-          export base_filename=$(echo ${{ steps.command.outputs.command-arguments }}_main_${base_ref}.json)
-          export bench_name=$(echo ${{ steps.command.outputs.command-arguments }})
-          echo "Here are your $bench_name benchmarks diff 👊" >> body.txt
-          echo '```' >> body.txt
-          ./benchmarks/scripts/compare.sh $base_filename ${{ steps.file.outputs.basename }}.json >> body.txt
-          echo '```' >> body.txt
-          gh pr comment ${{ steps.current_branch.outputs.name }} --body-file body.txt

.github/workflows/dependency-issue.yml

@@ -2,8 +2,8 @@ name: Create issue to upgrade dependencies
 
 on:
   schedule:
-    # Run the first of the month, every 6 month
-    - cron: '0 0 1 */6 *'
+    # Run the first of the month, every 3 month
+    - cron: '0 0 1 */3 *'
   workflow_dispatch:
 
 jobs:

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

@@ -50,9 +50,8 @@ jobs:
     needs: check-version
     steps:
       - name: Create PR to Homebrew
-        uses: mislav/bump-homebrew-formula-action@v3
+        uses: mislav/bump-homebrew-formula-action@v2
         with:
           formula-name: meilisearch
-          formula-path: Formula/m/meilisearch.rb
         env:
           COMMITTER_TOKEN: ${{ secrets.HOMEBREW_COMMITTER_TOKEN }}

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

@@ -57,20 +57,20 @@ jobs:
           echo "date=$commit_date" >> $GITHUB_OUTPUT
 
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
+        uses: docker/setup-qemu-action@v2
 
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
+        uses: docker/setup-buildx-action@v2
 
       - name: Login to Docker Hub
-        uses: docker/login-action@v3
+        uses: docker/login-action@v2
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
       - name: Docker meta
         id: meta
-        uses: docker/metadata-action@v5
+        uses: docker/metadata-action@v4
         with:
           images: getmeili/meilisearch
           # Prevent `latest` to be updated for each new tag pushed.
@@ -83,7 +83,7 @@ jobs:
             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@v4
         with:
           push: true
           platforms: linux/amd64,linux/arm64

.github/workflows/sdks-tests.yml

@@ -14,7 +14,6 @@ on:
 env:
   MEILI_MASTER_KEY: 'masterKey'
   MEILI_NO_ANALYTICS: 'true'
-  DISABLE_COVERAGE: 'true'
 
 jobs:
   define-docker-image:
@@ -31,117 +30,6 @@ jobs:
           if [[ $event == 'workflow_dispatch' ]]; then
             echo "docker-image=${{ github.event.inputs.docker_image }}" >> $GITHUB_OUTPUT
           fi
-      - name: Docker image is ${{ steps.define-image.outputs.docker-image }}
-        run: echo "Docker image is ${{ steps.define-image.outputs.docker-image }}"
-
-##########
-## SDKs ##
-##########
-
-  meilisearch-dotnet-tests:
-    needs: define-docker-image
-    name: .NET SDK tests
-    runs-on: ubuntu-latest
-    env:
-      MEILISEARCH_VERSION: ${{ needs.define-docker-image.outputs.docker-image }}
-
-    steps:
-      - uses: actions/checkout@v3
-        with:
-          repository: meilisearch/meilisearch-dotnet
-      - name: Setup .NET Core
-        uses: actions/setup-dotnet@v3
-        with:
-          dotnet-version: "6.0.x"
-      - name: Install dependencies
-        run: dotnet restore
-      - name: Build
-        run: dotnet build --configuration Release --no-restore
-      - name: Meilisearch (latest version) setup with Docker
-        run: docker compose up -d
-      - name: Run tests
-        run: dotnet test --no-restore --verbosity normal
-
-  meilisearch-dart-tests:
-    needs: define-docker-image
-    name: Dart SDK tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - uses: actions/checkout@v3
-        with:
-          repository: meilisearch/meilisearch-dart
-      - uses: dart-lang/setup-dart@v1
-        with:
-          sdk: 3.1.1
-      - name: Install dependencies
-        run: dart pub get
-      - name: Run integration tests
-        run: dart test --concurrency=4
-
-  meilisearch-go-tests:
-    needs: define-docker-image
-    name: Go SDK tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - name: Set up Go
-        uses: actions/setup-go@v4
-        with:
-          go-version: stable
-      - uses: actions/checkout@v3
-        with:
-          repository: meilisearch/meilisearch-go
-      - name: Get dependencies
-        run: |
-          go get -v -t -d ./...
-          if [ -f Gopkg.toml ]; then
-            curl https://raw.githubusercontent.com/golang/dep/master/install.sh | sh
-            dep ensure
-          fi
-      - name: Run integration tests
-        run: go test -v ./...
-
-  meilisearch-java-tests:
-    needs: define-docker-image
-    name: Java SDK tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - uses: actions/checkout@v3
-        with:
-          repository: meilisearch/meilisearch-java
-      - name: Set up Java
-        uses: actions/setup-java@v3
-        with:
-          java-version: 8
-          distribution: 'zulu'
-          cache: gradle
-      - name: Grant execute permission for gradlew
-        run: chmod +x gradlew
-      - name: Build and run unit and integration tests
-        run: ./gradlew build integrationTest
 
   meilisearch-js-tests:
     needs: define-docker-image
@@ -160,7 +48,7 @@ jobs:
         with:
           repository: meilisearch/meilisearch-js
       - name: Setup node
-        uses: actions/setup-node@v4
+        uses: actions/setup-node@v3
         with:
           cache: 'yarn'
       - name: Install dependencies
@@ -178,6 +66,33 @@ jobs:
       - name: Run Browser env
         run: yarn test:env:browser
 
+  instant-meilisearch-tests:
+    needs: define-docker-image
+    name: instant-meilisearch tests
+    runs-on: ubuntu-latest
+    services:
+      meilisearch:
+        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
+        env:
+          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
+          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
+        ports:
+          - '7700:7700'
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          repository: meilisearch/instant-meilisearch
+      - name: Setup node
+        uses: actions/setup-node@v3
+        with:
+          cache: yarn
+      - name: Install dependencies
+        run: yarn install
+      - name: Run tests
+        run: yarn test
+      - name: Build all the playgrounds and the packages
+        run: yarn build
+
   meilisearch-php-tests:
     needs: define-docker-image
     name: PHP SDK tests
@@ -196,6 +111,8 @@ jobs:
           repository: meilisearch/meilisearch-php
       - name: Install PHP
         uses: shivammathur/setup-php@v2
+        with:
+          coverage: none
       - name: Validate composer.json and composer.lock
         run: composer validate
       - name: Install dependencies
@@ -232,6 +149,36 @@ jobs:
       - name: Test with pytest
         run: pipenv run pytest
 
+  meilisearch-go-tests:
+    needs: define-docker-image
+    name: Go SDK tests
+    runs-on: ubuntu-latest
+    services:
+      meilisearch:
+        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
+        env:
+          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
+          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
+        ports:
+          - '7700:7700'
+    steps:
+      - name: Set up Go
+        uses: actions/setup-go@v4
+        with:
+          go-version: stable
+      - uses: actions/checkout@v3
+        with:
+          repository: meilisearch/meilisearch-go
+      - name: Get dependencies
+        run: |
+          go get -v -t -d ./...
+          if [ -f Gopkg.toml ]; then
+            curl https://raw.githubusercontent.com/golang/dep/master/install.sh | sh
+            dep ensure
+          fi
+      - name: Run integration tests
+        run: go test -v ./...
+
   meilisearch-ruby-tests:
     needs: define-docker-image
     name: Ruby SDK tests
@@ -277,110 +224,3 @@ jobs:
         run: cargo build --verbose
       - name: Run tests
         run: cargo test --verbose
-
-  meilisearch-swift-tests:
-    needs: define-docker-image
-    name: Swift SDK tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - uses: actions/checkout@v3
-        with:
-          repository: meilisearch/meilisearch-swift
-      - name: Run tests
-        run: swift test
-
-########################
-## FRONT-END PLUGINS ##
-########################
-
-  meilisearch-js-plugins-tests:
-    needs: define-docker-image
-    name: meilisearch-js-plugins tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - uses: actions/checkout@v3
-        with:
-          repository: meilisearch/meilisearch-js-plugins
-      - name: Setup node
-        uses: actions/setup-node@v4
-        with:
-          cache: yarn
-      - name: Install dependencies
-        run: yarn install
-      - name: Run tests
-        run: yarn test
-      - name: Build all the playgrounds and the packages
-        run: yarn build
-
-########################
-## BACK-END PLUGINS ###
-########################
-
-  meilisearch-rails-tests:
-    needs: define-docker-image
-    name: meilisearch-rails tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - uses: actions/checkout@v3
-        with:
-          repository: meilisearch/meilisearch-rails
-      - name: Set up Ruby 3
-        uses: ruby/setup-ruby@v1
-        with:
-          ruby-version: 3
-          bundler-cache: true
-      - name: Run tests
-        run: bundle exec rspec
-
-  meilisearch-symfony-tests:
-    needs: define-docker-image
-    name: meilisearch-symfony tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - uses: actions/checkout@v3
-        with:
-          repository: meilisearch/meilisearch-symfony
-      - name: Install PHP
-        uses: shivammathur/setup-php@v2
-        with:
-          tools: composer:v2, flex
-      - name: Validate composer.json and composer.lock
-        run: composer validate
-      - name: Install dependencies
-        run: composer install --prefer-dist --no-progress --quiet
-      - name: Remove doctrine/annotations
-        run: composer remove --dev doctrine/annotations
-      - name: Run test suite
-        run: composer test:unit

.github/workflows/test-suite.yml

@@ -43,7 +43,7 @@ jobs:
           toolchain: nightly
           override: true
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.7.1
+        uses: Swatinem/rust-cache@v2.6.2
       - name: Run cargo check without any default features
         uses: actions-rs/cargo@v1
         with:
@@ -65,7 +65,7 @@ jobs:
     steps:
       - uses: actions/checkout@v3
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.7.1
+        uses: Swatinem/rust-cache@v2.6.2
       - name: Run cargo check without any default features
         uses: actions-rs/cargo@v1
         with:
@@ -123,10 +123,7 @@ jobs:
           override: true
       - name: Run cargo tree without default features and check lindera is not present
         run: |
-          if cargo tree -f '{p} {f}' -e normal --no-default-features | grep -vqz lindera; then
-            echo "lindera has been found in the sources and it shouldn't"
-            exit 1
-          fi
+          cargo tree -f '{p} {f}' -e normal --no-default-features | grep lindera -vqz
       - name: Run cargo tree with default features and check lindera is pressent
         run: |
           cargo tree -f '{p} {f}' -e normal | grep lindera -qz
@@ -149,7 +146,7 @@ jobs:
           toolchain: stable
           override: true
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.7.1
+        uses: Swatinem/rust-cache@v2.6.2
       - name: Run tests in debug
         uses: actions-rs/cargo@v1
         with:
@@ -168,7 +165,7 @@ jobs:
           override: true
           components: clippy
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.7.1
+        uses: Swatinem/rust-cache@v2.6.2
       - name: Run cargo clippy
         uses: actions-rs/cargo@v1
         with:
@@ -187,7 +184,7 @@ jobs:
           override: true
           components: rustfmt
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.7.1
+        uses: Swatinem/rust-cache@v2.6.2
       - name: Run cargo fmt
         # Since we never ran the `build.rs` script in the benchmark directory we are missing one auto-generated import file.
         # Since we want to trigger (and fail) this action as fast as possible, instead of building the benchmark crate

Cargo.toml

@@ -2,7 +2,6 @@
 resolver = "2"
 members = [
     "meilisearch",
-    "meilitool",
     "meilisearch-types",
     "meilisearch-auth",
     "meili-snap",
@@ -19,7 +18,7 @@ members = [
 ]
 
 [workspace.package]
-version = "1.6.0"
+version = "1.4.0"
 authors = ["Quentin de Quelen <quentin@dequelen.me>", "Clément Renault <clement@meilisearch.com>"]
 description = "Meilisearch HTTP server"
 homepage = "https://meilisearch.com"

Dockerfile

@@ -1,9 +1,9 @@
 # Compile
-FROM    rust:1.71.1-alpine3.18 AS compiler
+FROM    rust:alpine3.16 AS compiler
 
 RUN     apk add -q --update-cache --no-cache build-base openssl-dev
 
-WORKDIR /
+WORKDIR /meilisearch
 
 ARG     COMMIT_SHA
 ARG     COMMIT_DATE
@@ -17,7 +17,7 @@ RUN     set -eux; \
         if [ "$apkArch" = "aarch64" ]; then \
             export JEMALLOC_SYS_WITH_LG_PAGE=16; \
         fi && \
-        cargo build --release -p meilisearch -p meilitool
+        cargo build --release
 
 # Run
 FROM    alpine:3.16
@@ -28,10 +28,9 @@ ENV     MEILI_SERVER_PROVIDER docker
 RUN     apk update --quiet \
         && apk add -q --no-cache libgcc tini curl
 
-# add meilisearch and meilitool to the `/bin` so you can run it from anywhere
-# and it's easy to find.
-COPY    --from=compiler /target/release/meilisearch /bin/meilisearch
-COPY    --from=compiler /target/release/meilitool /bin/meilitool
+# add meilisearch to the `/bin` so you can run it from anywhere and it's easy
+# to find.
+COPY    --from=compiler /meilisearch/target/release/meilisearch /bin/meilisearch
 # To stay compatible with the older version of the container (pre v0.27.0) we're
 # going to symlink the meilisearch binary in the path to `/meilisearch`
 RUN     ln -s /bin/meilisearch /meilisearch

PROFILING.md

@@ -1,14 +1,14 @@
 # Profiling Meilisearch
 
-Search engine technologies are complex pieces of software that require thorough profiling tools. We chose to use [Puffin](https://github.com/EmbarkStudios/puffin), which the Rust gaming industry uses extensively. You can export and import the profiling reports using the top bar's _File_ menu options [in Puffin Viewer](https://github.com/embarkstudios/puffin#ui).
+Search engine technologies are complex pieces of software that require thorough profiling tools. We chose to use [Puffin](https://github.com/EmbarkStudios/puffin), which the Rust gaming industry uses extensively. You can export and import the profiling reports using the top bar's _File_ menu options.
 
 ![An example profiling with Puffin viewer](assets/profiling-example.png)
 
 ## Profiling the Indexing Process
 
-When you enable [the `exportPuffinReports` experimental feature](https://www.meilisearch.com/docs/learn/experimental/overview) of Meilisearch, Puffin reports with the `.puffin` extension will be automatically exported to disk. When this option is enabled, the engine will automatically create a "frame" whenever it executes the `IndexScheduler::tick` method.
+When you enable the `profile-with-puffin` feature of Meilisearch, a Puffin HTTP server will run on Meilisearch and listen on the default _0.0.0.0:8585_ address. This server will record a "frame" whenever it executes the `IndexScheduler::tick` method.
 
-[Puffin Viewer](https://github.com/EmbarkStudios/puffin/tree/main/puffin_viewer) is used to analyze the reports. Those reports show areas where Meilisearch spent time during indexing.
+Once your Meilisearch is running and awaits new indexation operations, you must [install and run the `puffin_viewer` tool](https://github.com/EmbarkStudios/puffin/tree/main/puffin_viewer) to see the profiling results. I advise you to run the viewer with the `RUST_LOG=puffin_http::client=debug` environment variable to see the client trying to connect to your server.
 
 Another piece of advice on the Puffin viewer UI interface is to consider the _Merge children with same ID_ option. It can hide the exact actual timings at which events were sent. Please turn it off when you see strange gaps on the Flamegraph. It can help.
 

benchmarks/benches/indexing.rs

@@ -6,7 +6,9 @@ use std::path::Path;
 
 use criterion::{criterion_group, criterion_main, Criterion};
 use milli::heed::{EnvOpenOptions, RwTxn};
-use milli::update::{IndexDocuments, IndexDocumentsConfig, IndexerConfig, Settings};
+use milli::update::{
+    DeleteDocuments, IndexDocuments, IndexDocumentsConfig, IndexerConfig, Settings,
+};
 use milli::Index;
 use rand::seq::SliceRandom;
 use rand_chacha::rand_core::SeedableRng;
@@ -36,7 +38,7 @@ fn setup_index() -> Index {
 }
 
 fn setup_settings<'t>(
-    wtxn: &mut RwTxn<'t>,
+    wtxn: &mut RwTxn<'t, '_>,
     index: &'t Index,
     primary_key: &str,
     searchable_fields: &[&str],
@@ -264,7 +266,17 @@ fn deleting_songs_in_batches_default(c: &mut Criterion) {
                 (index, document_ids_to_delete)
             },
             move |(index, document_ids_to_delete)| {
-                delete_documents_from_ids(index, document_ids_to_delete)
+                let mut wtxn = index.write_txn().unwrap();
+
+                for ids in document_ids_to_delete {
+                    let mut builder = DeleteDocuments::new(&mut wtxn, &index).unwrap();
+                    builder.delete_documents(&ids);
+                    builder.execute().unwrap();
+                }
+
+                wtxn.commit().unwrap();
+
+                index.prepare_for_closing().wait();
             },
         )
     });
@@ -601,7 +613,17 @@ fn deleting_wiki_in_batches_default(c: &mut Criterion) {
                 (index, document_ids_to_delete)
             },
             move |(index, document_ids_to_delete)| {
-                delete_documents_from_ids(index, document_ids_to_delete)
+                let mut wtxn = index.write_txn().unwrap();
+
+                for ids in document_ids_to_delete {
+                    let mut builder = DeleteDocuments::new(&mut wtxn, &index).unwrap();
+                    builder.delete_documents(&ids);
+                    builder.execute().unwrap();
+                }
+
+                wtxn.commit().unwrap();
+
+                index.prepare_for_closing().wait();
             },
         )
     });
@@ -853,31 +875,22 @@ fn deleting_movies_in_batches_default(c: &mut Criterion) {
                 (index, document_ids_to_delete)
             },
             move |(index, document_ids_to_delete)| {
-                delete_documents_from_ids(index, document_ids_to_delete)
+                let mut wtxn = index.write_txn().unwrap();
+
+                for ids in document_ids_to_delete {
+                    let mut builder = DeleteDocuments::new(&mut wtxn, &index).unwrap();
+                    builder.delete_documents(&ids);
+                    builder.execute().unwrap();
+                }
+
+                wtxn.commit().unwrap();
+
+                index.prepare_for_closing().wait();
             },
         )
     });
 }
 
-fn delete_documents_from_ids(index: Index, document_ids_to_delete: Vec<RoaringBitmap>) {
-    let mut wtxn = index.write_txn().unwrap();
-
-    let indexer_config = IndexerConfig::default();
-    for ids in document_ids_to_delete {
-        let config = IndexDocumentsConfig::default();
-
-        let mut builder =
-            IndexDocuments::new(&mut wtxn, &index, &indexer_config, config, |_| (), || false)
-                .unwrap();
-        (builder, _) = builder.remove_documents_from_db_no_batch(&ids).unwrap();
-        builder.execute().unwrap();
-    }
-
-    wtxn.commit().unwrap();
-
-    index.prepare_for_closing().wait();
-}
-
 fn indexing_movies_in_three_batches(c: &mut Criterion) {
     let mut group = c.benchmark_group("indexing");
     group.sample_size(BENCHMARK_ITERATION);
@@ -1099,7 +1112,17 @@ fn deleting_nested_movies_in_batches_default(c: &mut Criterion) {
                 (index, document_ids_to_delete)
             },
             move |(index, document_ids_to_delete)| {
-                delete_documents_from_ids(index, document_ids_to_delete)
+                let mut wtxn = index.write_txn().unwrap();
+
+                for ids in document_ids_to_delete {
+                    let mut builder = DeleteDocuments::new(&mut wtxn, &index).unwrap();
+                    builder.delete_documents(&ids);
+                    builder.execute().unwrap();
+                }
+
+                wtxn.commit().unwrap();
+
+                index.prepare_for_closing().wait();
             },
         )
     });
@@ -1315,7 +1338,17 @@ fn deleting_geo_in_batches_default(c: &mut Criterion) {
                 (index, document_ids_to_delete)
             },
             move |(index, document_ids_to_delete)| {
-                delete_documents_from_ids(index, document_ids_to_delete)
+                let mut wtxn = index.write_txn().unwrap();
+
+                for ids in document_ids_to_delete {
+                    let mut builder = DeleteDocuments::new(&mut wtxn, &index).unwrap();
+                    builder.delete_documents(&ids);
+                    builder.execute().unwrap();
+                }
+
+                wtxn.commit().unwrap();
+
+                index.prepare_for_closing().wait();
             },
         )
     });

config.toml

@@ -129,6 +129,3 @@ experimental_enable_metrics = false
 
 # Experimental RAM reduction during indexing, do not use in production, see: <https://github.com/meilisearch/product/discussions/652>
 experimental_reduce_indexing_memory_usage = false
-
-# Experimentally reduces the maximum number of tasks that will be processed at once, see: <https://github.com/orgs/meilisearch/discussions/713>
-# experimental_max_number_of_batched_tasks = 100

dump/src/lib.rs

@@ -7,7 +7,7 @@ use meilisearch_types::milli::update::IndexDocumentsMethod;
 use meilisearch_types::settings::Unchecked;
 use meilisearch_types::tasks::{Details, IndexSwap, KindWithContent, Status, Task, TaskId};
 use meilisearch_types::InstanceUid;
-use roaring::RoaringBitmap;
+use roaring::RoaringTreemap;
 use serde::{Deserialize, Serialize};
 use time::OffsetDateTime;
 
@@ -121,11 +121,11 @@ pub enum KindDump {
     },
     TaskCancelation {
         query: String,
-        tasks: RoaringBitmap,
+        tasks: RoaringTreemap,
     },
     TasksDeletion {
         query: String,
-        tasks: RoaringBitmap,
+        tasks: RoaringTreemap,
     },
     DumpCreation {
         keys: Vec<Key>,
@@ -267,7 +267,6 @@ pub(crate) mod test {
             dictionary: Setting::NotSet,
             synonyms: Setting::NotSet,
             distinct_attribute: Setting::NotSet,
-            proximity_precision: Setting::NotSet,
             typo_tolerance: Setting::NotSet,
             faceting: Setting::Set(FacetingSettings {
                 max_values_per_facet: Setting::Set(111),
@@ -276,7 +275,6 @@ pub(crate) mod test {
                 ),
             }),
             pagination: Setting::NotSet,
-            embedders: Setting::NotSet,
             _kind: std::marker::PhantomData,
         };
         settings.check()

dump/src/reader/compat/v5_to_v6.rs

@@ -69,7 +69,7 @@ impl CompatV5ToV6 {
                 }
 
                 let task = v6::Task {
-                    uid: task_view.uid,
+                    uid: task_view.uid as u64,
                     index_uid: task_view.index_uid,
                     status: match task_view.status {
                         v5::Status::Enqueued => v6::Status::Enqueued,
@@ -345,7 +345,6 @@ impl<T> From<v5::Settings<T>> for v6::Settings<v6::Unchecked> {
             dictionary: v6::Setting::NotSet,
             synonyms: settings.synonyms.into(),
             distinct_attribute: settings.distinct_attribute.into(),
-            proximity_precision: v6::Setting::NotSet,
             typo_tolerance: match settings.typo_tolerance {
                 v5::Setting::Set(typo) => v6::Setting::Set(v6::TypoTolerance {
                     enabled: typo.enabled.into(),
@@ -378,7 +377,6 @@ impl<T> From<v5::Settings<T>> for v6::Settings<v6::Unchecked> {
                 v5::Setting::Reset => v6::Setting::Reset,
                 v5::Setting::NotSet => v6::Setting::NotSet,
             },
-            embedders: v6::Setting::NotSet,
             _kind: std::marker::PhantomData,
         }
     }

dump/src/reader/mod.rs

@@ -13,12 +13,12 @@ use crate::{Result, Version};
 
 mod compat;
 
-mod v1;
-mod v2;
-mod v3;
-mod v4;
-mod v5;
-mod v6;
+pub(self) mod v1;
+pub(self) mod v2;
+pub(self) mod v3;
+pub(self) mod v4;
+pub(self) mod v5;
+pub(self) mod v6;
 
 pub type Document = serde_json::Map<String, serde_json::Value>;
 pub type UpdateFile = dyn Iterator<Item = Result<Document>>;
@@ -526,12 +526,12 @@ pub(crate) mod test {
         assert!(indexes.is_empty());
 
         // products
-        insta::assert_json_snapshot!(products.metadata(), @r###"
+        insta::assert_json_snapshot!(products.metadata(), { ".createdAt" => "[now]", ".updatedAt" => "[now]" }, @r###"
         {
           "uid": "products",
           "primaryKey": "sku",
-          "createdAt": "2022-10-09T20:27:22.688964637Z",
-          "updatedAt": "2022-10-09T20:27:23.951017769Z"
+          "createdAt": "[now]",
+          "updatedAt": "[now]"
         }
         "###);
 
@@ -541,12 +541,12 @@ pub(crate) mod test {
         meili_snap::snapshot_hash!(format!("{:#?}", documents), @"548284a84de510f71e88e6cdea495cf5");
 
         // movies
-        insta::assert_json_snapshot!(movies.metadata(), @r###"
+        insta::assert_json_snapshot!(movies.metadata(), { ".createdAt" => "[now]", ".updatedAt" => "[now]" }, @r###"
         {
           "uid": "movies",
           "primaryKey": "id",
-          "createdAt": "2022-10-09T20:27:22.197788495Z",
-          "updatedAt": "2022-10-09T20:28:01.93111053Z"
+          "createdAt": "[now]",
+          "updatedAt": "[now]"
         }
         "###);
 
@@ -571,12 +571,12 @@ pub(crate) mod test {
         meili_snap::snapshot_hash!(format!("{:#?}", documents), @"d751713988987e9331980363e24189ce");
 
         // spells
-        insta::assert_json_snapshot!(spells.metadata(), @r###"
+        insta::assert_json_snapshot!(spells.metadata(), { ".createdAt" => "[now]", ".updatedAt" => "[now]" }, @r###"
         {
           "uid": "dnd_spells",
           "primaryKey": "index",
-          "createdAt": "2022-10-09T20:27:24.242683494Z",
-          "updatedAt": "2022-10-09T20:27:24.312809641Z"
+          "createdAt": "[now]",
+          "updatedAt": "[now]"
         }
         "###);
 
@@ -617,12 +617,12 @@ pub(crate) mod test {
         assert!(indexes.is_empty());
 
         // products
-        insta::assert_json_snapshot!(products.metadata(), @r###"
+        insta::assert_json_snapshot!(products.metadata(), { ".createdAt" => "[now]", ".updatedAt" => "[now]" }, @r###"
         {
           "uid": "products",
           "primaryKey": "sku",
-          "createdAt": "2023-01-30T16:25:56.595257Z",
-          "updatedAt": "2023-01-30T16:25:58.70348Z"
+          "createdAt": "[now]",
+          "updatedAt": "[now]"
         }
         "###);
 
@@ -632,12 +632,12 @@ pub(crate) mod test {
         meili_snap::snapshot_hash!(format!("{:#?}", documents), @"548284a84de510f71e88e6cdea495cf5");
 
         // movies
-        insta::assert_json_snapshot!(movies.metadata(), @r###"
+        insta::assert_json_snapshot!(movies.metadata(), { ".createdAt" => "[now]", ".updatedAt" => "[now]" }, @r###"
         {
           "uid": "movies",
           "primaryKey": "id",
-          "createdAt": "2023-01-30T16:25:56.192178Z",
-          "updatedAt": "2023-01-30T16:25:56.455714Z"
+          "createdAt": "[now]",
+          "updatedAt": "[now]"
         }
         "###);
 
@@ -647,12 +647,12 @@ pub(crate) mod test {
         meili_snap::snapshot_hash!(format!("{:#?}", documents), @"0227598af846e574139ee0b80e03a720");
 
         // spells
-        insta::assert_json_snapshot!(spells.metadata(), @r###"
+        insta::assert_json_snapshot!(spells.metadata(), { ".createdAt" => "[now]", ".updatedAt" => "[now]" }, @r###"
         {
           "uid": "dnd_spells",
           "primaryKey": "index",
-          "createdAt": "2023-01-30T16:25:58.876405Z",
-          "updatedAt": "2023-01-30T16:25:59.079906Z"
+          "createdAt": "[now]",
+          "updatedAt": "[now]"
         }
         "###);
 

dump/src/reader/snapshots/dump__reader__test__import_dump_v1-11.snap

@@ -0,0 +1,24 @@
+---
+source: dump/src/reader/mod.rs
+expression: spells.settings().unwrap()
+---
+{
+  "displayedAttributes": [
+    "*"
+  ],
+  "searchableAttributes": [
+    "*"
+  ],
+  "filterableAttributes": [],
+  "sortableAttributes": [],
+  "rankingRules": [
+    "typo",
+    "words",
+    "proximity",
+    "attribute",
+    "exactness"
+  ],
+  "stopWords": [],
+  "synonyms": {},
+  "distinctAttribute": null
+}

dump/src/reader/snapshots/dump__reader__test__import_dump_v1-5.snap

@@ -0,0 +1,38 @@
+---
+source: dump/src/reader/mod.rs
+expression: products.settings().unwrap()
+---
+{
+  "displayedAttributes": [
+    "*"
+  ],
+  "searchableAttributes": [
+    "*"
+  ],
+  "filterableAttributes": [],
+  "sortableAttributes": [],
+  "rankingRules": [
+    "typo",
+    "words",
+    "proximity",
+    "attribute",
+    "exactness"
+  ],
+  "stopWords": [],
+  "synonyms": {
+    "android": [
+      "phone",
+      "smartphone"
+    ],
+    "iphone": [
+      "phone",
+      "smartphone"
+    ],
+    "phone": [
+      "android",
+      "iphone",
+      "smartphone"
+    ]
+  },
+  "distinctAttribute": null
+}

dump/src/reader/snapshots/dump__reader__test__import_dump_v1-8.snap

@@ -0,0 +1,31 @@
+---
+source: dump/src/reader/mod.rs
+expression: movies.settings().unwrap()
+---
+{
+  "displayedAttributes": [
+    "*"
+  ],
+  "searchableAttributes": [
+    "*"
+  ],
+  "filterableAttributes": [
+    "genres",
+    "id"
+  ],
+  "sortableAttributes": [
+    "genres",
+    "id"
+  ],
+  "rankingRules": [
+    "typo",
+    "words",
+    "proximity",
+    "attribute",
+    "exactness",
+    "release_date:asc"
+  ],
+  "stopWords": [],
+  "synonyms": {},
+  "distinctAttribute": null
+}

dump/src/reader/v1/settings.rs

@@ -56,7 +56,8 @@ pub enum RankingRule {
     Desc(String),
 }
 
-static ASC_DESC_REGEX: Lazy<Regex> = Lazy::new(|| Regex::new(r"(asc|desc)\(([\w_-]+)\)").unwrap());
+static ASC_DESC_REGEX: Lazy<Regex> =
+    Lazy::new(|| Regex::new(r#"(asc|desc)\(([\w_-]+)\)"#).unwrap());
 
 impl FromStr for RankingRule {
     type Err = ();

dump/src/reader/v2/mod.rs

@@ -46,7 +46,6 @@ pub type Checked = settings::Checked;
 pub type Unchecked = settings::Unchecked;
 
 pub type Task = updates::UpdateEntry;
-pub type Kind = updates::UpdateMeta;
 
 // everything related to the errors
 pub type ResponseError = errors::ResponseError;
@@ -108,11 +107,8 @@ impl V2Reader {
     pub fn indexes(&self) -> Result<impl Iterator<Item = Result<V2IndexReader>> + '_> {
         Ok(self.index_uuid.iter().map(|index| -> Result<_> {
             V2IndexReader::new(
+                index.uid.clone(),
                 &self.dump.path().join("indexes").join(format!("index-{}", index.uuid)),
-                index,
-                BufReader::new(
-                    File::open(self.dump.path().join("updates").join("data.jsonl")).unwrap(),
-                ),
             )
         }))
     }
@@ -147,41 +143,16 @@ pub struct V2IndexReader {
 }
 
 impl V2IndexReader {
-    pub fn new(path: &Path, index_uuid: &IndexUuid, tasks: BufReader<File>) -> Result<Self> {
+    pub fn new(name: String, path: &Path) -> Result<Self> {
         let meta = File::open(path.join("meta.json"))?;
         let meta: DumpMeta = serde_json::from_reader(meta)?;
 
-        let mut created_at = None;
-        let mut updated_at = None;
-
-        for line in tasks.lines() {
-            let task: Task = serde_json::from_str(&line?)?;
-            if !(task.uuid == index_uuid.uuid && task.is_finished()) {
-                continue;
-            }
-
-            let new_created_at = match task.update.meta() {
-                Kind::DocumentsAddition { .. } | Kind::Settings(_) => task.update.finished_at(),
-                _ => None,
-            };
-            let new_updated_at = task.update.finished_at();
-
-            if created_at.is_none() || created_at > new_created_at {
-                created_at = new_created_at;
-            }
-
-            if updated_at.is_none() || updated_at < new_updated_at {
-                updated_at = new_updated_at;
-            }
-        }
-
-        let current_time = OffsetDateTime::now_utc();
-
         let metadata = IndexMetadata {
-            uid: index_uuid.uid.clone(),
+            uid: name,
             primary_key: meta.primary_key,
-            created_at: created_at.unwrap_or(current_time),
-            updated_at: updated_at.unwrap_or(current_time),
+            // FIXME: Iterate over the whole task queue to find the creation and last update date.
+            created_at: OffsetDateTime::now_utc(),
+            updated_at: OffsetDateTime::now_utc(),
         };
 
         let ret = V2IndexReader {
@@ -277,12 +248,12 @@ pub(crate) mod test {
         assert!(indexes.is_empty());
 
         // products
-        insta::assert_json_snapshot!(products.metadata(), @r###"
+        insta::assert_json_snapshot!(products.metadata(), { ".createdAt" => "[now]", ".updatedAt" => "[now]" }, @r###"
         {
           "uid": "products",
           "primaryKey": "sku",
-          "createdAt": "2022-10-09T20:27:22.688964637Z",
-          "updatedAt": "2022-10-09T20:27:23.951017769Z"
+          "createdAt": "[now]",
+          "updatedAt": "[now]"
         }
         "###);
 
@@ -292,12 +263,12 @@ pub(crate) mod test {
         meili_snap::snapshot_hash!(format!("{:#?}", documents), @"548284a84de510f71e88e6cdea495cf5");
 
         // movies
-        insta::assert_json_snapshot!(movies.metadata(), @r###"
+        insta::assert_json_snapshot!(movies.metadata(), { ".createdAt" => "[now]", ".updatedAt" => "[now]" }, @r###"
         {
           "uid": "movies",
           "primaryKey": "id",
-          "createdAt": "2022-10-09T20:27:22.197788495Z",
-          "updatedAt": "2022-10-09T20:28:01.93111053Z"
+          "createdAt": "[now]",
+          "updatedAt": "[now]"
         }
         "###);
 
@@ -322,12 +293,12 @@ pub(crate) mod test {
         meili_snap::snapshot_hash!(format!("{:#?}", documents), @"d751713988987e9331980363e24189ce");
 
         // spells
-        insta::assert_json_snapshot!(spells.metadata(), @r###"
+        insta::assert_json_snapshot!(spells.metadata(), { ".createdAt" => "[now]", ".updatedAt" => "[now]" }, @r###"
         {
           "uid": "dnd_spells",
           "primaryKey": "index",
-          "createdAt": "2022-10-09T20:27:24.242683494Z",
-          "updatedAt": "2022-10-09T20:27:24.312809641Z"
+          "createdAt": "[now]",
+          "updatedAt": "[now]"
         }
         "###);
 
@@ -369,12 +340,12 @@ pub(crate) mod test {
         assert!(indexes.is_empty());
 
         // products
-        insta::assert_json_snapshot!(products.metadata(), @r###"
+        insta::assert_json_snapshot!(products.metadata(), { ".createdAt" => "[now]", ".updatedAt" => "[now]" }, @r###"
         {
           "uid": "products",
           "primaryKey": "sku",
-          "createdAt": "2023-01-30T16:25:56.595257Z",
-          "updatedAt": "2023-01-30T16:25:58.70348Z"
+          "createdAt": "[now]",
+          "updatedAt": "[now]"
         }
         "###);
 
@@ -384,12 +355,12 @@ pub(crate) mod test {
         meili_snap::snapshot_hash!(format!("{:#?}", documents), @"548284a84de510f71e88e6cdea495cf5");
 
         // movies
-        insta::assert_json_snapshot!(movies.metadata(), @r###"
+        insta::assert_json_snapshot!(movies.metadata(), { ".createdAt" => "[now]", ".updatedAt" => "[now]" }, @r###"
         {
           "uid": "movies",
           "primaryKey": "id",
-          "createdAt": "2023-01-30T16:25:56.192178Z",
-          "updatedAt": "2023-01-30T16:25:56.455714Z"
+          "createdAt": "[now]",
+          "updatedAt": "[now]"
         }
         "###);
 
@@ -399,12 +370,12 @@ pub(crate) mod test {
         meili_snap::snapshot_hash!(format!("{:#?}", documents), @"0227598af846e574139ee0b80e03a720");
 
         // spells
-        insta::assert_json_snapshot!(spells.metadata(), @r###"
+        insta::assert_json_snapshot!(spells.metadata(), { ".createdAt" => "[now]", ".updatedAt" => "[now]" }, @r###"
         {
           "uid": "dnd_spells",
           "primaryKey": "index",
-          "createdAt": "2023-01-30T16:25:58.876405Z",
-          "updatedAt": "2023-01-30T16:25:59.079906Z"
+          "createdAt": "[now]",
+          "updatedAt": "[now]"
         }
         "###);
 

dump/src/reader/v2/updates.rs

@@ -227,14 +227,4 @@ impl UpdateStatus {
             _ => None,
         }
     }
-
-    pub fn finished_at(&self) -> Option<OffsetDateTime> {
-        match self {
-            UpdateStatus::Processing(_) => None,
-            UpdateStatus::Enqueued(_) => None,
-            UpdateStatus::Processed(u) => Some(u.processed_at),
-            UpdateStatus::Aborted(_) => None,
-            UpdateStatus::Failed(u) => Some(u.failed_at),
-        }
-    }
 }

filter-parser/Cargo.toml

@@ -14,7 +14,6 @@ license.workspace = true
 [dependencies]
 nom = "7.1.3"
 nom_locate = "4.1.0"
-unescaper = "0.1.2"
 
 [dev-dependencies]
 insta = "1.29.0"

filter-parser/src/error.rs

@@ -62,7 +62,6 @@ pub enum ErrorKind<'a> {
     MisusedGeoRadius,
     MisusedGeoBoundingBox,
     InvalidPrimary,
-    InvalidEscapedNumber,
     ExpectedEof,
     ExpectedValue(ExpectedValueKind),
     MalformedValue,
@@ -148,9 +147,6 @@ impl<'a> Display for Error<'a> {
                 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)?
             }
-            ErrorKind::InvalidEscapedNumber => {
-                writeln!(f, "Found an invalid escaped sequence number: `{}`.", escaped_input)?
-            }
             ErrorKind::ExpectedEof => {
                 writeln!(f, "Found unexpected characters at the end of the filter: `{}`. You probably forgot an `OR` or an `AND` rule.", escaped_input)?
             }

filter-parser/src/lib.rs

@@ -545,8 +545,6 @@ impl<'a> std::fmt::Display for Token<'a> {
 
 #[cfg(test)]
 pub mod tests {
-    use FilterCondition as Fc;
-
     use super::*;
 
     /// Create a raw [Token]. You must specify the string that appear BEFORE your element followed by your element
@@ -558,22 +556,14 @@ pub mod tests {
         unsafe { Span::new_from_raw_offset(offset, lines as u32, value, "") }.into()
     }
 
-    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\\\\}"#);
-        // but it also works with other sequencies
-        insta::assert_display_snapshot!(p(r#"title = 'foo\x20\n\t\"\'"'"#), @"{title} = {foo \n\t\"\'\"}");
-    }
-
     #[test]
     fn parse() {
+        use FilterCondition as Fc;
+
+        fn p(s: &str) -> impl std::fmt::Display + '_ {
+            Fc::parse(s).unwrap().unwrap()
+        }
+
         // Test equal
         insta::assert_display_snapshot!(p("channel = Ponce"), @"{channel} = {Ponce}");
         insta::assert_display_snapshot!(p("subscribers = 12"), @"{subscribers} = {12}");

filter-parser/src/value.rs

@@ -171,24 +171,7 @@ pub fn parse_value(input: Span) -> IResult<Token> {
         })
     })?;
 
-    match unescaper::unescape(value.value()) {
-        Ok(content) => {
-            if content.len() != value.value().len() {
-                Ok((input, Token::new(value.original_span(), Some(content))))
-            } else {
-                Ok((input, value))
-            }
-        }
-        Err(unescaper::Error::IncompleteStr(_)) => Err(nom::Err::Incomplete(nom::Needed::Unknown)),
-        Err(unescaper::Error::ParseIntError { .. }) => Err(nom::Err::Error(Error::new_from_kind(
-            value.original_span(),
-            ErrorKind::InvalidEscapedNumber,
-        ))),
-        Err(unescaper::Error::InvalidChar { .. }) => Err(nom::Err::Error(Error::new_from_kind(
-            value.original_span(),
-            ErrorKind::MalformedValue,
-        ))),
-    }
+    Ok((input, value))
 }
 
 fn is_value_component(c: char) -> bool {
@@ -270,8 +253,8 @@ pub mod test {
             ("aaaa", "", rtok("", "aaaa"), "aaaa"),
             (r#"aa"aa"#, r#""aa"#, rtok("", "aa"), "aa"),
             (r#"aa\"aa"#, r#""#, rtok("", r#"aa\"aa"#), r#"aa"aa"#),
-            (r"aa\\\aa", r#""#, rtok("", r"aa\\\aa"), r"aa\\\aa"),
-            (r#"aa\\"\aa"#, r#""\aa"#, rtok("", r"aa\\"), r"aa\\"),
+            (r#"aa\\\aa"#, r#""#, rtok("", r#"aa\\\aa"#), r#"aa\\\aa"#),
+            (r#"aa\\"\aa"#, r#""\aa"#, rtok("", r#"aa\\"#), r#"aa\\"#),
             (r#"aa\\\"\aa"#, r#""#, rtok("", r#"aa\\\"\aa"#), r#"aa\\"\aa"#),
             (r#"\"\""#, r#""#, rtok("", r#"\"\""#), r#""""#),
         ];
@@ -301,12 +284,12 @@ pub mod test {
         );
         // simple quote
         assert_eq!(
-            unescape(Span::new_extra(r"Hello \'World\'", ""), '\''),
+            unescape(Span::new_extra(r#"Hello \'World\'"#, ""), '\''),
             r#"Hello 'World'"#.to_string()
         );
         assert_eq!(
-            unescape(Span::new_extra(r"Hello \\\'World\\\'", ""), '\''),
-            r"Hello \\'World\\'".to_string()
+            unescape(Span::new_extra(r#"Hello \\\'World\\\'"#, ""), '\''),
+            r#"Hello \\'World\\'"#.to_string()
         );
     }
 
@@ -335,19 +318,19 @@ pub mod test {
             ("\"cha'nnel\"", "cha'nnel", false),
             ("I'm tamo", "I", false),
             // escaped thing but not quote
-            (r#""\\""#, r"\", true),
-            (r#""\\\\\\""#, r"\\\", true),
-            (r#""aa\\aa""#, r"aa\aa", true),
+            (r#""\\""#, r#"\\"#, false),
+            (r#""\\\\\\""#, r#"\\\\\\"#, false),
+            (r#""aa\\aa""#, r#"aa\\aa"#, false),
             // with double quote
             (r#""Hello \"world\"""#, r#"Hello "world""#, true),
-            (r#""Hello \\\"world\\\"""#, r#"Hello \"world\""#, true),
+            (r#""Hello \\\"world\\\"""#, r#"Hello \\"world\\""#, true),
             (r#""I'm \"super\" tamo""#, r#"I'm "super" tamo"#, true),
             (r#""\"\"""#, r#""""#, true),
             // with simple quote
-            (r"'Hello \'world\''", r#"Hello 'world'"#, true),
-            (r"'Hello \\\'world\\\''", r"Hello \'world\'", true),
+            (r#"'Hello \'world\''"#, r#"Hello 'world'"#, true),
+            (r#"'Hello \\\'world\\\''"#, r#"Hello \\'world\\'"#, true),
             (r#"'I\'m "super" tamo'"#, r#"I'm "super" tamo"#, true),
-            (r"'\'\''", r#"''"#, true),
+            (r#"'\'\''"#, r#"''"#, true),
         ];
 
         for (input, expected, escaped) in test_case {
@@ -367,14 +350,7 @@ pub mod test {
                 "Filter `{}` was not supposed to be escaped",
                 input
             );
-            assert_eq!(
-                token.value(),
-                expected,
-                "Filter `{}` failed by giving `{}` instead of `{}`.",
-                input,
-                token.value(),
-                expected
-            );
+            assert_eq!(token.value(), expected, "Filter `{}` failed.", input);
         }
     }
 

fuzzers/src/bin/fuzz-indexing.rs

@@ -113,7 +113,7 @@ fn main() {
                             index.documents(&wtxn, res.documents_ids).unwrap();
                             progression.fetch_add(1, Ordering::Relaxed);
                         }
-                        wtxn.abort();
+                        wtxn.abort().unwrap();
                     });
                     if let err @ Err(_) = handle.join() {
                         stop.store(true, Ordering::Relaxed);

index-scheduler/Cargo.toml

@@ -18,12 +18,11 @@ derive_builder = "0.12.0"
 dump = { path = "../dump" }
 enum-iterator = "1.4.0"
 file-store = { path = "../file-store" }
-flate2 = "1.0.28"
 log = "0.4.17"
 meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
 page_size = "0.5.0"
-puffin = { version = "0.16.0", features = ["serialization"] }
+puffin = "0.16.0"
 roaring = { version = "0.10.1", features = ["serde"] }
 serde = { version = "1.0.160", features = ["derive"] }
 serde_json = { version = "1.0.95", features = ["preserve_order"] }
@@ -31,7 +30,6 @@ synchronoise = "1.0.1"
 tempfile = "3.5.0"
 thiserror = "1.0.40"
 time = { version = "0.3.20", features = ["serde-well-known", "formatting", "parsing", "macros"] }
-ureq = "2.9.1"
 uuid = { version = "1.3.1", features = ["serde", "v4"] }
 
 [dev-dependencies]

index-scheduler/src/batch.rs

@@ -19,31 +19,31 @@ one indexing operation.
 
 use std::collections::{BTreeSet, HashSet};
 use std::ffi::OsStr;
-use std::fmt;
 use std::fs::{self, File};
 use std::io::BufWriter;
 
 use dump::IndexMetadata;
-use log::{debug, error, info, trace};
+use log::{debug, error, info};
 use meilisearch_types::error::Code;
 use meilisearch_types::heed::{RoTxn, RwTxn};
 use meilisearch_types::milli::documents::{obkv_to_object, DocumentsBatchReader};
 use meilisearch_types::milli::heed::CompactionOption;
 use meilisearch_types::milli::update::{
-    IndexDocumentsConfig, IndexDocumentsMethod, IndexerConfig, Settings as MilliSettings,
+    DeleteDocuments, DocumentDeletionResult, IndexDocumentsConfig, IndexDocumentsMethod,
+    Settings as MilliSettings,
 };
-use meilisearch_types::milli::{self, Filter};
+use meilisearch_types::milli::{self, Filter, BEU64};
 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};
-use roaring::RoaringBitmap;
+use roaring::RoaringTreemap;
 use time::macros::format_description;
 use time::OffsetDateTime;
 use uuid::Uuid;
 
 use crate::autobatcher::{self, BatchKind};
 use crate::utils::{self, swap_index_uid_in_task};
-use crate::{Error, IndexScheduler, MustStopProcessing, ProcessingTasks, Result, TaskId};
+use crate::{Error, IndexScheduler, ProcessingTasks, Result, TaskId};
 
 /// Represents a combination of tasks that can all be processed at the same time.
 ///
@@ -58,7 +58,7 @@ pub(crate) enum Batch {
         /// The date and time at which the previously processing tasks started.
         previous_started_at: OffsetDateTime,
         /// The list of tasks that were processing when this task cancelation appeared.
-        previous_processing_tasks: RoaringBitmap,
+        previous_processing_tasks: RoaringTreemap,
     },
     TaskDeletion(Task),
     SnapshotCreation(Vec<Task>),
@@ -67,6 +67,10 @@ pub(crate) enum Batch {
         op: IndexOperation,
         must_create_index: bool,
     },
+    IndexDocumentDeletionByFilter {
+        index_uid: String,
+        task: Task,
+    },
     IndexCreation {
         index_uid: String,
         primary_key: Option<String>,
@@ -104,9 +108,11 @@ pub(crate) enum IndexOperation {
         operations: Vec<DocumentOperation>,
         tasks: Vec<Task>,
     },
-    IndexDocumentDeletionByFilter {
+    DocumentDeletion {
         index_uid: String,
-        task: Task,
+        // The vec associated with each document deletion tasks.
+        documents: Vec<Vec<String>>,
+        tasks: Vec<Task>,
     },
     DocumentClear {
         index_uid: String,
@@ -149,17 +155,18 @@ impl Batch {
             | Batch::TaskDeletion(task)
             | Batch::Dump(task)
             | Batch::IndexCreation { task, .. }
+            | Batch::IndexDocumentDeletionByFilter { task, .. }
             | Batch::IndexUpdate { task, .. } => vec![task.uid],
             Batch::SnapshotCreation(tasks) | Batch::IndexDeletion { tasks, .. } => {
                 tasks.iter().map(|task| task.uid).collect()
             }
             Batch::IndexOperation { op, .. } => match op {
                 IndexOperation::DocumentOperation { tasks, .. }
+                | IndexOperation::DocumentDeletion { tasks, .. }
                 | IndexOperation::Settings { tasks, .. }
                 | IndexOperation::DocumentClear { tasks, .. } => {
                     tasks.iter().map(|task| task.uid).collect()
                 }
-                IndexOperation::IndexDocumentDeletionByFilter { task, .. } => vec![task.uid],
                 IndexOperation::SettingsAndDocumentOperation {
                     document_import_tasks: tasks,
                     settings_tasks: other,
@@ -187,30 +194,8 @@ impl Batch {
             IndexOperation { op, .. } => Some(op.index_uid()),
             IndexCreation { index_uid, .. }
             | IndexUpdate { index_uid, .. }
-            | IndexDeletion { index_uid, .. } => Some(index_uid),
-        }
-    }
-}
-
-impl fmt::Display for Batch {
-    /// A text used when we debug the profiling reports.
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        let index_uid = self.index_uid();
-        let tasks = self.ids();
-        match self {
-            Batch::TaskCancelation { .. } => f.write_str("TaskCancelation")?,
-            Batch::TaskDeletion(_) => f.write_str("TaskDeletion")?,
-            Batch::SnapshotCreation(_) => f.write_str("SnapshotCreation")?,
-            Batch::Dump(_) => f.write_str("Dump")?,
-            Batch::IndexOperation { op, .. } => write!(f, "{op}")?,
-            Batch::IndexCreation { .. } => f.write_str("IndexCreation")?,
-            Batch::IndexUpdate { .. } => f.write_str("IndexUpdate")?,
-            Batch::IndexDeletion { .. } => f.write_str("IndexDeletion")?,
-            Batch::IndexSwap { .. } => f.write_str("IndexSwap")?,
-        };
-        match index_uid {
-            Some(name) => f.write_fmt(format_args!(" on {name:?} from tasks: {tasks:?}")),
-            None => f.write_fmt(format_args!(" from tasks: {tasks:?}")),
+            | IndexDeletion { index_uid, .. }
+            | IndexDocumentDeletionByFilter { index_uid, .. } => Some(index_uid),
         }
     }
 }
@@ -219,7 +204,7 @@ impl IndexOperation {
     pub fn index_uid(&self) -> &str {
         match self {
             IndexOperation::DocumentOperation { index_uid, .. }
-            | IndexOperation::IndexDocumentDeletionByFilter { index_uid, .. }
+            | IndexOperation::DocumentDeletion { index_uid, .. }
             | IndexOperation::DocumentClear { index_uid, .. }
             | IndexOperation::Settings { index_uid, .. }
             | IndexOperation::DocumentClearAndSetting { index_uid, .. }
@@ -228,27 +213,6 @@ impl IndexOperation {
     }
 }
 
-impl fmt::Display for IndexOperation {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        match self {
-            IndexOperation::DocumentOperation { .. } => {
-                f.write_str("IndexOperation::DocumentOperation")
-            }
-            IndexOperation::IndexDocumentDeletionByFilter { .. } => {
-                f.write_str("IndexOperation::IndexDocumentDeletionByFilter")
-            }
-            IndexOperation::DocumentClear { .. } => f.write_str("IndexOperation::DocumentClear"),
-            IndexOperation::Settings { .. } => f.write_str("IndexOperation::Settings"),
-            IndexOperation::DocumentClearAndSetting { .. } => {
-                f.write_str("IndexOperation::DocumentClearAndSetting")
-            }
-            IndexOperation::SettingsAndDocumentOperation { .. } => {
-                f.write_str("IndexOperation::SettingsAndDocumentOperation")
-            }
-        }
-    }
-}
-
 impl IndexScheduler {
     /// Convert an [`BatchKind`](crate::autobatcher::BatchKind) into a [`Batch`].
     ///
@@ -275,12 +239,9 @@ impl IndexScheduler {
                 let task = self.get_task(rtxn, id)?.ok_or(Error::CorruptedTaskQueue)?;
                 match &task.kind {
                     KindWithContent::DocumentDeletionByFilter { index_uid, .. } => {
-                        Ok(Some(Batch::IndexOperation {
-                            op: IndexOperation::IndexDocumentDeletionByFilter {
-                                index_uid: index_uid.clone(),
-                                task,
-                            },
-                            must_create_index: false,
+                        Ok(Some(Batch::IndexDocumentDeletionByFilter {
+                            index_uid: index_uid.clone(),
+                            task,
                         }))
                     }
                     _ => unreachable!(),
@@ -336,27 +297,18 @@ impl IndexScheduler {
             BatchKind::DocumentDeletion { deletion_ids } => {
                 let tasks = self.get_existing_tasks(rtxn, deletion_ids)?;
 
-                let mut operations = Vec::with_capacity(tasks.len());
-                let mut documents_counts = Vec::with_capacity(tasks.len());
+                let mut documents = Vec::new();
                 for task in &tasks {
                     match task.kind {
                         KindWithContent::DocumentDeletion { ref documents_ids, .. } => {
-                            operations.push(DocumentOperation::Delete(documents_ids.clone()));
-                            documents_counts.push(documents_ids.len() as u64);
+                            documents.push(documents_ids.clone())
                         }
                         _ => unreachable!(),
                     }
                 }
 
                 Ok(Some(Batch::IndexOperation {
-                    op: IndexOperation::DocumentOperation {
-                        index_uid,
-                        primary_key: None,
-                        method: IndexDocumentsMethod::ReplaceDocuments,
-                        documents_counts,
-                        operations,
-                        tasks,
-                    },
+                    op: IndexOperation::DocumentDeletion { index_uid, documents, tasks },
                     must_create_index,
                 }))
             }
@@ -584,9 +536,7 @@ impl IndexScheduler {
         let index_tasks = self.index_tasks(rtxn, index_name)? & enqueued;
 
         // If autobatching is disabled we only take one task at a time.
-        // Otherwise, we take only a maximum of tasks to create batches.
-        let tasks_limit =
-            if self.autobatching_enabled { self.max_number_of_batched_tasks } else { 1 };
+        let tasks_limit = if self.autobatching_enabled { usize::MAX } else { 1 };
 
         let enqueued = index_tasks
             .into_iter()
@@ -628,7 +578,7 @@ impl IndexScheduler {
             self.breakpoint(crate::Breakpoint::InsideProcessBatch);
         }
 
-        puffin::profile_function!(batch.to_string());
+        puffin::profile_function!(format!("{:?}", batch));
 
         match batch {
             Batch::TaskCancelation { mut task, previous_started_at, previous_processing_tasks } => {
@@ -717,7 +667,7 @@ impl IndexScheduler {
 
                 // 2. Snapshot the index-scheduler LMDB env
                 //
-                // When we call copy_to_file, LMDB opens a read transaction by itself,
+                // When we call copy_to_path, LMDB opens a read transaction by itself,
                 // we can't provide our own. It is an issue as we would like to know
                 // the update files to copy but new ones can be enqueued between the copy
                 // of the env and the new transaction we open to retrieve the enqueued tasks.
@@ -730,7 +680,7 @@ impl IndexScheduler {
                 // 2.1 First copy the LMDB env of the index-scheduler
                 let dst = temp_snapshot_dir.path().join("tasks");
                 fs::create_dir_all(&dst)?;
-                self.env.copy_to_file(dst.join("data.mdb"), CompactionOption::Enabled)?;
+                self.env.copy_to_path(dst.join("data.mdb"), CompactionOption::Enabled)?;
 
                 // 2.2 Create a read transaction on the index-scheduler
                 let rtxn = self.env.read_txn()?;
@@ -755,7 +705,7 @@ impl IndexScheduler {
                     let index = self.index_mapper.index(&rtxn, name)?;
                     let dst = temp_snapshot_dir.path().join("indexes").join(uuid.to_string());
                     fs::create_dir_all(&dst)?;
-                    index.copy_to_file(dst.join("data.mdb"), CompactionOption::Enabled)?;
+                    index.copy_to_path(dst.join("data.mdb"), CompactionOption::Enabled)?;
                 }
 
                 drop(rtxn);
@@ -768,7 +718,7 @@ impl IndexScheduler {
                     .map_size(1024 * 1024 * 1024) // 1 GiB
                     .max_dbs(2)
                     .open(&self.auth_path)?;
-                auth.copy_to_file(dst.join("data.mdb"), CompactionOption::Enabled)?;
+                auth.copy_to_path(dst.join("data.mdb"), CompactionOption::Enabled)?;
 
                 // 5. Copy and tarball the flat snapshot
                 // 5.1 Find the original name of the database
@@ -824,10 +774,6 @@ impl IndexScheduler {
                 // 2. dump the tasks
                 let mut dump_tasks = dump.create_tasks_queue()?;
                 for ret in self.all_tasks.iter(&rtxn)? {
-                    if self.must_stop_processing.get() {
-                        return Err(Error::AbortedTask);
-                    }
-
                     let (_, mut t) = ret?;
                     let status = t.status;
                     let content_file = t.content_uuid();
@@ -848,9 +794,6 @@ impl IndexScheduler {
 
                     // 2.1. Dump the `content_file` associated with the task if there is one and the task is not finished yet.
                     if let Some(content_file) = content_file {
-                        if self.must_stop_processing.get() {
-                            return Err(Error::AbortedTask);
-                        }
                         if status == Status::Enqueued {
                             let content_file = self.file_store.get_update(content_file)?;
 
@@ -890,9 +833,6 @@ impl IndexScheduler {
 
                     // 3.1. Dump the documents
                     for ret in index.all_documents(&rtxn)? {
-                        if self.must_stop_processing.get() {
-                            return Err(Error::AbortedTask);
-                        }
                         let (_id, doc) = ret?;
                         let document = milli::obkv_to_json(&all_fields, &fields_ids_map, doc)?;
                         index_dumper.push_document(&document)?;
@@ -905,16 +845,13 @@ impl IndexScheduler {
                 })?;
 
                 // 4. Dump experimental feature settings
-                let features = self.features().runtime_features();
+                let features = self.features()?.runtime_features();
                 dump.create_experimental_features(features)?;
 
                 let dump_uid = started_at.format(format_description!(
                     "[year repr:full][month repr:numerical][day padding:zero]-[hour padding:zero][minute padding:zero][second padding:zero][subsecond digits:3]"
                 )).unwrap();
 
-                if self.must_stop_processing.get() {
-                    return Err(Error::AbortedTask);
-                }
                 let path = self.dumps_path.join(format!("{}.dump", dump_uid));
                 let file = File::create(path)?;
                 dump.persist_to(BufWriter::new(file))?;
@@ -935,10 +872,6 @@ impl IndexScheduler {
                     self.index_mapper.index(&rtxn, &index_uid)?
                 };
 
-                // the index operation can take a long time, so save this handle to make it available to the search for the duration of the tick
-                self.index_mapper
-                    .set_currently_updating_index(Some((index_uid.clone(), index.clone())));
-
                 let mut index_wtxn = index.write_txn()?;
                 let tasks = self.apply_index_operation(&mut index_wtxn, &index, op)?;
                 index_wtxn.commit()?;
@@ -963,6 +896,51 @@ impl IndexScheduler {
 
                 Ok(tasks)
             }
+            Batch::IndexDocumentDeletionByFilter { mut task, index_uid: _ } => {
+                let (index_uid, filter) =
+                    if let KindWithContent::DocumentDeletionByFilter { index_uid, filter_expr } =
+                        &task.kind
+                    {
+                        (index_uid, filter_expr)
+                    } else {
+                        unreachable!()
+                    };
+                let index = {
+                    let rtxn = self.env.read_txn()?;
+                    self.index_mapper.index(&rtxn, index_uid)?
+                };
+                let deleted_documents = delete_document_by_filter(filter, index);
+                let original_filter = if let Some(Details::DocumentDeletionByFilter {
+                    original_filter,
+                    deleted_documents: _,
+                }) = task.details
+                {
+                    original_filter
+                } else {
+                    // In the case of a `documentDeleteByFilter` the details MUST be set
+                    unreachable!();
+                };
+
+                match deleted_documents {
+                    Ok(deleted_documents) => {
+                        task.status = Status::Succeeded;
+                        task.details = Some(Details::DocumentDeletionByFilter {
+                            original_filter,
+                            deleted_documents: Some(deleted_documents),
+                        });
+                    }
+                    Err(e) => {
+                        task.status = Status::Failed;
+                        task.details = Some(Details::DocumentDeletionByFilter {
+                            original_filter,
+                            deleted_documents: Some(0),
+                        });
+                        task.error = Some(e.into());
+                    }
+                }
+
+                Ok(vec![task])
+            }
             Batch::IndexCreation { index_uid, primary_key, task } => {
                 let wtxn = self.env.write_txn()?;
                 if self.index_mapper.exists(&wtxn, &index_uid)? {
@@ -1087,7 +1065,13 @@ impl IndexScheduler {
     }
 
     /// Swap the index `lhs` with the index `rhs`.
-    fn apply_index_swap(&self, wtxn: &mut RwTxn, task_id: u32, lhs: &str, rhs: &str) -> Result<()> {
+    fn apply_index_swap(
+        &self,
+        wtxn: &mut RwTxn,
+        task_id: TaskId,
+        lhs: &str,
+        rhs: &str,
+    ) -> Result<()> {
         // 1. Verify that both lhs and rhs are existing indexes
         let index_lhs_exists = self.index_mapper.index_exists(wtxn, lhs)?;
         if !index_lhs_exists {
@@ -1108,7 +1092,7 @@ impl IndexScheduler {
         for task_id in &index_lhs_task_ids | &index_rhs_task_ids {
             let mut task = self.get_task(wtxn, task_id)?.ok_or(Error::CorruptedTaskQueue)?;
             swap_index_uid_in_task(&mut task, (lhs, rhs));
-            self.all_tasks.put(wtxn, &task_id, &task)?;
+            self.all_tasks.put(wtxn, &BEU64::new(task_id), &task)?;
         }
 
         // 4. remove the task from indexuid = before_name
@@ -1134,7 +1118,7 @@ impl IndexScheduler {
     /// The list of processed tasks.
     fn apply_index_operation<'i>(
         &self,
-        index_wtxn: &mut RwTxn<'i>,
+        index_wtxn: &mut RwTxn<'i, '_>,
         index: &'i Index,
         operation: IndexOperation,
     ) -> Result<Vec<Task>> {
@@ -1202,16 +1186,12 @@ impl IndexScheduler {
 
                 let config = IndexDocumentsConfig { update_method: method, ..Default::default() };
 
-                let embedder_configs = index.embedding_configs(index_wtxn)?;
-                // TODO: consider Arc'ing the map too (we only need read access + we'll be cloning it multiple times, so really makes sense)
-                let embedders = self.embedders(embedder_configs)?;
-
                 let mut builder = milli::update::IndexDocuments::new(
                     index_wtxn,
                     index,
                     indexer_config,
                     config,
-                    |indexing_step| trace!("update: {:?}", indexing_step),
+                    |indexing_step| debug!("update: {:?}", indexing_step),
                     || must_stop_processing.get(),
                 )?;
 
@@ -1224,8 +1204,6 @@ impl IndexScheduler {
                             let (new_builder, user_result) = builder.add_documents(reader)?;
                             builder = new_builder;
 
-                            builder = builder.with_embedders(embedders.clone());
-
                             let received_documents =
                                 if let Some(Details::DocumentAdditionOrUpdate {
                                     received_documents,
@@ -1260,8 +1238,7 @@ impl IndexScheduler {
                             let (new_builder, user_result) =
                                 builder.remove_documents(document_ids)?;
                             builder = new_builder;
-                            // Uses Invariant: remove documents actually always returns Ok for the inner result
-                            let count = user_result.unwrap();
+
                             let provided_ids =
                                 if let Some(Details::DocumentDeletion { provided_ids, .. }) =
                                     task.details
@@ -1272,11 +1249,23 @@ impl IndexScheduler {
                                     unreachable!();
                                 };
 
-                            task.status = Status::Succeeded;
-                            task.details = Some(Details::DocumentDeletion {
-                                provided_ids,
-                                deleted_documents: Some(count),
-                            });
+                            match user_result {
+                                Ok(count) => {
+                                    task.status = Status::Succeeded;
+                                    task.details = Some(Details::DocumentDeletion {
+                                        provided_ids,
+                                        deleted_documents: Some(count),
+                                    });
+                                }
+                                Err(e) => {
+                                    task.status = Status::Failed;
+                                    task.details = Some(Details::DocumentDeletion {
+                                        provided_ids,
+                                        deleted_documents: Some(0),
+                                    });
+                                    task.error = Some(milli::Error::from(e).into());
+                                }
+                            }
                         }
                     }
                 }
@@ -1291,59 +1280,30 @@ impl IndexScheduler {
                         milli::update::Settings::new(index_wtxn, index, indexer_config);
                     builder.reset_primary_key();
                     builder.execute(
-                        |indexing_step| trace!("update: {:?}", indexing_step),
+                        |indexing_step| debug!("update: {:?}", indexing_step),
                         || must_stop_processing.clone().get(),
                     )?;
                 }
 
                 Ok(tasks)
             }
-            IndexOperation::IndexDocumentDeletionByFilter { mut task, index_uid: _ } => {
-                let filter =
-                    if let KindWithContent::DocumentDeletionByFilter { filter_expr, .. } =
-                        &task.kind
-                    {
-                        filter_expr
-                    } else {
-                        unreachable!()
-                    };
-                let deleted_documents = delete_document_by_filter(
-                    index_wtxn,
-                    filter,
-                    self.index_mapper.indexer_config(),
-                    self.must_stop_processing.clone(),
-                    index,
-                );
-                let original_filter = if let Some(Details::DocumentDeletionByFilter {
-                    original_filter,
-                    deleted_documents: _,
-                }) = task.details
-                {
-                    original_filter
-                } else {
-                    // In the case of a `documentDeleteByFilter` the details MUST be set
-                    unreachable!();
-                };
+            IndexOperation::DocumentDeletion { index_uid: _, documents, mut tasks } => {
+                let mut builder = milli::update::DeleteDocuments::new(index_wtxn, index)?;
+                documents.iter().flatten().for_each(|id| {
+                    builder.delete_external_id(id);
+                });
 
-                match deleted_documents {
-                    Ok(deleted_documents) => {
-                        task.status = Status::Succeeded;
-                        task.details = Some(Details::DocumentDeletionByFilter {
-                            original_filter,
-                            deleted_documents: Some(deleted_documents),
-                        });
-                    }
-                    Err(e) => {
-                        task.status = Status::Failed;
-                        task.details = Some(Details::DocumentDeletionByFilter {
-                            original_filter,
-                            deleted_documents: Some(0),
-                        });
-                        task.error = Some(e.into());
-                    }
+                let DocumentDeletionResult { deleted_documents, .. } = builder.execute()?;
+
+                for (task, documents) in tasks.iter_mut().zip(documents) {
+                    task.status = Status::Succeeded;
+                    task.details = Some(Details::DocumentDeletion {
+                        provided_ids: documents.len(),
+                        deleted_documents: Some(deleted_documents.min(documents.len() as u64)),
+                    });
                 }
 
-                Ok(vec![task])
+                Ok(tasks)
             }
             IndexOperation::Settings { index_uid: _, settings, mut tasks } => {
                 let indexer_config = self.index_mapper.indexer_config();
@@ -1435,7 +1395,11 @@ impl IndexScheduler {
     /// Delete each given task from all the databases (if it is deleteable).
     ///
     /// Return the number of tasks that were actually deleted.
-    fn delete_matched_tasks(&self, wtxn: &mut RwTxn, matched_tasks: &RoaringBitmap) -> Result<u64> {
+    fn delete_matched_tasks(
+        &self,
+        wtxn: &mut RwTxn,
+        matched_tasks: &RoaringTreemap,
+    ) -> Result<u64> {
         // 1. Remove from this list the tasks that we are not allowed to delete
         let enqueued_tasks = self.get_status(wtxn, Status::Enqueued)?;
         let processing_tasks = &self.processing_tasks.read().unwrap().processing.clone();
@@ -1450,7 +1414,7 @@ impl IndexScheduler {
         let mut affected_indexes = HashSet::new();
         let mut affected_statuses = HashSet::new();
         let mut affected_kinds = HashSet::new();
-        let mut affected_canceled_by = RoaringBitmap::new();
+        let mut affected_canceled_by = RoaringTreemap::new();
 
         for task_id in to_delete_tasks.iter() {
             let task = self.get_task(wtxn, task_id)?.ok_or(Error::CorruptedTaskQueue)?;
@@ -1487,9 +1451,10 @@ impl IndexScheduler {
         }
 
         for task in to_delete_tasks.iter() {
-            self.all_tasks.delete(wtxn, &task)?;
+            self.all_tasks.delete(wtxn, &BEU64::new(task))?;
         }
         for canceled_by in affected_canceled_by {
+            let canceled_by = BEU64::new(canceled_by);
             if let Some(mut tasks) = self.canceled_by.get(wtxn, &canceled_by)? {
                 tasks -= &to_delete_tasks;
                 if tasks.is_empty() {
@@ -1510,9 +1475,9 @@ impl IndexScheduler {
         &self,
         wtxn: &mut RwTxn,
         cancel_task_id: TaskId,
-        matched_tasks: &RoaringBitmap,
+        matched_tasks: &RoaringTreemap,
         previous_started_at: OffsetDateTime,
-        previous_processing_tasks: &RoaringBitmap,
+        previous_processing_tasks: &RoaringTreemap,
     ) -> Result<Vec<Uuid>> {
         let now = OffsetDateTime::now_utc();
 
@@ -1537,47 +1502,29 @@ impl IndexScheduler {
             task.details = task.details.map(|d| d.to_failed());
             self.update_task(wtxn, &task)?;
         }
-        self.canceled_by.put(wtxn, &cancel_task_id, &tasks_to_cancel)?;
+        self.canceled_by.put(wtxn, &BEU64::new(cancel_task_id), &tasks_to_cancel)?;
 
         Ok(content_files_to_delete)
     }
 }
 
-fn delete_document_by_filter<'a>(
-    wtxn: &mut RwTxn<'a>,
-    filter: &serde_json::Value,
-    indexer_config: &IndexerConfig,
-    must_stop_processing: MustStopProcessing,
-    index: &'a Index,
-) -> Result<u64> {
+fn delete_document_by_filter(filter: &serde_json::Value, index: Index) -> Result<u64> {
     let filter = Filter::from_json(filter)?;
     Ok(if let Some(filter) = filter {
-        let candidates = filter.evaluate(wtxn, index).map_err(|err| match err {
+        let mut wtxn = index.write_txn()?;
+
+        let candidates = 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(),
         })?;
-
-        let config = IndexDocumentsConfig {
-            update_method: IndexDocumentsMethod::ReplaceDocuments,
-            ..Default::default()
-        };
-
-        let mut builder = milli::update::IndexDocuments::new(
-            wtxn,
-            index,
-            indexer_config,
-            config,
-            |indexing_step| debug!("update: {:?}", indexing_step),
-            || must_stop_processing.get(),
-        )?;
-
-        let (new_builder, count) = builder.remove_documents_from_db_no_batch(&candidates)?;
-        builder = new_builder;
-
-        let _ = builder.execute()?;
-        count
+        let mut delete_operation = DeleteDocuments::new(&mut wtxn, &index)?;
+        delete_operation.delete_documents(&candidates);
+        let deleted_documents =
+            delete_operation.execute().map(|result| result.deleted_documents)?;
+        wtxn.commit()?;
+        deleted_documents
     } else {
         0
     })

index-scheduler/src/error.rs

@@ -48,6 +48,8 @@ impl From<DateField> for Code {
 pub enum Error {
     #[error("{1}")]
     WithCustomErrorCode(Code, Box<Self>),
+    #[error("Received bad task id: {received} should be >= to {expected}.")]
+    BadTaskId { received: TaskId, expected: TaskId },
     #[error("Index `{0}` not found.")]
     IndexNotFound(String),
     #[error("Index `{0}` already exists.")]
@@ -108,8 +110,6 @@ pub enum Error {
     TaskDeletionWithEmptyQuery,
     #[error("Query parameters to filter the tasks to cancel are missing. Available query parameters are: `uids`, `indexUids`, `statuses`, `types`, `canceledBy`, `beforeEnqueuedAt`, `afterEnqueuedAt`, `beforeStartedAt`, `afterStartedAt`, `beforeFinishedAt`, `afterFinishedAt`.")]
     TaskCancelationWithEmptyQuery,
-    #[error("Aborted task")]
-    AbortedTask,
 
     #[error(transparent)]
     Dump(#[from] dump::Error),
@@ -161,6 +161,7 @@ impl Error {
         match self {
             Error::IndexNotFound(_)
             | Error::WithCustomErrorCode(_, _)
+            | Error::BadTaskId { .. }
             | Error::IndexAlreadyExists(_)
             | Error::SwapDuplicateIndexFound(_)
             | Error::SwapDuplicateIndexesFound(_)
@@ -177,7 +178,6 @@ impl Error {
             | Error::TaskNotFound(_)
             | Error::TaskDeletionWithEmptyQuery
             | Error::TaskCancelationWithEmptyQuery
-            | Error::AbortedTask
             | Error::Dump(_)
             | Error::Heed(_)
             | Error::Milli(_)
@@ -205,6 +205,7 @@ impl ErrorCode for Error {
     fn error_code(&self) -> Code {
         match self {
             Error::WithCustomErrorCode(code, _) => *code,
+            Error::BadTaskId { .. } => Code::BadRequest,
             Error::IndexNotFound(_) => Code::IndexNotFound,
             Error::IndexAlreadyExists(_) => Code::IndexAlreadyExists,
             Error::SwapDuplicateIndexesFound(_) => Code::InvalidSwapDuplicateIndexFound,
@@ -239,9 +240,6 @@ impl ErrorCode for Error {
             Error::TaskDatabaseUpdate(_) => Code::Internal,
             Error::CreateBatch(_) => Code::Internal,
 
-            // This one should never be seen by the end user
-            Error::AbortedTask => Code::Internal,
-
             #[cfg(test)]
             Error::PlannedFailure => Code::Internal,
         }

index-scheduler/src/features.rs

@@ -1,8 +1,6 @@
-use std::sync::{Arc, RwLock};
-
 use meilisearch_types::features::{InstanceTogglableFeatures, RuntimeTogglableFeatures};
 use meilisearch_types::heed::types::{SerdeJson, Str};
-use meilisearch_types::heed::{Database, Env, RwTxn};
+use meilisearch_types::heed::{Database, Env, RoTxn, RwTxn};
 
 use crate::error::FeatureNotEnabledError;
 use crate::Result;
@@ -11,19 +9,20 @@ const EXPERIMENTAL_FEATURES: &str = "experimental-features";
 
 #[derive(Clone)]
 pub(crate) struct FeatureData {
-    persisted: Database<Str, SerdeJson<RuntimeTogglableFeatures>>,
-    runtime: Arc<RwLock<RuntimeTogglableFeatures>>,
+    runtime: Database<Str, SerdeJson<RuntimeTogglableFeatures>>,
+    instance: InstanceTogglableFeatures,
 }
 
 #[derive(Debug, Clone, Copy)]
 pub struct RoFeatures {
     runtime: RuntimeTogglableFeatures,
+    instance: InstanceTogglableFeatures,
 }
 
 impl RoFeatures {
-    fn new(data: &FeatureData) -> Self {
-        let runtime = data.runtime_features();
-        Self { runtime }
+    fn new(txn: RoTxn<'_>, data: &FeatureData) -> Result<Self> {
+        let runtime = data.runtime_features(txn)?;
+        Ok(Self { runtime, instance: data.instance })
     }
 
     pub fn runtime_features(&self) -> RuntimeTogglableFeatures {
@@ -44,60 +43,39 @@ impl RoFeatures {
     }
 
     pub fn check_metrics(&self) -> Result<()> {
-        if self.runtime.metrics {
+        if self.instance.metrics {
             Ok(())
         } else {
             Err(FeatureNotEnabledError {
                 disabled_action: "Getting metrics",
                 feature: "metrics",
-                issue_link: "https://github.com/meilisearch/product/discussions/625",
+                issue_link: "https://github.com/meilisearch/meilisearch/discussions/3518",
             }
             .into())
         }
     }
 
-    pub fn check_vector(&self, disabled_action: &'static str) -> Result<()> {
+    pub fn check_vector(&self) -> Result<()> {
         if self.runtime.vector_store {
             Ok(())
         } else {
             Err(FeatureNotEnabledError {
-                disabled_action,
+                disabled_action: "Passing `vector` as a query parameter",
                 feature: "vector store",
                 issue_link: "https://github.com/meilisearch/product/discussions/677",
             }
             .into())
         }
     }
-
-    pub fn check_puffin(&self) -> Result<()> {
-        if self.runtime.export_puffin_reports {
-            Ok(())
-        } else {
-            Err(FeatureNotEnabledError {
-                disabled_action: "Outputting Puffin reports to disk",
-                feature: "export puffin reports",
-                issue_link: "https://github.com/meilisearch/product/discussions/693",
-            }
-            .into())
-        }
-    }
 }
 
 impl FeatureData {
     pub fn new(env: &Env, instance_features: InstanceTogglableFeatures) -> Result<Self> {
         let mut wtxn = env.write_txn()?;
-        let runtime_features_db = env.create_database(&mut wtxn, Some(EXPERIMENTAL_FEATURES))?;
+        let runtime_features = env.create_database(&mut wtxn, Some(EXPERIMENTAL_FEATURES))?;
         wtxn.commit()?;
 
-        let txn = env.read_txn()?;
-        let persisted_features: RuntimeTogglableFeatures =
-            runtime_features_db.get(&txn, EXPERIMENTAL_FEATURES)?.unwrap_or_default();
-        let runtime = Arc::new(RwLock::new(RuntimeTogglableFeatures {
-            metrics: instance_features.metrics || persisted_features.metrics,
-            ..persisted_features
-        }));
-
-        Ok(Self { persisted: runtime_features_db, runtime })
+        Ok(Self { runtime: runtime_features, instance: instance_features })
     }
 
     pub fn put_runtime_features(
@@ -105,25 +83,16 @@ impl FeatureData {
         mut wtxn: RwTxn,
         features: RuntimeTogglableFeatures,
     ) -> Result<()> {
-        self.persisted.put(&mut wtxn, EXPERIMENTAL_FEATURES, &features)?;
+        self.runtime.put(&mut wtxn, EXPERIMENTAL_FEATURES, &features)?;
         wtxn.commit()?;
-
-        // safe to unwrap, the lock will only fail if:
-        // 1. requested by the same thread concurrently -> it is called and released in methods that don't call each other
-        // 2. there's a panic while the thread is held -> it is only used for an assignment here.
-        let mut toggled_features = self.runtime.write().unwrap();
-        *toggled_features = features;
         Ok(())
     }
 
-    fn runtime_features(&self) -> RuntimeTogglableFeatures {
-        // sound to unwrap, the lock will only fail if:
-        // 1. requested by the same thread concurrently -> it is called and released in methods that don't call each other
-        // 2. there's a panic while the thread is held -> it is only used for copying the data here
-        *self.runtime.read().unwrap()
+    fn runtime_features(&self, txn: RoTxn) -> Result<RuntimeTogglableFeatures> {
+        Ok(self.runtime.get(&txn, EXPERIMENTAL_FEATURES)?.unwrap_or_default())
     }
 
-    pub fn features(&self) -> RoFeatures {
-        RoFeatures::new(self)
+    pub fn features(&self, txn: RoTxn) -> Result<RoFeatures> {
+        RoFeatures::new(txn, self)
     }
 }

index-scheduler/src/index_mapper/index_map.rs

@@ -1,8 +1,12 @@
+/// the map size to use when we don't succeed in reading it in indexes.
+const DEFAULT_MAP_SIZE: usize = 10 * 1024 * 1024 * 1024; // 10 GiB
+
 use std::collections::BTreeMap;
 use std::path::Path;
 use std::time::Duration;
 
-use meilisearch_types::heed::{EnvClosingEvent, EnvFlags, EnvOpenOptions};
+use meilisearch_types::heed::flags::Flags;
+use meilisearch_types::heed::{EnvClosingEvent, EnvOpenOptions};
 use meilisearch_types::milli::Index;
 use time::OffsetDateTime;
 use uuid::Uuid;
@@ -232,7 +236,7 @@ impl IndexMap {
         enable_mdb_writemap: bool,
         map_size_growth: usize,
     ) {
-        let map_size = index.map_size() + map_size_growth;
+        let map_size = index.map_size().unwrap_or(DEFAULT_MAP_SIZE) + map_size_growth;
         let closing_event = index.prepare_for_closing();
         let generation = self.next_generation();
         self.unavailable.insert(
@@ -305,7 +309,7 @@ fn create_or_open_index(
     options.map_size(clamp_to_page_size(map_size));
     options.max_readers(1024);
     if enable_mdb_writemap {
-        unsafe { options.flags(EnvFlags::WRITE_MAP) };
+        unsafe { options.flag(Flags::MdbWriteMap) };
     }
 
     if let Some((created, updated)) = date {
@@ -384,7 +388,7 @@ mod tests {
 
     fn assert_index_size(index: Index, expected: usize) {
         let expected = clamp_to_page_size(expected);
-        let index_map_size = index.map_size();
+        let index_map_size = index.map_size().unwrap();
         assert_eq!(index_map_size, expected);
     }
 }

index-scheduler/src/index_mapper/mod.rs

@@ -69,10 +69,6 @@ pub struct IndexMapper {
     /// Whether we open a meilisearch index with the MDB_WRITEMAP option or not.
     enable_mdb_writemap: bool,
     pub indexer_config: Arc<IndexerConfig>,
-
-    /// A few types of long running batches of tasks that act on a single index set this field
-    /// so that a handle to the index is available from other threads (search) in an optimized manner.
-    currently_updating_index: Arc<RwLock<Option<(String, Index)>>>,
 }
 
 /// Whether the index is available for use or is forbidden to be inserted back in the index map
@@ -155,7 +151,6 @@ impl IndexMapper {
             index_growth_amount,
             enable_mdb_writemap,
             indexer_config: Arc::new(indexer_config),
-            currently_updating_index: Default::default(),
         })
     }
 
@@ -308,14 +303,6 @@ impl IndexMapper {
 
     /// Return an index, may open it if it wasn't already opened.
     pub fn index(&self, rtxn: &RoTxn, name: &str) -> Result<Index> {
-        if let Some((current_name, current_index)) =
-            self.currently_updating_index.read().unwrap().as_ref()
-        {
-            if current_name == name {
-                return Ok(current_index.clone());
-            }
-        }
-
         let uuid = self
             .index_mapping
             .get(rtxn, name)?
@@ -487,8 +474,4 @@ impl IndexMapper {
     pub fn indexer_config(&self) -> &IndexerConfig {
         &self.indexer_config
     }
-
-    pub fn set_currently_updating_index(&self, index: Option<(String, Index)>) {
-        *self.currently_updating_index.write().unwrap() = index;
-    }
 }

index-scheduler/src/insta_snapshot.rs

@@ -1,11 +1,12 @@
 use std::collections::BTreeSet;
 use std::fmt::Write;
 
-use meilisearch_types::heed::types::{SerdeBincode, SerdeJson, Str};
+use meilisearch_types::heed::types::{OwnedType, SerdeBincode, SerdeJson, Str};
 use meilisearch_types::heed::{Database, RoTxn};
-use meilisearch_types::milli::{CboRoaringBitmapCodec, RoaringBitmapCodec, BEU32};
+use meilisearch_types::milli::heed_codec::{CboRoaringTreemapCodec, RoaringTreemapCodec};
+use meilisearch_types::milli::BEU64;
 use meilisearch_types::tasks::{Details, Task};
-use roaring::RoaringBitmap;
+use roaring::RoaringTreemap;
 
 use crate::index_mapper::IndexMapper;
 use crate::{IndexScheduler, Kind, Status, BEI128};
@@ -30,19 +31,14 @@ pub fn snapshot_index_scheduler(scheduler: &IndexScheduler) -> String {
         index_mapper,
         features: _,
         max_number_of_tasks: _,
-        max_number_of_batched_tasks: _,
-        puffin_frame: _,
         wake_up: _,
         dumps_path: _,
         snapshots_path: _,
         auth_path: _,
         version_file_path: _,
-        webhook_url: _,
-        webhook_authorization_header: _,
         test_breakpoint_sdr: _,
         planned_failures: _,
         run_loop_iteration: _,
-        embedders: _,
     } = scheduler;
 
     let rtxn = env.read_txn().unwrap();
@@ -52,7 +48,7 @@ pub fn snapshot_index_scheduler(scheduler: &IndexScheduler) -> String {
     let processing_tasks = processing_tasks.read().unwrap().processing.clone();
     snap.push_str(&format!("### Autobatching Enabled = {autobatching_enabled}\n"));
     snap.push_str("### Processing Tasks:\n");
-    snap.push_str(&snapshot_bitmap(&processing_tasks));
+    snap.push_str(&snapshot_treemap(&processing_tasks));
     snap.push_str("\n----------------------------------------------------------------------\n");
 
     snap.push_str("### All Tasks:\n");
@@ -108,7 +104,7 @@ pub fn snapshot_file_store(file_store: &file_store::FileStore) -> String {
     snap
 }
 
-pub fn snapshot_bitmap(r: &RoaringBitmap) -> String {
+pub fn snapshot_treemap(r: &RoaringTreemap) -> String {
     let mut snap = String::new();
     snap.push('[');
     for x in r {
@@ -118,7 +114,7 @@ pub fn snapshot_bitmap(r: &RoaringBitmap) -> String {
     snap
 }
 
-pub fn snapshot_all_tasks(rtxn: &RoTxn, db: Database<BEU32, SerdeJson<Task>>) -> String {
+pub fn snapshot_all_tasks(rtxn: &RoTxn, db: Database<OwnedType<BEU64>, SerdeJson<Task>>) -> String {
     let mut snap = String::new();
     let iter = db.iter(rtxn).unwrap();
     for next in iter {
@@ -128,12 +124,15 @@ pub fn snapshot_all_tasks(rtxn: &RoTxn, db: Database<BEU32, SerdeJson<Task>>) ->
     snap
 }
 
-pub fn snapshot_date_db(rtxn: &RoTxn, db: Database<BEI128, CboRoaringBitmapCodec>) -> String {
+pub fn snapshot_date_db(
+    rtxn: &RoTxn,
+    db: Database<OwnedType<BEI128>, CboRoaringTreemapCodec>,
+) -> String {
     let mut snap = String::new();
     let iter = db.iter(rtxn).unwrap();
     for next in iter {
         let (_timestamp, task_ids) = next.unwrap();
-        snap.push_str(&format!("[timestamp] {}\n", snapshot_bitmap(&task_ids)));
+        snap.push_str(&format!("[timestamp] {}\n", snapshot_treemap(&task_ids)));
     }
     snap
 }
@@ -218,42 +217,48 @@ fn snapshot_details(d: &Details) -> String {
 
 pub fn snapshot_status(
     rtxn: &RoTxn,
-    db: Database<SerdeBincode<Status>, RoaringBitmapCodec>,
+    db: Database<SerdeBincode<Status>, RoaringTreemapCodec>,
 ) -> String {
     let mut snap = String::new();
     let iter = db.iter(rtxn).unwrap();
     for next in iter {
         let (status, task_ids) = next.unwrap();
-        writeln!(snap, "{status} {}", snapshot_bitmap(&task_ids)).unwrap();
+        writeln!(snap, "{status} {}", snapshot_treemap(&task_ids)).unwrap();
     }
     snap
 }
-pub fn snapshot_kind(rtxn: &RoTxn, db: Database<SerdeBincode<Kind>, RoaringBitmapCodec>) -> String {
+pub fn snapshot_kind(
+    rtxn: &RoTxn,
+    db: Database<SerdeBincode<Kind>, RoaringTreemapCodec>,
+) -> String {
     let mut snap = String::new();
     let iter = db.iter(rtxn).unwrap();
     for next in iter {
         let (kind, task_ids) = next.unwrap();
         let kind = serde_json::to_string(&kind).unwrap();
-        writeln!(snap, "{kind} {}", snapshot_bitmap(&task_ids)).unwrap();
+        writeln!(snap, "{kind} {}", snapshot_treemap(&task_ids)).unwrap();
     }
     snap
 }
 
-pub fn snapshot_index_tasks(rtxn: &RoTxn, db: Database<Str, RoaringBitmapCodec>) -> String {
+pub fn snapshot_index_tasks(rtxn: &RoTxn, db: Database<Str, RoaringTreemapCodec>) -> String {
     let mut snap = String::new();
     let iter = db.iter(rtxn).unwrap();
     for next in iter {
         let (index, task_ids) = next.unwrap();
-        writeln!(snap, "{index} {}", snapshot_bitmap(&task_ids)).unwrap();
+        writeln!(snap, "{index} {}", snapshot_treemap(&task_ids)).unwrap();
     }
     snap
 }
-pub fn snapshot_canceled_by(rtxn: &RoTxn, db: Database<BEU32, RoaringBitmapCodec>) -> String {
+pub fn snapshot_canceled_by(
+    rtxn: &RoTxn,
+    db: Database<OwnedType<BEU64>, RoaringTreemapCodec>,
+) -> String {
     let mut snap = String::new();
     let iter = db.iter(rtxn).unwrap();
     for next in iter {
         let (kind, task_ids) = next.unwrap();
-        writeln!(snap, "{kind} {}", snapshot_bitmap(&task_ids)).unwrap();
+        writeln!(snap, "{kind} {}", snapshot_treemap(&task_ids)).unwrap();
     }
     snap
 }

index-scheduler/src/snapshots/lib.rs/cancel_enqueued_task/cancel_processed.snap

@@ -7,7 +7,7 @@ source: index-scheduler/src/lib.rs
 ----------------------------------------------------------------------
 ### All Tasks:
 0 {uid: 0, status: canceled, canceled_by: 1, details: { received_documents: 1, indexed_documents: Some(0) }, kind: DocumentAdditionOrUpdate { index_uid: "catto", primary_key: None, method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
-1 {uid: 1, status: succeeded, details: { matched_tasks: 1, canceled_tasks: Some(1), original_filter: "test_query" }, kind: TaskCancelation { query: "test_query", tasks: RoaringBitmap<[0]> }}
+1 {uid: 1, status: succeeded, details: { matched_tasks: 1, canceled_tasks: Some(1), original_filter: "test_query" }, kind: TaskCancelation { query: "test_query", tasks: RoaringTreemap<[0]> }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued []

index-scheduler/src/snapshots/lib.rs/cancel_enqueued_task/initial_tasks_enqueued.snap

@@ -7,7 +7,7 @@ source: index-scheduler/src/lib.rs
 ----------------------------------------------------------------------
 ### All Tasks:
 0 {uid: 0, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "catto", primary_key: None, method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
-1 {uid: 1, status: enqueued, details: { matched_tasks: 1, canceled_tasks: None, original_filter: "test_query" }, kind: TaskCancelation { query: "test_query", tasks: RoaringBitmap<[0]> }}
+1 {uid: 1, status: enqueued, details: { matched_tasks: 1, canceled_tasks: None, original_filter: "test_query" }, kind: TaskCancelation { query: "test_query", tasks: RoaringTreemap<[0]> }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued [0,1,]

index-scheduler/src/snapshots/lib.rs/cancel_mix_of_tasks/aborted_indexation.snap

@@ -9,7 +9,7 @@ source: index-scheduler/src/lib.rs
 0 {uid: 0, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "catto", primary_key: None, method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
 1 {uid: 1, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "beavero", primary_key: None, method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
 2 {uid: 2, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "wolfo", primary_key: None, method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000002, documents_count: 1, allow_index_creation: true }}
-3 {uid: 3, status: enqueued, details: { matched_tasks: 3, canceled_tasks: None, original_filter: "test_query" }, kind: TaskCancelation { query: "test_query", tasks: RoaringBitmap<[0, 1, 2]> }}
+3 {uid: 3, status: enqueued, details: { matched_tasks: 3, canceled_tasks: None, original_filter: "test_query" }, kind: TaskCancelation { query: "test_query", tasks: RoaringTreemap<[0, 1, 2]> }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued [1,2,3,]

index-scheduler/src/snapshots/lib.rs/cancel_mix_of_tasks/cancel_processed.snap

@@ -9,7 +9,7 @@ source: index-scheduler/src/lib.rs
 0 {uid: 0, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "catto", primary_key: None, method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
 1 {uid: 1, status: canceled, canceled_by: 3, details: { received_documents: 1, indexed_documents: Some(0) }, kind: DocumentAdditionOrUpdate { index_uid: "beavero", primary_key: None, method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
 2 {uid: 2, status: canceled, canceled_by: 3, details: { received_documents: 1, indexed_documents: Some(0) }, kind: DocumentAdditionOrUpdate { index_uid: "wolfo", primary_key: None, method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000002, documents_count: 1, allow_index_creation: true }}
-3 {uid: 3, status: succeeded, details: { matched_tasks: 3, canceled_tasks: Some(2), original_filter: "test_query" }, kind: TaskCancelation { query: "test_query", tasks: RoaringBitmap<[0, 1, 2]> }}
+3 {uid: 3, status: succeeded, details: { matched_tasks: 3, canceled_tasks: Some(2), original_filter: "test_query" }, kind: TaskCancelation { query: "test_query", tasks: RoaringTreemap<[0, 1, 2]> }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued []

index-scheduler/src/snapshots/lib.rs/cancel_mix_of_tasks/processing_second_task_cancel_enqueued.snap

@@ -9,7 +9,7 @@ source: index-scheduler/src/lib.rs
 0 {uid: 0, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "catto", primary_key: None, method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
 1 {uid: 1, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "beavero", primary_key: None, method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
 2 {uid: 2, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "wolfo", primary_key: None, method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000002, documents_count: 1, allow_index_creation: true }}
-3 {uid: 3, status: enqueued, details: { matched_tasks: 3, canceled_tasks: None, original_filter: "test_query" }, kind: TaskCancelation { query: "test_query", tasks: RoaringBitmap<[0, 1, 2]> }}
+3 {uid: 3, status: enqueued, details: { matched_tasks: 3, canceled_tasks: None, original_filter: "test_query" }, kind: TaskCancelation { query: "test_query", tasks: RoaringTreemap<[0, 1, 2]> }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued [1,2,3,]

index-scheduler/src/snapshots/lib.rs/cancel_processing_dump/after_dump_register.snap

@@ -1,35 +0,0 @@
----
-source: index-scheduler/src/lib.rs
----
-### Autobatching Enabled = true
-### Processing Tasks:
-[]
-----------------------------------------------------------------------
-### All Tasks:
-0 {uid: 0, status: enqueued, details: { dump_uid: None }, kind: DumpCreation { keys: [], instance_uid: None }}
-----------------------------------------------------------------------
-### Status:
-enqueued [0,]
-----------------------------------------------------------------------
-### Kind:
-"dumpCreation" [0,]
-----------------------------------------------------------------------
-### Index Tasks:
-----------------------------------------------------------------------
-### Index Mapper:
-
-----------------------------------------------------------------------
-### Canceled By:
-
-----------------------------------------------------------------------
-### Enqueued At:
-[timestamp] [0,]
-----------------------------------------------------------------------
-### Started At:
-----------------------------------------------------------------------
-### Finished At:
-----------------------------------------------------------------------
-### File Store:
-
-----------------------------------------------------------------------
-

index-scheduler/src/snapshots/lib.rs/cancel_processing_dump/cancel_processed.snap

@@ -1,45 +0,0 @@
----
-source: index-scheduler/src/lib.rs
----
-### Autobatching Enabled = true
-### Processing Tasks:
-[]
-----------------------------------------------------------------------
-### All Tasks:
-0 {uid: 0, status: canceled, canceled_by: 1, details: { dump_uid: None }, kind: DumpCreation { keys: [], instance_uid: None }}
-1 {uid: 1, status: succeeded, details: { matched_tasks: 1, canceled_tasks: Some(0), original_filter: "cancel dump" }, kind: TaskCancelation { query: "cancel dump", tasks: RoaringBitmap<[0]> }}
-----------------------------------------------------------------------
-### Status:
-enqueued []
-succeeded [1,]
-canceled [0,]
-----------------------------------------------------------------------
-### Kind:
-"taskCancelation" [1,]
-"dumpCreation" [0,]
-----------------------------------------------------------------------
-### Index Tasks:
-----------------------------------------------------------------------
-### Index Mapper:
-
-----------------------------------------------------------------------
-### Canceled By:
-1 [0,]
-
-----------------------------------------------------------------------
-### Enqueued At:
-[timestamp] [0,]
-[timestamp] [1,]
-----------------------------------------------------------------------
-### Started At:
-[timestamp] [0,]
-[timestamp] [1,]
-----------------------------------------------------------------------
-### Finished At:
-[timestamp] [0,]
-[timestamp] [1,]
-----------------------------------------------------------------------
-### File Store:
-
-----------------------------------------------------------------------
-

index-scheduler/src/snapshots/lib.rs/cancel_processing_dump/cancel_registered.snap

@@ -1,38 +0,0 @@
----
-source: index-scheduler/src/lib.rs
----
-### Autobatching Enabled = true
-### Processing Tasks:
-[0,]
-----------------------------------------------------------------------
-### All Tasks:
-0 {uid: 0, status: enqueued, details: { dump_uid: None }, kind: DumpCreation { keys: [], instance_uid: None }}
-1 {uid: 1, status: enqueued, details: { matched_tasks: 1, canceled_tasks: None, original_filter: "cancel dump" }, kind: TaskCancelation { query: "cancel dump", tasks: RoaringBitmap<[0]> }}
-----------------------------------------------------------------------
-### Status:
-enqueued [0,1,]
-----------------------------------------------------------------------
-### Kind:
-"taskCancelation" [1,]
-"dumpCreation" [0,]
-----------------------------------------------------------------------
-### Index Tasks:
-----------------------------------------------------------------------
-### Index Mapper:
-
-----------------------------------------------------------------------
-### Canceled By:
-
-----------------------------------------------------------------------
-### Enqueued At:
-[timestamp] [0,]
-[timestamp] [1,]
-----------------------------------------------------------------------
-### Started At:
-----------------------------------------------------------------------
-### Finished At:
-----------------------------------------------------------------------
-### File Store:
-
-----------------------------------------------------------------------
-

index-scheduler/src/snapshots/lib.rs/cancel_processing_task/aborted_indexation.snap

@@ -7,7 +7,7 @@ source: index-scheduler/src/lib.rs
 ----------------------------------------------------------------------
 ### All Tasks:
 0 {uid: 0, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "catto", primary_key: None, method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
-1 {uid: 1, status: enqueued, details: { matched_tasks: 1, canceled_tasks: None, original_filter: "test_query" }, kind: TaskCancelation { query: "test_query", tasks: RoaringBitmap<[0]> }}
+1 {uid: 1, status: enqueued, details: { matched_tasks: 1, canceled_tasks: None, original_filter: "test_query" }, kind: TaskCancelation { query: "test_query", tasks: RoaringTreemap<[0]> }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued [0,1,]

index-scheduler/src/snapshots/lib.rs/cancel_processing_task/cancel_processed.snap

@@ -7,7 +7,7 @@ source: index-scheduler/src/lib.rs
 ----------------------------------------------------------------------
 ### All Tasks:
 0 {uid: 0, status: canceled, canceled_by: 1, details: { received_documents: 1, indexed_documents: Some(0) }, kind: DocumentAdditionOrUpdate { index_uid: "catto", primary_key: None, method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
-1 {uid: 1, status: succeeded, details: { matched_tasks: 1, canceled_tasks: Some(1), original_filter: "test_query" }, kind: TaskCancelation { query: "test_query", tasks: RoaringBitmap<[0]> }}
+1 {uid: 1, status: succeeded, details: { matched_tasks: 1, canceled_tasks: Some(1), original_filter: "test_query" }, kind: TaskCancelation { query: "test_query", tasks: RoaringTreemap<[0]> }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued []

index-scheduler/src/snapshots/lib.rs/cancel_processing_task/cancel_task_registered.snap

@@ -7,7 +7,7 @@ source: index-scheduler/src/lib.rs
 ----------------------------------------------------------------------
 ### All Tasks:
 0 {uid: 0, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "catto", primary_key: None, method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
-1 {uid: 1, status: enqueued, details: { matched_tasks: 1, canceled_tasks: None, original_filter: "test_query" }, kind: TaskCancelation { query: "test_query", tasks: RoaringBitmap<[0]> }}
+1 {uid: 1, status: enqueued, details: { matched_tasks: 1, canceled_tasks: None, original_filter: "test_query" }, kind: TaskCancelation { query: "test_query", tasks: RoaringTreemap<[0]> }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued [0,1,]

index-scheduler/src/snapshots/lib.rs/cancel_succeeded_task/cancel_processed.snap

@@ -7,7 +7,7 @@ source: index-scheduler/src/lib.rs
 ----------------------------------------------------------------------
 ### All Tasks:
 0 {uid: 0, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "catto", primary_key: None, method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
-1 {uid: 1, status: succeeded, details: { matched_tasks: 1, canceled_tasks: Some(0), original_filter: "test_query" }, kind: TaskCancelation { query: "test_query", tasks: RoaringBitmap<[0]> }}
+1 {uid: 1, status: succeeded, details: { matched_tasks: 1, canceled_tasks: Some(0), original_filter: "test_query" }, kind: TaskCancelation { query: "test_query", tasks: RoaringTreemap<[0]> }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued []

index-scheduler/src/snapshots/lib.rs/query_tasks_canceled_by/start.snap

@@ -9,7 +9,7 @@ source: index-scheduler/src/lib.rs
 0 {uid: 0, status: succeeded, details: { primary_key: Some("mouse") }, kind: IndexCreation { index_uid: "catto", primary_key: Some("mouse") }}
 1 {uid: 1, status: canceled, canceled_by: 3, details: { primary_key: Some("sheep") }, kind: IndexCreation { index_uid: "doggo", primary_key: Some("sheep") }}
 2 {uid: 2, status: canceled, canceled_by: 3, details: { swaps: [IndexSwap { indexes: ("catto", "doggo") }] }, kind: IndexSwap { swaps: [IndexSwap { indexes: ("catto", "doggo") }] }}
-3 {uid: 3, status: succeeded, details: { matched_tasks: 3, canceled_tasks: Some(0), original_filter: "test_query" }, kind: TaskCancelation { query: "test_query", tasks: RoaringBitmap<[0, 1, 2]> }}
+3 {uid: 3, status: succeeded, details: { matched_tasks: 3, canceled_tasks: Some(0), original_filter: "test_query" }, kind: TaskCancelation { query: "test_query", tasks: RoaringTreemap<[0, 1, 2]> }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued []

index-scheduler/src/snapshots/lib.rs/task_deletion_delete_same_task_twice/task_deletion_processed.snap

@@ -7,8 +7,8 @@ source: index-scheduler/src/lib.rs
 ----------------------------------------------------------------------
 ### All Tasks:
 1 {uid: 1, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggo", primary_key: Some("bone"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
-2 {uid: 2, status: succeeded, details: { matched_tasks: 1, deleted_tasks: Some(1), original_filter: "test_query" }, kind: TaskDeletion { query: "test_query", tasks: RoaringBitmap<[0]> }}
-3 {uid: 3, status: succeeded, details: { matched_tasks: 1, deleted_tasks: Some(0), original_filter: "test_query" }, kind: TaskDeletion { query: "test_query", tasks: RoaringBitmap<[0]> }}
+2 {uid: 2, status: succeeded, details: { matched_tasks: 1, deleted_tasks: Some(1), original_filter: "test_query" }, kind: TaskDeletion { query: "test_query", tasks: RoaringTreemap<[0]> }}
+3 {uid: 3, status: succeeded, details: { matched_tasks: 1, deleted_tasks: Some(0), original_filter: "test_query" }, kind: TaskDeletion { query: "test_query", tasks: RoaringTreemap<[0]> }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued [1,]

index-scheduler/src/snapshots/lib.rs/task_deletion_deleteable/after_registering_the_task_deletion.snap

@@ -8,7 +8,7 @@ source: index-scheduler/src/lib.rs
 ### All Tasks:
 0 {uid: 0, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "catto", primary_key: None, method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
 1 {uid: 1, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggo", primary_key: Some("bone"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
-2 {uid: 2, status: enqueued, details: { matched_tasks: 1, deleted_tasks: None, original_filter: "test_query" }, kind: TaskDeletion { query: "test_query", tasks: RoaringBitmap<[0]> }}
+2 {uid: 2, status: enqueued, details: { matched_tasks: 1, deleted_tasks: None, original_filter: "test_query" }, kind: TaskDeletion { query: "test_query", tasks: RoaringTreemap<[0]> }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued [1,2,]

index-scheduler/src/snapshots/lib.rs/task_deletion_deleteable/task_deletion_processed.snap

@@ -7,7 +7,7 @@ source: index-scheduler/src/lib.rs
 ----------------------------------------------------------------------
 ### All Tasks:
 1 {uid: 1, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggo", primary_key: Some("bone"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
-2 {uid: 2, status: succeeded, details: { matched_tasks: 1, deleted_tasks: Some(1), original_filter: "test_query" }, kind: TaskDeletion { query: "test_query", tasks: RoaringBitmap<[0]> }}
+2 {uid: 2, status: succeeded, details: { matched_tasks: 1, deleted_tasks: Some(1), original_filter: "test_query" }, kind: TaskDeletion { query: "test_query", tasks: RoaringTreemap<[0]> }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued [1,]

index-scheduler/src/snapshots/lib.rs/task_deletion_undeleteable/task_deletion_done.snap

@@ -9,7 +9,7 @@ source: index-scheduler/src/lib.rs
 0 {uid: 0, status: enqueued, details: { primary_key: Some("mouse") }, kind: IndexCreation { index_uid: "catto", primary_key: Some("mouse") }}
 1 {uid: 1, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "catto", primary_key: None, method: ReplaceDocuments, 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: "doggo", primary_key: Some("bone"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
-3 {uid: 3, status: succeeded, details: { matched_tasks: 2, deleted_tasks: Some(0), original_filter: "test_query" }, kind: TaskDeletion { query: "test_query", tasks: RoaringBitmap<[0, 1]> }}
+3 {uid: 3, status: succeeded, details: { matched_tasks: 2, deleted_tasks: Some(0), original_filter: "test_query" }, kind: TaskDeletion { query: "test_query", tasks: RoaringTreemap<[0, 1]> }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued [0,1,2,]

index-scheduler/src/snapshots/lib.rs/task_deletion_undeleteable/task_deletion_enqueued.snap

@@ -9,7 +9,7 @@ source: index-scheduler/src/lib.rs
 0 {uid: 0, status: enqueued, details: { primary_key: Some("mouse") }, kind: IndexCreation { index_uid: "catto", primary_key: Some("mouse") }}
 1 {uid: 1, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "catto", primary_key: None, method: ReplaceDocuments, 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: "doggo", primary_key: Some("bone"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
-3 {uid: 3, status: enqueued, details: { matched_tasks: 2, deleted_tasks: None, original_filter: "test_query" }, kind: TaskDeletion { query: "test_query", tasks: RoaringBitmap<[0, 1]> }}
+3 {uid: 3, status: enqueued, details: { matched_tasks: 2, deleted_tasks: None, original_filter: "test_query" }, kind: TaskDeletion { query: "test_query", tasks: RoaringTreemap<[0, 1]> }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued [0,1,2,3,]

index-scheduler/src/snapshots/lib.rs/task_deletion_undeleteable/task_deletion_processing.snap

@@ -9,7 +9,7 @@ source: index-scheduler/src/lib.rs
 0 {uid: 0, status: enqueued, details: { primary_key: Some("mouse") }, kind: IndexCreation { index_uid: "catto", primary_key: Some("mouse") }}
 1 {uid: 1, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "catto", primary_key: None, method: ReplaceDocuments, 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: "doggo", primary_key: Some("bone"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
-3 {uid: 3, status: enqueued, details: { matched_tasks: 2, deleted_tasks: None, original_filter: "test_query" }, kind: TaskDeletion { query: "test_query", tasks: RoaringBitmap<[0, 1]> }}
+3 {uid: 3, status: enqueued, details: { matched_tasks: 2, deleted_tasks: None, original_filter: "test_query" }, kind: TaskDeletion { query: "test_query", tasks: RoaringTreemap<[0, 1]> }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued [0,1,2,3,]

index-scheduler/src/snapshots/lib.rs/test_auto_deletion_of_tasks/after_the_second_task_deletion.snap

@@ -41,6 +41,18 @@ source: index-scheduler/src/lib.rs
       "taskDeletion": {
         "query": "[query]",
         "tasks": [
+          1,
+          0,
+          0,
+          0,
+          0,
+          0,
+          0,
+          0,
+          0,
+          0,
+          0,
+          0,
           58,
           48,
           0,

index-scheduler/src/snapshots/lib.rs/test_auto_deletion_of_tasks/everything_has_been_processed.snap

@@ -21,6 +21,18 @@ source: index-scheduler/src/lib.rs
       "taskDeletion": {
         "query": "[query]",
         "tasks": [
+          1,
+          0,
+          0,
+          0,
+          0,
+          0,
+          0,
+          0,
+          0,
+          0,
+          0,
+          0,
           58,
           48,
           0,

index-scheduler/src/snapshots/lib.rs/test_auto_deletion_of_tasks/task_deletion_have_been_enqueued.snap

@@ -106,6 +106,18 @@ source: index-scheduler/src/lib.rs
       "taskDeletion": {
         "query": "[query]",
         "tasks": [
+          1,
+          0,
+          0,
+          0,
+          0,
+          0,
+          0,
+          0,
+          0,
+          0,
+          0,
+          0,
           58,
           48,
           0,

index-scheduler/src/snapshots/lib.rs/test_auto_deletion_of_tasks/task_deletion_have_been_processed.snap

@@ -61,6 +61,18 @@ source: index-scheduler/src/lib.rs
       "taskDeletion": {
         "query": "[query]",
         "tasks": [
+          1,
+          0,
+          0,
+          0,
+          0,
+          0,
+          0,
+          0,
+          0,
+          0,
+          0,
+          0,
           58,
           48,
           0,

index-scheduler/src/utils.rs

@@ -3,22 +3,23 @@
 use std::collections::{BTreeSet, HashSet};
 use std::ops::Bound;
 
-use meilisearch_types::heed::types::DecodeIgnore;
+use meilisearch_types::heed::types::{DecodeIgnore, OwnedType};
 use meilisearch_types::heed::{Database, RoTxn, RwTxn};
-use meilisearch_types::milli::CboRoaringBitmapCodec;
+use meilisearch_types::milli::heed_codec::CboRoaringTreemapCodec;
+use meilisearch_types::milli::BEU64;
 use meilisearch_types::tasks::{Details, IndexSwap, Kind, KindWithContent, Status};
-use roaring::{MultiOps, RoaringBitmap};
+use roaring::{MultiOps, RoaringTreemap};
 use time::OffsetDateTime;
 
 use crate::{Error, IndexScheduler, Result, Task, TaskId, BEI128};
 
 impl IndexScheduler {
-    pub(crate) fn all_task_ids(&self, rtxn: &RoTxn) -> Result<RoaringBitmap> {
+    pub(crate) fn all_task_ids(&self, rtxn: &RoTxn) -> Result<RoaringTreemap> {
         enum_iterator::all().map(|s| self.get_status(rtxn, s)).union()
     }
 
     pub(crate) fn last_task_id(&self, rtxn: &RoTxn) -> Result<Option<TaskId>> {
-        Ok(self.all_tasks.remap_data_type::<DecodeIgnore>().last(rtxn)?.map(|(k, _)| k + 1))
+        Ok(self.all_tasks.remap_data_type::<DecodeIgnore>().last(rtxn)?.map(|(k, _)| k.get() + 1))
     }
 
     pub(crate) fn next_task_id(&self, rtxn: &RoTxn) -> Result<TaskId> {
@@ -26,7 +27,7 @@ impl IndexScheduler {
     }
 
     pub(crate) fn get_task(&self, rtxn: &RoTxn, task_id: TaskId) -> Result<Option<Task>> {
-        Ok(self.all_tasks.get(rtxn, &task_id)?)
+        Ok(self.all_tasks.get(rtxn, &BEU64::new(task_id))?)
     }
 
     /// Convert an iterator to a `Vec` of tasks. The tasks MUST exist or a
@@ -88,12 +89,12 @@ impl IndexScheduler {
             }
         }
 
-        self.all_tasks.put(wtxn, &task.uid, task)?;
+        self.all_tasks.put(wtxn, &BEU64::new(task.uid), task)?;
         Ok(())
     }
 
     /// Returns the whole set of tasks that belongs to this index.
-    pub(crate) fn index_tasks(&self, rtxn: &RoTxn, index: &str) -> Result<RoaringBitmap> {
+    pub(crate) fn index_tasks(&self, rtxn: &RoTxn, index: &str) -> Result<RoaringTreemap> {
         Ok(self.index_tasks.get(rtxn, index)?.unwrap_or_default())
     }
 
@@ -101,7 +102,7 @@ impl IndexScheduler {
         &self,
         wtxn: &mut RwTxn,
         index: &str,
-        f: impl Fn(&mut RoaringBitmap),
+        f: impl Fn(&mut RoaringTreemap),
     ) -> Result<()> {
         let mut tasks = self.index_tasks(wtxn, index)?;
         f(&mut tasks);
@@ -114,7 +115,7 @@ impl IndexScheduler {
         Ok(())
     }
 
-    pub(crate) fn get_status(&self, rtxn: &RoTxn, status: Status) -> Result<RoaringBitmap> {
+    pub(crate) fn get_status(&self, rtxn: &RoTxn, status: Status) -> Result<RoaringTreemap> {
         Ok(self.status.get(rtxn, &status)?.unwrap_or_default())
     }
 
@@ -122,7 +123,7 @@ impl IndexScheduler {
         &self,
         wtxn: &mut RwTxn,
         status: Status,
-        bitmap: &RoaringBitmap,
+        bitmap: &RoaringTreemap,
     ) -> Result<()> {
         Ok(self.status.put(wtxn, &status, bitmap)?)
     }
@@ -131,7 +132,7 @@ impl IndexScheduler {
         &self,
         wtxn: &mut RwTxn,
         status: Status,
-        f: impl Fn(&mut RoaringBitmap),
+        f: impl Fn(&mut RoaringTreemap),
     ) -> Result<()> {
         let mut tasks = self.get_status(wtxn, status)?;
         f(&mut tasks);
@@ -140,7 +141,7 @@ impl IndexScheduler {
         Ok(())
     }
 
-    pub(crate) fn get_kind(&self, rtxn: &RoTxn, kind: Kind) -> Result<RoaringBitmap> {
+    pub(crate) fn get_kind(&self, rtxn: &RoTxn, kind: Kind) -> Result<RoaringTreemap> {
         Ok(self.kind.get(rtxn, &kind)?.unwrap_or_default())
     }
 
@@ -148,7 +149,7 @@ impl IndexScheduler {
         &self,
         wtxn: &mut RwTxn,
         kind: Kind,
-        bitmap: &RoaringBitmap,
+        bitmap: &RoaringTreemap,
     ) -> Result<()> {
         Ok(self.kind.put(wtxn, &kind, bitmap)?)
     }
@@ -157,7 +158,7 @@ impl IndexScheduler {
         &self,
         wtxn: &mut RwTxn,
         kind: Kind,
-        f: impl Fn(&mut RoaringBitmap),
+        f: impl Fn(&mut RoaringTreemap),
     ) -> Result<()> {
         let mut tasks = self.get_kind(wtxn, kind)?;
         f(&mut tasks);
@@ -169,30 +170,30 @@ impl IndexScheduler {
 
 pub(crate) fn insert_task_datetime(
     wtxn: &mut RwTxn,
-    database: Database<BEI128, CboRoaringBitmapCodec>,
+    database: Database<OwnedType<BEI128>, CboRoaringTreemapCodec>,
     time: OffsetDateTime,
     task_id: TaskId,
 ) -> Result<()> {
-    let timestamp = time.unix_timestamp_nanos();
+    let timestamp = BEI128::new(time.unix_timestamp_nanos());
     let mut task_ids = database.get(wtxn, &timestamp)?.unwrap_or_default();
     task_ids.insert(task_id);
-    database.put(wtxn, &timestamp, &RoaringBitmap::from_iter(task_ids))?;
+    database.put(wtxn, &timestamp, &RoaringTreemap::from_iter(task_ids))?;
     Ok(())
 }
 
 pub(crate) fn remove_task_datetime(
     wtxn: &mut RwTxn,
-    database: Database<BEI128, CboRoaringBitmapCodec>,
+    database: Database<OwnedType<BEI128>, CboRoaringTreemapCodec>,
     time: OffsetDateTime,
     task_id: TaskId,
 ) -> Result<()> {
-    let timestamp = time.unix_timestamp_nanos();
+    let timestamp = BEI128::new(time.unix_timestamp_nanos());
     if let Some(mut existing) = database.get(wtxn, &timestamp)? {
         existing.remove(task_id);
         if existing.is_empty() {
             database.delete(wtxn, &timestamp)?;
         } else {
-            database.put(wtxn, &timestamp, &RoaringBitmap::from_iter(existing))?;
+            database.put(wtxn, &timestamp, &RoaringTreemap::from_iter(existing))?;
         }
     }
 
@@ -201,8 +202,8 @@ pub(crate) fn remove_task_datetime(
 
 pub(crate) fn keep_tasks_within_datetimes(
     rtxn: &RoTxn,
-    tasks: &mut RoaringBitmap,
-    database: Database<BEI128, CboRoaringBitmapCodec>,
+    tasks: &mut RoaringTreemap,
+    database: Database<OwnedType<BEI128>, CboRoaringTreemapCodec>,
     after: Option<OffsetDateTime>,
     before: Option<OffsetDateTime>,
 ) -> Result<()> {
@@ -212,9 +213,9 @@ pub(crate) fn keep_tasks_within_datetimes(
         (Some(after), None) => (Bound::Excluded(*after), Bound::Unbounded),
         (Some(after), Some(before)) => (Bound::Excluded(*after), Bound::Excluded(*before)),
     };
-    let mut collected_task_ids = RoaringBitmap::new();
-    let start = map_bound(start, |b| b.unix_timestamp_nanos());
-    let end = map_bound(end, |b| b.unix_timestamp_nanos());
+    let mut collected_task_ids = RoaringTreemap::new();
+    let start = map_bound(start, |b| BEI128::new(b.unix_timestamp_nanos()));
+    let end = map_bound(end, |b| BEI128::new(b.unix_timestamp_nanos()));
     let iter = database.range(rtxn, &(start, end))?;
     for r in iter {
         let (_timestamp, task_ids) = r?;
@@ -337,6 +338,8 @@ impl IndexScheduler {
         let rtxn = self.env.read_txn().unwrap();
         for task in self.all_tasks.iter(&rtxn).unwrap() {
             let (task_id, task) = task.unwrap();
+            let task_id = task_id.get();
+
             let task_index_uid = task.index_uid().map(ToOwned::to_owned);
 
             let Task {
@@ -359,13 +362,16 @@ impl IndexScheduler {
                     .unwrap()
                     .contains(task.uid));
             }
-            let db_enqueued_at =
-                self.enqueued_at.get(&rtxn, &enqueued_at.unix_timestamp_nanos()).unwrap().unwrap();
+            let db_enqueued_at = self
+                .enqueued_at
+                .get(&rtxn, &BEI128::new(enqueued_at.unix_timestamp_nanos()))
+                .unwrap()
+                .unwrap();
             assert!(db_enqueued_at.contains(task_id));
             if let Some(started_at) = started_at {
                 let db_started_at = self
                     .started_at
-                    .get(&rtxn, &started_at.unix_timestamp_nanos())
+                    .get(&rtxn, &BEI128::new(started_at.unix_timestamp_nanos()))
                     .unwrap()
                     .unwrap();
                 assert!(db_started_at.contains(task_id));
@@ -373,7 +379,7 @@ impl IndexScheduler {
             if let Some(finished_at) = finished_at {
                 let db_finished_at = self
                     .finished_at
-                    .get(&rtxn, &finished_at.unix_timestamp_nanos())
+                    .get(&rtxn, &BEI128::new(finished_at.unix_timestamp_nanos()))
                     .unwrap()
                     .unwrap();
                 assert!(db_finished_at.contains(task_id));

index-scheduler/src/uuid_codec.rs

@@ -1,7 +1,7 @@
 use std::borrow::Cow;
 use std::convert::TryInto;
 
-use meilisearch_types::heed::{BoxedError, BytesDecode, BytesEncode};
+use meilisearch_types::heed::{BytesDecode, BytesEncode};
 use uuid::Uuid;
 
 /// A heed codec for value of struct Uuid.
@@ -10,15 +10,15 @@ pub struct UuidCodec;
 impl<'a> BytesDecode<'a> for UuidCodec {
     type DItem = Uuid;
 
-    fn bytes_decode(bytes: &'a [u8]) -> Result<Self::DItem, BoxedError> {
-        bytes.try_into().map(Uuid::from_bytes).map_err(Into::into)
+    fn bytes_decode(bytes: &'a [u8]) -> Option<Self::DItem> {
+        bytes.try_into().ok().map(Uuid::from_bytes)
     }
 }
 
 impl BytesEncode<'_> for UuidCodec {
     type EItem = Uuid;
 
-    fn bytes_encode(item: &Self::EItem) -> Result<Cow<[u8]>, BoxedError> {
-        Ok(Cow::Borrowed(item.as_bytes()))
+    fn bytes_encode(item: &Self::EItem) -> Option<Cow<[u8]>> {
+        Some(Cow::Borrowed(item.as_bytes()))
     }
 }

meilisearch-auth/src/store.rs

@@ -4,20 +4,17 @@ use std::collections::HashSet;
 use std::convert::{TryFrom, TryInto};
 use std::fs::create_dir_all;
 use std::path::Path;
-use std::result::Result as StdResult;
 use std::str;
 use std::str::FromStr;
 use std::sync::Arc;
 
 use hmac::{Hmac, Mac};
-use meilisearch_types::heed::BoxedError;
 use meilisearch_types::index_uid_pattern::IndexUidPattern;
 use meilisearch_types::keys::KeyId;
 use meilisearch_types::milli;
-use meilisearch_types::milli::heed::types::{Bytes, DecodeIgnore, SerdeJson};
+use meilisearch_types::milli::heed::types::{ByteSlice, DecodeIgnore, SerdeJson};
 use meilisearch_types::milli::heed::{Database, Env, EnvOpenOptions, RwTxn};
 use sha2::Sha256;
-use thiserror::Error;
 use time::OffsetDateTime;
 use uuid::fmt::Hyphenated;
 use uuid::Uuid;
@@ -33,7 +30,7 @@ const KEY_ID_ACTION_INDEX_EXPIRATION_DB_NAME: &str = "keyid-action-index-expirat
 #[derive(Clone)]
 pub struct HeedAuthStore {
     env: Arc<Env>,
-    keys: Database<Bytes, SerdeJson<Key>>,
+    keys: Database<ByteSlice, SerdeJson<Key>>,
     action_keyid_index_expiration: Database<KeyIdActionCodec, SerdeJson<Option<OffsetDateTime>>>,
     should_close_on_drop: bool,
 }
@@ -132,9 +129,6 @@ impl HeedAuthStore {
                 Action::DumpsAll => {
                     actions.insert(Action::DumpsCreate);
                 }
-                Action::SnapshotsAll => {
-                    actions.insert(Action::SnapshotsCreate);
-                }
                 Action::TasksAll => {
                     actions.extend([Action::TasksGet, Action::TasksDelete, Action::TasksCancel]);
                 }
@@ -279,7 +273,7 @@ impl HeedAuthStore {
     fn delete_key_from_inverted_db(&self, wtxn: &mut RwTxn, key: &KeyId) -> Result<()> {
         let mut iter = self
             .action_keyid_index_expiration
-            .remap_types::<Bytes, DecodeIgnore>()
+            .remap_types::<ByteSlice, DecodeIgnore>()
             .prefix_iter_mut(wtxn, key.as_bytes())?;
         while iter.next().transpose()?.is_some() {
             // safety: we don't keep references from inside the LMDB database.
@@ -297,24 +291,23 @@ pub struct KeyIdActionCodec;
 impl<'a> milli::heed::BytesDecode<'a> for KeyIdActionCodec {
     type DItem = (KeyId, Action, Option<&'a [u8]>);
 
-    fn bytes_decode(bytes: &'a [u8]) -> StdResult<Self::DItem, BoxedError> {
-        let (key_id_bytes, action_bytes) = try_split_array_at(bytes).ok_or(SliceTooShortError)?;
-        let (&action_byte, index) =
-            match try_split_array_at(action_bytes).ok_or(SliceTooShortError)? {
-                ([action], []) => (action, None),
-                ([action], index) => (action, Some(index)),
-            };
+    fn bytes_decode(bytes: &'a [u8]) -> Option<Self::DItem> {
+        let (key_id_bytes, action_bytes) = try_split_array_at(bytes)?;
+        let (action_bytes, index) = match try_split_array_at(action_bytes)? {
+            (action, []) => (action, None),
+            (action, index) => (action, Some(index)),
+        };
         let key_id = Uuid::from_bytes(*key_id_bytes);
-        let action = Action::from_repr(action_byte).ok_or(InvalidActionError { action_byte })?;
+        let action = Action::from_repr(u8::from_be_bytes(*action_bytes))?;
 
-        Ok((key_id, action, index))
+        Some((key_id, action, index))
     }
 }
 
 impl<'a> milli::heed::BytesEncode<'a> for KeyIdActionCodec {
     type EItem = (&'a KeyId, &'a Action, Option<&'a [u8]>);
 
-    fn bytes_encode((key_id, action, index): &Self::EItem) -> StdResult<Cow<[u8]>, BoxedError> {
+    fn bytes_encode((key_id, action, index): &Self::EItem) -> Option<Cow<[u8]>> {
         let mut bytes = Vec::new();
 
         bytes.extend_from_slice(key_id.as_bytes());
@@ -324,20 +317,10 @@ impl<'a> milli::heed::BytesEncode<'a> for KeyIdActionCodec {
             bytes.extend_from_slice(index);
         }
 
-        Ok(Cow::Owned(bytes))
+        Some(Cow::Owned(bytes))
     }
 }
 
-#[derive(Error, Debug)]
-#[error("the slice is too short")]
-pub struct SliceTooShortError;
-
-#[derive(Error, Debug)]
-#[error("cannot construct a valid Action from {action_byte}")]
-pub struct InvalidActionError {
-    pub action_byte: u8,
-}
-
 pub fn generate_key_as_hexa(uid: Uuid, master_key: &[u8]) -> String {
     // format uid as hyphenated allowing user to generate their own keys.
     let mut uid_buffer = [0; Hyphenated::LENGTH];

meilisearch-types/Cargo.toml

@@ -15,7 +15,7 @@ actix-web = { version = "4.3.1", default-features = false }
 anyhow = "1.0.70"
 convert_case = "0.6.0"
 csv = "1.2.1"
-deserr = { version = "0.6.0", features = ["actix-web"] }
+deserr = { version = "0.6.0", features = ["actix-web"]}
 either = { version = "1.8.1", features = ["serde"] }
 enum-iterator = "1.4.0"
 file-store = { path = "../file-store" }
@@ -50,7 +50,6 @@ hebrew = ["milli/hebrew"]
 japanese = ["milli/japanese"]
 # thai specialized tokenization
 thai = ["milli/thai"]
+
 # allow greek specialized tokenization
 greek = ["milli/greek"]
-# allow khmer specialized tokenization
-khmer = ["milli/khmer"]

meilisearch-types/src/deserr/mod.rs

@@ -188,4 +188,3 @@ 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!(InvalidSearchSemanticRatio);

meilisearch-types/src/deserr/query_params.rs

@@ -104,6 +104,7 @@ macro_rules! impl_from_query_param_wrap_original_value_in_error {
 }
 impl_from_query_param_wrap_original_value_in_error!(usize, DeserrParseIntError);
 impl_from_query_param_wrap_original_value_in_error!(u32, DeserrParseIntError);
+impl_from_query_param_wrap_original_value_in_error!(u64, DeserrParseIntError);
 impl_from_query_param_wrap_original_value_in_error!(bool, DeserrParseBoolError);
 
 impl FromQueryParameter for String {

meilisearch-types/src/error.rs

@@ -222,8 +222,6 @@ InvalidVectorsType                    , InvalidRequest       , BAD_REQUEST ;
 InvalidDocumentId                     , InvalidRequest       , BAD_REQUEST ;
 InvalidDocumentLimit                  , InvalidRequest       , BAD_REQUEST ;
 InvalidDocumentOffset                 , InvalidRequest       , BAD_REQUEST ;
-InvalidEmbedder                       , InvalidRequest       , BAD_REQUEST ;
-InvalidHybridQuery                    , InvalidRequest       , BAD_REQUEST ;
 InvalidIndexLimit                     , InvalidRequest       , BAD_REQUEST ;
 InvalidIndexOffset                    , InvalidRequest       , BAD_REQUEST ;
 InvalidIndexPrimaryKey                , InvalidRequest       , BAD_REQUEST ;
@@ -235,7 +233,6 @@ InvalidSearchAttributesToRetrieve     , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchCropLength               , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchCropMarker               , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchFacets                   , InvalidRequest       , BAD_REQUEST ;
-InvalidSearchSemanticRatio            , InvalidRequest       , BAD_REQUEST ;
 InvalidFacetSearchFacetName           , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchFilter                   , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchHighlightPostTag         , InvalidRequest       , BAD_REQUEST ;
@@ -255,11 +252,9 @@ InvalidSearchShowRankingScoreDetails  , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchSort                     , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsDisplayedAttributes    , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsDistinctAttribute      , InvalidRequest       , BAD_REQUEST ;
-InvalidSettingsProximityPrecision     , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsFaceting               , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsFilterableAttributes   , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsPagination             , InvalidRequest       , BAD_REQUEST ;
-InvalidSettingsEmbedders              , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsRankingRules           , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsSearchableAttributes   , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsSortableAttributes     , InvalidRequest       , BAD_REQUEST ;
@@ -299,18 +294,15 @@ MissingFacetSearchFacetName           , InvalidRequest       , BAD_REQUEST ;
 MissingIndexUid                       , InvalidRequest       , BAD_REQUEST ;
 MissingMasterKey                      , Auth                 , UNAUTHORIZED ;
 MissingPayload                        , InvalidRequest       , BAD_REQUEST ;
-MissingSearchHybrid                   , InvalidRequest       , BAD_REQUEST ;
 MissingSwapIndexes                    , InvalidRequest       , BAD_REQUEST ;
 MissingTaskFilters                    , InvalidRequest       , BAD_REQUEST ;
 NoSpaceLeftOnDevice                   , System               , UNPROCESSABLE_ENTITY;
 PayloadTooLarge                       , InvalidRequest       , PAYLOAD_TOO_LARGE ;
 TaskNotFound                          , InvalidRequest       , NOT_FOUND ;
 TooManyOpenFiles                      , System               , UNPROCESSABLE_ENTITY ;
-TooManyVectors                        , InvalidRequest       , BAD_REQUEST ;
 UnretrievableDocument                 , Internal             , BAD_REQUEST ;
 UnretrievableErrorCode                , InvalidRequest       , BAD_REQUEST ;
-UnsupportedMediaType                  , InvalidRequest       , UNSUPPORTED_MEDIA_TYPE ;
-VectorEmbeddingError                  , InvalidRequest       , BAD_REQUEST
+UnsupportedMediaType                  , InvalidRequest       , UNSUPPORTED_MEDIA_TYPE
 }
 
 impl ErrorCode for JoinError {
@@ -332,6 +324,7 @@ impl ErrorCode for milli::Error {
                     UserError::SerdeJson(_)
                     | UserError::InvalidLmdbOpenOptions
                     | UserError::DocumentLimitReached
+                    | UserError::AccessingSoftDeletedDocument { .. }
                     | UserError::UnknownInternalDocumentId { .. } => Code::Internal,
                     UserError::InvalidStoreFile => Code::InvalidStoreFile,
                     UserError::NoSpaceLeftOnDevice => Code::NoSpaceLeftOnDevice,
@@ -343,13 +336,6 @@ impl ErrorCode for milli::Error {
                     UserError::InvalidDocumentId { .. } | UserError::TooManyDocumentIds { .. } => {
                         Code::InvalidDocumentId
                     }
-                    UserError::MissingDocumentField(_) => Code::InvalidDocumentFields,
-                    UserError::InvalidFieldForSource { .. }
-                    | UserError::MissingFieldForSource { .. }
-                    | UserError::InvalidOpenAiModel { .. }
-                    | UserError::InvalidPrompt(_) => Code::InvalidSettingsEmbedders,
-                    UserError::TooManyEmbedders(_) => Code::InvalidSettingsEmbedders,
-                    UserError::InvalidPromptForEmbeddings(..) => Code::InvalidSettingsEmbedders,
                     UserError::NoPrimaryKeyCandidateFound => Code::IndexPrimaryKeyNoCandidateFound,
                     UserError::MultiplePrimaryKeyCandidatesFound { .. } => {
                         Code::IndexPrimaryKeyMultipleCandidatesFound
@@ -367,15 +353,11 @@ impl ErrorCode for milli::Error {
                     UserError::CriterionError(_) => Code::InvalidSettingsRankingRules,
                     UserError::InvalidGeoField { .. } => Code::InvalidDocumentGeoField,
                     UserError::InvalidVectorDimensions { .. } => Code::InvalidVectorDimensions,
-                    UserError::InvalidVectorsMapType { .. } => Code::InvalidVectorsType,
                     UserError::InvalidVectorsType { .. } => Code::InvalidVectorsType,
-                    UserError::TooManyVectors(_, _) => Code::TooManyVectors,
                     UserError::SortError(_) => Code::InvalidSearchSort,
                     UserError::InvalidMinTypoWordLenSetting(_, _) => {
                         Code::InvalidSettingsTypoTolerance
                     }
-                    UserError::InvalidEmbedder(_) => Code::InvalidEmbedder,
-                    UserError::VectorEmbeddingError(_) => Code::VectorEmbeddingError,
                 }
             }
         }
@@ -405,11 +387,11 @@ impl ErrorCode for HeedError {
             HeedError::Mdb(MdbError::Invalid) => Code::InvalidStoreFile,
             HeedError::Io(e) => e.error_code(),
             HeedError::Mdb(_)
-            | HeedError::Encoding(_)
-            | HeedError::Decoding(_)
+            | HeedError::Encoding
+            | HeedError::Decoding
             | HeedError::InvalidDatabaseTyping
             | HeedError::DatabaseClosing
-            | HeedError::BadOpenOptions { .. } => Code::Internal,
+            | HeedError::BadOpenOptions => Code::Internal,
         }
     }
 }
@@ -463,15 +445,6 @@ impl fmt::Display for DeserrParseIntError {
     }
 }
 
-impl fmt::Display for deserr_codes::InvalidSearchSemanticRatio {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        write!(
-            f,
-            "the value of `semanticRatio` is invalid, expected a float between `0.0` and `1.0`."
-        )
-    }
-}
-
 #[macro_export]
 macro_rules! internal_error {
     ($target:ty : $($other:path), *) => {

meilisearch-types/src/features.rs

@@ -5,8 +5,6 @@ use serde::{Deserialize, Serialize};
 pub struct RuntimeTogglableFeatures {
     pub score_details: bool,
     pub vector_store: bool,
-    pub metrics: bool,
-    pub export_puffin_reports: bool,
 }
 
 #[derive(Default, Debug, Clone, Copy)]

meilisearch-types/src/keys.rs

@@ -257,12 +257,6 @@ pub enum Action {
     #[serde(rename = "dumps.create")]
     #[deserr(rename = "dumps.create")]
     DumpsCreate,
-    #[serde(rename = "snapshots.*")]
-    #[deserr(rename = "snapshots.*")]
-    SnapshotsAll,
-    #[serde(rename = "snapshots.create")]
-    #[deserr(rename = "snapshots.create")]
-    SnapshotsCreate,
     #[serde(rename = "version")]
     #[deserr(rename = "version")]
     Version,
@@ -315,7 +309,6 @@ impl Action {
             METRICS_GET => Some(Self::MetricsGet),
             DUMPS_ALL => Some(Self::DumpsAll),
             DUMPS_CREATE => Some(Self::DumpsCreate),
-            SNAPSHOTS_CREATE => Some(Self::SnapshotsCreate),
             VERSION => Some(Self::Version),
             KEYS_CREATE => Some(Self::KeysAdd),
             KEYS_GET => Some(Self::KeysGet),
@@ -360,7 +353,6 @@ pub mod actions {
     pub const METRICS_GET: u8 = MetricsGet.repr();
     pub const DUMPS_ALL: u8 = DumpsAll.repr();
     pub const DUMPS_CREATE: u8 = DumpsCreate.repr();
-    pub const SNAPSHOTS_CREATE: u8 = SnapshotsCreate.repr();
     pub const VERSION: u8 = Version.repr();
     pub const KEYS_CREATE: u8 = KeysAdd.repr();
     pub const KEYS_GET: u8 = KeysGet.repr();

meilisearch-types/src/lib.rs

@@ -9,7 +9,6 @@ pub mod index_uid_pattern;
 pub mod keys;
 pub mod settings;
 pub mod star_or;
-pub mod task_view;
 pub mod tasks;
 pub mod versioning;
 pub use milli::{heed, Index};

meilisearch-types/src/settings.rs

@@ -8,7 +8,6 @@ use std::str::FromStr;
 
 use deserr::{DeserializeError, Deserr, ErrorKind, MergeWithError, ValuePointerRef};
 use fst::IntoStreamer;
-use milli::proximity::ProximityPrecision;
 use milli::update::Setting;
 use milli::{Criterion, CriterionError, Index, DEFAULT_VALUES_PER_FACET};
 use serde::{Deserialize, Serialize, Serializer};
@@ -187,9 +186,6 @@ pub struct Settings<T> {
     #[deserr(default, error = DeserrJsonError<InvalidSettingsDistinctAttribute>)]
     pub distinct_attribute: Setting<String>,
     #[serde(default, skip_serializing_if = "Setting::is_not_set")]
-    #[deserr(default, error = DeserrJsonError<InvalidSettingsProximityPrecision>)]
-    pub proximity_precision: Setting<ProximityPrecisionView>,
-    #[serde(default, skip_serializing_if = "Setting::is_not_set")]
     #[deserr(default, error = DeserrJsonError<InvalidSettingsTypoTolerance>)]
     pub typo_tolerance: Setting<TypoSettings>,
     #[serde(default, skip_serializing_if = "Setting::is_not_set")]
@@ -199,10 +195,6 @@ pub struct Settings<T> {
     #[deserr(default, error = DeserrJsonError<InvalidSettingsPagination>)]
     pub pagination: Setting<PaginationSettings>,
 
-    #[serde(default, skip_serializing_if = "Setting::is_not_set")]
-    #[deserr(default, error = DeserrJsonError<InvalidSettingsEmbedders>)]
-    pub embedders: Setting<BTreeMap<String, Setting<milli::vector::settings::EmbeddingSettings>>>,
-
     #[serde(skip)]
     #[deserr(skip)]
     pub _kind: PhantomData<T>,
@@ -222,11 +214,9 @@ impl Settings<Checked> {
             separator_tokens: Setting::Reset,
             dictionary: Setting::Reset,
             distinct_attribute: Setting::Reset,
-            proximity_precision: Setting::Reset,
             typo_tolerance: Setting::Reset,
             faceting: Setting::Reset,
             pagination: Setting::Reset,
-            embedders: Setting::Reset,
             _kind: PhantomData,
         }
     }
@@ -244,11 +234,9 @@ impl Settings<Checked> {
             dictionary,
             synonyms,
             distinct_attribute,
-            proximity_precision,
             typo_tolerance,
             faceting,
             pagination,
-            embedders,
             ..
         } = self;
 
@@ -264,11 +252,9 @@ impl Settings<Checked> {
             dictionary,
             synonyms,
             distinct_attribute,
-            proximity_precision,
             typo_tolerance,
             faceting,
             pagination,
-            embedders,
             _kind: PhantomData,
         }
     }
@@ -310,29 +296,12 @@ impl Settings<Unchecked> {
             separator_tokens: self.separator_tokens,
             dictionary: self.dictionary,
             distinct_attribute: self.distinct_attribute,
-            proximity_precision: self.proximity_precision,
             typo_tolerance: self.typo_tolerance,
             faceting: self.faceting,
             pagination: self.pagination,
-            embedders: self.embedders,
             _kind: PhantomData,
         }
     }
-
-    pub fn validate(self) -> Result<Self, milli::Error> {
-        self.validate_embedding_settings()
-    }
-
-    fn validate_embedding_settings(mut self) -> Result<Self, milli::Error> {
-        let Setting::Set(mut configs) = self.embedders else { return Ok(self) };
-        for (name, config) in configs.iter_mut() {
-            let config_to_check = std::mem::take(config);
-            let checked_config = milli::update::validate_embedding_settings(config_to_check, name)?;
-            *config = checked_config
-        }
-        self.embedders = Setting::Set(configs);
-        Ok(self)
-    }
 }
 
 #[derive(Debug, Clone, Serialize, Deserialize)]
@@ -421,12 +390,6 @@ pub fn apply_settings_to_builder(
         Setting::NotSet => (),
     }
 
-    match settings.proximity_precision {
-        Setting::Set(ref precision) => builder.set_proximity_precision((*precision).into()),
-        Setting::Reset => builder.reset_proximity_precision(),
-        Setting::NotSet => (),
-    }
-
     match settings.typo_tolerance {
         Setting::Set(ref value) => {
             match value.enabled {
@@ -513,12 +476,6 @@ pub fn apply_settings_to_builder(
         Setting::Reset => builder.reset_pagination_max_total_hits(),
         Setting::NotSet => (),
     }
-
-    match settings.embedders.clone() {
-        Setting::Set(value) => builder.set_embedder_settings(value),
-        Setting::Reset => builder.reset_embedder_settings(),
-        Setting::NotSet => (),
-    }
 }
 
 pub fn settings(
@@ -552,8 +509,6 @@ pub fn settings(
 
     let distinct_field = index.distinct_field(rtxn)?.map(String::from);
 
-    let proximity_precision = index.proximity_precision(rtxn)?.map(ProximityPrecisionView::from);
-
     let synonyms = index.user_defined_synonyms(rtxn)?;
 
     let min_typo_word_len = MinWordSizeTyposSetting {
@@ -577,10 +532,7 @@ pub fn settings(
 
     let faceting = FacetingSettings {
         max_values_per_facet: Setting::Set(
-            index
-                .max_values_per_facet(rtxn)?
-                .map(|x| x as usize)
-                .unwrap_or(DEFAULT_VALUES_PER_FACET),
+            index.max_values_per_facet(rtxn)?.unwrap_or(DEFAULT_VALUES_PER_FACET),
         ),
         sort_facet_values_by: Setting::Set(
             index
@@ -593,20 +545,10 @@ pub fn settings(
 
     let pagination = PaginationSettings {
         max_total_hits: Setting::Set(
-            index
-                .pagination_max_total_hits(rtxn)?
-                .map(|x| x as usize)
-                .unwrap_or(DEFAULT_PAGINATION_MAX_TOTAL_HITS),
+            index.pagination_max_total_hits(rtxn)?.unwrap_or(DEFAULT_PAGINATION_MAX_TOTAL_HITS),
         ),
     };
 
-    let embedders: BTreeMap<_, _> = index
-        .embedding_configs(rtxn)?
-        .into_iter()
-        .map(|(name, config)| (name, Setting::Set(config.into())))
-        .collect();
-    let embedders = if embedders.is_empty() { Setting::NotSet } else { Setting::Set(embedders) };
-
     Ok(Settings {
         displayed_attributes: match displayed_attributes {
             Some(attrs) => Setting::Set(attrs),
@@ -627,12 +569,10 @@ pub fn settings(
             Some(field) => Setting::Set(field),
             None => Setting::Reset,
         },
-        proximity_precision: Setting::Set(proximity_precision.unwrap_or_default()),
         synonyms: Setting::Set(synonyms),
         typo_tolerance: Setting::Set(typo_tolerance),
         faceting: Setting::Set(faceting),
         pagination: Setting::Set(pagination),
-        embedders,
         _kind: PhantomData,
     })
 }
@@ -733,32 +673,6 @@ impl From<RankingRuleView> for Criterion {
     }
 }
 
-#[derive(Default, Debug, Clone, Copy, PartialEq, Eq, Deserr, Serialize, Deserialize)]
-#[serde(deny_unknown_fields, rename_all = "camelCase")]
-#[deserr(error = DeserrJsonError<InvalidSettingsProximityPrecision>, rename_all = camelCase, deny_unknown_fields)]
-pub enum ProximityPrecisionView {
-    #[default]
-    ByWord,
-    ByAttribute,
-}
-
-impl From<ProximityPrecision> for ProximityPrecisionView {
-    fn from(value: ProximityPrecision) -> Self {
-        match value {
-            ProximityPrecision::ByWord => ProximityPrecisionView::ByWord,
-            ProximityPrecision::ByAttribute => ProximityPrecisionView::ByAttribute,
-        }
-    }
-}
-impl From<ProximityPrecisionView> for ProximityPrecision {
-    fn from(value: ProximityPrecisionView) -> Self {
-        match value {
-            ProximityPrecisionView::ByWord => ProximityPrecision::ByWord,
-            ProximityPrecisionView::ByAttribute => ProximityPrecision::ByAttribute,
-        }
-    }
-}
-
 #[cfg(test)]
 pub(crate) mod test {
     use super::*;
@@ -778,11 +692,9 @@ pub(crate) mod test {
             dictionary: Setting::NotSet,
             synonyms: Setting::NotSet,
             distinct_attribute: Setting::NotSet,
-            proximity_precision: Setting::NotSet,
             typo_tolerance: Setting::NotSet,
             faceting: Setting::NotSet,
             pagination: Setting::NotSet,
-            embedders: Setting::NotSet,
             _kind: PhantomData::<Unchecked>,
         };
 
@@ -804,11 +716,9 @@ pub(crate) mod test {
             dictionary: Setting::NotSet,
             synonyms: Setting::NotSet,
             distinct_attribute: Setting::NotSet,
-            proximity_precision: Setting::NotSet,
             typo_tolerance: Setting::NotSet,
             faceting: Setting::NotSet,
             pagination: Setting::NotSet,
-            embedders: Setting::NotSet,
             _kind: PhantomData::<Unchecked>,
         };
 

meilisearch-types/src/task_view.rs

@@ -1,139 +0,0 @@
-use serde::Serialize;
-use time::{Duration, OffsetDateTime};
-
-use crate::error::ResponseError;
-use crate::settings::{Settings, Unchecked};
-use crate::tasks::{serialize_duration, Details, IndexSwap, Kind, Status, Task, TaskId};
-
-#[derive(Debug, Clone, PartialEq, Eq, Serialize)]
-#[serde(rename_all = "camelCase")]
-pub struct TaskView {
-    pub uid: TaskId,
-    #[serde(default)]
-    pub index_uid: Option<String>,
-    pub status: Status,
-    #[serde(rename = "type")]
-    pub kind: Kind,
-    pub canceled_by: Option<TaskId>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub details: Option<DetailsView>,
-    pub error: Option<ResponseError>,
-    #[serde(serialize_with = "serialize_duration", default)]
-    pub duration: Option<Duration>,
-    #[serde(with = "time::serde::rfc3339")]
-    pub enqueued_at: OffsetDateTime,
-    #[serde(with = "time::serde::rfc3339::option", default)]
-    pub started_at: Option<OffsetDateTime>,
-    #[serde(with = "time::serde::rfc3339::option", default)]
-    pub finished_at: Option<OffsetDateTime>,
-}
-
-impl TaskView {
-    pub fn from_task(task: &Task) -> TaskView {
-        TaskView {
-            uid: task.uid,
-            index_uid: task.index_uid().map(ToOwned::to_owned),
-            status: task.status,
-            kind: task.kind.as_kind(),
-            canceled_by: task.canceled_by,
-            details: task.details.clone().map(DetailsView::from),
-            error: task.error.clone(),
-            duration: task.started_at.zip(task.finished_at).map(|(start, end)| end - start),
-            enqueued_at: task.enqueued_at,
-            started_at: task.started_at,
-            finished_at: task.finished_at,
-        }
-    }
-}
-
-#[derive(Default, Debug, PartialEq, Eq, Clone, Serialize)]
-#[serde(rename_all = "camelCase")]
-pub struct DetailsView {
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub received_documents: Option<u64>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub indexed_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>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub deleted_documents: Option<Option<u64>>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub matched_tasks: Option<u64>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub canceled_tasks: Option<Option<u64>>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub deleted_tasks: Option<Option<u64>>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub original_filter: Option<Option<String>>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub dump_uid: Option<Option<String>>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    #[serde(flatten)]
-    pub settings: Option<Box<Settings<Unchecked>>>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub swaps: Option<Vec<IndexSwap>>,
-}
-
-impl From<Details> for DetailsView {
-    fn from(details: Details) -> Self {
-        match details {
-            Details::DocumentAdditionOrUpdate { received_documents, indexed_documents } => {
-                DetailsView {
-                    received_documents: Some(received_documents),
-                    indexed_documents: Some(indexed_documents),
-                    ..DetailsView::default()
-                }
-            }
-            Details::SettingsUpdate { settings } => {
-                DetailsView { settings: Some(settings), ..DetailsView::default() }
-            }
-            Details::IndexInfo { primary_key } => {
-                DetailsView { primary_key: Some(primary_key), ..DetailsView::default() }
-            }
-            Details::DocumentDeletion {
-                provided_ids: received_document_ids,
-                deleted_documents,
-            } => DetailsView {
-                provided_ids: Some(received_document_ids),
-                deleted_documents: Some(deleted_documents),
-                original_filter: Some(None),
-                ..DetailsView::default()
-            },
-            Details::DocumentDeletionByFilter { original_filter, deleted_documents } => {
-                DetailsView {
-                    provided_ids: Some(0),
-                    original_filter: Some(Some(original_filter)),
-                    deleted_documents: Some(deleted_documents),
-                    ..DetailsView::default()
-                }
-            }
-            Details::ClearAll { deleted_documents } => {
-                DetailsView { deleted_documents: Some(deleted_documents), ..DetailsView::default() }
-            }
-            Details::TaskCancelation { matched_tasks, canceled_tasks, original_filter } => {
-                DetailsView {
-                    matched_tasks: Some(matched_tasks),
-                    canceled_tasks: Some(canceled_tasks),
-                    original_filter: Some(Some(original_filter)),
-                    ..DetailsView::default()
-                }
-            }
-            Details::TaskDeletion { matched_tasks, deleted_tasks, original_filter } => {
-                DetailsView {
-                    matched_tasks: Some(matched_tasks),
-                    deleted_tasks: Some(deleted_tasks),
-                    original_filter: Some(Some(original_filter)),
-                    ..DetailsView::default()
-                }
-            }
-            Details::Dump { dump_uid } => {
-                DetailsView { dump_uid: Some(dump_uid), ..DetailsView::default() }
-            }
-            Details::IndexSwap { swaps } => {
-                DetailsView { swaps: Some(swaps), ..Default::default() }
-            }
-        }
-    }
-}

meilisearch-types/src/tasks.rs

@@ -5,7 +5,7 @@ use std::str::FromStr;
 
 use enum_iterator::Sequence;
 use milli::update::IndexDocumentsMethod;
-use roaring::RoaringBitmap;
+use roaring::RoaringTreemap;
 use serde::{Deserialize, Serialize, Serializer};
 use time::{Duration, OffsetDateTime};
 use uuid::Uuid;
@@ -15,7 +15,7 @@ use crate::keys::Key;
 use crate::settings::{Settings, Unchecked};
 use crate::InstanceUid;
 
-pub type TaskId = u32;
+pub type TaskId = u64;
 
 #[derive(Clone, Debug, PartialEq, Serialize, Deserialize)]
 #[serde(rename_all = "camelCase")]
@@ -127,11 +127,11 @@ pub enum KindWithContent {
     },
     TaskCancelation {
         query: String,
-        tasks: RoaringBitmap,
+        tasks: RoaringTreemap,
     },
     TaskDeletion {
         query: String,
-        tasks: RoaringBitmap,
+        tasks: RoaringTreemap,
     },
     DumpCreation {
         keys: Vec<Key>,

meilisearch/Cargo.toml

@@ -39,7 +39,7 @@ byte-unit = { version = "4.0.19", default-features = false, features = [
 bytes = "1.4.0"
 clap = { version = "4.2.1", features = ["derive", "env"] }
 crossbeam-channel = "0.5.8"
-deserr = { version = "0.6.0", features = ["actix-web"] }
+deserr = { version = "0.6.0", features = ["actix-web"]}
 dump = { path = "../dump" }
 either = "1.8.1"
 env_logger = "0.10.0"
@@ -69,7 +69,8 @@ permissive-json-pointer = { path = "../permissive-json-pointer" }
 pin-project-lite = "0.2.9"
 platform-dirs = "0.3.0"
 prometheus = { version = "0.13.3", features = ["process"] }
-puffin = { version = "0.16.0", features = ["serialization"] }
+puffin = "0.16.0"
+puffin_http = { version = "0.13.0", optional = true }
 rand = "0.8.5"
 rayon = "1.7.0"
 regex = "1.7.3"
@@ -104,7 +105,6 @@ walkdir = "2.3.3"
 yaup = "0.2.1"
 serde_urlencoded = "0.7.1"
 termcolor = "1.2.0"
-url = { version = "2.5.0", features = ["serde"] }
 
 [dev-dependencies]
 actix-rt = "2.8.0"
@@ -135,6 +135,7 @@ zip = { version = "0.6.4", optional = true }
 [features]
 default = ["analytics", "meilisearch-types/all-tokenizations", "mini-dashboard"]
 analytics = ["segment"]
+profile-with-puffin = ["dep:puffin_http"]
 mini-dashboard = [
     "actix-web-static-files",
     "static-files",
@@ -151,8 +152,7 @@ hebrew = ["meilisearch-types/hebrew"]
 japanese = ["meilisearch-types/japanese"]
 thai = ["meilisearch-types/thai"]
 greek = ["meilisearch-types/greek"]
-khmer = ["meilisearch-types/khmer"]
 
 [package.metadata.mini-dashboard]
-assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.2.12/build.zip"
-sha1 = "acfe9a018c93eb0604ea87ee87bff7df5474e18e"
+assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.2.11/build.zip"
+sha1 = "83cd44ed1e5f97ecb581dc9f958a63f4ccc982d9"

meilisearch/src/analytics/mod.rs

@@ -1,5 +1,6 @@
 mod mock_analytics;
-#[cfg(feature = "analytics")]
+// if we are in release mode and the feature analytics was enabled
+#[cfg(all(not(debug_assertions), feature = "analytics"))]
 mod segment_analytics;
 
 use std::fs;
@@ -16,25 +17,26 @@ use serde_json::Value;
 use crate::routes::indexes::documents::UpdateDocumentsQuery;
 use crate::routes::tasks::TasksFilterQuery;
 
-// if the analytics feature is disabled
+// if we are in debug mode OR the analytics feature is disabled
 // the `SegmentAnalytics` point to the mock instead of the real analytics
-#[cfg(not(feature = "analytics"))]
+#[cfg(any(debug_assertions, not(feature = "analytics")))]
 pub type SegmentAnalytics = mock_analytics::MockAnalytics;
-#[cfg(not(feature = "analytics"))]
+#[cfg(any(debug_assertions, not(feature = "analytics")))]
 pub type SearchAggregator = mock_analytics::SearchAggregator;
-#[cfg(not(feature = "analytics"))]
+#[cfg(any(debug_assertions, not(feature = "analytics")))]
 pub type MultiSearchAggregator = mock_analytics::MultiSearchAggregator;
-#[cfg(not(feature = "analytics"))]
+#[cfg(any(debug_assertions, not(feature = "analytics")))]
 pub type FacetSearchAggregator = mock_analytics::FacetSearchAggregator;
 
-// if the feature analytics is enabled we use the real analytics
-#[cfg(feature = "analytics")]
+// if we are in release mode and the feature analytics was enabled
+// we use the real analytics
+#[cfg(all(not(debug_assertions), feature = "analytics"))]
 pub type SegmentAnalytics = segment_analytics::SegmentAnalytics;
-#[cfg(feature = "analytics")]
+#[cfg(all(not(debug_assertions), feature = "analytics"))]
 pub type SearchAggregator = segment_analytics::SearchAggregator;
-#[cfg(feature = "analytics")]
+#[cfg(all(not(debug_assertions), feature = "analytics"))]
 pub type MultiSearchAggregator = segment_analytics::MultiSearchAggregator;
-#[cfg(feature = "analytics")]
+#[cfg(all(not(debug_assertions), feature = "analytics"))]
 pub type FacetSearchAggregator = segment_analytics::FacetSearchAggregator;
 
 /// The Meilisearch config dir:

meilisearch/src/error.rs

@@ -51,8 +51,6 @@ pub enum MeilisearchHttpError {
     DocumentFormat(#[from] DocumentFormatError),
     #[error(transparent)]
     Join(#[from] JoinError),
-    #[error("Invalid request: missing `hybrid` parameter when both `q` and `vector` are present.")]
-    MissingSearchHybrid,
 }
 
 impl ErrorCode for MeilisearchHttpError {
@@ -76,7 +74,6 @@ impl ErrorCode for MeilisearchHttpError {
             MeilisearchHttpError::FileStore(_) => Code::Internal,
             MeilisearchHttpError::DocumentFormat(e) => e.error_code(),
             MeilisearchHttpError::Join(_) => Code::Internal,
-            MeilisearchHttpError::MissingSearchHybrid => Code::MissingSearchHybrid,
         }
     }
 }

meilisearch/src/lib.rs

@@ -114,7 +114,10 @@ pub fn create_app(
         .configure(routes::configure)
         .configure(|s| dashboard(s, enable_dashboard));
 
-    let app = app.wrap(middleware::RouteMetrics);
+    let app = app.wrap(actix_web::middleware::Condition::new(
+        opt.experimental_enable_metrics,
+        middleware::RouteMetrics,
+    ));
     app.wrap(
         Cors::default()
             .send_wildcard()
@@ -200,7 +203,7 @@ pub fn setup_meilisearch(opt: &Opt) -> anyhow::Result<(Arc<IndexScheduler>, Arc<
             .name(String::from("register-snapshot-tasks"))
             .spawn(move || loop {
                 thread::sleep(snapshot_delay);
-                if let Err(e) = index_scheduler.register(KindWithContent::SnapshotCreation) {
+                if let Err(e) = index_scheduler.register(KindWithContent::SnapshotCreation, None) {
                     error!("Error while registering snapshot: {}", e);
                 }
             })
@@ -228,15 +231,12 @@ fn open_or_create_database_unchecked(
             indexes_path: opt.db_path.join("indexes"),
             snapshots_path: opt.snapshot_dir.clone(),
             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,
             enable_mdb_writemap: opt.experimental_reduce_indexing_memory_usage,
             indexer_config: (&opt.indexer_options).try_into()?,
             autobatching_enabled: true,
             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_count: DEFAULT_INDEX_COUNT,
             instance_features,
@@ -365,7 +365,7 @@ fn import_dump(
                 update_method: IndexDocumentsMethod::ReplaceDocuments,
                 ..Default::default()
             },
-            |indexing_step| log::trace!("update: {:?}", indexing_step),
+            |indexing_step| log::debug!("update: {:?}", indexing_step),
             || false,
         )?;
 
@@ -400,7 +400,6 @@ pub fn configure_data(
         .app_data(web::Data::from(analytics))
         .app_data(
             web::JsonConfig::default()
-                .limit(http_payload_size_limit)
                 .content_type(|mime| mime == mime::APPLICATION_JSON)
                 .error_handler(|err, req: &HttpRequest| match err {
                     JsonPayloadError::ContentType => match req.headers().get(CONTENT_TYPE) {

meilisearch/src/main.rs

@@ -19,11 +19,7 @@ static ALLOC: mimalloc::MiMalloc = mimalloc::MiMalloc;
 /// does all the setup before meilisearch is launched
 fn setup(opt: &Opt) -> anyhow::Result<()> {
     let mut log_builder = env_logger::Builder::new();
-    let log_filters = format!(
-        "{},h2=warn,hyper=warn,tokio_util=warn,tracing=warn,rustls=warn,mio=warn,reqwest=warn",
-        opt.log_level
-    );
-    log_builder.parse_filters(&log_filters);
+    log_builder.parse_filters(&opt.log_level.to_string());
 
     log_builder.init();
 
@@ -34,6 +30,10 @@ fn setup(opt: &Opt) -> anyhow::Result<()> {
 async fn main() -> anyhow::Result<()> {
     let (opt, config_read_from) = Opt::try_build()?;
 
+    #[cfg(feature = "profile-with-puffin")]
+    let _server = puffin_http::Server::new(&format!("0.0.0.0:{}", puffin_http::DEFAULT_PORT))?;
+    puffin::set_scopes_on(cfg!(feature = "profile-with-puffin"));
+
     anyhow::ensure!(
         !(cfg!(windows) && opt.experimental_reduce_indexing_memory_usage),
         "The `experimental-reduce-indexing-memory-usage` flag is not supported on Windows"

meilisearch/src/middleware.rs

@@ -3,10 +3,8 @@
 use std::future::{ready, Ready};
 
 use actix_web::dev::{self, Service, ServiceRequest, ServiceResponse, Transform};
-use actix_web::web::Data;
 use actix_web::Error;
 use futures_util::future::LocalBoxFuture;
-use index_scheduler::IndexScheduler;
 use prometheus::HistogramTimer;
 
 pub struct RouteMetrics;
@@ -49,27 +47,19 @@ where
 
     fn call(&self, req: ServiceRequest) -> Self::Future {
         let mut histogram_timer: Option<HistogramTimer> = None;
-
-        // calling unwrap here is safe because index scheduler is added to app data while creating actix app.
-        // also, the tests will fail if this is not present.
-        let index_scheduler = req.app_data::<Data<IndexScheduler>>().unwrap();
-        let features = index_scheduler.features();
-
-        if features.check_metrics().is_ok() {
-            let request_path = req.path();
-            let is_registered_resource = req.resource_map().has_resource(request_path);
-            if is_registered_resource {
-                let request_method = req.method().to_string();
-                histogram_timer = Some(
-                    crate::metrics::MEILISEARCH_HTTP_RESPONSE_TIME_SECONDS
-                        .with_label_values(&[&request_method, request_path])
-                        .start_timer(),
-                );
-                crate::metrics::MEILISEARCH_HTTP_REQUESTS_TOTAL
+        let request_path = req.path();
+        let is_registered_resource = req.resource_map().has_resource(request_path);
+        if is_registered_resource {
+            let request_method = req.method().to_string();
+            histogram_timer = Some(
+                crate::metrics::MEILISEARCH_HTTP_RESPONSE_TIME_SECONDS
                     .with_label_values(&[&request_method, request_path])
-                    .inc();
-            }
-        };
+                    .start_timer(),
+            );
+            crate::metrics::MEILISEARCH_HTTP_REQUESTS_TOTAL
+                .with_label_values(&[&request_method, request_path])
+                .inc();
+        }
 
         let fut = self.service.call(req);
 

meilisearch/src/option.rs

@@ -21,7 +21,6 @@ use rustls::RootCertStore;
 use rustls_pemfile::{certs, pkcs8_private_keys, rsa_private_keys};
 use serde::{Deserialize, Serialize};
 use sysinfo::{RefreshKind, System, SystemExt};
-use url::Url;
 
 const POSSIBLE_ENV: [&str; 2] = ["development", "production"];
 
@@ -29,9 +28,7 @@ const MEILI_DB_PATH: &str = "MEILI_DB_PATH";
 const MEILI_HTTP_ADDR: &str = "MEILI_HTTP_ADDR";
 const MEILI_MASTER_KEY: &str = "MEILI_MASTER_KEY";
 const MEILI_ENV: &str = "MEILI_ENV";
-const MEILI_TASK_WEBHOOK_URL: &str = "MEILI_TASK_WEBHOOK_URL";
-const MEILI_TASK_WEBHOOK_AUTHORIZATION_HEADER: &str = "MEILI_TASK_WEBHOOK_AUTHORIZATION_HEADER";
-#[cfg(feature = "analytics")]
+#[cfg(all(not(debug_assertions), feature = "analytics"))]
 const MEILI_NO_ANALYTICS: &str = "MEILI_NO_ANALYTICS";
 const MEILI_HTTP_PAYLOAD_SIZE_LIMIT: &str = "MEILI_HTTP_PAYLOAD_SIZE_LIMIT";
 const MEILI_SSL_CERT_PATH: &str = "MEILI_SSL_CERT_PATH";
@@ -54,8 +51,6 @@ const MEILI_LOG_LEVEL: &str = "MEILI_LOG_LEVEL";
 const MEILI_EXPERIMENTAL_ENABLE_METRICS: &str = "MEILI_EXPERIMENTAL_ENABLE_METRICS";
 const MEILI_EXPERIMENTAL_REDUCE_INDEXING_MEMORY_USAGE: &str =
     "MEILI_EXPERIMENTAL_REDUCE_INDEXING_MEMORY_USAGE";
-const MEILI_EXPERIMENTAL_MAX_NUMBER_OF_BATCHED_TASKS: &str =
-    "MEILI_EXPERIMENTAL_MAX_NUMBER_OF_BATCHED_TASKS";
 
 const DEFAULT_CONFIG_FILE_PATH: &str = "./config.toml";
 const DEFAULT_DB_PATH: &str = "./data.ms";
@@ -159,20 +154,12 @@ pub struct Opt {
     #[serde(default = "default_env")]
     pub env: String,
 
-    /// Called whenever a task finishes so a third party can be notified.
-    #[clap(long, env = MEILI_TASK_WEBHOOK_URL)]
-    pub task_webhook_url: Option<Url>,
-
-    /// The Authorization header to send on the webhook URL whenever a task finishes so a third party can be notified.
-    #[clap(long, env = MEILI_TASK_WEBHOOK_AUTHORIZATION_HEADER)]
-    pub task_webhook_authorization_header: Option<String>,
-
     /// Deactivates Meilisearch's built-in telemetry when provided.
     ///
     /// Meilisearch automatically collects data from all instances that do not opt out using this flag.
     /// All gathered data is used solely for the purpose of improving Meilisearch, and can be deleted
     /// at any time.
-    #[cfg(feature = "analytics")]
+    #[cfg(all(not(debug_assertions), feature = "analytics"))]
     #[serde(default)] // we can't send true
     #[clap(long, env = MEILI_NO_ANALYTICS)]
     pub no_analytics: bool,
@@ -314,11 +301,6 @@ pub struct Opt {
     #[serde(default)]
     pub experimental_reduce_indexing_memory_usage: bool,
 
-    /// Experimentally reduces the maximum number of tasks that will be processed at once, see: <https://github.com/orgs/meilisearch/discussions/713>
-    #[clap(long, env = MEILI_EXPERIMENTAL_MAX_NUMBER_OF_BATCHED_TASKS, default_value_t = default_limit_batched_tasks())]
-    #[serde(default = "default_limit_batched_tasks")]
-    pub experimental_max_number_of_batched_tasks: usize,
-
     #[serde(flatten)]
     #[clap(flatten)]
     pub indexer_options: IndexerOpts,
@@ -386,12 +368,9 @@ impl Opt {
             http_addr,
             master_key,
             env,
-            task_webhook_url,
-            task_webhook_authorization_header,
             max_index_size: _,
             max_task_db_size: _,
             http_payload_size_limit,
-            experimental_max_number_of_batched_tasks,
             ssl_cert_path,
             ssl_key_path,
             ssl_auth_path,
@@ -411,10 +390,10 @@ impl Opt {
             ignore_missing_dump: _,
             ignore_dump_if_db_exists: _,
             config_file_path: _,
-            #[cfg(feature = "analytics")]
+            #[cfg(all(not(debug_assertions), feature = "analytics"))]
             no_analytics,
-            experimental_enable_metrics,
-            experimental_reduce_indexing_memory_usage,
+            experimental_enable_metrics: enable_metrics_route,
+            experimental_reduce_indexing_memory_usage: reduce_indexing_memory_usage,
         } = self;
         export_to_env_if_not_present(MEILI_DB_PATH, db_path);
         export_to_env_if_not_present(MEILI_HTTP_ADDR, http_addr);
@@ -422,17 +401,7 @@ impl Opt {
             export_to_env_if_not_present(MEILI_MASTER_KEY, master_key);
         }
         export_to_env_if_not_present(MEILI_ENV, env);
-        if let Some(task_webhook_url) = task_webhook_url {
-            export_to_env_if_not_present(MEILI_TASK_WEBHOOK_URL, task_webhook_url.to_string());
-        }
-        if let Some(task_webhook_authorization_header) = task_webhook_authorization_header {
-            export_to_env_if_not_present(
-                MEILI_TASK_WEBHOOK_AUTHORIZATION_HEADER,
-                task_webhook_authorization_header,
-            );
-        }
-
-        #[cfg(feature = "analytics")]
+        #[cfg(all(not(debug_assertions), feature = "analytics"))]
         {
             export_to_env_if_not_present(MEILI_NO_ANALYTICS, no_analytics.to_string());
         }
@@ -440,10 +409,6 @@ impl Opt {
             MEILI_HTTP_PAYLOAD_SIZE_LIMIT,
             http_payload_size_limit.to_string(),
         );
-        export_to_env_if_not_present(
-            MEILI_EXPERIMENTAL_MAX_NUMBER_OF_BATCHED_TASKS,
-            experimental_max_number_of_batched_tasks.to_string(),
-        );
         if let Some(ssl_cert_path) = ssl_cert_path {
             export_to_env_if_not_present(MEILI_SSL_CERT_PATH, ssl_cert_path);
         }
@@ -468,11 +433,11 @@ impl Opt {
         export_to_env_if_not_present(MEILI_LOG_LEVEL, log_level.to_string());
         export_to_env_if_not_present(
             MEILI_EXPERIMENTAL_ENABLE_METRICS,
-            experimental_enable_metrics.to_string(),
+            enable_metrics_route.to_string(),
         );
         export_to_env_if_not_present(
             MEILI_EXPERIMENTAL_REDUCE_INDEXING_MEMORY_USAGE,
-            experimental_reduce_indexing_memory_usage.to_string(),
+            reduce_indexing_memory_usage.to_string(),
         );
         indexer_options.export_to_env();
     }
@@ -762,10 +727,6 @@ fn default_http_payload_size_limit() -> Byte {
     Byte::from_str(DEFAULT_HTTP_PAYLOAD_SIZE_LIMIT).unwrap()
 }
 
-fn default_limit_batched_tasks() -> usize {
-    usize::MAX
-}
-
 fn default_snapshot_dir() -> PathBuf {
     PathBuf::from(DEFAULT_SNAPSHOT_DIR)
 }

meilisearch/src/routes/dump.rs

@@ -11,7 +11,7 @@ use crate::analytics::Analytics;
 use crate::extractors::authentication::policies::*;
 use crate::extractors::authentication::GuardedData;
 use crate::extractors::sequential_extractor::SeqHandler;
-use crate::routes::SummarizedTaskView;
+use crate::routes::{get_task_id, SummarizedTaskView};
 
 pub fn configure(cfg: &mut web::ServiceConfig) {
     cfg.service(web::resource("").route(web::post().to(SeqHandler(create_dump))));
@@ -29,8 +29,9 @@ pub async fn create_dump(
         keys: auth_controller.list_keys()?,
         instance_uid: analytics.instance_uid().cloned(),
     };
+    let uid = get_task_id(&req)?;
     let task: SummarizedTaskView =
-        tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
+        tokio::task::spawn_blocking(move || index_scheduler.register(task, uid)).await??.into();
 
     debug!("returns: {:?}", task);
     Ok(HttpResponse::Accepted().json(task))

meilisearch/src/routes/features.rs

@@ -29,12 +29,12 @@ async fn get_features(
     >,
     req: HttpRequest,
     analytics: Data<dyn Analytics>,
-) -> HttpResponse {
-    let features = index_scheduler.features();
+) -> Result<HttpResponse, ResponseError> {
+    let features = index_scheduler.features()?;
 
     analytics.publish("Experimental features Seen".to_string(), json!(null), Some(&req));
     debug!("returns: {:?}", features.runtime_features());
-    HttpResponse::Ok().json(features.runtime_features())
+    Ok(HttpResponse::Ok().json(features.runtime_features()))
 }
 
 #[derive(Debug, Deserr)]
@@ -44,10 +44,6 @@ pub struct RuntimeTogglableFeatures {
     pub score_details: Option<bool>,
     #[deserr(default)]
     pub vector_store: Option<bool>,
-    #[deserr(default)]
-    pub metrics: Option<bool>,
-    #[deserr(default)]
-    pub export_puffin_reports: Option<bool>,
 }
 
 async fn patch_features(
@@ -59,36 +55,26 @@ async fn patch_features(
     req: HttpRequest,
     analytics: Data<dyn Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
-    let features = index_scheduler.features();
+    let features = index_scheduler.features()?;
 
     let old_features = features.runtime_features();
+
     let new_features = meilisearch_types::features::RuntimeTogglableFeatures {
         score_details: new_features.0.score_details.unwrap_or(old_features.score_details),
         vector_store: new_features.0.vector_store.unwrap_or(old_features.vector_store),
-        metrics: new_features.0.metrics.unwrap_or(old_features.metrics),
-        export_puffin_reports: new_features
-            .0
-            .export_puffin_reports
-            .unwrap_or(old_features.export_puffin_reports),
     };
 
     // 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 {
-        score_details,
-        vector_store,
-        metrics,
-        export_puffin_reports,
-    } = new_features;
+    let meilisearch_types::features::RuntimeTogglableFeatures { score_details, vector_store } =
+        new_features;
 
     analytics.publish(
         "Experimental features Updated".to_string(),
         json!({
             "score_details": score_details,
             "vector_store": vector_store,
-            "metrics": metrics,
-            "export_puffin_reports": export_puffin_reports,
         }),
         Some(&req),
     );

meilisearch/src/routes/indexes/documents.rs

@@ -3,11 +3,11 @@ use std::io::ErrorKind;
 use actix_web::http::header::CONTENT_TYPE;
 use actix_web::web::Data;
 use actix_web::{web, HttpMessage, HttpRequest, HttpResponse};
-use bstr::ByteSlice as _;
+use bstr::ByteSlice;
 use deserr::actix_web::{AwebJson, AwebQueryParameter};
 use deserr::Deserr;
 use futures::StreamExt;
-use index_scheduler::IndexScheduler;
+use index_scheduler::{IndexScheduler, TaskId};
 use log::debug;
 use meilisearch_types::deserr::query_params::Param;
 use meilisearch_types::deserr::{DeserrJsonError, DeserrQueryParamError};
@@ -36,7 +36,7 @@ use crate::extractors::authentication::policies::*;
 use crate::extractors::authentication::GuardedData;
 use crate::extractors::payload::Payload;
 use crate::extractors::sequential_extractor::SeqHandler;
-use crate::routes::{PaginationView, SummarizedTaskView, PAGINATION_DEFAULT_LIMIT};
+use crate::routes::{get_task_id, PaginationView, SummarizedTaskView, PAGINATION_DEFAULT_LIMIT};
 use crate::search::parse_filter;
 
 static ACCEPTED_CONTENT_TYPE: Lazy<Vec<String>> = Lazy::new(|| {
@@ -129,8 +129,9 @@ pub async fn delete_document(
         index_uid: index_uid.to_string(),
         documents_ids: vec![document_id],
     };
+    let uid = get_task_id(&req)?;
     let task: SummarizedTaskView =
-        tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
+        tokio::task::spawn_blocking(move || index_scheduler.register(task, uid)).await??.into();
     debug!("returns: {:?}", task);
     Ok(HttpResponse::Accepted().json(task))
 }
@@ -277,6 +278,7 @@ pub async fn replace_documents(
     analytics.add_documents(&params, index_scheduler.index(&index_uid).is_err(), &req);
 
     let allow_index_creation = index_scheduler.filters().allow_index_creation(&index_uid);
+    let uid = get_task_id(&req)?;
     let task = document_addition(
         extract_mime_type(&req)?,
         index_scheduler,
@@ -285,6 +287,7 @@ pub async fn replace_documents(
         params.csv_delimiter,
         body,
         IndexDocumentsMethod::ReplaceDocuments,
+        uid,
         allow_index_creation,
     )
     .await?;
@@ -308,6 +311,7 @@ pub async fn update_documents(
     analytics.update_documents(&params, index_scheduler.index(&index_uid).is_err(), &req);
 
     let allow_index_creation = index_scheduler.filters().allow_index_creation(&index_uid);
+    let uid = get_task_id(&req)?;
     let task = document_addition(
         extract_mime_type(&req)?,
         index_scheduler,
@@ -316,6 +320,7 @@ pub async fn update_documents(
         params.csv_delimiter,
         body,
         IndexDocumentsMethod::UpdateDocuments,
+        uid,
         allow_index_creation,
     )
     .await?;
@@ -332,6 +337,7 @@ async fn document_addition(
     csv_delimiter: Option<u8>,
     mut body: Payload,
     method: IndexDocumentsMethod,
+    task_id: Option<TaskId>,
     allow_index_creation: bool,
 ) -> Result<SummarizedTaskView, MeilisearchHttpError> {
     let format = match (
@@ -445,7 +451,7 @@ async fn document_addition(
     };
 
     let scheduler = index_scheduler.clone();
-    let task = match tokio::task::spawn_blocking(move || scheduler.register(task)).await? {
+    let task = match tokio::task::spawn_blocking(move || scheduler.register(task, task_id)).await? {
         Ok(task) => task,
         Err(e) => {
             index_scheduler.delete_update_file(uuid)?;
@@ -476,8 +482,9 @@ pub async fn delete_documents_batch(
 
     let task =
         KindWithContent::DocumentDeletion { index_uid: index_uid.to_string(), documents_ids: ids };
+    let uid = get_task_id(&req)?;
     let task: SummarizedTaskView =
-        tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
+        tokio::task::spawn_blocking(move || index_scheduler.register(task, uid)).await??.into();
 
     debug!("returns: {:?}", task);
     Ok(HttpResponse::Accepted().json(task))
@@ -512,8 +519,9 @@ pub async fn delete_documents_by_filter(
     .map_err(|err| ResponseError::from_msg(err.message, Code::InvalidDocumentFilter))?;
     let task = KindWithContent::DocumentDeletionByFilter { index_uid, filter_expr: filter };
 
+    let uid = get_task_id(&req)?;
     let task: SummarizedTaskView =
-        tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
+        tokio::task::spawn_blocking(move || index_scheduler.register(task, uid)).await??.into();
 
     debug!("returns: {:?}", task);
     Ok(HttpResponse::Accepted().json(task))
@@ -529,8 +537,9 @@ pub async fn clear_all_documents(
     analytics.delete_documents(DocumentDeletionKind::ClearAll, &req);
 
     let task = KindWithContent::DocumentClear { index_uid: index_uid.to_string() };
+    let uid = get_task_id(&req)?;
     let task: SummarizedTaskView =
-        tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
+        tokio::task::spawn_blocking(move || index_scheduler.register(task, uid)).await??.into();
 
     debug!("returns: {:?}", task);
     Ok(HttpResponse::Accepted().json(task))
@@ -612,8 +621,8 @@ fn retrieve_document<S: AsRef<str>>(
     let all_fields: Vec<_> = fields_ids_map.iter().map(|(id, _)| id).collect();
 
     let internal_id = index
-        .external_documents_ids()
-        .get(&txn, doc_id)?
+        .external_documents_ids(&txn)?
+        .get(doc_id.as_bytes())
         .ok_or_else(|| MeilisearchHttpError::DocumentNotFound(doc_id.to_string()))?;
 
     let document = index

meilisearch/src/routes/indexes/facet_search.rs

@@ -13,9 +13,9 @@ use crate::analytics::{Analytics, FacetSearchAggregator};
 use crate::extractors::authentication::policies::*;
 use crate::extractors::authentication::GuardedData;
 use crate::search::{
-    add_search_rules, perform_facet_search, HybridQuery, MatchingStrategy, SearchQuery,
-    DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG,
-    DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET,
+    add_search_rules, perform_facet_search, MatchingStrategy, SearchQuery, DEFAULT_CROP_LENGTH,
+    DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG,
+    DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET,
 };
 
 pub fn configure(cfg: &mut web::ServiceConfig) {
@@ -36,8 +36,6 @@ pub struct FacetSearchQuery {
     pub q: Option<String>,
     #[deserr(default, error = DeserrJsonError<InvalidSearchVector>)]
     pub vector: Option<Vec<f32>>,
-    #[deserr(default, error = DeserrJsonError<InvalidHybridQuery>)]
-    pub hybrid: Option<HybridQuery>,
     #[deserr(default, error = DeserrJsonError<InvalidSearchFilter>)]
     pub filter: Option<Value>,
     #[deserr(default, error = DeserrJsonError<InvalidSearchMatchingStrategy>, default)]
@@ -70,7 +68,7 @@ pub async fn search(
     }
 
     let index = index_scheduler.index(&index_uid)?;
-    let features = index_scheduler.features();
+    let features = index_scheduler.features()?;
     let search_result = tokio::task::spawn_blocking(move || {
         perform_facet_search(&index, search_query, facet_query, facet_name, features)
     })
@@ -97,7 +95,6 @@ impl From<FacetSearchQuery> for SearchQuery {
             filter,
             matching_strategy,
             attributes_to_search_on,
-            hybrid,
         } = value;
 
         SearchQuery {
@@ -122,7 +119,6 @@ impl From<FacetSearchQuery> for SearchQuery {
             matching_strategy,
             vector,
             attributes_to_search_on,
-            hybrid,
         }
     }
 }

meilisearch/src/routes/indexes/mod.rs

@@ -17,7 +17,7 @@ use serde::Serialize;
 use serde_json::json;
 use time::OffsetDateTime;
 
-use super::{Pagination, SummarizedTaskView, PAGINATION_DEFAULT_LIMIT};
+use super::{get_task_id, Pagination, SummarizedTaskView, PAGINATION_DEFAULT_LIMIT};
 use crate::analytics::Analytics;
 use crate::extractors::authentication::policies::*;
 use crate::extractors::authentication::{AuthenticationError, GuardedData};
@@ -135,8 +135,9 @@ pub async fn create_index(
         );
 
         let task = KindWithContent::IndexCreation { index_uid: uid.to_string(), primary_key };
+        let uid = get_task_id(&req)?;
         let task: SummarizedTaskView =
-            tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
+            tokio::task::spawn_blocking(move || index_scheduler.register(task, uid)).await??.into();
 
         Ok(HttpResponse::Accepted().json(task))
     } else {
@@ -203,8 +204,9 @@ pub async fn update_index(
         primary_key: body.primary_key,
     };
 
+    let uid = get_task_id(&req)?;
     let task: SummarizedTaskView =
-        tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
+        tokio::task::spawn_blocking(move || index_scheduler.register(task, uid)).await??.into();
 
     debug!("returns: {:?}", task);
     Ok(HttpResponse::Accepted().json(task))
@@ -213,11 +215,13 @@ pub async fn update_index(
 pub async fn delete_index(
     index_scheduler: GuardedData<ActionPolicy<{ actions::INDEXES_DELETE }>, Data<IndexScheduler>>,
     index_uid: web::Path<String>,
+    req: HttpRequest,
 ) -> Result<HttpResponse, ResponseError> {
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
     let task = KindWithContent::IndexDeletion { index_uid: index_uid.into_inner() };
+    let uid = get_task_id(&req)?;
     let task: SummarizedTaskView =
-        tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
+        tokio::task::spawn_blocking(move || index_scheduler.register(task, uid)).await??.into();
 
     Ok(HttpResponse::Accepted().json(task))
 }

meilisearch/src/routes/indexes/search.rs

@@ -2,14 +2,12 @@ use actix_web::web::Data;
 use actix_web::{web, HttpRequest, HttpResponse};
 use deserr::actix_web::{AwebJson, AwebQueryParameter};
 use index_scheduler::IndexScheduler;
-use log::{debug, warn};
+use log::debug;
 use meilisearch_types::deserr::query_params::Param;
 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::milli;
-use meilisearch_types::milli::vector::DistributionShift;
 use meilisearch_types::serde_cs::vec::CS;
 use serde_json::Value;
 
@@ -18,9 +16,9 @@ use crate::extractors::authentication::policies::*;
 use crate::extractors::authentication::GuardedData;
 use crate::extractors::sequential_extractor::SeqHandler;
 use crate::search::{
-    add_search_rules, perform_search, HybridQuery, MatchingStrategy, SearchQuery, SemanticRatio,
-    DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG,
-    DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET, DEFAULT_SEMANTIC_RATIO,
+    add_search_rules, perform_search, MatchingStrategy, SearchQuery, DEFAULT_CROP_LENGTH,
+    DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG,
+    DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET,
 };
 
 pub fn configure(cfg: &mut web::ServiceConfig) {
@@ -76,31 +74,6 @@ pub struct SearchQueryGet {
     matching_strategy: MatchingStrategy,
     #[deserr(default, error = DeserrQueryParamError<InvalidSearchAttributesToSearchOn>)]
     pub attributes_to_search_on: Option<CS<String>>,
-    #[deserr(default, error = DeserrQueryParamError<InvalidEmbedder>)]
-    pub hybrid_embedder: Option<String>,
-    #[deserr(default, error = DeserrQueryParamError<InvalidSearchSemanticRatio>)]
-    pub hybrid_semantic_ratio: Option<SemanticRatioGet>,
-}
-
-#[derive(Debug, Clone, Copy, Default, PartialEq, deserr::Deserr)]
-#[deserr(try_from(String) = TryFrom::try_from -> InvalidSearchSemanticRatio)]
-pub struct SemanticRatioGet(SemanticRatio);
-
-impl std::convert::TryFrom<String> for SemanticRatioGet {
-    type Error = InvalidSearchSemanticRatio;
-
-    fn try_from(s: String) -> Result<Self, Self::Error> {
-        let f: f32 = s.parse().map_err(|_| InvalidSearchSemanticRatio)?;
-        Ok(SemanticRatioGet(SemanticRatio::try_from(f)?))
-    }
-}
-
-impl std::ops::Deref for SemanticRatioGet {
-    type Target = SemanticRatio;
-
-    fn deref(&self) -> &Self::Target {
-        &self.0
-    }
 }
 
 impl From<SearchQueryGet> for SearchQuery {
@@ -113,20 +86,6 @@ impl From<SearchQueryGet> for SearchQuery {
             None => None,
         };
 
-        let hybrid = match (other.hybrid_embedder, other.hybrid_semantic_ratio) {
-            (None, None) => None,
-            (None, Some(semantic_ratio)) => {
-                Some(HybridQuery { semantic_ratio: *semantic_ratio, embedder: None })
-            }
-            (Some(embedder), None) => Some(HybridQuery {
-                semantic_ratio: DEFAULT_SEMANTIC_RATIO(),
-                embedder: Some(embedder),
-            }),
-            (Some(embedder), Some(semantic_ratio)) => {
-                Some(HybridQuery { semantic_ratio: *semantic_ratio, embedder: Some(embedder) })
-            }
-        };
-
         Self {
             q: other.q,
             vector: other.vector.map(CS::into_inner),
@@ -149,7 +108,6 @@ impl From<SearchQueryGet> for SearchQuery {
             crop_marker: other.crop_marker,
             matching_strategy: other.matching_strategy,
             attributes_to_search_on: other.attributes_to_search_on.map(|o| o.into_iter().collect()),
-            hybrid,
         }
     }
 }
@@ -199,13 +157,9 @@ pub async fn search_with_url_query(
     let mut aggregate = SearchAggregator::from_query(&query, &req);
 
     let index = index_scheduler.index(&index_uid)?;
-    let features = index_scheduler.features();
-
-    let distribution = embed(&mut query, index_scheduler.get_ref(), &index).await?;
-
+    let features = index_scheduler.features()?;
     let search_result =
-        tokio::task::spawn_blocking(move || perform_search(&index, query, features, distribution))
-            .await?;
+        tokio::task::spawn_blocking(move || perform_search(&index, query, features)).await?;
     if let Ok(ref search_result) = search_result {
         aggregate.succeed(search_result);
     }
@@ -238,13 +192,9 @@ pub async fn search_with_post(
 
     let index = index_scheduler.index(&index_uid)?;
 
-    let features = index_scheduler.features();
-
-    let distribution = embed(&mut query, index_scheduler.get_ref(), &index).await?;
-
+    let features = index_scheduler.features()?;
     let search_result =
-        tokio::task::spawn_blocking(move || perform_search(&index, query, features, distribution))
-            .await?;
+        tokio::task::spawn_blocking(move || perform_search(&index, query, features)).await?;
     if let Ok(ref search_result) = search_result {
         aggregate.succeed(search_result);
     }
@@ -256,80 +206,6 @@ pub async fn search_with_post(
     Ok(HttpResponse::Ok().json(search_result))
 }
 
-pub async fn embed(
-    query: &mut SearchQuery,
-    index_scheduler: &IndexScheduler,
-    index: &milli::Index,
-) -> Result<Option<DistributionShift>, ResponseError> {
-    match (&query.hybrid, &query.vector, &query.q) {
-        (Some(HybridQuery { semantic_ratio: _, embedder }), None, Some(q))
-            if !q.trim().is_empty() =>
-        {
-            let embedder_configs = index.embedding_configs(&index.read_txn()?)?;
-            let embedders = index_scheduler.embedders(embedder_configs)?;
-
-            let embedder = if let Some(embedder_name) = embedder {
-                embedders.get(embedder_name)
-            } else {
-                embedders.get_default()
-            };
-
-            let embedder = embedder
-                .ok_or(milli::UserError::InvalidEmbedder("default".to_owned()))
-                .map_err(milli::Error::from)?
-                .0;
-
-            let distribution = embedder.distribution();
-
-            let embeddings = embedder
-                .embed(vec![q.to_owned()])
-                .await
-                .map_err(milli::vector::Error::from)
-                .map_err(milli::Error::from)?
-                .pop()
-                .expect("No vector returned from embedding");
-
-            if embeddings.iter().nth(1).is_some() {
-                warn!("Ignoring embeddings past the first one in long search query");
-                query.vector = Some(embeddings.iter().next().unwrap().to_vec());
-            } else {
-                query.vector = Some(embeddings.into_inner());
-            }
-            Ok(distribution)
-        }
-        (Some(hybrid), vector, _) => {
-            let embedder_configs = index.embedding_configs(&index.read_txn()?)?;
-            let embedders = index_scheduler.embedders(embedder_configs)?;
-
-            let embedder = if let Some(embedder_name) = &hybrid.embedder {
-                embedders.get(embedder_name)
-            } else {
-                embedders.get_default()
-            };
-
-            let embedder = embedder
-                .ok_or(milli::UserError::InvalidEmbedder("default".to_owned()))
-                .map_err(milli::Error::from)?
-                .0;
-
-            if let Some(vector) = vector {
-                if vector.len() != embedder.dimensions() {
-                    return Err(meilisearch_types::milli::Error::UserError(
-                        meilisearch_types::milli::UserError::InvalidVectorDimensions {
-                            expected: embedder.dimensions(),
-                            found: vector.len(),
-                        },
-                    )
-                    .into());
-                }
-            }
-
-            Ok(embedder.distribution())
-        }
-        _ => Ok(None),
-    }
-}
-
 #[cfg(test)]
 mod test {
     use super::*;

meilisearch/src/routes/indexes/settings.rs

@@ -7,7 +7,6 @@ use meilisearch_types::deserr::DeserrJsonError;
 use meilisearch_types::error::ResponseError;
 use meilisearch_types::facet_values_sort::FacetValuesSort;
 use meilisearch_types::index_uid::IndexUid;
-use meilisearch_types::milli::update::Setting;
 use meilisearch_types::settings::{settings, RankingRuleView, Settings, Unchecked};
 use meilisearch_types::tasks::KindWithContent;
 use serde_json::json;
@@ -15,7 +14,7 @@ use serde_json::json;
 use crate::analytics::Analytics;
 use crate::extractors::authentication::policies::*;
 use crate::extractors::authentication::GuardedData;
-use crate::routes::SummarizedTaskView;
+use crate::routes::{get_task_id, SummarizedTaskView};
 
 #[macro_export]
 macro_rules! make_setting_route {
@@ -34,7 +33,7 @@ macro_rules! make_setting_route {
             use $crate::extractors::authentication::policies::*;
             use $crate::extractors::authentication::GuardedData;
             use $crate::extractors::sequential_extractor::SeqHandler;
-            use $crate::routes::SummarizedTaskView;
+            use $crate::routes::{get_task_id, SummarizedTaskView};
 
             pub async fn delete(
                 index_scheduler: GuardedData<
@@ -42,6 +41,7 @@ macro_rules! make_setting_route {
                     Data<IndexScheduler>,
                 >,
                 index_uid: web::Path<String>,
+                req: HttpRequest,
             ) -> Result<HttpResponse, ResponseError> {
                 let index_uid = IndexUid::try_from(index_uid.into_inner())?;
 
@@ -56,8 +56,9 @@ macro_rules! make_setting_route {
                     is_deletion: true,
                     allow_index_creation,
                 };
+                let uid = get_task_id(&req)?;
                 let task: SummarizedTaskView =
-                    tokio::task::spawn_blocking(move || index_scheduler.register(task))
+                    tokio::task::spawn_blocking(move || index_scheduler.register(task, uid))
                         .await??
                         .into();
 
@@ -79,7 +80,6 @@ macro_rules! make_setting_route {
 
                 let body = body.into_inner();
 
-                #[allow(clippy::redundant_closure_call)]
                 $analytics(&body, &req);
 
                 let new_settings = Settings {
@@ -90,11 +90,6 @@ macro_rules! make_setting_route {
                     ..Default::default()
                 };
 
-                let new_settings = $crate::routes::indexes::settings::validate_settings(
-                    new_settings,
-                    &index_scheduler,
-                )?;
-
                 let allow_index_creation =
                     index_scheduler.filters().allow_index_creation(&index_uid);
 
@@ -104,8 +99,9 @@ macro_rules! make_setting_route {
                     is_deletion: false,
                     allow_index_creation,
                 };
+                let uid = get_task_id(&req)?;
                 let task: SummarizedTaskView =
-                    tokio::task::spawn_blocking(move || index_scheduler.register(task))
+                    tokio::task::spawn_blocking(move || index_scheduler.register(task, uid))
                         .await??
                         .into();
 
@@ -441,31 +437,6 @@ make_setting_route!(
     }
 );
 
-make_setting_route!(
-    "/proximity-precision",
-    put,
-    meilisearch_types::settings::ProximityPrecisionView,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsProximityPrecision,
-    >,
-    proximity_precision,
-    "proximityPrecision",
-    analytics,
-    |precision: &Option<meilisearch_types::settings::ProximityPrecisionView>, req: &HttpRequest| {
-        use serde_json::json;
-        analytics.publish(
-            "ProximityPrecision Updated".to_string(),
-            json!({
-                "proximity_precision": {
-                    "set": precision.is_some(),
-                    "value": precision.unwrap_or_default(),
-                }
-            }),
-            Some(req),
-        );
-    }
-);
-
 make_setting_route!(
     "/ranking-rules",
     put,
@@ -552,67 +523,6 @@ make_setting_route!(
     }
 );
 
-make_setting_route!(
-    "/embedders",
-    patch,
-    std::collections::BTreeMap<String, Setting<meilisearch_types::milli::vector::settings::EmbeddingSettings>>,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsEmbedders,
-    >,
-    embedders,
-    "embedders",
-    analytics,
-    |setting: &Option<std::collections::BTreeMap<String, Setting<meilisearch_types::milli::vector::settings::EmbeddingSettings>>>, req: &HttpRequest| {
-
-
-        analytics.publish(
-            "Embedders Updated".to_string(),
-            serde_json::json!({"embedders": crate::routes::indexes::settings::embedder_analytics(setting.as_ref())}),
-            Some(req),
-        );
-    }
-);
-
-fn embedder_analytics(
-    setting: Option<
-        &std::collections::BTreeMap<
-            String,
-            Setting<meilisearch_types::milli::vector::settings::EmbeddingSettings>,
-        >,
-    >,
-) -> serde_json::Value {
-    let mut sources = std::collections::HashSet::new();
-
-    if let Some(s) = &setting {
-        for source in s
-            .values()
-            .filter_map(|config| config.clone().set())
-            .filter_map(|config| config.source.set())
-        {
-            use meilisearch_types::milli::vector::settings::EmbedderSource;
-            match source {
-                EmbedderSource::OpenAi => sources.insert("openAi"),
-                EmbedderSource::HuggingFace => sources.insert("huggingFace"),
-                EmbedderSource::UserProvided => sources.insert("userProvided"),
-            };
-        }
-    };
-
-    let document_template_used = setting.as_ref().map(|map| {
-        map.values()
-            .filter_map(|config| config.clone().set())
-            .any(|config| config.document_template.set().is_some())
-    });
-
-    json!(
-        {
-            "total": setting.as_ref().map(|s| s.len()),
-            "sources": sources,
-            "document_template_used": document_template_used,
-        }
-    )
-}
-
 macro_rules! generate_configure {
     ($($mod:ident),*) => {
         pub fn configure(cfg: &mut web::ServiceConfig) {
@@ -633,7 +543,6 @@ generate_configure!(
     displayed_attributes,
     searchable_attributes,
     distinct_attribute,
-    proximity_precision,
     stop_words,
     separator_tokens,
     non_separator_tokens,
@@ -642,8 +551,7 @@ generate_configure!(
     ranking_rules,
     typo_tolerance,
     pagination,
-    faceting,
-    embedders
+    faceting
 );
 
 pub async fn update_all(
@@ -656,7 +564,6 @@ pub async fn update_all(
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
 
     let new_settings = body.into_inner();
-    let new_settings = validate_settings(new_settings, &index_scheduler)?;
 
     analytics.publish(
         "Settings Updated".to_string(),
@@ -689,10 +596,6 @@ pub async fn update_all(
             "distinct_attribute": {
                 "set": new_settings.distinct_attribute.as_ref().set().is_some()
             },
-            "proximity_precision": {
-                "set": new_settings.proximity_precision.as_ref().set().is_some(),
-                "value": new_settings.proximity_precision.as_ref().set().copied().unwrap_or_default()
-            },
             "typo_tolerance": {
                 "enabled": new_settings.typo_tolerance
                     .as_ref()
@@ -752,7 +655,6 @@ pub async fn update_all(
             "synonyms": {
                 "total": new_settings.synonyms.as_ref().set().map(|synonyms| synonyms.len()),
             },
-            "embedders": crate::routes::indexes::settings::embedder_analytics(new_settings.embedders.as_ref().set())
         }),
         Some(&req),
     );
@@ -765,8 +667,9 @@ pub async fn update_all(
         is_deletion: false,
         allow_index_creation,
     };
+    let uid = get_task_id(&req)?;
     let task: SummarizedTaskView =
-        tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
+        tokio::task::spawn_blocking(move || index_scheduler.register(task, uid)).await??.into();
 
     debug!("returns: {:?}", task);
     Ok(HttpResponse::Accepted().json(task))
@@ -788,6 +691,7 @@ pub async fn get_all(
 pub async fn delete_all(
     index_scheduler: GuardedData<ActionPolicy<{ actions::SETTINGS_UPDATE }>, Data<IndexScheduler>>,
     index_uid: web::Path<String>,
+    req: HttpRequest,
 ) -> Result<HttpResponse, ResponseError> {
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
 
@@ -801,19 +705,10 @@ pub async fn delete_all(
         is_deletion: true,
         allow_index_creation,
     };
+    let uid = get_task_id(&req)?;
     let task: SummarizedTaskView =
-        tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
+        tokio::task::spawn_blocking(move || index_scheduler.register(task, uid)).await??.into();
 
     debug!("returns: {:?}", task);
     Ok(HttpResponse::Accepted().json(task))
 }
-
-fn validate_settings(
-    settings: Settings<Unchecked>,
-    index_scheduler: &IndexScheduler,
-) -> Result<Settings<Unchecked>, ResponseError> {
-    if matches!(settings.embedders, Setting::Set(_)) {
-        index_scheduler.features().check_vector("Passing `embedders` in settings")?
-    }
-    Ok(settings.validate()?)
-}

meilisearch/src/routes/metrics.rs

@@ -19,7 +19,7 @@ pub async fn get_metrics(
     index_scheduler: GuardedData<ActionPolicy<{ actions::METRICS_GET }>, Data<IndexScheduler>>,
     auth_controller: Data<AuthController>,
 ) -> Result<HttpResponse, ResponseError> {
-    index_scheduler.features().check_metrics()?;
+    index_scheduler.features()?.check_metrics()?;
     let auth_filters = index_scheduler.filters();
     if !auth_filters.all_indexes_authorized() {
         let mut error = ResponseError::from(AuthenticationError::InvalidToken);

meilisearch/src/routes/mod.rs

@@ -5,7 +5,7 @@ use actix_web::{web, HttpRequest, HttpResponse};
 use index_scheduler::IndexScheduler;
 use log::debug;
 use meilisearch_auth::AuthController;
-use meilisearch_types::error::ResponseError;
+use meilisearch_types::error::{Code, ResponseError};
 use meilisearch_types::settings::{Settings, Unchecked};
 use meilisearch_types::tasks::{Kind, Status, Task, TaskId};
 use serde::{Deserialize, Serialize};
@@ -24,7 +24,6 @@ pub mod features;
 pub mod indexes;
 mod metrics;
 mod multi_search;
-mod snapshot;
 mod swap_indexes;
 pub mod tasks;
 
@@ -33,7 +32,6 @@ pub fn configure(cfg: &mut web::ServiceConfig) {
         .service(web::resource("/health").route(web::get().to(get_health)))
         .service(web::scope("/keys").configure(api_key::configure))
         .service(web::scope("/dumps").configure(dump::configure))
-        .service(web::scope("/snapshots").configure(snapshot::configure))
         .service(web::resource("/stats").route(web::get().to(get_stats)))
         .service(web::resource("/version").route(web::get().to(get_version)))
         .service(web::scope("/indexes").configure(indexes::configure))
@@ -43,6 +41,34 @@ pub fn configure(cfg: &mut web::ServiceConfig) {
         .service(web::scope("/experimental-features").configure(features::configure));
 }
 
+pub fn get_task_id(req: &HttpRequest) -> Result<Option<TaskId>, ResponseError> {
+    let task_id = req
+        .headers()
+        .get("TaskId")
+        .map(|header| {
+            header.to_str().map_err(|e| {
+                ResponseError::from_msg(
+                    format!("TaskId is not a valid utf-8 string: {e}"),
+                    Code::BadRequest,
+                )
+            })
+        })
+        .transpose()?
+        .map(|s| {
+            s.parse::<TaskId>().map_err(|e| {
+                ResponseError::from_msg(
+                    format!(
+                        "Could not parse the TaskId as a {}: {e}",
+                        std::any::type_name::<TaskId>(),
+                    ),
+                    Code::BadRequest,
+                )
+            })
+        })
+        .transpose()?;
+    Ok(task_id)
+}
+
 #[derive(Debug, Serialize)]
 #[serde(rename_all = "camelCase")]
 pub struct SummarizedTaskView {

meilisearch/src/routes/multi_search.rs

@@ -13,7 +13,6 @@ use crate::analytics::{Analytics, MultiSearchAggregator};
 use crate::extractors::authentication::policies::ActionPolicy;
 use crate::extractors::authentication::{AuthenticationError, GuardedData};
 use crate::extractors::sequential_extractor::SeqHandler;
-use crate::routes::indexes::search::embed;
 use crate::search::{
     add_search_rules, perform_search, SearchQueryWithIndex, SearchResultWithIndex,
 };
@@ -42,56 +41,54 @@ pub async fn multi_search_with_post(
     let queries = params.into_inner().queries;
 
     let mut multi_aggregate = MultiSearchAggregator::from_queries(&queries, &req);
-    let features = index_scheduler.features();
+    let features = index_scheduler.features()?;
 
     // 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!("multi-search #{query_index}: called with params: {:?}", query);
-
-            // Check index from API key
-            if !index_scheduler.filters().is_index_authorized(&index_uid) {
-                return 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)
+    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()
             {
-                add_search_rules(&mut query, search_rules);
+                debug!("multi-search #{query_index}: called with params: {:?}", query);
+
+                // Check index from API key
+                if !index_scheduler.filters().is_index_authorized(&index_uid) {
+                    return Err(AuthenticationError::InvalidToken).with_index(query_index);
+                }
+                // Apply search rules from tenant token
+                if let Some(search_rules) =
+                    index_scheduler.filters().get_index_search_rules(&index_uid)
+                {
+                    add_search_rules(&mut query, 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_result =
+                    tokio::task::spawn_blocking(move || perform_search(&index, query, features))
+                        .await
+                        .with_index(query_index)?;
+
+                search_results.push(SearchResultWithIndex {
+                    index_uid: index_uid.into_inner(),
+                    result: search_result.with_index(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 distribution = embed(&mut query, index_scheduler.get_ref(), &index)
-                .await
-                .with_index(query_index)?;
-
-            let search_result = tokio::task::spawn_blocking(move || {
-                perform_search(&index, query, features, distribution)
-            })
-            .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)
         }
-        Ok(search_results)
-    }
+    })()
     .await;
 
     if search_results.is_ok() {

meilisearch/src/routes/snapshot.rs

@@ -1,32 +0,0 @@
-use actix_web::web::Data;
-use actix_web::{web, HttpRequest, HttpResponse};
-use index_scheduler::IndexScheduler;
-use log::debug;
-use meilisearch_types::error::ResponseError;
-use meilisearch_types::tasks::KindWithContent;
-use serde_json::json;
-
-use crate::analytics::Analytics;
-use crate::extractors::authentication::policies::*;
-use crate::extractors::authentication::GuardedData;
-use crate::extractors::sequential_extractor::SeqHandler;
-use crate::routes::SummarizedTaskView;
-
-pub fn configure(cfg: &mut web::ServiceConfig) {
-    cfg.service(web::resource("").route(web::post().to(SeqHandler(create_snapshot))));
-}
-
-pub async fn create_snapshot(
-    index_scheduler: GuardedData<ActionPolicy<{ actions::SNAPSHOTS_CREATE }>, Data<IndexScheduler>>,
-    req: HttpRequest,
-    analytics: web::Data<dyn Analytics>,
-) -> Result<HttpResponse, ResponseError> {
-    analytics.publish("Snapshot Created".to_string(), json!({}), Some(&req));
-
-    let task = KindWithContent::SnapshotCreation;
-    let task: SummarizedTaskView =
-        tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
-
-    debug!("returns: {:?}", task);
-    Ok(HttpResponse::Accepted().json(task))
-}

meilisearch/src/routes/swap_indexes.rs

@@ -10,7 +10,7 @@ use meilisearch_types::index_uid::IndexUid;
 use meilisearch_types::tasks::{IndexSwap, KindWithContent};
 use serde_json::json;
 
-use super::SummarizedTaskView;
+use super::{get_task_id, SummarizedTaskView};
 use crate::analytics::Analytics;
 use crate::error::MeilisearchHttpError;
 use crate::extractors::authentication::policies::*;
@@ -60,7 +60,9 @@ pub async fn swap_indexes(
     }
 
     let task = KindWithContent::IndexSwap { swaps };
+
+    let uid = get_task_id(&req)?;
     let task: SummarizedTaskView =
-        tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
+        tokio::task::spawn_blocking(move || index_scheduler.register(task, uid)).await??.into();
     Ok(HttpResponse::Accepted().json(task))
 }

meilisearch/src/routes/tasks.rs

@@ -8,9 +8,11 @@ use meilisearch_types::deserr::DeserrQueryParamError;
 use meilisearch_types::error::deserr_codes::*;
 use meilisearch_types::error::{InvalidTaskDateError, ResponseError};
 use meilisearch_types::index_uid::IndexUid;
+use meilisearch_types::settings::{Settings, Unchecked};
 use meilisearch_types::star_or::{OptionStarOr, OptionStarOrList};
-use meilisearch_types::task_view::TaskView;
-use meilisearch_types::tasks::{Kind, KindWithContent, Status};
+use meilisearch_types::tasks::{
+    serialize_duration, Details, IndexSwap, Kind, KindWithContent, Status, Task,
+};
 use serde::Serialize;
 use serde_json::json;
 use time::format_description::well_known::Rfc3339;
@@ -18,13 +20,13 @@ use time::macros::format_description;
 use time::{Date, Duration, OffsetDateTime, Time};
 use tokio::task;
 
-use super::SummarizedTaskView;
+use super::{get_task_id, SummarizedTaskView};
 use crate::analytics::Analytics;
 use crate::extractors::authentication::policies::*;
 use crate::extractors::authentication::GuardedData;
 use crate::extractors::sequential_extractor::SeqHandler;
 
-const DEFAULT_LIMIT: u32 = 20;
+const DEFAULT_LIMIT: u64 = 20;
 
 pub fn configure(cfg: &mut web::ServiceConfig) {
     cfg.service(
@@ -35,18 +37,152 @@ pub fn configure(cfg: &mut web::ServiceConfig) {
     .service(web::resource("/cancel").route(web::post().to(SeqHandler(cancel_tasks))))
     .service(web::resource("/{task_id}").route(web::get().to(SeqHandler(get_task))));
 }
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct TaskView {
+    pub uid: TaskId,
+    #[serde(default)]
+    pub index_uid: Option<String>,
+    pub status: Status,
+    #[serde(rename = "type")]
+    pub kind: Kind,
+    pub canceled_by: Option<TaskId>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub details: Option<DetailsView>,
+    pub error: Option<ResponseError>,
+    #[serde(serialize_with = "serialize_duration", default)]
+    pub duration: Option<Duration>,
+    #[serde(with = "time::serde::rfc3339")]
+    pub enqueued_at: OffsetDateTime,
+    #[serde(with = "time::serde::rfc3339::option", default)]
+    pub started_at: Option<OffsetDateTime>,
+    #[serde(with = "time::serde::rfc3339::option", default)]
+    pub finished_at: Option<OffsetDateTime>,
+}
+
+impl TaskView {
+    pub fn from_task(task: &Task) -> TaskView {
+        TaskView {
+            uid: task.uid,
+            index_uid: task.index_uid().map(ToOwned::to_owned),
+            status: task.status,
+            kind: task.kind.as_kind(),
+            canceled_by: task.canceled_by,
+            details: task.details.clone().map(DetailsView::from),
+            error: task.error.clone(),
+            duration: task.started_at.zip(task.finished_at).map(|(start, end)| end - start),
+            enqueued_at: task.enqueued_at,
+            started_at: task.started_at,
+            finished_at: task.finished_at,
+        }
+    }
+}
+
+#[derive(Default, Debug, PartialEq, Eq, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct DetailsView {
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub received_documents: Option<u64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub indexed_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>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub deleted_documents: Option<Option<u64>>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub matched_tasks: Option<u64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub canceled_tasks: Option<Option<u64>>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub deleted_tasks: Option<Option<u64>>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub original_filter: Option<Option<String>>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub dump_uid: Option<Option<String>>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    #[serde(flatten)]
+    pub settings: Option<Box<Settings<Unchecked>>>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub swaps: Option<Vec<IndexSwap>>,
+}
+
+impl From<Details> for DetailsView {
+    fn from(details: Details) -> Self {
+        match details {
+            Details::DocumentAdditionOrUpdate { received_documents, indexed_documents } => {
+                DetailsView {
+                    received_documents: Some(received_documents),
+                    indexed_documents: Some(indexed_documents),
+                    ..DetailsView::default()
+                }
+            }
+            Details::SettingsUpdate { settings } => {
+                DetailsView { settings: Some(settings), ..DetailsView::default() }
+            }
+            Details::IndexInfo { primary_key } => {
+                DetailsView { primary_key: Some(primary_key), ..DetailsView::default() }
+            }
+            Details::DocumentDeletion {
+                provided_ids: received_document_ids,
+                deleted_documents,
+            } => DetailsView {
+                provided_ids: Some(received_document_ids),
+                deleted_documents: Some(deleted_documents),
+                original_filter: Some(None),
+                ..DetailsView::default()
+            },
+            Details::DocumentDeletionByFilter { original_filter, deleted_documents } => {
+                DetailsView {
+                    provided_ids: Some(0),
+                    original_filter: Some(Some(original_filter)),
+                    deleted_documents: Some(deleted_documents),
+                    ..DetailsView::default()
+                }
+            }
+            Details::ClearAll { deleted_documents } => {
+                DetailsView { deleted_documents: Some(deleted_documents), ..DetailsView::default() }
+            }
+            Details::TaskCancelation { matched_tasks, canceled_tasks, original_filter } => {
+                DetailsView {
+                    matched_tasks: Some(matched_tasks),
+                    canceled_tasks: Some(canceled_tasks),
+                    original_filter: Some(Some(original_filter)),
+                    ..DetailsView::default()
+                }
+            }
+            Details::TaskDeletion { matched_tasks, deleted_tasks, original_filter } => {
+                DetailsView {
+                    matched_tasks: Some(matched_tasks),
+                    deleted_tasks: Some(deleted_tasks),
+                    original_filter: Some(Some(original_filter)),
+                    ..DetailsView::default()
+                }
+            }
+            Details::Dump { dump_uid } => {
+                DetailsView { dump_uid: Some(dump_uid), ..DetailsView::default() }
+            }
+            Details::IndexSwap { swaps } => {
+                DetailsView { swaps: Some(swaps), ..Default::default() }
+            }
+        }
+    }
+}
+
 #[derive(Debug, Deserr)]
 #[deserr(error = DeserrQueryParamError, rename_all = camelCase, deny_unknown_fields)]
 pub struct TasksFilterQuery {
     #[deserr(default = Param(DEFAULT_LIMIT), error = DeserrQueryParamError<InvalidTaskLimit>)]
-    pub limit: Param<u32>,
+    pub limit: Param<TaskId>,
     #[deserr(default, error = DeserrQueryParamError<InvalidTaskFrom>)]
     pub from: Option<Param<TaskId>>,
 
     #[deserr(default, error = DeserrQueryParamError<InvalidTaskUids>)]
-    pub uids: OptionStarOrList<u32>,
+    pub uids: OptionStarOrList<TaskId>,
     #[deserr(default, error = DeserrQueryParamError<InvalidTaskCanceledBy>)]
-    pub canceled_by: OptionStarOrList<u32>,
+    pub canceled_by: OptionStarOrList<TaskId>,
     #[deserr(default, error = DeserrQueryParamError<InvalidTaskTypes>)]
     pub types: OptionStarOrList<Kind>,
     #[deserr(default, error = DeserrQueryParamError<InvalidTaskStatuses>)]
@@ -113,9 +249,9 @@ impl TaskDeletionOrCancelationQuery {
 #[deserr(error = DeserrQueryParamError, rename_all = camelCase, deny_unknown_fields)]
 pub struct TaskDeletionOrCancelationQuery {
     #[deserr(default, error = DeserrQueryParamError<InvalidTaskUids>)]
-    pub uids: OptionStarOrList<u32>,
+    pub uids: OptionStarOrList<TaskId>,
     #[deserr(default, error = DeserrQueryParamError<InvalidTaskCanceledBy>)]
-    pub canceled_by: OptionStarOrList<u32>,
+    pub canceled_by: OptionStarOrList<TaskId>,
     #[deserr(default, error = DeserrQueryParamError<InvalidTaskTypes>)]
     pub types: OptionStarOrList<Kind>,
     #[deserr(default, error = DeserrQueryParamError<InvalidTaskStatuses>)]
@@ -197,7 +333,9 @@ async fn cancel_tasks(
     let task_cancelation =
         KindWithContent::TaskCancelation { query: format!("?{}", req.query_string()), tasks };
 
-    let task = task::spawn_blocking(move || index_scheduler.register(task_cancelation)).await??;
+    let uid = get_task_id(&req)?;
+    let task =
+        task::spawn_blocking(move || index_scheduler.register(task_cancelation, uid)).await??;
     let task: SummarizedTaskView = task.into();
 
     Ok(HttpResponse::Ok().json(task))
@@ -242,7 +380,8 @@ async fn delete_tasks(
     let task_deletion =
         KindWithContent::TaskDeletion { query: format!("?{}", req.query_string()), tasks };
 
-    let task = task::spawn_blocking(move || index_scheduler.register(task_deletion)).await??;
+    let uid = get_task_id(&req)?;
+    let task = task::spawn_blocking(move || index_scheduler.register(task_deletion, uid)).await??;
     let task: SummarizedTaskView = task.into();
 
     Ok(HttpResponse::Ok().json(task))
@@ -252,9 +391,9 @@ async fn delete_tasks(
 pub struct AllTasks {
     results: Vec<TaskView>,
     total: u64,
-    limit: u32,
-    from: Option<u32>,
-    next: Option<u32>,
+    limit: TaskId,
+    from: Option<TaskId>,
+    next: Option<TaskId>,
 }
 
 async fn get_tasks(

meilisearch/src/search.rs

@@ -7,21 +7,24 @@ use deserr::Deserr;
 use either::Either;
 use index_scheduler::RoFeatures;
 use indexmap::IndexMap;
+use log::warn;
 use meilisearch_auth::IndexSearchRules;
 use meilisearch_types::deserr::DeserrJsonError;
 use meilisearch_types::error::deserr_codes::*;
 use meilisearch_types::heed::RoTxn;
 use meilisearch_types::index_uid::IndexUid;
-use meilisearch_types::milli::score_details::{self, ScoreDetails, ScoringStrategy};
-use meilisearch_types::milli::vector::DistributionShift;
-use meilisearch_types::milli::{FacetValueHit, OrderBy, SearchForFacetValues};
+use meilisearch_types::milli::score_details::{ScoreDetails, ScoringStrategy};
+use meilisearch_types::milli::{
+    dot_product_similarity, FacetValueHit, InternalError, OrderBy, SearchForFacetValues,
+};
 use meilisearch_types::settings::DEFAULT_PAGINATION_MAX_TOTAL_HITS;
 use meilisearch_types::{milli, Document};
 use milli::tokenizer::TokenizerBuilder;
 use milli::{
     AscDesc, FieldId, FieldsIdsMap, Filter, FormatOptions, Index, MatchBounds, MatcherBuilder,
-    SortError, TermsMatchingStrategy, DEFAULT_VALUES_PER_FACET,
+    SortError, TermsMatchingStrategy, VectorOrArrayOfVectors, DEFAULT_VALUES_PER_FACET,
 };
+use ordered_float::OrderedFloat;
 use regex::Regex;
 use serde::Serialize;
 use serde_json::{json, Value};
@@ -36,7 +39,6 @@ pub const DEFAULT_CROP_LENGTH: fn() -> usize = || 10;
 pub const DEFAULT_CROP_MARKER: fn() -> String = || "…".to_string();
 pub const DEFAULT_HIGHLIGHT_PRE_TAG: fn() -> String = || "<em>".to_string();
 pub const DEFAULT_HIGHLIGHT_POST_TAG: fn() -> String = || "</em>".to_string();
-pub const DEFAULT_SEMANTIC_RATIO: fn() -> SemanticRatio = || SemanticRatio(0.5);
 
 #[derive(Debug, Clone, Default, PartialEq, Deserr)]
 #[deserr(error = DeserrJsonError, rename_all = camelCase, deny_unknown_fields)]
@@ -45,8 +47,6 @@ pub struct SearchQuery {
     pub q: Option<String>,
     #[deserr(default, error = DeserrJsonError<InvalidSearchVector>)]
     pub vector: Option<Vec<f32>>,
-    #[deserr(default, error = DeserrJsonError<InvalidHybridQuery>)]
-    pub hybrid: Option<HybridQuery>,
     #[deserr(default = DEFAULT_SEARCH_OFFSET(), error = DeserrJsonError<InvalidSearchOffset>)]
     pub offset: usize,
     #[deserr(default = DEFAULT_SEARCH_LIMIT(), error = DeserrJsonError<InvalidSearchLimit>)]
@@ -87,48 +87,6 @@ pub struct SearchQuery {
     pub attributes_to_search_on: Option<Vec<String>>,
 }
 
-#[derive(Debug, Clone, Default, PartialEq, Deserr)]
-#[deserr(error = DeserrJsonError<InvalidHybridQuery>, rename_all = camelCase, deny_unknown_fields)]
-pub struct HybridQuery {
-    /// TODO validate that sementic ratio is between 0.0 and 1,0
-    #[deserr(default, error = DeserrJsonError<InvalidSearchSemanticRatio>, default)]
-    pub semantic_ratio: SemanticRatio,
-    #[deserr(default, error = DeserrJsonError<InvalidEmbedder>, default)]
-    pub embedder: Option<String>,
-}
-
-#[derive(Debug, Clone, Copy, PartialEq, Deserr)]
-#[deserr(try_from(f32) = TryFrom::try_from -> InvalidSearchSemanticRatio)]
-pub struct SemanticRatio(f32);
-
-impl Default for SemanticRatio {
-    fn default() -> Self {
-        DEFAULT_SEMANTIC_RATIO()
-    }
-}
-
-impl std::convert::TryFrom<f32> for SemanticRatio {
-    type Error = InvalidSearchSemanticRatio;
-
-    fn try_from(f: f32) -> Result<Self, Self::Error> {
-        // the suggested "fix" is: `!(0.0..=1.0).contains(&f)`` which is allegedly less readable
-        #[allow(clippy::manual_range_contains)]
-        if f > 1.0 || f < 0.0 {
-            Err(InvalidSearchSemanticRatio)
-        } else {
-            Ok(SemanticRatio(f))
-        }
-    }
-}
-
-impl std::ops::Deref for SemanticRatio {
-    type Target = f32;
-
-    fn deref(&self) -> &Self::Target {
-        &self.0
-    }
-}
-
 impl SearchQuery {
     pub fn is_finite_pagination(&self) -> bool {
         self.page.or(self.hits_per_page).is_some()
@@ -148,8 +106,6 @@ pub struct SearchQueryWithIndex {
     pub q: Option<String>,
     #[deserr(default, error = DeserrJsonError<InvalidSearchQ>)]
     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>)]
@@ -215,7 +171,6 @@ impl SearchQueryWithIndex {
             crop_marker,
             matching_strategy,
             attributes_to_search_on,
-            hybrid,
         } = self;
         (
             index_uid,
@@ -241,7 +196,6 @@ impl SearchQueryWithIndex {
                 crop_marker,
                 matching_strategy,
                 attributes_to_search_on,
-                hybrid,
                 // do not use ..Default::default() here,
                 // rather add any missing field from `SearchQuery` to `SearchQueryWithIndex`
             },
@@ -381,44 +335,19 @@ fn prepare_search<'t>(
     rtxn: &'t RoTxn,
     query: &'t SearchQuery,
     features: RoFeatures,
-    distribution: Option<DistributionShift>,
 ) -> Result<(milli::Search<'t>, bool, usize, usize), MeilisearchHttpError> {
     let mut search = index.search(rtxn);
 
-    if query.vector.is_some() {
-        features.check_vector("Passing `vector` as a query parameter")?;
+    if query.vector.is_some() && query.q.is_some() {
+        warn!("Ignoring the query string `q` when used with the `vector` parameter.");
     }
 
-    if query.hybrid.is_some() {
-        features.check_vector("Passing `hybrid` as a query parameter")?;
-    }
-
-    if query.hybrid.is_none() && query.q.is_some() && query.vector.is_some() {
-        return Err(MeilisearchHttpError::MissingSearchHybrid);
-    }
-
-    search.distribution_shift(distribution);
-
     if let Some(ref vector) = query.vector {
-        match &query.hybrid {
-            // If semantic ratio is 0.0, only the query search will impact the search results,
-            // skip the vector
-            Some(hybrid) if *hybrid.semantic_ratio == 0.0 => (),
-            _otherwise => {
-                search.vector(vector.clone());
-            }
-        }
+        search.vector(vector.clone());
     }
 
-    if let Some(ref q) = query.q {
-        match &query.hybrid {
-            // If semantic ratio is 1.0, only the vector search will impact the search results,
-            // skip the query
-            Some(hybrid) if *hybrid.semantic_ratio == 1.0 => (),
-            _otherwise => {
-                search.query(q);
-            }
-        }
+    if let Some(ref query) = query.q {
+        search.query(query);
     }
 
     if let Some(ref searchable) = query.attributes_to_search_on {
@@ -431,7 +360,6 @@ fn prepare_search<'t>(
     let max_total_hits = index
         .pagination_max_total_hits(rtxn)
         .map_err(milli::Error::from)?
-        .map(|x| x as usize)
         .unwrap_or(DEFAULT_PAGINATION_MAX_TOTAL_HITS);
 
     search.exhaustive_number_hits(is_finite_pagination);
@@ -445,8 +373,8 @@ fn prepare_search<'t>(
         features.check_score_details()?;
     }
 
-    if let Some(HybridQuery { embedder: Some(embedder), .. }) = &query.hybrid {
-        search.embedder_name(embedder);
+    if query.vector.is_some() {
+        features.check_vector()?;
     }
 
     // compute the offset on the limit depending on the pagination mode.
@@ -492,22 +420,15 @@ pub fn perform_search(
     index: &Index,
     query: SearchQuery,
     features: RoFeatures,
-    distribution: Option<DistributionShift>,
 ) -> Result<SearchResult, MeilisearchHttpError> {
     let before_search = Instant::now();
     let rtxn = index.read_txn()?;
 
     let (search, is_finite_pagination, max_total_hits, offset) =
-        prepare_search(index, &rtxn, &query, features, distribution)?;
+        prepare_search(index, &rtxn, &query, features)?;
 
     let milli::SearchResult { documents_ids, matching_words, candidates, document_scores, .. } =
-        match &query.hybrid {
-            Some(hybrid) => match *hybrid.semantic_ratio {
-                ratio if ratio == 0.0 || ratio == 1.0 => search.execute()?,
-                ratio => search.execute_hybrid(ratio)?,
-            },
-            None => search.execute()?,
-        };
+        search.execute()?;
 
     let fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
 
@@ -616,17 +537,13 @@ pub fn perform_search(
             insert_geo_distance(sort, &mut document);
         }
 
-        let mut semantic_score = None;
-        for details in &score {
-            if let ScoreDetails::Vector(score_details::Vector {
-                target_vector: _,
-                value_similarity: Some((_matching_vector, similarity)),
-            }) = details
-            {
-                semantic_score = Some(*similarity);
-                break;
-            }
-        }
+        let semantic_score = match query.vector.as_ref() {
+            Some(vector) => match extract_field("_vectors", &fields_ids_map, obkv)? {
+                Some(vectors) => compute_semantic_score(vector, vectors)?,
+                None => None,
+            },
+            None => None,
+        };
 
         let ranking_score =
             query.show_ranking_score.then(|| ScoreDetails::global_score(score.iter()));
@@ -669,7 +586,6 @@ pub fn perform_search(
             let max_values_by_facet = index
                 .max_values_per_facet(&rtxn)
                 .map_err(milli::Error::from)?
-                .map(|x| x as usize)
                 .unwrap_or(DEFAULT_VALUES_PER_FACET);
             facet_distribution.max_values_per_facet(max_values_by_facet);
 
@@ -729,15 +645,11 @@ pub fn perform_facet_search(
     let before_search = Instant::now();
     let rtxn = index.read_txn()?;
 
-    let (search, _, _, _) = prepare_search(index, &rtxn, &search_query, features, None)?;
-    let mut facet_search =
-        SearchForFacetValues::new(facet_name, search, search_query.hybrid.is_some());
+    let (search, _, _, _) = prepare_search(index, &rtxn, &search_query, features)?;
+    let mut facet_search = SearchForFacetValues::new(facet_name, search);
     if let Some(facet_query) = &facet_query {
         facet_search.query(facet_query);
     }
-    if let Some(max_facets) = index.max_values_per_facet(&rtxn)? {
-        facet_search.max_values(max_facets as usize);
-    }
 
     Ok(FacetSearchResult {
         facet_hits: facet_search.execute()?,
@@ -762,6 +674,18 @@ fn insert_geo_distance(sorts: &[String], document: &mut Document) {
     }
 }
 
+fn compute_semantic_score(query: &[f32], vectors: Value) -> milli::Result<Option<f32>> {
+    let vectors = serde_json::from_value(vectors)
+        .map(VectorOrArrayOfVectors::into_array_of_vectors)
+        .map_err(InternalError::SerdeJson)?;
+    Ok(vectors
+        .into_iter()
+        .flatten()
+        .map(|v| OrderedFloat(dot_product_similarity(query, &v)))
+        .max()
+        .map(OrderedFloat::into_inner))
+}
+
 fn compute_formatted_options(
     attr_to_highlight: &HashSet<String>,
     attr_to_crop: &[String],
@@ -889,6 +813,22 @@ fn make_document(
     Ok(document)
 }
 
+/// Extract the JSON value under the field name specified
+/// but doesn't support nested objects.
+fn extract_field(
+    field_name: &str,
+    field_ids_map: &FieldsIdsMap,
+    obkv: obkv::KvReaderU16,
+) -> Result<Option<serde_json::Value>, MeilisearchHttpError> {
+    match field_ids_map.id(field_name) {
+        Some(fid) => match obkv.get(fid) {
+            Some(value) => Ok(serde_json::from_slice(value).map(Some)?),
+            None => Ok(None),
+        },
+        None => Ok(None),
+    }
+}
+
 fn format_fields<'a>(
     document: &Document,
     field_ids_map: &FieldsIdsMap,
@@ -900,14 +840,6 @@ fn format_fields<'a>(
     let mut matches_position = compute_matches.then(BTreeMap::new);
     let mut document = document.clone();
 
-    // reduce the formatted option list to the attributes that should be formatted,
-    // instead of all the attributes to display.
-    let formatting_fields_options: Vec<_> = formatted_options
-        .iter()
-        .filter(|(_, option)| option.should_format())
-        .map(|(fid, option)| (field_ids_map.name(*fid).unwrap(), option))
-        .collect();
-
     // select the attributes to retrieve
     let displayable_names =
         displayable_ids.iter().map(|&fid| field_ids_map.name(fid).expect("Missing field name"));
@@ -916,15 +848,13 @@ fn format_fields<'a>(
         // to the value and merge them together. eg. If a user said he wanted to highlight `doggo`
         // and crop `doggo.name`. `doggo.name` needs to be highlighted + cropped while `doggo.age` is only
         // highlighted.
-        // Warn: The time to compute the format list scales with the number of fields to format;
-        // cumulated with map_leaf_values that iterates over all the nested fields, it gives a quadratic complexity:
-        // d*f where d is the total number of fields to display and f is the total number of fields to format.
-        let format = formatting_fields_options
+        let format = formatted_options
             .iter()
-            .filter(|(name, _option)| {
+            .filter(|(field, _option)| {
+                let name = field_ids_map.name(**field).unwrap();
                 milli::is_faceted_by(name, key) || milli::is_faceted_by(key, name)
             })
-            .map(|(_, option)| **option)
+            .map(|(_, option)| *option)
             .reduce(|acc, option| acc.merge(option));
         let mut infos = Vec::new();
 
@@ -1021,7 +951,7 @@ fn format_value<'a>(
                     let value = matcher.format(format_options);
                     Value::String(value.into_owned())
                 }
-                None => Value::String(s),
+                None => Value::Number(number),
             }
         }
         value => value,

meilisearch/tests/auth/api_keys.rs

@@ -1,7 +1,8 @@
 use std::{thread, time};
 
-use crate::common::{Server, Value};
-use crate::json;
+use serde_json::{json, Value};
+
+use crate::common::Server;
 
 #[actix_rt::test]
 async fn add_valid_api_key() {
@@ -161,7 +162,7 @@ async fn add_valid_api_key_null_description() {
     server.use_api_key("MASTER_KEY");
 
     let content = json!({
-        "description": json!(null),
+        "description": Value::Null,
         "indexes": ["products"],
         "actions": ["documents.add"],
         "expiresAt": "2050-11-13T00:00:00"
@@ -364,7 +365,7 @@ async fn error_add_api_key_invalid_index_uids() {
     server.use_api_key("MASTER_KEY");
 
     let content = json!({
-        "description": json!(null),
+        "description": Value::Null,
         "indexes": ["invalid index # / \\name with spaces"],
         "actions": [
             "documents.add"
@@ -421,7 +422,7 @@ async fn error_add_api_key_invalid_parameters_actions() {
     meili_snap::snapshot!(code, @"400 Bad Request");
     meili_snap::snapshot!(meili_snap::json_string!(response, { ".createdAt" => "[ignored]", ".updatedAt" => "[ignored]" }), @r###"
     {
-      "message": "Unknown value `doc.add` at `.actions[0]`: expected one of `*`, `search`, `documents.*`, `documents.add`, `documents.get`, `documents.delete`, `indexes.*`, `indexes.create`, `indexes.get`, `indexes.update`, `indexes.delete`, `indexes.swap`, `tasks.*`, `tasks.cancel`, `tasks.delete`, `tasks.get`, `settings.*`, `settings.get`, `settings.update`, `stats.*`, `stats.get`, `metrics.*`, `metrics.get`, `dumps.*`, `dumps.create`, `snapshots.*`, `snapshots.create`, `version`, `keys.create`, `keys.get`, `keys.update`, `keys.delete`, `experimental.get`, `experimental.update`",
+      "message": "Unknown value `doc.add` at `.actions[0]`: expected one of `*`, `search`, `documents.*`, `documents.add`, `documents.get`, `documents.delete`, `indexes.*`, `indexes.create`, `indexes.get`, `indexes.update`, `indexes.delete`, `indexes.swap`, `tasks.*`, `tasks.cancel`, `tasks.delete`, `tasks.get`, `settings.*`, `settings.get`, `settings.update`, `stats.*`, `stats.get`, `metrics.*`, `metrics.get`, `dumps.*`, `dumps.create`, `version`, `keys.create`, `keys.get`, `keys.update`, `keys.delete`, `experimental.get`, `experimental.update`",
       "code": "invalid_api_key_actions",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_api_key_actions"
@@ -506,7 +507,7 @@ async fn error_add_api_key_invalid_parameters_uid() {
 async fn error_add_api_key_parameters_uid_already_exist() {
     let mut server = Server::new_auth().await;
     server.use_api_key("MASTER_KEY");
-    let content: Value = json!({
+    let content = json!({
         "uid": "4bc0887a-0e41-4f3b-935d-0c451dcee9c8",
         "indexes": ["products"],
         "actions": ["search"],
@@ -1145,7 +1146,7 @@ async fn patch_api_key_description() {
     meili_snap::snapshot!(code, @"200 OK");
 
     // Remove the description
-    let content = json!({ "description": null });
+    let content = json!({ "description": serde_json::Value::Null });
 
     let (response, code) = server.patch_api_key(&uid, content).await;
     meili_snap::snapshot!(meili_snap::json_string!(response, { ".createdAt" => "[ignored]", ".updatedAt" => "[ignored]", ".uid" => "[ignored]", ".key" => "[ignored]" }), @r###"

meilisearch/tests/auth/authorization.rs

@@ -2,13 +2,11 @@ use std::collections::{HashMap, HashSet};
 
 use ::time::format_description::well_known::Rfc3339;
 use maplit::{hashmap, hashset};
-use meilisearch::Opt;
 use once_cell::sync::Lazy;
-use tempfile::TempDir;
+use serde_json::{json, Value};
 use time::{Duration, OffsetDateTime};
 
-use crate::common::{default_settings, Server, Value};
-use crate::json;
+use crate::common::Server;
 
 pub static AUTHORIZATIONS: Lazy<HashMap<(&'static str, &'static str), HashSet<&'static str>>> =
     Lazy::new(|| {
@@ -56,7 +54,6 @@ pub static AUTHORIZATIONS: Lazy<HashMap<(&'static str, &'static str), HashSet<&'
             ("GET",     "/indexes/products/stats") =>                          hashset!{"stats.get", "stats.*", "*"},
             ("GET",     "/stats") =>                                           hashset!{"stats.get", "stats.*", "*"},
             ("POST",    "/dumps") =>                                           hashset!{"dumps.create", "dumps.*", "*"},
-            ("POST",    "/snapshots") =>                                       hashset!{"snapshots.create", "snapshots.*", "*"},
             ("GET",     "/version") =>                                         hashset!{"version", "*"},
             ("GET",     "/metrics") =>                                         hashset!{"metrics.get", "metrics.*", "*"},
             ("PATCH",   "/keys/mykey/") =>                                     hashset!{"keys.update", "*"},
@@ -197,9 +194,7 @@ async fn access_authorized_master_key() {
 
 #[actix_rt::test]
 async fn access_authorized_restricted_index() {
-    let dir = TempDir::new().unwrap();
-    let enable_metrics = Opt { experimental_enable_metrics: true, ..default_settings(dir.path()) };
-    let mut server = Server::new_auth_with_options(enable_metrics, dir).await;
+    let mut server = Server::new_auth().await;
     for ((method, route), actions) in AUTHORIZATIONS.iter() {
         for action in actions {
             // create a new API key letting only the needed action.

meilisearch/tests/auth/errors.rs

@@ -1,8 +1,8 @@
 use meili_snap::*;
+use serde_json::json;
 use uuid::Uuid;
 
 use crate::common::Server;
-use crate::json;
 
 #[actix_rt::test]
 async fn create_api_key_bad_description() {
@@ -90,7 +90,7 @@ async fn create_api_key_bad_actions() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Unknown value `doggo` at `.actions[0]`: expected one of `*`, `search`, `documents.*`, `documents.add`, `documents.get`, `documents.delete`, `indexes.*`, `indexes.create`, `indexes.get`, `indexes.update`, `indexes.delete`, `indexes.swap`, `tasks.*`, `tasks.cancel`, `tasks.delete`, `tasks.get`, `settings.*`, `settings.get`, `settings.update`, `stats.*`, `stats.get`, `metrics.*`, `metrics.get`, `dumps.*`, `dumps.create`, `snapshots.*`, `snapshots.create`, `version`, `keys.create`, `keys.get`, `keys.update`, `keys.delete`, `experimental.get`, `experimental.update`",
+      "message": "Unknown value `doggo` at `.actions[0]`: expected one of `*`, `search`, `documents.*`, `documents.add`, `documents.get`, `documents.delete`, `indexes.*`, `indexes.create`, `indexes.get`, `indexes.update`, `indexes.delete`, `indexes.swap`, `tasks.*`, `tasks.cancel`, `tasks.delete`, `tasks.get`, `settings.*`, `settings.get`, `settings.update`, `stats.*`, `stats.get`, `metrics.*`, `metrics.get`, `dumps.*`, `dumps.create`, `version`, `keys.create`, `keys.get`, `keys.update`, `keys.delete`, `experimental.get`, `experimental.update`",
       "code": "invalid_api_key_actions",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_api_key_actions"

meilisearch/tests/auth/mod.rs

@@ -7,9 +7,9 @@ mod tenant_token;
 mod tenant_token_multi_search;
 
 use actix_web::http::StatusCode;
+use serde_json::{json, Value};
 
-use crate::common::{Server, Value};
-use crate::json;
+use crate::common::Server;
 
 impl Server {
     pub fn use_api_key(&mut self, api_key: impl AsRef<str>) {

meilisearch/tests/auth/tenant_token.rs

@@ -3,11 +3,11 @@ use std::collections::HashMap;
 use ::time::format_description::well_known::Rfc3339;
 use maplit::hashmap;
 use once_cell::sync::Lazy;
+use serde_json::{json, Value};
 use time::{Duration, OffsetDateTime};
 
 use super::authorization::{ALL_ACTIONS, AUTHORIZATIONS};
-use crate::common::{Server, Value};
-use crate::json;
+use crate::common::Server;
 
 fn generate_tenant_token(
     parent_uid: impl AsRef<str>,
@@ -233,31 +233,31 @@ async fn search_authorized_simple_token() {
         },
         hashmap! {
             "searchRules" => json!({"*": {}}),
-            "exp" => json!(null)
+            "exp" => Value::Null
         },
         hashmap! {
-            "searchRules" => json!({"*": null}),
-            "exp" => json!(null)
+            "searchRules" => json!({"*": Value::Null}),
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!(["*"]),
-            "exp" => json!(null)
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!({"sales": {}}),
-            "exp" => json!(null)
+            "exp" => Value::Null
         },
         hashmap! {
-            "searchRules" => json!({"sales": null}),
-            "exp" => json!(null)
+            "searchRules" => json!({"sales": Value::Null}),
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!(["sales"]),
-            "exp" => json!(null)
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!(["sa*"]),
-            "exp" => json!(null)
+            "exp" => Value::Null
         },
     ];
 
@@ -386,7 +386,7 @@ async fn error_search_token_forbidden_parent_key() {
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
-            "searchRules" => json!({"*": null}),
+            "searchRules" => json!({"*": Value::Null}),
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
@@ -398,7 +398,7 @@ async fn error_search_token_forbidden_parent_key() {
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
-            "searchRules" => json!({"sales": null}),
+            "searchRules" => json!({"sales": Value::Null}),
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
@@ -428,15 +428,15 @@ async fn error_search_forbidden_token() {
         },
         hashmap! {
             "searchRules" => json!({"products": {}}),
-            "exp" => json!(null)
+            "exp" => Value::Null
         },
         hashmap! {
-            "searchRules" => json!({"products": null}),
-            "exp" => json!(null)
+            "searchRules" => json!({"products": Value::Null}),
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!(["products"]),
-            "exp" => json!(null)
+            "exp" => Value::Null
         },
         // expired token
         hashmap! {
@@ -444,7 +444,7 @@ async fn error_search_forbidden_token() {
             "exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
-            "searchRules" => json!({"*": null}),
+            "searchRules" => json!({"*": Value::Null}),
             "exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
@@ -456,7 +456,7 @@ async fn error_search_forbidden_token() {
             "exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
-            "searchRules" => json!({"sales": null}),
+            "searchRules" => json!({"sales": Value::Null}),
             "exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
         },
         hashmap! {