WIP

.github/ISSUE_TEMPLATE/new_feature_issue.md

@@ -24,11 +24,6 @@ TBD
 - [ ] If not, add the `no db change` label to your PR, and you're good to merge.
 - [ ] If yes, add the `db change` label to your PR. You'll receive a message explaining you what to do.
 
-### Reminders when adding features
-
-- [ ] Write unit tests using insta
-- [ ] Write declarative integration tests in [workloads/tests](https://github.com/meilisearch/meilisearch/tree/main/workloads/test). Specify the routes to call and then call `cargo xtask test workloads/tests/YOUR_TEST.json --update-responses` so that responses are automatically filled.
-
 ### Reminders when modifying the API
 
 - [ ] Update the openAPI file with utoipa:

.github/dependabot.yml

@@ -7,5 +7,6 @@ updates:
     schedule:
       interval: "monthly"
     labels:
+      - 'skip changelog'
       - 'dependencies'
     rebase-strategy: disabled

.github/release-draft-template.yml

@@ -0,0 +1,33 @@
+name-template: 'v$RESOLVED_VERSION'
+tag-template: 'v$RESOLVED_VERSION'
+exclude-labels:
+  - 'skip changelog'
+version-resolver:
+  minor:
+    labels:
+      - 'enhancement'
+  default: patch
+categories:
+  - title: '⚠️ Breaking changes'
+    label: 'breaking-change'
+  - title: '🚀 Enhancements'
+    label: 'enhancement'
+  - title: '🐛 Bug Fixes'
+    label: 'bug'
+  - title: '🔒 Security'
+    label: 'security'
+  - title: '⚙️ Maintenance/misc'
+    label:
+      - 'maintenance'
+      - 'documentation'
+template: |
+  $CHANGES
+
+  ❤️  Huge thanks to our contributors: $CONTRIBUTORS.
+no-changes-template: 'Changes are coming soon 😎'
+sort-direction: 'ascending'
+replacers:
+  - search: '/(?:and )?@dependabot-preview(?:\[bot\])?,?/g'
+    replace: ''
+  - search: '/(?:and )?@dependabot(?:\[bot\])?,?/g'
+    replace: ''

.github/workflows/bench-pr.yml

@@ -67,6 +67,8 @@ jobs:
           ref: ${{ steps.comment-branch.outputs.head_ref }}
 
       - uses: dtolnay/rust-toolchain@1.89
+        with:
+          profile: minimal
 
       - name: Run benchmarks on PR ${{ github.event.issue.id }}
         run: |

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

@@ -13,6 +13,8 @@ jobs:
     steps:
       - uses: actions/checkout@v5
       - uses: dtolnay/rust-toolchain@1.89
+        with:
+          profile: minimal
 
       # Run benchmarks
       - name: Run benchmarks - Dataset ${BENCH_NAME} - Branch main - Commit ${{ github.sha }}

.github/workflows/db-change-comments.yml

@@ -19,7 +19,6 @@ env:
 
     - [ ] Detail the change to the DB format and why they are forward compatible
     - [ ] Forward-compatibility: A database created before this PR and using the features touched by this PR was able to be opened by a Meilisearch produced by the code of this PR.
-    - [ ] Declarative test: add a [declarative test containing a dumpless upgrade](https://github.com/meilisearch/meilisearch/blob/main/TESTING.md#typical-usage)
 
 
     ## This PR makes breaking changes
@@ -36,7 +35,8 @@ env:
       - [ ] Write the code to go from the old database to the new one
         - If the change happened in milli, the upgrade function should be written and called [here](https://github.com/meilisearch/meilisearch/blob/3fd86e8d76d7d468b0095d679adb09211ca3b6c0/crates/milli/src/update/upgrade/mod.rs#L24-L47)
         - If the change happened in the index-scheduler, we've never done it yet, but the right place to do it should be [here](https://github.com/meilisearch/meilisearch/blob/3fd86e8d76d7d468b0095d679adb09211ca3b6c0/crates/index-scheduler/src/scheduler/process_upgrade/mod.rs#L13)
-      - [ ] Declarative test: add a [declarative test containing a dumpless upgrade](https://github.com/meilisearch/meilisearch/blob/main/TESTING.md#typical-usage)
+      - [ ] Write an integration test [here](https://github.com/meilisearch/meilisearch/blob/main/crates/meilisearch/tests/upgrade/mod.rs) ensuring you can read the old database, upgrade to the new database, and read the new database as expected
+    
 
 jobs:
   add-comment:

.github/workflows/flaky-tests.yml

@@ -13,12 +13,6 @@ jobs:
       image: ubuntu:22.04
     steps:
       - uses: actions/checkout@v5
-      - name: Clean space as per https://github.com/actions/virtual-environments/issues/709
-        run: |
-          sudo rm -rf "/opt/ghc" || true
-          sudo rm -rf "/usr/share/dotnet" || true
-          sudo rm -rf "/usr/local/lib/android" || true
-          sudo rm -rf "/usr/local/share/boost" || true
       - name: Install needed dependencies
         run: |
           apt-get update && apt-get install -y curl

.github/workflows/fuzzer-indexing.yml

@@ -13,6 +13,8 @@ jobs:
     steps:
       - uses: actions/checkout@v5
       - uses: dtolnay/rust-toolchain@1.89
+        with:
+          profile: minimal
 
       # Run benchmarks
       - name: Run the fuzzer

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

@@ -25,12 +25,6 @@ jobs:
         run: |
           apt-get update && apt-get install -y curl
           apt-get install build-essential -y
-      - name: Clean space as per https://github.com/actions/virtual-environments/issues/709
-        run: |
-          sudo rm -rf "/opt/ghc" || true
-          sudo rm -rf "/usr/share/dotnet" || true
-          sudo rm -rf "/usr/local/lib/android" || true
-          sudo rm -rf "/usr/local/share/boost" || true
       - uses: dtolnay/rust-toolchain@1.89
       - name: Install cargo-deb
         run: cargo install cargo-deb

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

@@ -14,105 +14,10 @@ on:
   workflow_dispatch:
 
 jobs:
-  build:
+  docker:
-    runs-on: ${{ matrix.runner }}
+    runs-on: docker
-
-    strategy:
-      matrix:
-        platform: [amd64, arm64]
-        edition: [community, enterprise]
-        include:
-          - platform: amd64
-            runner: ubuntu-24.04
-          - platform: arm64
-            runner: ubuntu-24.04-arm
-          - edition: community
-            registry: getmeili/meilisearch
-            feature-flag: ""
-          - edition: enterprise
-            registry: getmeili/meilisearch-enterprise
-            feature-flag: "--features enterprise"
-
-    permissions: {}
-    steps:
-      - uses: actions/checkout@v5
-
-      - name: Prepare
-        run: |
-          platform=linux/${{ matrix.platform }}
-          echo "PLATFORM_PAIR=${platform//\//-}" >> $GITHUB_ENV
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-        with:
-          platforms: linux/${{ matrix.platform }}
-          install: true
-
-      - name: Login to Docker Hub
-        uses: docker/login-action@v3
-        with:
-          username: ${{ secrets.DOCKERHUB_USERNAME }}
-          password: ${{ secrets.DOCKERHUB_TOKEN }}
-
-      - name: Docker meta
-        id: meta
-        uses: docker/metadata-action@v5
-        with:
-          images: ${{ matrix.registry }}
-          # Prevent `latest` to be updated for each new tag pushed.
-          # We need latest and `vX.Y` tags to only be pushed for the stable Meilisearch releases.
-          flavor: latest=false
-          tags: |
-            type=ref,event=tag
-            type=raw,value=nightly,enable=${{ github.event_name != 'push' }}
-            type=semver,pattern=v{{major}}.{{minor}},enable=${{ steps.check-tag-format.outputs.stable == 'true' }}
-            type=semver,pattern=v{{major}},enable=${{ steps.check-tag-format.outputs.stable == 'true' }}
-            type=raw,value=latest,enable=${{ steps.check-tag-format.outputs.stable == 'true' && steps.check-tag-format.outputs.latest == 'true' }}
-
-      - name: Build and push by digest
-        uses: docker/build-push-action@v6
-        id: build-and-push
-        with:
-          platforms: linux/${{ matrix.platform }}
-          labels: ${{ steps.meta.outputs.labels }}
-          tags: ${{ matrix.registry }}
-          outputs: type=image,push-by-digest=true,name-canonical=true,push=true
-          build-args: |
-            COMMIT_SHA=${{ github.sha }}
-            COMMIT_DATE=${{ steps.build-metadata.outputs.date }}
-            GIT_TAG=${{ github.ref_name }}
-            EXTRA_ARGS=${{ matrix.feature-flag }}
-
-      - name: Export digest
-        run: |
-          mkdir -p ${{ runner.temp }}/digests
-          digest="${{ steps.build-and-push.outputs.digest }}"
-          touch "${{ runner.temp }}/digests/${digest#sha256:}"
-
-      - name: Upload digest
-        uses: actions/upload-artifact@v4
-        with:
-          name: digests-${{ matrix.edition }}-${{ env.PLATFORM_PAIR }}
-          path: ${{ runner.temp }}/digests/*
-          if-no-files-found: error
-          retention-days: 1
-
-  merge:
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        edition: [community, enterprise]
-        include:
-          - edition: community
-            registry: getmeili/meilisearch
-          - edition: enterprise
-            registry: getmeili/meilisearch-enterprise
-    needs:
-      - build
-
     permissions:
       id-token: write # This is needed to use Cosign in keyless mode
-
     steps:
       - uses: actions/checkout@v5
 
@@ -153,15 +58,14 @@ jobs:
 
           echo "date=$commit_date" >> $GITHUB_OUTPUT
 
-      - name: Install cosign
+      - name: Set up QEMU
-        uses: sigstore/cosign-installer@d7543c93d881b35a8faa02e8e3605f69b7a1ce62 # tag=v3.10.0
+        uses: docker/setup-qemu-action@v3
 
-      - name: Download digests
+      - name: Set up Docker Buildx
-        uses: actions/download-artifact@v4
+        uses: docker/setup-buildx-action@v3
-        with:
+
-          path: ${{ runner.temp }}/digests
+      - name: Install cosign
-          pattern: digests-${{ matrix.edition }}-*
+        uses: sigstore/cosign-installer@d58896d6a1865668819e1d91763c7751a165e159 # tag=v3.9.2
-          merge-multiple: true
 
       - name: Login to Docker Hub
         uses: docker/login-action@v3
@@ -169,14 +73,11 @@ jobs:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-
       - name: Docker meta
         id: meta
         uses: docker/metadata-action@v5
         with:
-          images: ${{ matrix.registry }}
+          images: getmeili/meilisearch
           # Prevent `latest` to be updated for each new tag pushed.
           # We need latest and `vX.Y` tags to only be pushed for the stable Meilisearch releases.
           flavor: latest=false
@@ -187,31 +88,33 @@ jobs:
             type=semver,pattern=v{{major}},enable=${{ steps.check-tag-format.outputs.stable == 'true' }}
             type=raw,value=latest,enable=${{ steps.check-tag-format.outputs.stable == 'true' && steps.check-tag-format.outputs.latest == 'true' }}
 
-      - name: Create manifest list and push
+      - name: Build and push
-        working-directory: ${{ runner.temp }}/digests
+        uses: docker/build-push-action@v6
-        run: |
+        id: build-and-push
-          docker buildx imagetools create $(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "$DOCKER_METADATA_OUTPUT_JSON") \
+        with:
-            $(printf '${{ matrix.registry }}@sha256:%s ' *)
+          push: true
-
+          platforms: linux/amd64,linux/arm64
-      - name: Inspect image to fetch digest to sign
+          tags: ${{ steps.meta.outputs.tags }}
-        run: |
+          build-args: |
-          digest=$(docker buildx imagetools inspect --format='{{ json .Manifest }}' ${{ matrix.registry }}:${{ steps.meta.outputs.version }} | jq -r '.digest')
+            COMMIT_SHA=${{ github.sha }}
-          echo "DIGEST=${digest}" >> $GITHUB_ENV
+            COMMIT_DATE=${{ steps.build-metadata.outputs.date }}
+            GIT_TAG=${{ github.ref_name }}
 
       - name: Sign the images with GitHub OIDC Token
         env:
+          DIGEST: ${{ steps.build-and-push.outputs.digest }}
           TAGS: ${{ steps.meta.outputs.tags }}
         run: |
           images=""
           for tag in ${TAGS}; do
-            images+="${tag}@${{ env.DIGEST }} "
+            images+="${tag}@${DIGEST} "
           done
           cosign sign --yes ${images}
 
-      # /!\ Don't touch this without checking with engineers working on the Cloud code base on #discussion-engineering Slack channel
+      # /!\ Don't touch this without checking with Cloud team
-      - name: Notify meilisearch-cloud 
+      - name: Send CI information to Cloud team
         # Do not send if nightly build (i.e. 'schedule' or 'workflow_dispatch' event)
-        if: ${{ (github.event_name == 'push') && (matrix.edition == 'enterprise') }}
+        if: github.event_name == 'push'
         uses: peter-evans/repository-dispatch@v3
         with:
           token: ${{ secrets.MEILI_BOT_GH_PAT }}
@@ -219,13 +122,21 @@ jobs:
           event-type: cloud-docker-build
           client-payload: '{ "meilisearch_version": "${{ github.ref_name }}", "stable": "${{ steps.check-tag-format.outputs.stable }}" }'
 
-      # /!\ Don't touch this without checking with integration team members on #discussion-integrations Slack channel 
+      # Send notification to Swarmia to notify of a deployment: https://app.swarmia.com
-      - name: Notify meilisearch-kubernetes
+      # - name: 'Setup jq'
-        # Do not send if nightly build (i.e. 'schedule' or 'workflow_dispatch' event), or if not stable
+      #   uses: dcarbone/install-jq-action
-        if: ${{ github.event_name == 'push' && matrix.edition == 'community' && steps.check-tag-format.outputs.stable == 'true' }}
+      # - name: Send deployment to Swarmia
-        uses: peter-evans/repository-dispatch@v3
+      #   if: github.event_name == 'push' && success()
-        with:
+      #   run: |
-          token: ${{ secrets.MEILI_BOT_GH_PAT }}
+      #     JSON_STRING=$( jq --null-input --compact-output \
-          repository: meilisearch/meilisearch-kubernetes
+      #     --arg version "${{ github.ref_name }}" \
-          event-type: meilisearch-release
+      #     --arg appName "meilisearch" \
-          client-payload: '{ "version": "${{ github.ref_name }}" }'
+      #     --arg environment "production" \
+      #     --arg commitSha "${{ github.sha }}" \
+      #     --arg repositoryFullName "${{ github.repository }}" \
+      #     '{"version": $version, "appName": $appName, "environment": $environment, "commitSha": $commitSha, "repositoryFullName": $repositoryFullName}' )
+
+      #     curl -H "Authorization: ${{ secrets.SWARMIA_DEPLOYMENTS_AUTHORIZATION }}" \
+      #       -H "Content-Type: application/json" \
+      #       -d "$JSON_STRING" \
+      #       https://hook.swarmia.com/deployments

.github/workflows/publish-release-assets.yml

@@ -11,7 +11,7 @@ jobs:
   check-version:
     name: Check the version validity
     runs-on: ubuntu-latest
-    # No need to check the version for dry run (cron or workflow_dispatch)
+    # No need to check the version for dry run (cron)
     steps:
       - uses: actions/checkout@v5
       # Check if the tag has the v<nmumber>.<number>.<number> format.
@@ -32,66 +32,161 @@ jobs:
         if: github.event_name == 'release' && steps.check-tag-format.outputs.stable == 'true'
         run: bash .github/scripts/check-release.sh
 
-  publish-binaries:
+  publish-linux:
-    name: Publish binary for ${{ matrix.release }} ${{ matrix.edition }} edition
+    name: Publish binary for Linux
-    runs-on: ${{ matrix.os }}
+    runs-on: ubuntu-latest
-    strategy:
-      fail-fast: false
-      matrix:
-        edition: [community, enterprise]
-        release:
-          [macos-amd64, macos-aarch64, windows, linux-amd64, linux-aarch64]
-        include:
-          - edition: "community"
-            feature-flag: ""
-            edition-suffix: ""
-          - edition: "enterprise"
-            feature-flag: "--features enterprise"
-            edition-suffix: "enterprise-"
-          - release: macos-amd64
-            os: macos-15-intel
-            binary_path: release/meilisearch
-            asset_name: macos-amd64
-            extra-args: ""
-          - release: macos-aarch64
-            os: macos-14
-            binary_path: aarch64-apple-darwin/release/meilisearch
-            asset_name: macos-apple-silicon
-            extra-args: "--target aarch64-apple-darwin"
-          - release: windows
-            os: windows-2022
-            binary_path: release/meilisearch.exe
-            asset_name: windows-amd64.exe
-            extra-args: ""
-          - release: linux-amd64
-            os: ubuntu-22.04
-            binary_path: x86_64-unknown-linux-gnu/release/meilisearch
-            asset_name: linux-amd64
-            extra-args: "--target x86_64-unknown-linux-gnu"
-          - release: linux-aarch64
-            os: ubuntu-22.04-arm
-            binary_path: aarch64-unknown-linux-gnu/release/meilisearch
-            asset_name: linux-aarch64
-            extra-args: "--target aarch64-unknown-linux-gnu"
     needs: check-version
+    container:
+      # Use ubuntu-22.04 to compile with glibc 2.35
+      image: ubuntu:22.04
     steps:
       - uses: actions/checkout@v5
+      - name: Install needed dependencies
+        run: |
+          apt-get update && apt-get install -y curl
+          apt-get install build-essential -y
       - uses: dtolnay/rust-toolchain@1.89
       - name: Build
-        run: cargo build --release --locked ${{ matrix.feature-flag }} ${{ matrix.extra-args }}
+        run: cargo build --release --locked
-      # No need to upload binaries for dry run (cron or workflow_dispatch)
+      # No need to upload binaries for dry run (cron)
       - name: Upload binaries to release
         if: github.event_name == 'release'
         uses: svenstaro/upload-release-action@2.11.2
         with:
           repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
-          file: target/${{ matrix.binary_path }}
+          file: target/release/meilisearch
-          asset_name: meilisearch-${{ matrix.edition-suffix }}${{ matrix.asset_name }}
+          asset_name: meilisearch-linux-amd64
+          tag: ${{ github.ref }}
+
+  publish-macos-windows:
+    name: Publish binary for ${{ matrix.os }}
+    runs-on: ${{ matrix.os }}
+    needs: check-version
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [macos-13, windows-2022]
+        include:
+          - os: macos-13
+            artifact_name: meilisearch
+            asset_name: meilisearch-macos-amd64
+          - os: windows-2022
+            artifact_name: meilisearch.exe
+            asset_name: meilisearch-windows-amd64.exe
+    steps:
+      - uses: actions/checkout@v5
+      - uses: dtolnay/rust-toolchain@1.89
+      - name: Build
+        run: cargo build --release --locked
+      # No need to upload binaries for dry run (cron)
+      - name: Upload binaries to release
+        if: github.event_name == 'release'
+        uses: svenstaro/upload-release-action@2.11.2
+        with:
+          repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
+          file: target/release/${{ matrix.artifact_name }}
+          asset_name: ${{ matrix.asset_name }}
+          tag: ${{ github.ref }}
+
+  publish-macos-apple-silicon:
+    name: Publish binary for macOS silicon
+    runs-on: macos-13
+    needs: check-version
+    strategy:
+      matrix:
+        include:
+          - target: aarch64-apple-darwin
+            asset_name: meilisearch-macos-apple-silicon
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v5
+      - name: Installing Rust toolchain
+        uses: dtolnay/rust-toolchain@1.89
+        with:
+          profile: minimal
+          target: ${{ matrix.target }}
+      - name: Cargo build
+        uses: actions-rs/cargo@v1
+        with:
+          command: build
+          args: --release --target ${{ matrix.target }}
+      - name: Upload the binary to release
+        # No need to upload binaries for dry run (cron)
+        if: github.event_name == 'release'
+        uses: svenstaro/upload-release-action@2.11.2
+        with:
+          repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
+          file: target/${{ matrix.target }}/release/meilisearch
+          asset_name: ${{ matrix.asset_name }}
+          tag: ${{ github.ref }}
+
+  publish-aarch64:
+    name: Publish binary for aarch64
+    runs-on: ubuntu-latest
+    needs: check-version
+    env:
+      DEBIAN_FRONTEND: noninteractive
+    container:
+      # Use ubuntu-22.04 to compile with glibc 2.35
+      image: ubuntu:22.04
+    strategy:
+      matrix:
+        include:
+          - target: aarch64-unknown-linux-gnu
+            asset_name: meilisearch-linux-aarch64
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v5
+      - name: Install needed dependencies
+        run: |
+          apt-get update -y && apt upgrade -y
+          apt-get install -y curl build-essential gcc-aarch64-linux-gnu
+      - name: Set up Docker for cross compilation
+        run: |
+          apt-get install -y curl apt-transport-https ca-certificates software-properties-common
+          curl -fsSL https://download.docker.com/linux/ubuntu/gpg | apt-key add -
+          add-apt-repository "deb [arch=$(dpkg --print-architecture)] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable"
+          apt-get update -y && apt-get install -y docker-ce
+      - name: Installing Rust toolchain
+        uses: dtolnay/rust-toolchain@1.89
+        with:
+          profile: minimal
+          target: ${{ matrix.target }}
+      - name: Configure target aarch64 GNU
+        ## Environment variable is not passed using env:
+        ## LD gold won't work with MUSL
+        # env:
+        #   JEMALLOC_SYS_WITH_LG_PAGE: 16
+        #   RUSTFLAGS: '-Clink-arg=-fuse-ld=gold'
+        run: |
+          echo '[target.aarch64-unknown-linux-gnu]' >> ~/.cargo/config
+          echo 'linker = "aarch64-linux-gnu-gcc"' >> ~/.cargo/config
+          echo 'JEMALLOC_SYS_WITH_LG_PAGE=16' >> $GITHUB_ENV
+      - name: Install a default toolchain that will be used to build cargo cross
+        run: |
+          rustup default stable
+      - name: Cargo build
+        uses: actions-rs/cargo@v1
+        with:
+          command: build
+          use-cross: true
+          args: --release --target ${{ matrix.target }}
+        env:
+          CROSS_DOCKER_IN_DOCKER: true
+      - name: List target output files
+        run: ls -lR ./target
+      - name: Upload the binary to release
+        # No need to upload binaries for dry run (cron)
+        if: github.event_name == 'release'
+        uses: svenstaro/upload-release-action@2.11.2
+        with:
+          repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
+          file: target/${{ matrix.target }}/release/meilisearch
+          asset_name: ${{ matrix.asset_name }}
           tag: ${{ github.ref }}
 
   publish-openapi-file:
     name: Publish OpenAPI file
-    needs: check-version
     runs-on: ubuntu-latest
     steps:
       - name: Checkout code
@@ -106,7 +201,7 @@ jobs:
           cd crates/openapi-generator
           cargo run --release -- --pretty --output ../../meilisearch.json
       - name: Upload OpenAPI to Release
-        # No need to upload for dry run (cron or workflow_dispatch)
+        # No need to upload for dry run (cron)
         if: github.event_name == 'release'
         uses: svenstaro/upload-release-action@2.11.2
         with:

.github/workflows/release-drafter.yml

@@ -0,0 +1,20 @@
+name: Release Drafter
+
+permissions:
+  contents: read
+  pull-requests: write
+
+on:
+  push:
+    branches:
+      - main
+
+jobs:
+  update_release_draft:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: release-drafter/release-drafter@v6
+        with:
+          config-name: release-draft-template.yml
+        env:
+          GITHUB_TOKEN: ${{ secrets.RELEASE_DRAFTER_TOKEN }}

.github/workflows/sdks-tests.yml

@@ -50,7 +50,7 @@ jobs:
         with:
           repository: meilisearch/meilisearch-dotnet
       - name: Setup .NET Core
-        uses: actions/setup-dotnet@v5
+        uses: actions/setup-dotnet@v4
         with:
           dotnet-version: "8.0.x"
       - name: Install dependencies
@@ -68,7 +68,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
+        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -92,7 +92,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
+        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -100,7 +100,7 @@ jobs:
           - '7700:7700'
     steps:
       - name: Set up Go
-        uses: actions/setup-go@v6
+        uses: actions/setup-go@v5
         with:
           go-version: stable
       - uses: actions/checkout@v5
@@ -122,7 +122,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
+        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 }}
@@ -135,13 +135,13 @@ jobs:
       - name: Set up Java
         uses: actions/setup-java@v5
         with:
-          java-version: 17
+          java-version: 8
-          distribution: 'temurin'
+          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 --info
+        run: ./gradlew build integrationTest
 
   meilisearch-js-tests:
     needs: define-docker-image
@@ -149,7 +149,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
+        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -160,7 +160,7 @@ jobs:
         with:
           repository: meilisearch/meilisearch-js
       - name: Setup node
-        uses: actions/setup-node@v5
+        uses: actions/setup-node@v4
         with:
           cache: 'yarn'
       - name: Install dependencies
@@ -184,7 +184,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
+        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -213,7 +213,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
+        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -224,7 +224,7 @@ jobs:
         with:
           repository: meilisearch/meilisearch-python
       - name: Set up Python
-        uses: actions/setup-python@v6
+        uses: actions/setup-python@v5
       - name: Install pipenv
         uses: dschep/install-pipenv-action@v1
       - name: Install dependencies
@@ -238,7 +238,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
+        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -263,7 +263,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
+        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -284,7 +284,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
+        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -307,7 +307,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
+        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -318,7 +318,7 @@ jobs:
         with:
           repository: meilisearch/meilisearch-js-plugins
       - name: Setup node
-        uses: actions/setup-node@v5
+        uses: actions/setup-node@v4
         with:
           cache: yarn
       - name: Install dependencies
@@ -338,7 +338,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
+        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -370,7 +370,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
+        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 }}

.github/workflows/test-suite.yml

@@ -15,40 +15,31 @@ env:
 
 jobs:
   test-linux:
-    name: Tests on Ubuntu
+    name: Tests on ubuntu-22.04
-    runs-on: ${{ matrix.runner }}
+    runs-on: ubuntu-latest
-    strategy:
+    container:
-      matrix:
+      # Use ubuntu-22.04 to compile with glibc 2.35
-        runner: [ubuntu-22.04, ubuntu-22.04-arm]
+      image: ubuntu:22.04
-        features: ["", "--features enterprise"]
     steps:
       - uses: actions/checkout@v5
-      - name: check free space before
+      - name: Install needed dependencies
-        run: df -h
-      - name: Clean space as per https://github.com/actions/virtual-environments/issues/709
         run: |
-          sudo rm -rf "/opt/ghc" || true
+          apt-get update && apt-get install -y curl
-          sudo rm -rf "/usr/share/dotnet" || true
+          apt-get install build-essential -y
-          sudo rm -rf "/usr/local/lib/android" || true
-          sudo rm -rf "/usr/local/share/boost" || true
-      - name: check free space after
-        run: df -h
       - name: Setup test with Rust stable
         uses: dtolnay/rust-toolchain@1.89
       - name: Cache dependencies
         uses: Swatinem/rust-cache@v2.8.0
-        with:
+      - name: Run cargo check without any default features
-          key: ${{ matrix.features }}
-      - name: Run cargo build without any default features
         uses: actions-rs/cargo@v1
         with:
           command: build
-          args: --locked --no-default-features --all
+          args: --locked --release --no-default-features --all
       - name: Run cargo test
         uses: actions-rs/cargo@v1
         with:
           command: test
-          args: --locked --all ${{ matrix.features }}
+          args: --locked --release --all
 
   test-others:
     name: Tests on ${{ matrix.os }}
@@ -56,58 +47,51 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        os: [macos-14, windows-2022]
+        os: [macos-13, windows-2022]
-        features: ["", "--features enterprise"]
-    if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
     steps:
       - uses: actions/checkout@v5
       - name: Cache dependencies
         uses: Swatinem/rust-cache@v2.8.0
       - uses: dtolnay/rust-toolchain@1.89
-      - name: Run cargo build without any default features
+      - name: Run cargo check without any default features
         uses: actions-rs/cargo@v1
         with:
           command: build
-          args: --locked --no-default-features --all
+          args: --locked --release --no-default-features --all
       - name: Run cargo test
         uses: actions-rs/cargo@v1
         with:
           command: test
-          args: --locked --all ${{ matrix.features }}
+          args: --locked --release --all
 
   test-all-features:
     name: Tests almost all features
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-latest
+    container:
+      # Use ubuntu-22.04 to compile with glibc 2.35
+      image: ubuntu:22.04
     if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
     steps:
       - uses: actions/checkout@v5
-      - name: Clean space as per https://github.com/actions/virtual-environments/issues/709
+      - name: Install needed dependencies
         run: |
-          sudo rm -rf "/opt/ghc" || true
+          apt-get update
-          sudo rm -rf "/usr/share/dotnet" || true
+          apt-get install --assume-yes build-essential curl
-          sudo rm -rf "/usr/local/lib/android" || true
-          sudo rm -rf "/usr/local/share/boost" || true
       - uses: dtolnay/rust-toolchain@1.89
       - name: Run cargo build with almost all features
         run: |
-          cargo build --workspace --locked --features "$(cargo xtask list-features --exclude-feature cuda,test-ollama)"
+          cargo build --workspace --locked --release --features "$(cargo xtask list-features --exclude-feature cuda,test-ollama)"
       - name: Run cargo test with almost all features
         run: |
-          cargo test --workspace --locked --features "$(cargo xtask list-features --exclude-feature cuda,test-ollama)"
+          cargo test --workspace --locked --release --features "$(cargo xtask list-features --exclude-feature cuda,test-ollama)"
 
   ollama-ubuntu:
     name: Test with Ollama
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-latest
     env:
       MEILI_TEST_OLLAMA_SERVER: "http://localhost:11434"
     steps:
       - uses: actions/checkout@v5
-      - name: Clean space as per https://github.com/actions/virtual-environments/issues/709
-        run: |
-          sudo rm -rf "/opt/ghc" || true
-          sudo rm -rf "/usr/share/dotnet" || true
-          sudo rm -rf "/usr/local/lib/android" || true
-          sudo rm -rf "/usr/local/share/boost" || true
       - name: Install Ollama
         run: |
           curl -fsSL https://ollama.com/install.sh | sudo -E sh
@@ -131,20 +115,20 @@ jobs:
         uses: actions-rs/cargo@v1
         with:
           command: test
-          args: --locked -p meilisearch --features test-ollama ollama
+          args: --locked --release --all --features test-ollama ollama
 
   test-disabled-tokenization:
     name: Test disabled tokenization
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-latest
+    container:
+      image: ubuntu:22.04
     if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
     steps:
       - uses: actions/checkout@v5
-      - name: Clean space as per https://github.com/actions/virtual-environments/issues/709
+      - name: Install needed dependencies
         run: |
-          sudo rm -rf "/opt/ghc" || true
+          apt-get update
-          sudo rm -rf "/usr/share/dotnet" || true
+          apt-get install --assume-yes build-essential curl
-          sudo rm -rf "/usr/local/lib/android" || true
-          sudo rm -rf "/usr/local/share/boost" || true
       - uses: dtolnay/rust-toolchain@1.89
       - name: Run cargo tree without default features and check lindera is not present
         run: |
@@ -156,39 +140,36 @@ jobs:
         run: |
           cargo tree -f '{p} {f}' -e normal | grep lindera -qz
 
-  build:
+  # We run tests in debug also, to make sure that the debug_assertions are hit
-    name: Build in release
+  test-debug:
-    runs-on: ubuntu-22.04
+    name: Run tests in debug
+    runs-on: ubuntu-latest
+    container:
+      # Use ubuntu-22.04 to compile with glibc 2.35
+      image: ubuntu:22.04
     steps:
       - uses: actions/checkout@v5
-      - name: Clean space as per https://github.com/actions/virtual-environments/issues/709
+      - name: Install needed dependencies
         run: |
-          sudo rm -rf "/opt/ghc" || true
+          apt-get update && apt-get install -y curl
-          sudo rm -rf "/usr/share/dotnet" || true
+          apt-get install build-essential -y
-          sudo rm -rf "/usr/local/lib/android" || true
-          sudo rm -rf "/usr/local/share/boost" || true
       - uses: dtolnay/rust-toolchain@1.89
       - name: Cache dependencies
         uses: Swatinem/rust-cache@v2.8.0
-      - name: Build
+      - name: Run tests in debug
-        run: cargo build --release --locked --target x86_64-unknown-linux-gnu
+        uses: actions-rs/cargo@v1
+        with:
+          command: test
+          args: --locked --all
 
   clippy:
     name: Run Clippy
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        features: ["", "--features enterprise"]
     steps:
       - uses: actions/checkout@v5
-      - name: Clean space as per https://github.com/actions/virtual-environments/issues/709
-        run: |
-          sudo rm -rf "/opt/ghc" || true
-          sudo rm -rf "/usr/share/dotnet" || true
-          sudo rm -rf "/usr/local/lib/android" || true
-          sudo rm -rf "/usr/local/share/boost" || true
       - uses: dtolnay/rust-toolchain@1.89
         with:
+          profile: minimal
           components: clippy
       - name: Cache dependencies
         uses: Swatinem/rust-cache@v2.8.0
@@ -196,21 +177,18 @@ jobs:
         uses: actions-rs/cargo@v1
         with:
           command: clippy
-          args: --all-targets ${{ matrix.features }} -- --deny warnings
+          args: --all-targets -- --deny warnings
 
   fmt:
     name: Run Rustfmt
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v5
-      - name: Clean space as per https://github.com/actions/virtual-environments/issues/709
-        run: |
-          sudo rm -rf "/opt/ghc" || true
-          sudo rm -rf "/usr/share/dotnet" || true
-          sudo rm -rf "/usr/local/lib/android" || true
-          sudo rm -rf "/usr/local/share/boost" || true
       - uses: dtolnay/rust-toolchain@1.89
         with:
+          profile: minimal
+          toolchain: nightly-2024-07-09
+          override: true
           components: rustfmt
       - name: Cache dependencies
         uses: Swatinem/rust-cache@v2.8.0
@@ -221,23 +199,3 @@ jobs:
         run: |
           echo -ne "\n" > crates/benchmarks/benches/datasets_paths.rs
           cargo fmt --all -- --check
-
-  declarative-tests:
-    name: Run declarative tests
-    runs-on: ubuntu-22.04-arm
-    permissions:
-      contents: read
-    steps:
-      - uses: actions/checkout@v5
-      - name: Clean space as per https://github.com/actions/virtual-environments/issues/709
-        run: |
-          sudo rm -rf "/opt/ghc" || true
-          sudo rm -rf "/usr/share/dotnet" || true
-          sudo rm -rf "/usr/local/lib/android" || true
-          sudo rm -rf "/usr/local/share/boost" || true
-      - uses: dtolnay/rust-toolchain@1.89
-      - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.8.0
-      - name: Run declarative tests
-        run: |
-          cargo xtask test workloads/tests/*.json

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

@@ -18,13 +18,9 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v5
-      - name: Clean space as per https://github.com/actions/virtual-environments/issues/709
-        run: |
-          sudo rm -rf "/opt/ghc" || true
-          sudo rm -rf "/usr/share/dotnet" || true
-          sudo rm -rf "/usr/local/lib/android" || true
-          sudo rm -rf "/usr/local/share/boost" || true
       - uses: dtolnay/rust-toolchain@1.89
+        with:
+          profile: minimal
       - name: Install sd
         run: cargo install sd
       - name: Update Cargo.toml file

BENCHMARKS.md

@@ -124,7 +124,6 @@ They are JSON files with the following structure (comments are not actually supp
 {
   // Name of the workload. Must be unique to the workload, as it will be used to group results on the dashboard.
   "name": "hackernews.ndjson_1M,no-threads",
-  "type": "bench",
   // Number of consecutive runs of the commands that should be performed.
   // Each run uses a fresh instance of Meilisearch and a fresh database.
   // Each run produces its own report file.

Cargo.toml

@@ -23,7 +23,7 @@ members = [
 ]
 
 [workspace.package]
-version = "1.29.0"
+version = "1.21.0"
 authors = [
     "Quentin de Quelen <quentin@dequelen.me>",
     "Clément Renault <clement@meilisearch.com>",
@@ -50,5 +50,3 @@ opt-level = 3
 opt-level = 3
 [profile.dev.package.roaring]
 opt-level = 3
-[profile.dev.package.gemm-f16]
-opt-level = 3

Cross.toml

@@ -0,0 +1,7 @@
+[build.env]
+passthrough = [
+    "RUST_BACKTRACE",
+    "CARGO_TERM_COLOR",
+    "RUSTFLAGS",
+    "JEMALLOC_SYS_WITH_LG_PAGE"
+]

Dockerfile

@@ -1,5 +1,5 @@
 # Compile
-FROM    rust:1.89-alpine3.22 AS compiler
+FROM    rust:1.89-alpine3.20 AS compiler
 
 RUN     apk add -q --no-cache build-base openssl-dev
 
@@ -8,17 +8,19 @@ WORKDIR /
 ARG     COMMIT_SHA
 ARG     COMMIT_DATE
 ARG     GIT_TAG
-ARG     EXTRA_ARGS
 ENV     VERGEN_GIT_SHA=${COMMIT_SHA} VERGEN_GIT_COMMIT_TIMESTAMP=${COMMIT_DATE} VERGEN_GIT_DESCRIBE=${GIT_TAG}
 ENV     RUSTFLAGS="-C target-feature=-crt-static"
 
 COPY    . .
 RUN     set -eux; \
         apkArch="$(apk --print-arch)"; \
-        cargo build --release -p meilisearch -p meilitool ${EXTRA_ARGS}
+        if [ "$apkArch" = "aarch64" ]; then \
+            export JEMALLOC_SYS_WITH_LG_PAGE=16; \
+        fi && \
+        cargo build --release -p meilisearch -p meilitool
 
 # Run
-FROM    alpine:3.22
+FROM    alpine:3.20
 LABEL   org.opencontainers.image.source="https://github.com/meilisearch/meilisearch"
 
 ENV     MEILI_HTTP_ADDR 0.0.0.0:7700

LICENSE

@@ -1,9 +1,29 @@
-# License
+MIT License
 
 Copyright (c) 2019-2025 Meili SAS
 
-Part of this work fall under the Meilisearch Enterprise Edition (EE) and are licensed under the Business Source License 1.1, please refer to [LICENSE-EE](./LICENSE-EE) for details.
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
 
-The other parts of this work are licensed under the [MIT license](./LICENSE-MIT).
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
 
-`SPDX-License-Identifier: MIT AND BUSL-1.1`
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
+
+---
+
+🔒 Meilisearch Enterprise Edition (EE)
+
+Certain parts of this codebase are not licensed under the MIT license and governed by the Business Source License 1.1.
+
+See the LICENSE-EE file for details.

LICENSE-MIT

@@ -1,21 +0,0 @@
-MIT License
-
-Copyright (c) 2019-2025 Meili SAS
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.

README.md

@@ -39,7 +39,6 @@
 ## 🖥 Examples
 
 - [**Movies**](https://where2watch.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=organization) — An application to help you find streaming platforms to watch movies using [hybrid search](https://www.meilisearch.com/solutions/hybrid-search?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos).
-- [**Flickr**](https://flickr.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=organization) — Search and explore one hundred million Flickr images with semantic search.
 - [**Ecommerce**](https://ecommerce.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos) — Ecommerce website using disjunctive [facets](https://www.meilisearch.com/docs/learn/fine_tuning_results/faceted_search?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos), range and rating filtering, and pagination.
 - [**Songs**](https://music.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos) — Search through 47 million of songs.
 - [**SaaS**](https://saas.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos) — Search for contacts, deals, and companies in this [multi-tenant](https://www.meilisearch.com/docs/learn/security/multitenancy_tenant_tokens?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos) CRM application.
@@ -122,7 +121,7 @@ If you want to know more about the kind of data we collect and what we use it fo
 
 Meilisearch is a search engine created by [Meili](https://www.meilisearch.com/careers), a software development company headquartered in France and with team members all over the world. Want to know more about us? [Check out our blog!](https://blog.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=contact)
 
-🗞 [Subscribe to our newsletter](https://share-eu1.hsforms.com/1LN5N0x_GQgq7ss7tXmSykwfg3aq) if you don't want to miss any updates! We promise we won't clutter your mailbox: we only send one edition every two months.
+🗞 [Subscribe to our newsletter](https://meilisearch.us2.list-manage.com/subscribe?u=27870f7b71c908a8b359599fb&id=79582d828e) if you don't want to miss any updates! We promise we won't clutter your mailbox: we only send one edition every two months.
 
 💌 Want to make a suggestion or give feedback? Here are some of the channels where you can reach us:
 

TESTING.md

@@ -1,326 +0,0 @@
-# Declarative tests
-
-Declarative tests ensure that Meilisearch features remain stable across versions.
-
-While we already have unit tests, those are run against **temporary databases** that are created fresh each time and therefore never risk corruption.
-
-Declarative tests instead **simulate the lifetime of a database**: they chain together commands and requests to change the binary, verifying that database state and API responses remain consistent.
-
-## Basic example
-
-```jsonc
-{
-  "type": "test",
-  "name": "api-keys",
-  "binary": { // the first command will run on the binary following this specification.
-    "source": "release", // get the binary as a release from GitHub
-    "version": "1.19.0", // version to fetch
-    "edition": "community" // edition to fetch
-  },
-  "commands": []
-}
-```
-
-This example defines a no-op test (it does nothing).
-
-If the file is saved at `workloads/tests/example.json`, you can run it with:
-
-```bash
-cargo xtask test workloads/tests/example.json
-```
-
-## Commands
-
-Commands represent API requests sent to Meilisearch endpoints during a test.
-
-They are executed sequentially, and their responses can be validated to ensure consistent behavior across upgrades.
-
-```jsonc
-
-{
-  "route": "keys",
-  "method": "POST",
-  "body": {
-    "inline": {
-      "actions": [
-        "search",
-        "documents.add"
-      ],
-      "description": "Test API Key",
-      "expiresAt": null,
-      "indexes": [ "movies" ]
-    }
-  }
-}
-```
-
-This command issues a `POST /keys` request, creating an API key with permissions to search and add documents in the `movies` index.
-
-### Using assets in commands
-
-To keep tests concise and reusable, you can define **assets** at the root of the workload file.
-
-Assets are external data sources (such as datasets) that are cached between runs, making tests faster and easier to read.
-
-```jsonc
-{
-  "type": "test",
-  "name": "movies",
-  "binary": {
-    "source": "release",
-    "version": "1.19.0",
-    "edition": "community"
-  },
-  "assets": {
-    "movies.json": {
-      "local_location": null,
-      "remote_location": "https://milli-benchmarks.fra1.digitaloceanspaces.com/bench/datasets/movies.json",
-      "sha256": "5b6e4cb660bc20327776e8a33ea197b43d9ec84856710ead1cc87ab24df77de1"
-    }
-  },
-  "commands": [
-    {
-      "route": "indexes/movies/documents",
-      "method": "POST",
-      "body": {
-        "asset": "movies.json"
-      }
-    }
-  ]
-}
-```
-
-In this example:
-- The `movies.json` dataset is defined as an asset, pointing to a remote URL.
-- The SHA-256 checksum ensures integrity.
-- The `POST /indexes/movies/documents` command uses this asset as the request body.
-
-This makes the test much cleaner than inlining a large dataset directly into the command.
-
-For asset handling, please refer to the [declarative benchmarks documentation](/BENCHMARKS.md#adding-new-assets).
-
-### Asserting responses
-
-Commands can specify both the **expected status code** and the **expected response body**.
-
-```jsonc
-{
-  "route": "indexes/movies/documents",
-  "method": "POST",
-  "body": {
-    "asset": "movies.json"
-  },
-  "expectedStatus": 202,
-  "expectedResponse": {
-    "enqueuedAt": "[timestamp]", // Set to a bracketed string to ignore the value
-    "indexUid": "movies",
-    "status": "enqueued",
-    "taskUid": 1,
-    "type": "documentAdditionOrUpdate"
-  },
-  "synchronous": "WaitForTask"
-}
-```
-
-Manually writing `expectedResponse` fields can be tedious.
-
-Instead, you can let the test runner populate them automatically:
-
-```bash
-# Run the workload to populate expected fields. Only adds the missing ones, doesn't change existing data
-cargo xtask test workloads/tests/example.json --add-missing-responses
-
-# OR
-
-# Run the workload to populate expected fields. Updates all fields including existing ones
-cargo xtask test workloads/tests/example.json --update-responses
-```
-
-This workflow is recommended:
-
-1. Write the test without expected fields.
-2. Run it with `--add-missing-responses` to capture the actual responses.
-3. Review and commit the generated expectations.
-
-## Changing binary
-
-It is possible to insert an instruction to change the current Meilisearch instance from one binary specification to another during a test.
-
-When executed, such an instruction will:
-1. Stop the current Meilisearch instance.
-2. Fetch the binary specified by the instruction.
-3. Restart the server with the specified binary on the same database.
-
-```jsonc
-{
-  "type": "test",
-  "name": "movies",
-  "binary": {
-    "source": "release",
-    "version": "1.19.0", // start with version v1.19.0
-    "edition": "community"
-  },
-  "assets": {
-    "movies.json": {
-      "local_location": null,
-      "remote_location": "https://milli-benchmarks.fra1.digitaloceanspaces.com/bench/datasets/movies.json",
-      "sha256": "5b6e4cb660bc20327776e8a33ea197b43d9ec84856710ead1cc87ab24df77de1"
-    }
-  },
-  "commands": [
-    // setup some data
-    {
-      "route": "indexes/movies/documents",
-      "method": "POST",
-      "body": {
-        "asset": "movies.json"
-      }
-    },
-    // switch binary to v1.24.0
-    {
-      "binary": {
-        "source": "release",
-        "version": "1.24.0",
-        "edition": "community"
-      }
-    }
-  ]
-}
-```
-
-### Typical Usage
-
-In most cases, the change binary instruction will be used to update a database.
-
-- **Set up** some data using commands on an older version.
-- **Upgrade** to the latest version.
-- **Assert** that the data and API behavior remain correct after the upgrade.
-
-To properly test the dumpless upgrade, one should typically:
-
-1. Open the database without processing the update task: Use a `binary` instruction to switch to the desired version, passing `--experimental-dumpless-upgrade` and `--experimental-max-number-of-batched-tasks=0` as extra CLI arguments
-2. Check that the search, stats and task queue still work.
-3. Open the database and process the update task: Use a `binary` instruction to switch to the desired version, passing `--experimental-dumpless-upgrade` as the extra CLI argument. Use a `health` command to wait for the upgrade task to finish.
-4. Check that the indexing, search, stats, and task queue still work.
-
-```jsonc
-{
-  "type": "test",
-  "name": "movies",
-  "binary": {
-    "source": "release",
-    "version": "1.12.0",
-    "edition": "community"
-  },
-  "commands": [
-    // 0. Run commands to populate the database
-    {
-      // ..
-    },
-    // 1. Open the database with new MS without processing the update task
-    {
-      "binary": {
-        "source": "build", // build the binary from the sources in the current git repository
-        "edition": "community",
-        "extraCliArgs": [
-          "--experimental-dumpless-upgrade", // allows to open with a newer MS
-          "--experimental-max-number-of-batched-tasks=0" // prevent processing of the update task
-        ]
-      }
-    },
-    // 2. Check the search etc.
-    {
-      // ..
-    },
-    // 3. Open the database with new MS and processing the update task
-    {
-      "binary": {
-        "source": "build", // build the binary from the sources in the current git repository
-        "edition": "community",
-        "extraCliArgs": [
-          "--experimental-dumpless-upgrade" // allows to open with a newer MS
-          // no `--experimental-max-number-of-batched-tasks=0`
-        ]
-      }
-    },
-    // 4. Check the indexing, search, etc.
-    {
-      // ..
-    }
-  ]
-}
-```
-
-This ensures backward compatibility: databases created with older Meilisearch versions should remain functional and consistent after an upgrade.
-
-## Variables
-
-Sometimes a command needs to use a value returned by a **previous response**.
-These values can be captured and reused using the register field.
-
-```jsonc
-{
-  "route": "keys",
-  "method": "POST",
-  "body": {
-    "inline": {
-        "actions": [
-        "search",
-        "documents.add"
-        ],
-        "description": "Test API Key",
-        "expiresAt": null,
-        "indexes": [ "movies" ]
-    }
-  },
-  "expectedResponse": {
-      "key": "c6f64630bad2996b1f675007c8800168e14adf5d6a7bb1a400a6d2b158050eaf",
-      // ...
-  },
-  "register": {
-    "key": "/key"
-  },
-  "synchronous": "WaitForResponse"
-}
-```
-
-The `register` field captures the value at the JSON path `/key` from the response.
-Paths follow the **JavaScript Object Notation Pointer (RFC 6901)** format.
-Registered variables are available for all subsequent commands.
-
-Registered variables can be referenced by wrapping their name in double curly braces:
-
-In the route/path:
-
-```jsonc
-{
-  "route": "tasks/{{ task_id }}",
-  "method": "GET"
-}
-```
-
-In the request body:
-
-```jsonc
-{
-  "route": "indexes/movies/documents",
-  "method": "PATCH",
-  "body": {
-    "inline": {
-      "id": "{{ document_id }}",
-      "overview": "Shazam turns evil and the world is in danger.",
-    }
-  }
-}
-```
-
-Or they can be referenced by their name (**without curly braces**) as an API key:
-
-```jsonc
-{
-  "route": "indexes/movies/documents",
-  "method": "POST",
-  "body": { /* ... */ },
-  "apiKeyVariable": "key" // The **content** of the key variable will be used as an API key
-}
-```

crates/benchmarks/Cargo.toml

@@ -11,27 +11,27 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-anyhow = "1.0.100"
+anyhow = "1.0.98"
-bumpalo = "3.19.0"
+bumpalo = "3.18.1"
-csv = "1.4.0"
+csv = "1.3.1"
-memmap2 = "0.9.9"
+memmap2 = "0.9.7"
 milli = { path = "../milli" }
-mimalloc = { version = "0.1.48", default-features = false }
+mimalloc = { version = "0.1.47", default-features = false }
-serde_json = { version = "1.0.145", features = ["preserve_order"] }
+serde_json = { version = "1.0.140", features = ["preserve_order"] }
-tempfile = "3.23.0"
+tempfile = "3.20.0"
 
 [dev-dependencies]
-criterion = { version = "0.7.0", features = ["html_reports"] }
+criterion = { version = "0.6.0", features = ["html_reports"] }
 rand = "0.8.5"
 rand_chacha = "0.3.1"
 roaring = "0.10.12"
 
 [build-dependencies]
-anyhow = "1.0.100"
+anyhow = "1.0.98"
-bytes = "1.11.0"
+bytes = "1.10.1"
-convert_case = "0.9.0"
+convert_case = "0.8.0"
-flate2 = "1.1.5"
+flate2 = "1.1.2"
-reqwest = { version = "0.12.24", features = ["blocking", "rustls-tls"], default-features = false }
+reqwest = { version = "0.12.20", features = ["blocking", "rustls-tls"], default-features = false }
 
 [features]
 default = ["milli/all-tokenizations"]

crates/benchmarks/benches/indexing.rs

@@ -21,10 +21,6 @@ use roaring::RoaringBitmap;
 #[global_allocator]
 static ALLOC: mimalloc::MiMalloc = mimalloc::MiMalloc;
 
-fn no_cancel() -> bool {
-    false
-}
-
 const BENCHMARK_ITERATION: usize = 10;
 
 fn setup_dir(path: impl AsRef<Path>) {
@@ -69,7 +65,7 @@ fn setup_settings<'t>(
     let sortable_fields = sortable_fields.iter().map(|s| s.to_string()).collect();
     builder.set_sortable_fields(sortable_fields);
 
-    builder.execute(&no_cancel, &Progress::default(), Default::default()).unwrap();
+    builder.execute(&|| false, &Progress::default(), Default::default()).unwrap();
 }
 
 fn setup_index_with_settings(
@@ -156,7 +152,7 @@ fn indexing_songs_default(c: &mut Criterion) {
                         &rtxn,
                         None,
                         &mut new_fields_ids_map,
-                        &no_cancel,
+                        &|| false,
                         Progress::default(),
                         None,
                     )
@@ -172,7 +168,7 @@ fn indexing_songs_default(c: &mut Criterion) {
                     primary_key,
                     &document_changes,
                     RuntimeEmbedders::default(),
-                    &no_cancel,
+                    &|| false,
                     &Progress::default(),
                     &Default::default(),
                 )
@@ -224,7 +220,7 @@ fn reindexing_songs_default(c: &mut Criterion) {
                         &rtxn,
                         None,
                         &mut new_fields_ids_map,
-                        &no_cancel,
+                        &|| false,
                         Progress::default(),
                         None,
                     )
@@ -240,7 +236,7 @@ fn reindexing_songs_default(c: &mut Criterion) {
                     primary_key,
                     &document_changes,
                     RuntimeEmbedders::default(),
-                    &no_cancel,
+                    &|| false,
                     &Progress::default(),
                     &Default::default(),
                 )
@@ -270,7 +266,7 @@ fn reindexing_songs_default(c: &mut Criterion) {
                         &rtxn,
                         None,
                         &mut new_fields_ids_map,
-                        &no_cancel,
+                        &|| false,
                         Progress::default(),
                         None,
                     )
@@ -286,7 +282,7 @@ fn reindexing_songs_default(c: &mut Criterion) {
                     primary_key,
                     &document_changes,
                     RuntimeEmbedders::default(),
-                    &no_cancel,
+                    &|| false,
                     &Progress::default(),
                     &Default::default(),
                 )
@@ -340,7 +336,7 @@ fn deleting_songs_in_batches_default(c: &mut Criterion) {
                         &rtxn,
                         None,
                         &mut new_fields_ids_map,
-                        &no_cancel,
+                        &|| false,
                         Progress::default(),
                         None,
                     )
@@ -356,7 +352,7 @@ fn deleting_songs_in_batches_default(c: &mut Criterion) {
                     primary_key,
                     &document_changes,
                     RuntimeEmbedders::default(),
-                    &no_cancel,
+                    &|| false,
                     &Progress::default(),
                     &Default::default(),
                 )
@@ -418,7 +414,7 @@ fn indexing_songs_in_three_batches_default(c: &mut Criterion) {
                         &rtxn,
                         None,
                         &mut new_fields_ids_map,
-                        &no_cancel,
+                        &|| false,
                         Progress::default(),
                         None,
                     )
@@ -434,7 +430,7 @@ fn indexing_songs_in_three_batches_default(c: &mut Criterion) {
                     primary_key,
                     &document_changes,
                     RuntimeEmbedders::default(),
-                    &no_cancel,
+                    &|| false,
                     &Progress::default(),
                     &Default::default(),
                 )
@@ -464,7 +460,7 @@ fn indexing_songs_in_three_batches_default(c: &mut Criterion) {
                         &rtxn,
                         None,
                         &mut new_fields_ids_map,
-                        &no_cancel,
+                        &|| false,
                         Progress::default(),
                         None,
                     )
@@ -480,7 +476,7 @@ fn indexing_songs_in_three_batches_default(c: &mut Criterion) {
                     primary_key,
                     &document_changes,
                     RuntimeEmbedders::default(),
-                    &no_cancel,
+                    &|| false,
                     &Progress::default(),
                     &Default::default(),
                 )
@@ -506,7 +502,7 @@ fn indexing_songs_in_three_batches_default(c: &mut Criterion) {
                         &rtxn,
                         None,
                         &mut new_fields_ids_map,
-                        &no_cancel,
+                        &|| false,
                         Progress::default(),
                         None,
                     )
@@ -522,7 +518,7 @@ fn indexing_songs_in_three_batches_default(c: &mut Criterion) {
                     primary_key,
                     &document_changes,
                     RuntimeEmbedders::default(),
-                    &no_cancel,
+                    &|| false,
                     &Progress::default(),
                     &Default::default(),
                 )
@@ -575,7 +571,7 @@ fn indexing_songs_without_faceted_numbers(c: &mut Criterion) {
                         &rtxn,
                         None,
                         &mut new_fields_ids_map,
-                        &no_cancel,
+                        &|| false,
                         Progress::default(),
                         None,
                     )
@@ -591,7 +587,7 @@ fn indexing_songs_without_faceted_numbers(c: &mut Criterion) {
                     primary_key,
                     &document_changes,
                     RuntimeEmbedders::default(),
-                    &no_cancel,
+                    &|| false,
                     &Progress::default(),
                     &Default::default(),
                 )
@@ -643,7 +639,7 @@ fn indexing_songs_without_faceted_fields(c: &mut Criterion) {
                         &rtxn,
                         None,
                         &mut new_fields_ids_map,
-                        &no_cancel,
+                        &|| false,
                         Progress::default(),
                         None,
                     )
@@ -659,7 +655,7 @@ fn indexing_songs_without_faceted_fields(c: &mut Criterion) {
                     primary_key,
                     &document_changes,
                     RuntimeEmbedders::default(),
-                    &no_cancel,
+                    &|| false,
                     &Progress::default(),
                     &Default::default(),
                 )
@@ -711,7 +707,7 @@ fn indexing_wiki(c: &mut Criterion) {
                         &rtxn,
                         None,
                         &mut new_fields_ids_map,
-                        &no_cancel,
+                        &|| false,
                         Progress::default(),
                         None,
                     )
@@ -727,7 +723,7 @@ fn indexing_wiki(c: &mut Criterion) {
                     primary_key,
                     &document_changes,
                     RuntimeEmbedders::default(),
-                    &no_cancel,
+                    &|| false,
                     &Progress::default(),
                     &Default::default(),
                 )
@@ -778,7 +774,7 @@ fn reindexing_wiki(c: &mut Criterion) {
                         &rtxn,
                         None,
                         &mut new_fields_ids_map,
-                        &no_cancel,
+                        &|| false,
                         Progress::default(),
                         None,
                     )
@@ -794,7 +790,7 @@ fn reindexing_wiki(c: &mut Criterion) {
                     primary_key,
                     &document_changes,
                     RuntimeEmbedders::default(),
-                    &no_cancel,
+                    &|| false,
                     &Progress::default(),
                     &Default::default(),
                 )
@@ -824,7 +820,7 @@ fn reindexing_wiki(c: &mut Criterion) {
                         &rtxn,
                         None,
                         &mut new_fields_ids_map,
-                        &no_cancel,
+                        &|| false,
                         Progress::default(),
                         None,
                     )
@@ -840,7 +836,7 @@ fn reindexing_wiki(c: &mut Criterion) {
                     primary_key,
                     &document_changes,
                     RuntimeEmbedders::default(),
-                    &no_cancel,
+                    &|| false,
                     &Progress::default(),
                     &Default::default(),
                 )
@@ -893,7 +889,7 @@ fn deleting_wiki_in_batches_default(c: &mut Criterion) {
                         &rtxn,
                         None,
                         &mut new_fields_ids_map,
-                        &no_cancel,
+                        &|| false,
                         Progress::default(),
                         None,
                     )
@@ -909,7 +905,7 @@ fn deleting_wiki_in_batches_default(c: &mut Criterion) {
                     primary_key,
                     &document_changes,
                     RuntimeEmbedders::default(),
-                    &no_cancel,
+                    &|| false,
                     &Progress::default(),
                     &Default::default(),
                 )
@@ -971,7 +967,7 @@ fn indexing_wiki_in_three_batches(c: &mut Criterion) {
                         &rtxn,
                         None,
                         &mut new_fields_ids_map,
-                        &no_cancel,
+                        &|| false,
                         Progress::default(),
                         None,
                     )
@@ -987,7 +983,7 @@ fn indexing_wiki_in_three_batches(c: &mut Criterion) {
                     primary_key,
                     &document_changes,
                     RuntimeEmbedders::default(),
-                    &no_cancel,
+                    &|| false,
                     &Progress::default(),
                     &Default::default(),
                 )
@@ -1018,7 +1014,7 @@ fn indexing_wiki_in_three_batches(c: &mut Criterion) {
                         &rtxn,
                         None,
                         &mut new_fields_ids_map,
-                        &no_cancel,
+                        &|| false,
                         Progress::default(),
                         None,
                     )
@@ -1034,7 +1030,7 @@ fn indexing_wiki_in_three_batches(c: &mut Criterion) {
                     primary_key,
                     &document_changes,
                     RuntimeEmbedders::default(),
-                    &no_cancel,
+                    &|| false,
                     &Progress::default(),
                     &Default::default(),
                 )
@@ -1061,7 +1057,7 @@ fn indexing_wiki_in_three_batches(c: &mut Criterion) {
                         &rtxn,
                         None,
                         &mut new_fields_ids_map,
-                        &no_cancel,
+                        &|| false,
                         Progress::default(),
                         None,
                     )
@@ -1077,7 +1073,7 @@ fn indexing_wiki_in_three_batches(c: &mut Criterion) {
                     primary_key,
                     &document_changes,
                     RuntimeEmbedders::default(),
-                    &no_cancel,
+                    &|| false,
                     &Progress::default(),
                     &Default::default(),
                 )
@@ -1129,7 +1125,7 @@ fn indexing_movies_default(c: &mut Criterion) {
                         &rtxn,
                         None,
                         &mut new_fields_ids_map,
-                        &no_cancel,
+                        &|| false,
                         Progress::default(),
                         None,
                     )
@@ -1145,7 +1141,7 @@ fn indexing_movies_default(c: &mut Criterion) {
                     primary_key,
                     &document_changes,
                     RuntimeEmbedders::default(),
-                    &no_cancel,
+                    &|| false,
                     &Progress::default(),
                     &Default::default(),
                 )
@@ -1196,7 +1192,7 @@ fn reindexing_movies_default(c: &mut Criterion) {
                         &rtxn,
                         None,
                         &mut new_fields_ids_map,
-                        &no_cancel,
+                        &|| false,
                         Progress::default(),
                         None,
                     )
@@ -1212,7 +1208,7 @@ fn reindexing_movies_default(c: &mut Criterion) {
                     primary_key,
                     &document_changes,
                     RuntimeEmbedders::default(),
-                    &no_cancel,
+                    &|| false,
                     &Progress::default(),
                     &Default::default(),
                 )
@@ -1242,7 +1238,7 @@ fn reindexing_movies_default(c: &mut Criterion) {
                         &rtxn,
                         None,
                         &mut new_fields_ids_map,
-                        &no_cancel,
+                        &|| false,
                         Progress::default(),
                         None,
                     )
@@ -1258,7 +1254,7 @@ fn reindexing_movies_default(c: &mut Criterion) {
                     primary_key,
                     &document_changes,
                     RuntimeEmbedders::default(),
-                    &no_cancel,
+                    &|| false,
                     &Progress::default(),
                     &Default::default(),
                 )
@@ -1311,7 +1307,7 @@ fn deleting_movies_in_batches_default(c: &mut Criterion) {
                         &rtxn,
                         None,
                         &mut new_fields_ids_map,
-                        &no_cancel,
+                        &|| false,
                         Progress::default(),
                         None,
                     )
@@ -1327,7 +1323,7 @@ fn deleting_movies_in_batches_default(c: &mut Criterion) {
                     primary_key,
                     &document_changes,
                     RuntimeEmbedders::default(),
-                    &no_cancel,
+                    &|| false,
                     &Progress::default(),
                     &Default::default(),
                 )
@@ -1376,7 +1372,7 @@ fn delete_documents_from_ids(index: Index, document_ids_to_delete: Vec<RoaringBi
             Some(primary_key),
             &document_changes,
             RuntimeEmbedders::default(),
-            &no_cancel,
+            &|| false,
             &Progress::default(),
             &Default::default(),
         )
@@ -1426,7 +1422,7 @@ fn indexing_movies_in_three_batches(c: &mut Criterion) {
                         &rtxn,
                         None,
                         &mut new_fields_ids_map,
-                        &no_cancel,
+                        &|| false,
                         Progress::default(),
                         None,
                     )
@@ -1442,7 +1438,7 @@ fn indexing_movies_in_three_batches(c: &mut Criterion) {
                     primary_key,
                     &document_changes,
                     RuntimeEmbedders::default(),
-                    &no_cancel,
+                    &|| false,
                     &Progress::default(),
                     &Default::default(),
                 )
@@ -1472,7 +1468,7 @@ fn indexing_movies_in_three_batches(c: &mut Criterion) {
                         &rtxn,
                         None,
                         &mut new_fields_ids_map,
-                        &no_cancel,
+                        &|| false,
                         Progress::default(),
                         None,
                     )
@@ -1488,7 +1484,7 @@ fn indexing_movies_in_three_batches(c: &mut Criterion) {
                     primary_key,
                     &document_changes,
                     RuntimeEmbedders::default(),
-                    &no_cancel,
+                    &|| false,
                     &Progress::default(),
                     &Default::default(),
                 )
@@ -1514,7 +1510,7 @@ fn indexing_movies_in_three_batches(c: &mut Criterion) {
                         &rtxn,
                         None,
                         &mut new_fields_ids_map,
-                        &no_cancel,
+                        &|| false,
                         Progress::default(),
                         None,
                     )
@@ -1530,7 +1526,7 @@ fn indexing_movies_in_three_batches(c: &mut Criterion) {
                     primary_key,
                     &document_changes,
                     RuntimeEmbedders::default(),
-                    &no_cancel,
+                    &|| false,
                     &Progress::default(),
                     &Default::default(),
                 )
@@ -1605,7 +1601,7 @@ fn indexing_nested_movies_default(c: &mut Criterion) {
                         &rtxn,
                         None,
                         &mut new_fields_ids_map,
-                        &no_cancel,
+                        &|| false,
                         Progress::default(),
                         None,
                     )
@@ -1621,7 +1617,7 @@ fn indexing_nested_movies_default(c: &mut Criterion) {
                     primary_key,
                     &document_changes,
                     RuntimeEmbedders::default(),
-                    &no_cancel,
+                    &|| false,
                     &Progress::default(),
                     &Default::default(),
                 )
@@ -1697,7 +1693,7 @@ fn deleting_nested_movies_in_batches_default(c: &mut Criterion) {
                         &rtxn,
                         None,
                         &mut new_fields_ids_map,
-                        &no_cancel,
+                        &|| false,
                         Progress::default(),
                         None,
                     )
@@ -1713,7 +1709,7 @@ fn deleting_nested_movies_in_batches_default(c: &mut Criterion) {
                     primary_key,
                     &document_changes,
                     RuntimeEmbedders::default(),
-                    &no_cancel,
+                    &|| false,
                     &Progress::default(),
                     &Default::default(),
                 )
@@ -1781,7 +1777,7 @@ fn indexing_nested_movies_without_faceted_fields(c: &mut Criterion) {
                         &rtxn,
                         None,
                         &mut new_fields_ids_map,
-                        &no_cancel,
+                        &|| false,
                         Progress::default(),
                         None,
                     )
@@ -1797,7 +1793,7 @@ fn indexing_nested_movies_without_faceted_fields(c: &mut Criterion) {
                     primary_key,
                     &document_changes,
                     RuntimeEmbedders::default(),
-                    &no_cancel,
+                    &|| false,
                     &Progress::default(),
                     &Default::default(),
                 )
@@ -1849,7 +1845,7 @@ fn indexing_geo(c: &mut Criterion) {
                         &rtxn,
                         None,
                         &mut new_fields_ids_map,
-                        &no_cancel,
+                        &|| false,
                         Progress::default(),
                         None,
                     )
@@ -1865,7 +1861,7 @@ fn indexing_geo(c: &mut Criterion) {
                     primary_key,
                     &document_changes,
                     RuntimeEmbedders::default(),
-                    &no_cancel,
+                    &|| false,
                     &Progress::default(),
                     &Default::default(),
                 )
@@ -1916,7 +1912,7 @@ fn reindexing_geo(c: &mut Criterion) {
                         &rtxn,
                         None,
                         &mut new_fields_ids_map,
-                        &no_cancel,
+                        &|| false,
                         Progress::default(),
                         None,
                     )
@@ -1932,7 +1928,7 @@ fn reindexing_geo(c: &mut Criterion) {
                     primary_key,
                     &document_changes,
                     RuntimeEmbedders::default(),
-                    &no_cancel,
+                    &|| false,
                     &Progress::default(),
                     &Default::default(),
                 )
@@ -1962,7 +1958,7 @@ fn reindexing_geo(c: &mut Criterion) {
                         &rtxn,
                         None,
                         &mut new_fields_ids_map,
-                        &no_cancel,
+                        &|| false,
                         Progress::default(),
                         None,
                     )
@@ -1978,7 +1974,7 @@ fn reindexing_geo(c: &mut Criterion) {
                     primary_key,
                     &document_changes,
                     RuntimeEmbedders::default(),
-                    &no_cancel,
+                    &|| false,
                     &Progress::default(),
                     &Default::default(),
                 )
@@ -2031,7 +2027,7 @@ fn deleting_geo_in_batches_default(c: &mut Criterion) {
                         &rtxn,
                         None,
                         &mut new_fields_ids_map,
-                        &no_cancel,
+                        &|| false,
                         Progress::default(),
                         None,
                     )
@@ -2047,7 +2043,7 @@ fn deleting_geo_in_batches_default(c: &mut Criterion) {
                     primary_key,
                     &document_changes,
                     RuntimeEmbedders::default(),
-                    &no_cancel,
+                    &|| false,
                     &Progress::default(),
                     &Default::default(),
                 )

crates/build-info/Cargo.toml

@@ -11,8 +11,8 @@ license.workspace = true
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
-time = { version = "0.3.44", features = ["parsing"] }
+time = { version = "0.3.41", features = ["parsing"] }
 
 [build-dependencies]
-anyhow = "1.0.100"
+anyhow = "1.0.98"
-vergen-gitcl = "1.0.8"
+vergen-git2 = "1.0.7"

crates/build-info/build.rs

@@ -15,7 +15,7 @@ fn emit_git_variables() -> anyhow::Result<()> {
     // Note: any code that needs VERGEN_ environment variables should take care to define them manually in the Dockerfile and pass them
     // in the corresponding GitHub workflow (publish_docker.yml).
     // This is due to the Dockerfile building the binary outside of the git directory.
-    let mut builder = vergen_gitcl::GitclBuilder::default();
+    let mut builder = vergen_git2::Git2Builder::default();
 
     builder.branch(true);
     builder.commit_timestamp(true);
@@ -25,5 +25,5 @@ fn emit_git_variables() -> anyhow::Result<()> {
 
     let git2 = builder.build()?;
 
-    vergen_gitcl::Emitter::default().fail_on_error().add_instructions(&git2)?.emit()
+    vergen_git2::Emitter::default().fail_on_error().add_instructions(&git2)?.emit()
 }

crates/build-info/src/main.rs

@@ -1,6 +0,0 @@
-use build_info::BuildInfo;
-
-fn main() {
-    let info = BuildInfo::from_build();
-    dbg!(info);
-}

crates/dump/Cargo.toml

@@ -11,27 +11,24 @@ readme.workspace = true
 license.workspace = true
 
 [dependencies]
-anyhow = "1.0.100"
+anyhow = "1.0.98"
-flate2 = "1.1.5"
+flate2 = "1.1.2"
 http = "1.3.1"
 meilisearch-types = { path = "../meilisearch-types" }
 once_cell = "1.21.3"
-regex = "1.12.2"
+regex = "1.11.1"
 roaring = { version = "0.10.12", features = ["serde"] }
-serde = { version = "1.0.228", features = ["derive"] }
+serde = { version = "1.0.219", features = ["derive"] }
-serde_json = { version = "1.0.145", features = ["preserve_order"] }
+serde_json = { version = "1.0.140", features = ["preserve_order"] }
 tar = "0.4.44"
-tempfile = "3.23.0"
+tempfile = "3.20.0"
-thiserror = "2.0.17"
+thiserror = "2.0.12"
-time = { version = "0.3.44", features = ["serde-well-known", "formatting", "parsing", "macros"] }
+time = { version = "0.3.41", features = ["serde-well-known", "formatting", "parsing", "macros"] }
 tracing = "0.1.41"
-uuid = { version = "1.18.1", features = ["serde", "v4"] }
+uuid = { version = "1.17.0", features = ["serde", "v4"] }
 
 [dev-dependencies]
 big_s = "1.0.2"
 maplit = "1.0.2"
 meili-snap = { path = "../meili-snap" }
 meilisearch-types = { path = "../meilisearch-types" }
-
-[features]
-enterprise = ["meilisearch-types/enterprise"]

crates/dump/src/lib.rs

@@ -96,8 +96,6 @@ pub struct TaskDump {
     pub finished_at: Option<OffsetDateTime>,
     #[serde(default, skip_serializing_if = "Option::is_none")]
     pub network: Option<TaskNetwork>,
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub custom_metadata: Option<String>,
 }
 
 // A `Kind` specific version made for the dump. If modified you may break the dump.
@@ -160,8 +158,9 @@ pub enum KindDump {
     UpgradeDatabase {
         from: (u32, u32, u32),
     },
-    IndexCompaction {
+    NetworkTopologyChange {
-        index_uid: String,
+        network: Option<meilisearch_types::enterprise_edition::network::Network>,
+        origin: Option<meilisearch_types::tasks::Origin>,
     },
 }
 
@@ -180,7 +179,6 @@ impl From<Task> for TaskDump {
             started_at: task.started_at,
             finished_at: task.finished_at,
             network: task.network,
-            custom_metadata: task.custom_metadata,
         }
     }
 }
@@ -246,8 +244,8 @@ impl From<KindWithContent> for KindDump {
             KindWithContent::UpgradeDatabase { from: version } => {
                 KindDump::UpgradeDatabase { from: version }
             }
-            KindWithContent::IndexCompaction { index_uid } => {
+            KindWithContent::NetworkTopologyChange { network, origin } => {
-                KindDump::IndexCompaction { index_uid }
+                KindDump::NetworkTopologyChange { network, origin }
             }
         }
     }
@@ -262,13 +260,13 @@ pub(crate) mod test {
     use big_s::S;
     use maplit::{btreemap, btreeset};
     use meilisearch_types::batches::{Batch, BatchEnqueuedAt, BatchStats};
+    use meilisearch_types::enterprise_edition::network::{DbNetwork, DbRemote};
     use meilisearch_types::facet_values_sort::FacetValuesSort;
     use meilisearch_types::features::RuntimeTogglableFeatures;
     use meilisearch_types::index_uid_pattern::IndexUidPattern;
     use meilisearch_types::keys::{Action, Key};
     use meilisearch_types::milli::update::Setting;
     use meilisearch_types::milli::{self, FilterableAttributesRule};
-    use meilisearch_types::network::{Network, Remote};
     use meilisearch_types::settings::{Checked, FacetingSettings, Settings};
     use meilisearch_types::task_view::DetailsView;
     use meilisearch_types::tasks::{BatchStopReason, Details, Kind, Status};
@@ -399,7 +397,6 @@ pub(crate) mod test {
                     started_at: Some(datetime!(2022-11-20 0:00 UTC)),
                     finished_at: Some(datetime!(2022-11-21 0:00 UTC)),
                     network: None,
-                    custom_metadata: None,
                 },
                 None,
             ),
@@ -425,7 +422,6 @@ pub(crate) mod test {
                     started_at: None,
                     finished_at: None,
                     network: None,
-                    custom_metadata: None,
                 },
                 Some(vec![
                     json!({ "id": 4, "race": "leonberg" }).as_object().unwrap().clone(),
@@ -446,7 +442,6 @@ pub(crate) mod test {
                     started_at: None,
                     finished_at: None,
                     network: None,
-                    custom_metadata: None,
                 },
                 None,
             ),
@@ -556,10 +551,10 @@ pub(crate) mod test {
         RuntimeTogglableFeatures::default()
     }
 
-    fn create_test_network() -> Network {
+    fn create_test_network() -> DbNetwork {
-        Network {
+        DbNetwork {
             local: Some("myself".to_string()),
-            remotes: maplit::btreemap! {"other".to_string() => Remote { url: "http://test".to_string(), search_api_key: Some("apiKey".to_string()), write_api_key: Some("docApiKey".to_string()) }},
+            remotes: maplit::btreemap! {"other".to_string() => DbRemote { url: "http://test".to_string(), search_api_key: Some("apiKey".to_string()), write_api_key: Some("docApiKey".to_string()) }},
             sharding: false,
         }
     }

crates/dump/src/reader/compat/v5_to_v6.rs

@@ -164,7 +164,6 @@ impl CompatV5ToV6 {
                     started_at: task_view.started_at,
                     finished_at: task_view.finished_at,
                     network: None,
-                    custom_metadata: None,
                 };
 
                 (task, content_file)

crates/dump/src/reader/v6/mod.rs

@@ -24,7 +24,7 @@ pub type Batch = meilisearch_types::batches::Batch;
 pub type Key = meilisearch_types::keys::Key;
 pub type ChatCompletionSettings = meilisearch_types::features::ChatCompletionSettings;
 pub type RuntimeTogglableFeatures = meilisearch_types::features::RuntimeTogglableFeatures;
-pub type Network = meilisearch_types::network::Network;
+pub type Network = meilisearch_types::enterprise_edition::network::DbNetwork;
 pub type Webhooks = meilisearch_types::webhooks::WebhooksDumpView;
 
 // ===== Other types to clarify the code of the compat module

crates/dump/src/writer.rs

@@ -5,9 +5,9 @@ use std::path::PathBuf;
 use flate2::write::GzEncoder;
 use flate2::Compression;
 use meilisearch_types::batches::Batch;
+use meilisearch_types::enterprise_edition::network::DbNetwork;
 use meilisearch_types::features::{ChatCompletionSettings, RuntimeTogglableFeatures};
 use meilisearch_types::keys::Key;
-use meilisearch_types::network::Network;
 use meilisearch_types::settings::{Checked, Settings};
 use meilisearch_types::webhooks::WebhooksDumpView;
 use serde_json::{Map, Value};
@@ -72,7 +72,7 @@ impl DumpWriter {
         )?)
     }
 
-    pub fn create_network(&self, network: Network) -> Result<()> {
+    pub fn create_network(&self, network: DbNetwork) -> Result<()> {
         Ok(std::fs::write(self.dir.path().join("network.json"), serde_json::to_string(&network)?)?)
     }
 

crates/file-store/Cargo.toml

@@ -11,7 +11,7 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-tempfile = "3.23.0"
+tempfile = "3.20.0"
-thiserror = "2.0.17"
+thiserror = "2.0.12"
 tracing = "0.1.41"
-uuid = { version = "1.18.1", features = ["serde", "v4"] }
+uuid = { version = "1.17.0", features = ["serde", "v4"] }

crates/file-store/src/lib.rs

@@ -60,7 +60,7 @@ impl FileStore {
 
     /// Returns the file corresponding to the requested uuid.
     pub fn get_update(&self, uuid: Uuid) -> Result<StdFile> {
-        let path = self.update_path(uuid);
+        let path = self.get_update_path(uuid);
         let file = match StdFile::open(path) {
             Ok(file) => file,
             Err(e) => {
@@ -72,7 +72,7 @@ impl FileStore {
     }
 
     /// Returns the path that correspond to this uuid, the path could not exists.
-    pub fn update_path(&self, uuid: Uuid) -> PathBuf {
+    pub fn get_update_path(&self, uuid: Uuid) -> PathBuf {
         self.path.join(uuid.to_string())
     }
 

crates/flatten-serde-json/Cargo.toml

@@ -16,7 +16,7 @@ license.workspace = true
 serde_json = "1.0"
 
 [dev-dependencies]
-criterion = { version = "0.7.0", features = ["html_reports"] }
+criterion = { version = "0.6.0", features = ["html_reports"] }
 
 [[bench]]
 name = "benchmarks"

crates/fuzzers/Cargo.toml

@@ -11,12 +11,12 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-arbitrary = { version = "1.4.2", features = ["derive"] }
+arbitrary = { version = "1.4.1", features = ["derive"] }
-bumpalo = "3.19.0"
+bumpalo = "3.18.1"
-clap = { version = "4.5.52", features = ["derive"] }
+clap = { version = "4.5.40", features = ["derive"] }
 either = "1.15.0"
 fastrand = "2.3.0"
 milli = { path = "../milli" }
-serde = { version = "1.0.228", features = ["derive"] }
+serde = { version = "1.0.219", features = ["derive"] }
-serde_json = { version = "1.0.145", features = ["preserve_order"] }
+serde_json = { version = "1.0.140", features = ["preserve_order"] }
-tempfile = "3.23.0"
+tempfile = "3.20.0"

crates/index-scheduler/Cargo.toml

@@ -11,33 +11,32 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-anyhow = "1.0.100"
+anyhow = "1.0.98"
 bincode = "1.3.3"
 byte-unit = "5.1.6"
-bytes = "1.11.0"
+bumpalo = "3.18.1"
-bumpalo = "3.19.0"
 bumparaw-collections = "0.1.4"
-convert_case = "0.9.0"
+convert_case = "0.8.0"
-csv = "1.4.0"
+csv = "1.3.1"
 derive_builder = "0.20.2"
 dump = { path = "../dump" }
-enum-iterator = "2.3.0"
+enum-iterator = "2.1.0"
 file-store = { path = "../file-store" }
-flate2 = "1.1.5"
+flate2 = "1.1.2"
-indexmap = "2.12.0"
+hashbrown = "0.15.4"
+indexmap = "2.9.0"
 meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
-memmap2 = "0.9.9"
+memmap2 = "0.9.7"
 page_size = "0.6.0"
-rayon = "1.11.0"
+rayon = "1.10.0"
 roaring = { version = "0.10.12", features = ["serde"] }
-serde = { version = "1.0.228", features = ["derive"] }
+serde = { version = "1.0.219", features = ["derive"] }
-serde_json = { version = "1.0.145", features = ["preserve_order"] }
+serde_json = { version = "1.0.140", features = ["preserve_order"] }
-tar = "0.4.44"
 synchronoise = "1.0.1"
-tempfile = "3.23.0"
+tempfile = "3.20.0"
-thiserror = "2.0.17"
+thiserror = "2.0.12"
-time = { version = "0.3.44", features = [
+time = { version = "0.3.41", features = [
     "serde-well-known",
     "formatting",
     "parsing",
@@ -45,11 +44,10 @@ time = { version = "0.3.44", features = [
 ] }
 tracing = "0.1.41"
 ureq = "2.12.1"
-uuid = { version = "1.18.1", features = ["serde", "v4"] }
+uuid = { version = "1.17.0", features = ["serde", "v4"] }
 backoff = "0.4.0"
-reqwest = { version = "0.12.24", features = ["rustls-tls", "http2"], default-features = false }
+itertools = "0.14.0"
-rusty-s3 = "0.8.1"
+tokio = { version = "1.47.1", features = ["full"] }
-tokio = { version = "1.48.0", features = ["full"] }
 
 [dev-dependencies]
 big_s = "1.0.2"

crates/index-scheduler/src/dump.rs

@@ -150,7 +150,6 @@ impl<'a> Dump<'a> {
             details: task.details,
             status: task.status,
             network: task.network,
-            custom_metadata: task.custom_metadata,
             kind: match task.kind {
                 KindDump::DocumentImport {
                     primary_key,
@@ -235,8 +234,8 @@ impl<'a> Dump<'a> {
                     }
                 }
                 KindDump::UpgradeDatabase { from } => KindWithContent::UpgradeDatabase { from },
-                KindDump::IndexCompaction { index_uid } => {
+                KindDump::NetworkTopologyChange { network: new_network, origin } => {
-                    KindWithContent::IndexCompaction { index_uid }
+                    KindWithContent::NetworkTopologyChange { network: new_network, origin }
                 }
             },
         };

crates/index-scheduler/src/error.rs

@@ -5,7 +5,6 @@ use meilisearch_types::error::{Code, ErrorCode};
 use meilisearch_types::milli::index::RollbackOutcome;
 use meilisearch_types::tasks::{Kind, Status};
 use meilisearch_types::{heed, milli};
-use reqwest::StatusCode;
 use thiserror::Error;
 
 use crate::TaskId;
@@ -128,14 +127,6 @@ pub enum Error {
     #[error("Aborted task")]
     AbortedTask,
 
-    #[error("S3 error: status: {status}, body: {body}")]
-    S3Error { status: StatusCode, body: String },
-    #[error("S3 HTTP error: {0}")]
-    S3HttpError(reqwest::Error),
-    #[error("S3 XML error: {0}")]
-    S3XmlError(Box<dyn std::error::Error + Send + Sync>),
-    #[error("S3 bucket error: {0}")]
-    S3BucketError(rusty_s3::BucketError),
     #[error(transparent)]
     Dump(#[from] dump::Error),
     #[error(transparent)]
@@ -235,10 +226,6 @@ impl Error {
             | Error::TaskCancelationWithEmptyQuery
             | Error::FromRemoteWhenExporting { .. }
             | Error::AbortedTask
-            | Error::S3Error { .. }
-            | Error::S3HttpError(_)
-            | Error::S3XmlError(_)
-            | Error::S3BucketError(_)
             | Error::Dump(_)
             | Error::Heed(_)
             | Error::Milli { .. }
@@ -306,14 +293,8 @@ impl ErrorCode for Error {
             Error::BatchNotFound(_) => Code::BatchNotFound,
             Error::TaskDeletionWithEmptyQuery => Code::MissingTaskFilters,
             Error::TaskCancelationWithEmptyQuery => Code::MissingTaskFilters,
+            // TODO: not sure of the Code to use
             Error::NoSpaceLeftInTaskQueue => Code::NoSpaceLeftOnDevice,
-            Error::S3Error { status, .. } if status.is_client_error() => {
-                Code::InvalidS3SnapshotRequest
-            }
-            Error::S3Error { .. } => Code::S3SnapshotServerError,
-            Error::S3HttpError(_) => Code::S3SnapshotServerError,
-            Error::S3XmlError(_) => Code::S3SnapshotServerError,
-            Error::S3BucketError(_) => Code::InvalidS3SnapshotParameters,
             Error::Dump(e) => e.error_code(),
             Error::Milli { error, .. } => error.error_code(),
             Error::ProcessBatchPanicked(_) => Code::Internal,

crates/index-scheduler/src/features.rs

@@ -1,9 +1,9 @@
 use std::sync::{Arc, RwLock};
 
+use meilisearch_types::enterprise_edition::network::DbNetwork;
 use meilisearch_types::features::{InstanceTogglableFeatures, RuntimeTogglableFeatures};
 use meilisearch_types::heed::types::{SerdeJson, Str};
 use meilisearch_types::heed::{Database, Env, RwTxn, WithoutTls};
-use meilisearch_types::network::Network;
 
 use crate::error::FeatureNotEnabledError;
 use crate::Result;
@@ -24,7 +24,7 @@ mod db_keys {
 pub(crate) struct FeatureData {
     persisted: Database<Str, SerdeJson<RuntimeTogglableFeatures>>,
     runtime: Arc<RwLock<RuntimeTogglableFeatures>>,
-    network: Arc<RwLock<Network>>,
+    network: Arc<RwLock<DbNetwork>>,
 }
 
 #[derive(Debug, Clone, Copy)]
@@ -197,8 +197,8 @@ impl FeatureData {
         }));
 
         // Once this is stabilized, network should be stored along with webhooks in index-scheduler's persisted database
-        let network_db = runtime_features_db.remap_data_type::<SerdeJson<Network>>();
+        let network_db = runtime_features_db.remap_data_type::<SerdeJson<DbNetwork>>();
-        let network: Network = network_db.get(wtxn, db_keys::NETWORK)?.unwrap_or_default();
+        let network: DbNetwork = network_db.get(wtxn, db_keys::NETWORK)?.unwrap_or_default();
 
         Ok(Self {
             persisted: runtime_features_db,
@@ -234,8 +234,8 @@ impl FeatureData {
         RoFeatures::new(self)
     }
 
-    pub fn put_network(&self, mut wtxn: RwTxn, new_network: Network) -> Result<()> {
+    pub fn put_network(&self, mut wtxn: RwTxn, new_network: DbNetwork) -> Result<()> {
-        self.persisted.remap_data_type::<SerdeJson<Network>>().put(
+        self.persisted.remap_data_type::<SerdeJson<DbNetwork>>().put(
             &mut wtxn,
             db_keys::NETWORK,
             &new_network,
@@ -247,7 +247,7 @@ impl FeatureData {
         Ok(())
     }
 
-    pub fn network(&self) -> Network {
+    pub fn network(&self) -> DbNetwork {
-        Network::clone(&*self.network.read().unwrap())
+        DbNetwork::clone(&*self.network.read().unwrap())
     }
 }

crates/index-scheduler/src/index_mapper/mod.rs

@@ -199,7 +199,7 @@ impl IndexMapper {
                 let uuid = Uuid::new_v4();
                 self.index_mapping.put(&mut wtxn, name, &uuid)?;
 
-                let index_path = self.index_path(uuid);
+                let index_path = self.base_path.join(uuid.to_string());
                 fs::create_dir_all(&index_path)?;
 
                 // Error if the UUIDv4 somehow already exists in the map, since it should be fresh.
@@ -286,7 +286,7 @@ impl IndexMapper {
         };
 
         let index_map = self.index_map.clone();
-        let index_path = self.index_path(uuid);
+        let index_path = self.base_path.join(uuid.to_string());
         let index_name = name.to_string();
         thread::Builder::new()
             .name(String::from("index_deleter"))
@@ -341,26 +341,6 @@ impl IndexMapper {
         Ok(())
     }
 
-    /// Closes the specified index.
-    ///
-    /// This operation involves closing the underlying environment and so can take a long time to complete.
-    ///
-    /// # Panics
-    ///
-    /// - If the Index corresponding to the passed name is concurrently being deleted/resized or cannot be found in the
-    ///   in memory hash map.
-    pub fn close_index(&self, rtxn: &RoTxn, name: &str) -> Result<()> {
-        let uuid = self
-            .index_mapping
-            .get(rtxn, name)?
-            .ok_or_else(|| Error::IndexNotFound(name.to_string()))?;
-
-        // We remove the index from the in-memory index map.
-        self.index_map.write().unwrap().close_for_resize(&uuid, self.enable_mdb_writemap, 0);
-
-        Ok(())
-    }
-
     /// 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)) =
@@ -408,7 +388,7 @@ impl IndexMapper {
                     } else {
                         continue;
                     };
-                    let index_path = self.index_path(uuid);
+                    let index_path = self.base_path.join(uuid.to_string());
                     // take the lock to reopen the environment.
                     reopen
                         .reopen(&mut self.index_map.write().unwrap(), &index_path)
@@ -425,7 +405,7 @@ impl IndexMapper {
                     // if it's not already there.
                     match index_map.get(&uuid) {
                         Missing => {
-                            let index_path = self.index_path(uuid);
+                            let index_path = self.base_path.join(uuid.to_string());
 
                             break index_map
                                 .create(
@@ -452,14 +432,6 @@ impl IndexMapper {
         Ok(index)
     }
 
-    /// Returns the path of the index.
-    ///
-    /// The folder located at this path is containing the data.mdb,
-    /// the lock.mdb and an optional data.mdb.cpy file.
-    pub fn index_path(&self, uuid: Uuid) -> PathBuf {
-        self.base_path.join(uuid.to_string())
-    }
-
     pub fn rollback_index(
         &self,
         rtxn: &RoTxn,
@@ -500,7 +472,7 @@ impl IndexMapper {
             };
         }
 
-        let index_path = self.index_path(uuid);
+        let index_path = self.base_path.join(uuid.to_string());
         Index::rollback(milli::heed::EnvOpenOptions::new().read_txn_without_tls(), index_path, to)
             .map_err(|err| crate::Error::from_milli(err, Some(name.to_string())))
     }

crates/index-scheduler/src/insta_snapshot.rs

@@ -6,7 +6,7 @@ use meilisearch_types::heed::types::{SerdeBincode, SerdeJson, Str};
 use meilisearch_types::heed::{Database, RoTxn};
 use meilisearch_types::milli::{CboRoaringBitmapCodec, RoaringBitmapCodec, BEU32};
 use meilisearch_types::tasks::{Details, Kind, Status, Task};
-use meilisearch_types::versioning::{self, VERSION_MAJOR, VERSION_MINOR, VERSION_PATCH};
+use meilisearch_types::versioning;
 use roaring::RoaringBitmap;
 
 use crate::index_mapper::IndexMapper;
@@ -232,7 +232,6 @@ pub fn snapshot_task(task: &Task) -> String {
         status,
         kind,
         network,
-        custom_metadata,
     } = task;
     snap.push('{');
     snap.push_str(&format!("uid: {uid}, "));
@@ -253,9 +252,6 @@ pub fn snapshot_task(task: &Task) -> String {
     if let Some(network) = network {
         snap.push_str(&format!("network: {network:?}, "))
     }
-    if let Some(custom_metadata) = custom_metadata {
-        snap.push_str(&format!("custom_metadata: {custom_metadata:?}"))
-    }
 
     snap.push('}');
     snap
@@ -320,14 +316,10 @@ fn snapshot_details(d: &Details) -> String {
             format!("{{ url: {url:?}, api_key: {api_key:?}, payload_size: {payload_size:?}, indexes: {indexes:?} }}")
         }
         Details::UpgradeDatabase { from, to } => {
-            if to == &(VERSION_MAJOR, VERSION_MINOR, VERSION_PATCH) {
-                format!("{{ from: {from:?}, to: [current version] }}")
-            } else {
             format!("{{ from: {from:?}, to: {to:?} }}")
         }
-        }
+        Details::NetworkTopologyChange { network: new_network } => {
-        Details::IndexCompaction { index_uid, pre_compaction_size, post_compaction_size } => {
+            format!("{{ new_network: {new_network:?} }}")
-            format!("{{ index_uid: {index_uid:?}, pre_compaction_size: {pre_compaction_size:?}, post_compaction_size: {post_compaction_size:?} }}")
         }
     }
 }
@@ -404,21 +396,7 @@ pub fn snapshot_batch(batch: &Batch) -> String {
 
     snap.push('{');
     snap.push_str(&format!("uid: {uid}, "));
-    let details = if let Some(upgrade_to) = &details.upgrade_to {
+    snap.push_str(&format!("details: {}, ", serde_json::to_string(details).unwrap()));
-        if upgrade_to.as_str()
-            == format!("v{VERSION_MAJOR}.{VERSION_MINOR}.{VERSION_PATCH}").as_str()
-        {
-            let mut details = details.clone();
-
-            details.upgrade_to = Some("[current version]".into());
-            serde_json::to_string(&details).unwrap()
-        } else {
-            serde_json::to_string(details).unwrap()
-        }
-    } else {
-        serde_json::to_string(details).unwrap()
-    };
-    snap.push_str(&format!("details: {details}, "));
     snap.push_str(&format!("stats: {}, ", serde_json::to_string(&stats).unwrap()));
     if !embedder_stats.skip_serializing() {
         snap.push_str(&format!(

crates/index-scheduler/src/lib.rs

@@ -54,6 +54,7 @@ pub use features::RoFeatures;
 use flate2::bufread::GzEncoder;
 use flate2::Compression;
 use meilisearch_types::batches::Batch;
+use meilisearch_types::enterprise_edition::network::DbNetwork;
 use meilisearch_types::features::{
     ChatCompletionSettings, InstanceTogglableFeatures, RuntimeTogglableFeatures,
 };
@@ -66,7 +67,6 @@ use meilisearch_types::milli::vector::{
     Embedder, EmbedderOptions, RuntimeEmbedder, RuntimeEmbedders, RuntimeFragment,
 };
 use meilisearch_types::milli::{self, Index};
-use meilisearch_types::network::Network;
 use meilisearch_types::task_view::TaskView;
 use meilisearch_types::tasks::{KindWithContent, Task, TaskNetwork};
 use meilisearch_types::webhooks::{Webhook, WebhooksDumpView, WebhooksView};
@@ -217,7 +217,6 @@ pub struct IndexScheduler {
     #[cfg(test)]
     run_loop_iteration: Arc<RwLock<usize>>,
 
-    /// The tokio runtime used for asynchronous tasks.
     runtime: Option<tokio::runtime::Handle>,
 }
 
@@ -259,23 +258,14 @@ impl IndexScheduler {
     }
 
     /// Create an index scheduler and start its run loop.
+    #[allow(private_interfaces)] // because test_utils is private
     pub fn new(
         options: IndexSchedulerOptions,
         auth_env: Env<WithoutTls>,
         from_db_version: (u32, u32, u32),
         runtime: Option<tokio::runtime::Handle>,
-    ) -> Result<Self> {
+        #[cfg(test)] test_breakpoint_sdr: crossbeam_channel::Sender<(test_utils::Breakpoint, bool)>,
-        let this = Self::new_without_run(options, auth_env, from_db_version, runtime)?;
+        #[cfg(test)] planned_failures: Vec<(usize, test_utils::FailureLocation)>,
-
-        this.run();
-        Ok(this)
-    }
-
-    fn new_without_run(
-        options: IndexSchedulerOptions,
-        auth_env: Env<WithoutTls>,
-        from_db_version: (u32, u32, u32),
-        runtime: Option<tokio::runtime::Handle>,
     ) -> Result<Self> {
         std::fs::create_dir_all(&options.tasks_path)?;
         std::fs::create_dir_all(&options.update_file_path)?;
@@ -330,7 +320,8 @@ impl IndexScheduler {
 
         wtxn.commit()?;
 
-        Ok(Self {
+        // allow unreachable_code to get rids of the warning in the case of a test build.
+        let this = Self {
             processing_tasks: Arc::new(RwLock::new(ProcessingTasks::new())),
             version,
             queue,
@@ -346,32 +337,16 @@ impl IndexScheduler {
             webhooks: Arc::new(webhooks),
             embedders: Default::default(),
 
-            #[cfg(test)] // Will be replaced in `new_tests` in test environments
+            #[cfg(test)]
-            test_breakpoint_sdr: crossbeam_channel::bounded(0).0,
+            test_breakpoint_sdr,
-            #[cfg(test)] // Will be replaced in `new_tests` in test environments
+            #[cfg(test)]
-            planned_failures: Default::default(),
+            planned_failures,
             #[cfg(test)]
             run_loop_iteration: Arc::new(RwLock::new(0)),
             features,
             chat_settings,
             runtime,
-        })
+        };
-    }
-
-    /// Create an index scheduler and start its run loop.
-    #[cfg(test)]
-    fn new_test(
-        options: IndexSchedulerOptions,
-        auth_env: Env<WithoutTls>,
-        from_db_version: (u32, u32, u32),
-        runtime: Option<tokio::runtime::Handle>,
-        test_breakpoint_sdr: crossbeam_channel::Sender<(test_utils::Breakpoint, bool)>,
-        planned_failures: Vec<(usize, test_utils::FailureLocation)>,
-    ) -> Result<Self> {
-        let mut this = Self::new_without_run(options, auth_env, from_db_version, runtime)?;
-
-        this.test_breakpoint_sdr = test_breakpoint_sdr;
-        this.planned_failures = planned_failures;
 
         this.run();
         Ok(this)
@@ -756,19 +731,6 @@ impl IndexScheduler {
         kind: KindWithContent,
         task_id: Option<TaskId>,
         dry_run: bool,
-    ) -> Result<Task> {
-        self.register_with_custom_metadata(kind, task_id, None, dry_run)
-    }
-
-    /// Register a new task in the scheduler, with metadata.
-    ///
-    /// If it fails and data was associated with the task, it tries to delete the associated data.
-    pub fn register_with_custom_metadata(
-        &self,
-        kind: KindWithContent,
-        task_id: Option<TaskId>,
-        custom_metadata: Option<String>,
-        dry_run: bool,
     ) -> Result<Task> {
         // if the task doesn't delete or cancel anything and 40% of the task queue is full, we must refuse to enqueue the incoming task
         if !matches!(&kind, KindWithContent::TaskDeletion { tasks, .. } | KindWithContent::TaskCancelation { tasks, .. } if !tasks.is_empty())
@@ -779,7 +741,7 @@ impl IndexScheduler {
         }
 
         let mut wtxn = self.env.write_txn()?;
-        let task = self.queue.register(&mut wtxn, &kind, task_id, custom_metadata, dry_run)?;
+        let task = self.queue.register(&mut wtxn, &kind, task_id, dry_run)?;
 
         // If the registered task is a task cancelation
         // we inform the processing tasks to stop (if necessary).
@@ -935,13 +897,13 @@ impl IndexScheduler {
         Ok(())
     }
 
-    pub fn put_network(&self, network: Network) -> Result<()> {
+    pub fn put_network(&self, network: DbNetwork) -> Result<()> {
         let wtxn = self.env.write_txn().map_err(Error::HeedTransaction)?;
         self.features.put_network(wtxn, network)?;
         Ok(())
     }
 
-    pub fn network(&self) -> Network {
+    pub fn network(&self) -> DbNetwork {
         self.features.network()
     }
 
@@ -970,9 +932,10 @@ impl IndexScheduler {
 
     pub fn embedders(
         &self,
-        index_uid: String,
+        index_uid: &str,
         embedding_configs: Vec<IndexEmbeddingConfig>,
     ) -> Result<RuntimeEmbedders> {
+        let err = |err| Error::from_milli(err, Some(index_uid.to_owned()));
         let res: Result<_> = embedding_configs
             .into_iter()
             .map(
@@ -985,7 +948,7 @@ impl IndexScheduler {
                     let document_template = prompt
                         .try_into()
                         .map_err(meilisearch_types::milli::Error::from)
-                        .map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?;
+                        .map_err(err)?;
 
                     let fragments = fragments
                         .into_inner()
@@ -1015,9 +978,8 @@ impl IndexScheduler {
                     let embedder = Arc::new(
                         Embedder::new(embedder_options.clone(), self.scheduler.embedding_cache_cap)
                             .map_err(meilisearch_types::milli::vector::Error::from)
-                            .map_err(|err| {
+                            .map_err(milli::Error::from)
-                                Error::from_milli(err.into(), Some(index_uid.clone()))
+                            .map_err(err)?,
-                            })?,
                     );
                     {
                         let mut embedders = self.embedders.write().unwrap();

crates/index-scheduler/src/processing.rs

@@ -75,7 +75,6 @@ make_enum_progress! {
     pub enum TaskCancelationProgress {
         RetrievingTasks,
         CancelingUpgrade,
-        CleaningCompactionLeftover,
         UpdatingTasks,
     }
 }
@@ -139,17 +138,6 @@ make_enum_progress! {
     }
 }
 
-make_enum_progress! {
-    pub enum IndexCompaction {
-        RetrieveTheIndex,
-        CreateTemporaryFile,
-        CopyAndCompactTheIndex,
-        PersistTheCompactedIndex,
-        CloseTheIndex,
-        ReopenTheIndex,
-    }
-}
-
 make_enum_progress! {
     pub enum InnerSwappingTwoIndexes {
         RetrieveTheTasks,

crates/index-scheduler/src/queue/mod.rs

@@ -257,7 +257,6 @@ impl Queue {
         wtxn: &mut RwTxn,
         kind: &KindWithContent,
         task_id: Option<TaskId>,
-        custom_metadata: Option<String>,
         dry_run: bool,
     ) -> Result<Task> {
         let next_task_id = self.tasks.next_task_id(wtxn)?;
@@ -281,7 +280,6 @@ impl Queue {
             status: Status::Enqueued,
             kind: kind.clone(),
             network: None,
-            custom_metadata,
         };
         // For deletion and cancelation tasks, we want to make extra sure that they
         // don't attempt to delete/cancel tasks that are newer than themselves.
@@ -312,8 +310,7 @@ impl Queue {
             | self.tasks.status.get(wtxn, &Status::Failed)?.unwrap_or_default()
             | self.tasks.status.get(wtxn, &Status::Canceled)?.unwrap_or_default();
 
-        let to_delete =
+        let to_delete = RoaringBitmap::from_iter(finished.into_iter().rev().take(100_000));
-            RoaringBitmap::from_sorted_iter(finished.into_iter().take(100_000)).unwrap();
 
         // /!\ the len must be at least 2 or else we might enter an infinite loop where we only delete
         //     the deletion tasks we enqueued ourselves.
@@ -346,7 +343,6 @@ impl Queue {
                 tasks: to_delete,
             },
             None,
-            None,
             false,
         )?;
 

crates/index-scheduler/src/scheduler/autobatcher.rs

@@ -68,14 +68,14 @@ impl From<KindWithContent> for AutobatchKind {
             KindWithContent::IndexCreation { .. } => AutobatchKind::IndexCreation,
             KindWithContent::IndexUpdate { .. } => AutobatchKind::IndexUpdate,
             KindWithContent::IndexSwap { .. } => AutobatchKind::IndexSwap,
-            KindWithContent::IndexCompaction { .. }
+            KindWithContent::TaskCancelation { .. }
-            | KindWithContent::TaskCancelation { .. }
             | KindWithContent::TaskDeletion { .. }
             | KindWithContent::DumpCreation { .. }
             | KindWithContent::Export { .. }
             | KindWithContent::UpgradeDatabase { .. }
+            | KindWithContent::NetworkTopologyChange { .. }
             | KindWithContent::SnapshotCreation => {
-                panic!("The autobatcher should never be called with tasks with special priority or that don't apply to an index.")
+                panic!("The autobatcher should never be called with tasks that don't apply to an index.")
             }
         }
     }
@@ -289,9 +289,7 @@ impl BatchKind {
 
         match (self, autobatch_kind) {
             // We don't batch any of these operations
-            (this, K::IndexCreation | K::IndexUpdate | K::IndexSwap | K::DocumentEdition) => {
+            (this, K::IndexCreation | K::IndexUpdate | K::IndexSwap | K::DocumentEdition) => Break((this, BatchStopReason::TaskCannotBeBatched { kind, id })),
-                Break((this, BatchStopReason::TaskCannotBeBatched { kind, id }))
-            },
             // We must not batch tasks that don't have the same index creation rights if the index doesn't already exists.
             (this, kind) if !index_already_exists && this.allow_index_creation() == Some(false) && kind.allow_index_creation() == Some(true) => {
                 Break((this, BatchStopReason::IndexCreationMismatch { id }))

crates/index-scheduler/src/scheduler/create_batch.rs

@@ -55,9 +55,8 @@ pub(crate) enum Batch {
     UpgradeDatabase {
         tasks: Vec<Task>,
     },
-    IndexCompaction {
+    NetworkTopologyChanges {
-        index_uid: String,
+        tasks: Vec<Task>,
-        task: Task,
     },
 }
 
@@ -114,14 +113,14 @@ impl Batch {
             | Batch::Dump(task)
             | Batch::IndexCreation { task, .. }
             | Batch::Export { task }
-            | Batch::IndexUpdate { task, .. }
+            | Batch::IndexUpdate { task, .. } => {
-            | Batch::IndexCompaction { task, .. } => {
                 RoaringBitmap::from_sorted_iter(std::iter::once(task.uid)).unwrap()
             }
             Batch::SnapshotCreation(tasks)
             | Batch::TaskDeletions(tasks)
             | Batch::UpgradeDatabase { tasks }
-            | Batch::IndexDeletion { tasks, .. } => {
+            | Batch::IndexDeletion { tasks, .. }
+            | Batch::NetworkTopologyChanges { tasks } => {
                 RoaringBitmap::from_iter(tasks.iter().map(|task| task.uid))
             }
             Batch::IndexOperation { op, .. } => match op {
@@ -156,12 +155,12 @@ impl Batch {
             | Dump(_)
             | Export { .. }
             | UpgradeDatabase { .. }
+            | NetworkTopologyChanges { .. }
             | IndexSwap { .. } => None,
             IndexOperation { op, .. } => Some(op.index_uid()),
             IndexCreation { index_uid, .. }
             | IndexUpdate { index_uid, .. }
-            | IndexDeletion { index_uid, .. }
+            | IndexDeletion { index_uid, .. } => Some(index_uid),
-            | IndexCompaction { index_uid, .. } => Some(index_uid),
         }
     }
 }
@@ -181,8 +180,8 @@ impl fmt::Display for Batch {
             Batch::IndexUpdate { .. } => f.write_str("IndexUpdate")?,
             Batch::IndexDeletion { .. } => f.write_str("IndexDeletion")?,
             Batch::IndexSwap { .. } => f.write_str("IndexSwap")?,
-            Batch::IndexCompaction { .. } => f.write_str("IndexCompaction")?,
             Batch::Export { .. } => f.write_str("Export")?,
+            Batch::NetworkTopologyChanges { .. } => f.write_str("NetworkTopologyChange")?,
             Batch::UpgradeDatabase { .. } => f.write_str("UpgradeDatabase")?,
         };
         match index_uid {
@@ -519,33 +518,17 @@ impl IndexScheduler {
             return Ok(Some((Batch::TaskDeletions(tasks), current_batch)));
         }
 
-        // 3. we get the next task to compact
+        // 3. we batch the export.
-        let to_compact = self.queue.tasks.get_kind(rtxn, Kind::IndexCompaction)? & enqueued;
-        if let Some(task_id) = to_compact.min() {
-            let mut task =
-                self.queue.tasks.get_task(rtxn, task_id)?.ok_or(Error::CorruptedTaskQueue)?;
-            current_batch.processing(Some(&mut task));
-            current_batch.reason(BatchStopReason::TaskCannotBeBatched {
-                kind: Kind::IndexCompaction,
-                id: task_id,
-            });
-            let index_uid =
-                task.index_uid().expect("Compaction task must have an index uid").to_owned();
-            return Ok(Some((Batch::IndexCompaction { index_uid, task }, current_batch)));
-        }
-
-        // 4. we batch the export.
         let to_export = self.queue.tasks.get_kind(rtxn, Kind::Export)? & enqueued;
         if !to_export.is_empty() {
             let task_id = to_export.iter().next().expect("There must be at least one export task");
             let mut task = self.queue.tasks.get_task(rtxn, task_id)?.unwrap();
             current_batch.processing([&mut task]);
-            current_batch
+            current_batch.reason(BatchStopReason::TaskKindCannotBeBatched { kind: Kind::Export });
-                .reason(BatchStopReason::TaskCannotBeBatched { kind: Kind::Export, id: task_id });
             return Ok(Some((Batch::Export { task }, current_batch)));
         }
 
-        // 5. we batch the snapshot.
+        // 4. we batch the snapshot.
         let to_snapshot = self.queue.tasks.get_kind(rtxn, Kind::SnapshotCreation)? & enqueued;
         if !to_snapshot.is_empty() {
             let mut tasks = self.queue.tasks.get_existing_tasks(rtxn, to_snapshot)?;
@@ -555,7 +538,7 @@ impl IndexScheduler {
             return Ok(Some((Batch::SnapshotCreation(tasks), current_batch)));
         }
 
-        // 6. we batch the dumps.
+        // 5. we batch the dumps.
         let to_dump = self.queue.tasks.get_kind(rtxn, Kind::DumpCreation)? & enqueued;
         if let Some(to_dump) = to_dump.min() {
             let mut task =
@@ -568,6 +551,17 @@ impl IndexScheduler {
             return Ok(Some((Batch::Dump(task), current_batch)));
         }
 
+        // 6. We batch the network changes.
+        let to_network = self.queue.tasks.get_kind(rtxn, Kind::NetworkTopologyChange)? & enqueued;
+        if !to_network.is_empty() {
+            let mut tasks = self.queue.tasks.get_existing_tasks(rtxn, to_network)?;
+            current_batch.processing(&mut tasks);
+            current_batch.reason(BatchStopReason::TaskKindCannotBeBatched {
+                kind: Kind::NetworkTopologyChange,
+            });
+            return Ok(Some((Batch::NetworkTopologyChanges { tasks }, current_batch)));
+        }
+
         // 7. We make a batch from the unprioritised tasks. Start by taking the next enqueued task.
         let task_id = if let Some(task_id) = enqueued.min() { task_id } else { return Ok(None) };
         let mut task =

crates/index-scheduler/src/scheduler/enterprise_edition/mod.rs

@@ -0,0 +1,6 @@
+// Copyright © 2025 Meilisearch Some Rights Reserved
+// This file is part of Meilisearch Enterprise Edition (EE).
+// Use of this source code is governed by the Business Source License 1.1,
+// as found in the LICENSE-EE file or at <https://mariadb.com/bsl11>
+
+mod process_network;

crates/index-scheduler/src/scheduler/enterprise_edition/process_network.rs

@@ -0,0 +1,362 @@
+// Copyright © 2025 Meilisearch Some Rights Reserved
+// This file is part of Meilisearch Enterprise Edition (EE).
+// Use of this source code is governed by the Business Source License 1.1,
+// as found in the LICENSE-EE file or at <https://mariadb.com/bsl11>
+
+use std::collections::BTreeMap;
+use std::time::Duration;
+
+use bumpalo::Bump;
+use itertools::{EitherOrBoth, Itertools};
+use meilisearch_types::enterprise_edition::network::{DbNetwork, DbRemote, Network, Remote};
+use meilisearch_types::milli::documents::PrimaryKey;
+use meilisearch_types::milli::progress::{EmbedderStats, Progress};
+use meilisearch_types::milli::update::new::indexer;
+use meilisearch_types::milli::update::Setting;
+use meilisearch_types::milli::{self};
+use meilisearch_types::tasks::{KindWithContent, Status, Task};
+use roaring::RoaringBitmap;
+
+use crate::scheduler::process_export::{ExportContext, ExportOptions, TargetInstance};
+use crate::{Error, IndexScheduler};
+
+impl IndexScheduler {
+    pub(crate) fn process_network_changes(
+        &self,
+        progress: Progress,
+        mut tasks: Vec<Task>,
+    ) -> crate::Result<Vec<Task>> {
+        let old_network = self.network();
+        let mut current_network = Some(old_network.clone());
+        for task in &tasks {
+            let KindWithContent::NetworkTopologyChange { network, origin } = &task.kind else {
+                continue;
+            };
+            current_network = match (current_network, network) {
+                (None, None) => None,
+                (None, Some(network)) => Some(accumulate(DbNetwork::default(), network.clone())?),
+                (Some(current_network), None) => Some(current_network),
+                (Some(current_network), Some(new_network)) => {
+                    Some(accumulate(current_network, new_network.clone())?)
+                }
+            };
+        }
+
+        'network: {
+            let mut new_network = current_network.unwrap_or_default();
+            if old_network == new_network {
+                // no change, exit
+                break 'network;
+            }
+
+            /// TODO: only do this if the task originates with an end-user
+            let must_replicate = old_network.sharding || new_network.sharding;
+
+            if !must_replicate {
+                self.put_network(new_network)?;
+                break 'network;
+            }
+
+            let must_stop_processing = &self.scheduler.must_stop_processing;
+
+            /// FIXME: make it mandatory for `self` to be part of the network
+            let old_this = old_network.local.as_deref();
+            /// FIXME: error here
+            let new_this = new_network.local.unwrap();
+
+            // in network replication, we need to tell old nodes that they are no longer part of the network.
+            // This is made difficult by "node aliasing": Meilisearch has no way of knowing if two nodes with different names
+            // or even different URLs actually refer to the same machine in two different versions of the network.
+            //
+            // This implementation ignores aliasing: a node is the same when it has the same name.
+            //
+            // To defeat aliasing, we iterate a first time to collect all deletions and additions, then we make sure to process the deletions
+            // first, rather than processing the tasks in the alphalexical order of remotes.
+            let mut node_deletions = Vec::new();
+            let mut node_additions = Vec::new();
+            for eob in old_network
+                .remotes
+                .iter()
+                .merge_join_by(new_network.remotes.iter(), |(left, _), (right, _)| left.cmp(right))
+            {
+                match eob {
+                    EitherOrBoth::Both((to_update_name, _), (_, new_node)) => {
+                        if to_update_name.as_str() == new_this {
+                            continue; // skip `self`
+                        }
+                        node_additions.push((to_update_name, new_node));
+                    }
+                    EitherOrBoth::Left((to_delete_name, to_delete_node)) => {
+                        if Some(to_delete_name.as_str()) == old_this {
+                            continue; // skip `self`
+                        }
+                        node_deletions.push((to_delete_name, to_delete_node));
+                    }
+                    EitherOrBoth::Right((to_add_name, to_add_node)) => {
+                        if to_add_name.as_str() == new_this {
+                            continue; // skip `self`
+                        }
+                        node_additions.push((to_add_name, to_add_node));
+                    }
+                }
+            }
+
+            let runtime = self.runtime.clone().unwrap();
+            let mut in_flight = Vec::new();
+            // process deletions
+            for (to_delete_name, to_delete) in node_deletions {
+                // set `self` to None so that this node is forgotten about
+                new_network.local = None;
+                in_flight.push(proxy_network(&runtime, to_delete.url.as_str(), &new_network)?);
+            }
+
+            runtime.block_on(async {
+                for task in in_flight.drain(..) {
+                    // TODO: log and ignore errors during deletion
+                    let res = task.await;
+                }
+            });
+
+            // process additions
+            for (to_add_name, to_add) in node_additions {
+                new_network.local = Some(to_add_name.clone());
+                in_flight.push(proxy_network(&runtime, to_add.url.as_str(), &new_network)?);
+            }
+
+            runtime.block_on(async {
+                for task in in_flight.drain(..) {
+                    // TODO: handle errors during addition
+                    let res = task.await;
+                }
+            });
+
+            // balance documents
+            new_network.local = Some(new_this);
+
+            self.balance_documents(&new_network, &progress, &must_stop_processing)?;
+
+            self.put_network(new_network)?;
+        }
+
+        for task in &mut tasks {
+            task.status = Status::Succeeded;
+        }
+        Ok(tasks)
+    }
+
+    fn balance_documents(
+        &self,
+        new_network: &DbNetwork,
+        progress: &Progress,
+        must_stop_processing: &crate::scheduler::MustStopProcessing,
+    ) -> crate::Result<()> {
+        /// FIXME unwrap
+        let new_shards = new_network.shards().unwrap();
+
+        // TECHDEBT: this spawns a `ureq` agent additionally to `reqwest`. We probably want to harmonize all of this.
+        let agent = ureq::AgentBuilder::new().timeout(Duration::from_secs(5)).build();
+
+        let mut indexer_alloc = Bump::new();
+
+        // process by batches of 20MiB. Allow for compression? Don't forget about embeddings
+        let _: Vec<()> = self.try_for_each_index(|index_uid, index| -> crate::Result<()> {
+            indexer_alloc.reset();
+            let err = |err| Error::from_milli(err, Some(index_uid.to_string()));
+            let index_rtxn = index.read_txn()?;
+            let all_docids = index.external_documents_ids();
+            let mut documents_to_move_to: hashbrown::HashMap<String, RoaringBitmap> =
+                hashbrown::HashMap::new();
+            let mut documents_to_delete = RoaringBitmap::new();
+
+            for res in all_docids.iter(&index_rtxn)? {
+                let (external_docid, docid) = res?;
+                match new_shards.processing_shard(external_docid) {
+                    Some(shard) if shard.is_own => continue,
+                    Some(shard) => {
+                        documents_to_move_to
+                            .entry_ref(shard.name.as_str())
+                            .or_default()
+                            .insert(docid);
+                    }
+                    None => {
+                        documents_to_delete.insert(docid);
+                    }
+                }
+            }
+
+            let fields_ids_map = index.fields_ids_map(&index_rtxn)?;
+
+            for (remote, documents_to_move) in documents_to_move_to {
+                /// TODO: justify the unwrap
+                let remote = new_network.remotes.get(&remote).unwrap();
+
+                let target = TargetInstance {
+                    base_url: &remote.url,
+                    api_key: remote.write_api_key.as_deref(),
+                };
+                let options = ExportOptions {
+                    index_uid,
+                    payload_size: None,
+                    override_settings: false,
+                    extra_headers: &Default::default(),
+                };
+                let ctx = ExportContext {
+                    index,
+                    index_rtxn: &index_rtxn,
+                    universe: &documents_to_move,
+                    progress,
+                    agent: &agent,
+                    must_stop_processing,
+                };
+
+                self.export_one_index(target, options, ctx)?;
+
+                documents_to_delete |= documents_to_move;
+            }
+
+            if documents_to_delete.is_empty() {
+                return Ok(());
+            }
+
+            let mut new_fields_ids_map = fields_ids_map.clone();
+
+            // candidates not empty => index not empty => a primary key is set
+            let primary_key = index.primary_key(&index_rtxn)?.unwrap();
+
+            let primary_key = PrimaryKey::new_or_insert(primary_key, &mut new_fields_ids_map)
+                .map_err(milli::Error::from)
+                .map_err(err)?;
+
+            let mut index_wtxn = index.write_txn()?;
+
+            let mut indexer = indexer::DocumentDeletion::new();
+            indexer.delete_documents_by_docids(documents_to_delete);
+            let document_changes = indexer.into_changes(&indexer_alloc, primary_key);
+            let embedders = index
+                .embedding_configs()
+                .embedding_configs(&index_wtxn)
+                .map_err(milli::Error::from)
+                .map_err(err)?;
+            let embedders = self.embedders(index_uid, embedders)?;
+            let indexer_config = self.index_mapper.indexer_config();
+            let pool = &indexer_config.thread_pool;
+
+            indexer::index(
+                &mut index_wtxn,
+                index,
+                pool,
+                indexer_config.grenad_parameters(),
+                &fields_ids_map,
+                new_fields_ids_map,
+                None, // document deletion never changes primary key
+                &document_changes,
+                embedders,
+                &|| must_stop_processing.get(),
+                &progress,
+                &EmbedderStats::default(),
+            )
+            .map_err(err)?;
+
+            index_wtxn.commit()?;
+
+            Ok(())
+        })?;
+        Ok(())
+    }
+}
+
+fn proxy_network(
+    runtime: &tokio::runtime::Handle,
+    url: &str,
+    network: &DbNetwork,
+) -> crate::Result<tokio::task::JoinHandle<()>> {
+    todo!()
+}
+
+fn accumulate(old_network: DbNetwork, new_network: Network) -> crate::Result<DbNetwork> {
+    let err = |err| Err(Error::from_milli(milli::Error::UserError(err), None));
+
+    let merged_local = match new_network.local {
+        Setting::Set(new_self) => Some(new_self),
+        Setting::Reset => None,
+        Setting::NotSet => old_network.local,
+    };
+
+    let merged_sharding = match new_network.sharding {
+        Setting::Set(new_sharding) => new_sharding,
+        Setting::Reset => false,
+        Setting::NotSet => old_network.sharding,
+    };
+
+    if merged_sharding && merged_local.is_none() {
+        return err(milli::UserError::NetworkShardingWithoutSelf);
+    }
+
+    let merged_remotes = match new_network.remotes {
+        Setting::Set(new_remotes) => {
+            let mut merged_remotes = BTreeMap::new();
+            for either_or_both in old_network
+                .remotes
+                .into_iter()
+                .merge_join_by(new_remotes.into_iter(), |left, right| left.0.cmp(&right.0))
+            {
+                match either_or_both {
+                    EitherOrBoth::Both((name, old), (_, Some(new))) => {
+                        let DbRemote {
+                            url: old_url,
+                            search_api_key: old_search_api_key,
+                            write_api_key: old_write_api_key,
+                        } = old;
+
+                        let Remote {
+                            url: new_url,
+                            search_api_key: new_search_api_key,
+                            write_api_key: new_write_api_key,
+                        } = new;
+
+                        let merged = DbRemote {
+                            url: match new_url {
+                                Setting::Set(new_url) => new_url,
+                                Setting::Reset => {
+                                    return err(milli::UserError::NetworkMissingUrl(name))
+                                }
+                                Setting::NotSet => old_url,
+                            },
+                            search_api_key: match new_search_api_key {
+                                Setting::Set(new_search_api_key) => Some(new_search_api_key),
+                                Setting::Reset => None,
+                                Setting::NotSet => old_search_api_key,
+                            },
+                            write_api_key: match new_write_api_key {
+                                Setting::Set(new_write_api_key) => Some(new_write_api_key),
+                                Setting::Reset => None,
+                                Setting::NotSet => old_write_api_key,
+                            },
+                        };
+                        merged_remotes.insert(name, merged);
+                    }
+                    EitherOrBoth::Both((_, _), (_, None)) | EitherOrBoth::Right((_, None)) => {}
+                    EitherOrBoth::Left((name, node)) => {
+                        merged_remotes.insert(name, node);
+                    }
+                    EitherOrBoth::Right((name, Some(node))) => {
+                        let Some(url) = node.url.set() else {
+                            return err(milli::UserError::NetworkMissingUrl(name));
+                        };
+                        let node = DbRemote {
+                            url,
+                            search_api_key: node.search_api_key.set(),
+                            write_api_key: node.write_api_key.set(),
+                        };
+                        merged_remotes.insert(name, node);
+                    }
+                }
+            }
+            merged_remotes
+        }
+        Setting::Reset => BTreeMap::new(),
+        Setting::NotSet => old_network.remotes,
+    };
+
+    Ok(DbNetwork { local: merged_local, remotes: merged_remotes, sharding: merged_sharding })
+}

crates/index-scheduler/src/scheduler/mod.rs

@@ -2,6 +2,7 @@ mod autobatcher;
 #[cfg(test)]
 mod autobatcher_test;
 mod create_batch;
+mod enterprise_edition;
 mod process_batch;
 mod process_dump_creation;
 mod process_export;
@@ -25,7 +26,6 @@ use convert_case::{Case, Casing as _};
 use meilisearch_types::error::ResponseError;
 use meilisearch_types::heed::{Env, WithoutTls};
 use meilisearch_types::milli;
-use meilisearch_types::milli::update::S3SnapshotOptions;
 use meilisearch_types::tasks::Status;
 use process_batch::ProcessBatchInfo;
 use rayon::current_num_threads;
@@ -88,14 +88,11 @@ pub struct Scheduler {
 
     /// Snapshot compaction status.
     pub(crate) experimental_no_snapshot_compaction: bool,
-
-    /// S3 Snapshot options.
-    pub(crate) s3_snapshot_options: Option<S3SnapshotOptions>,
 }
 
 impl Scheduler {
-    pub(crate) fn private_clone(&self) -> Self {
+    pub(crate) fn private_clone(&self) -> Scheduler {
-        Self {
+        Scheduler {
             must_stop_processing: self.must_stop_processing.clone(),
             wake_up: self.wake_up.clone(),
             autobatching_enabled: self.autobatching_enabled,
@@ -107,52 +104,23 @@ impl Scheduler {
             version_file_path: self.version_file_path.clone(),
             embedding_cache_cap: self.embedding_cache_cap,
             experimental_no_snapshot_compaction: self.experimental_no_snapshot_compaction,
-            s3_snapshot_options: self.s3_snapshot_options.clone(),
         }
     }
 
     pub fn new(options: &IndexSchedulerOptions, auth_env: Env<WithoutTls>) -> Scheduler {
-        let IndexSchedulerOptions {
-            version_file_path,
-            auth_path: _,
-            tasks_path: _,
-            update_file_path: _,
-            indexes_path: _,
-            snapshots_path,
-            dumps_path,
-            cli_webhook_url: _,
-            cli_webhook_authorization: _,
-            task_db_size: _,
-            index_base_map_size: _,
-            enable_mdb_writemap: _,
-            index_growth_amount: _,
-            index_count: _,
-            indexer_config,
-            autobatching_enabled,
-            cleanup_enabled: _,
-            max_number_of_tasks: _,
-            max_number_of_batched_tasks,
-            batched_tasks_size_limit,
-            instance_features: _,
-            auto_upgrade: _,
-            embedding_cache_cap,
-            experimental_no_snapshot_compaction,
-        } = options;
-
         Scheduler {
             must_stop_processing: MustStopProcessing::default(),
             // we want to start the loop right away in case meilisearch was ctrl+Ced while processing things
             wake_up: Arc::new(SignalEvent::auto(true)),
-            autobatching_enabled: *autobatching_enabled,
+            autobatching_enabled: options.autobatching_enabled,
-            max_number_of_batched_tasks: *max_number_of_batched_tasks,
+            max_number_of_batched_tasks: options.max_number_of_batched_tasks,
-            batched_tasks_size_limit: *batched_tasks_size_limit,
+            batched_tasks_size_limit: options.batched_tasks_size_limit,
-            dumps_path: dumps_path.clone(),
+            dumps_path: options.dumps_path.clone(),
-            snapshots_path: snapshots_path.clone(),
+            snapshots_path: options.snapshots_path.clone(),
             auth_env,
-            version_file_path: version_file_path.clone(),
+            version_file_path: options.version_file_path.clone(),
-            embedding_cache_cap: *embedding_cache_cap,
+            embedding_cache_cap: options.embedding_cache_cap,
-            experimental_no_snapshot_compaction: *experimental_no_snapshot_compaction,
+            experimental_no_snapshot_compaction: options.experimental_no_snapshot_compaction,
-            s3_snapshot_options: indexer_config.s3_snapshot_options.clone(),
         }
     }
 }

crates/index-scheduler/src/scheduler/process_batch.rs

@@ -1,27 +1,22 @@
 use std::collections::{BTreeSet, HashMap, HashSet};
-use std::fs::{remove_file, File};
-use std::io::{ErrorKind, Seek, SeekFrom};
 use std::panic::{catch_unwind, AssertUnwindSafe};
 use std::sync::atomic::Ordering;
 
-use byte_unit::Byte;
 use meilisearch_types::batches::{BatchEnqueuedAt, BatchId};
 use meilisearch_types::heed::{RoTxn, RwTxn};
-use meilisearch_types::milli::heed::CompactionOption;
 use meilisearch_types::milli::progress::{Progress, VariableNameStep};
 use meilisearch_types::milli::{self, ChannelCongestion};
 use meilisearch_types::tasks::{Details, IndexSwap, Kind, KindWithContent, Status, Task};
 use meilisearch_types::versioning::{VERSION_MAJOR, VERSION_MINOR, VERSION_PATCH};
 use milli::update::Settings as MilliSettings;
 use roaring::RoaringBitmap;
-use tempfile::{PersistError, TempPath};
 use time::OffsetDateTime;
 
 use super::create_batch::Batch;
 use crate::processing::{
     AtomicBatchStep, AtomicTaskStep, CreateIndexProgress, DeleteIndexProgress, FinalizingIndexStep,
-    IndexCompaction, InnerSwappingTwoIndexes, SwappingTheIndexes, TaskCancelationProgress,
+    InnerSwappingTwoIndexes, SwappingTheIndexes, TaskCancelationProgress, TaskDeletionProgress,
-    TaskDeletionProgress, UpdateIndexProgress,
+    UpdateIndexProgress,
 };
 use crate::utils::{
     self, remove_n_tasks_datetime_earlier_than, remove_task_datetime, swap_index_uid_in_task,
@@ -29,9 +24,6 @@ use crate::utils::{
 };
 use crate::{Error, IndexScheduler, Result, TaskId};
 
-/// The name of the copy of the data.mdb file used during compaction.
-const DATA_MDB_COPY_NAME: &str = "data.mdb.cpy";
-
 #[derive(Debug, Default)]
 pub struct ProcessBatchInfo {
     /// The write channel congestion. None when unavailable: settings update.
@@ -143,6 +135,9 @@ impl IndexScheduler {
             Batch::Dump(task) => self
                 .process_dump_creation(progress, task)
                 .map(|tasks| (tasks, ProcessBatchInfo::default())),
+            Batch::NetworkTopologyChanges { tasks } => self
+                .process_network_changes(progress, tasks)
+                .map(|tasks| (tasks, ProcessBatchInfo::default())),
             Batch::IndexOperation { op, must_create_index } => {
                 let index_uid = op.index_uid().to_string();
                 let index = if must_create_index {
@@ -426,47 +421,6 @@ impl IndexScheduler {
                 task.status = Status::Succeeded;
                 Ok((vec![task], ProcessBatchInfo::default()))
             }
-            Batch::IndexCompaction { index_uid: _, mut task } => {
-                let KindWithContent::IndexCompaction { index_uid } = &task.kind else {
-                    unreachable!()
-                };
-
-                let rtxn = self.env.read_txn()?;
-                let ret = catch_unwind(AssertUnwindSafe(|| {
-                    self.apply_compaction(&rtxn, &progress, index_uid)
-                }));
-
-                let (pre_size, post_size) = match ret {
-                    Ok(Ok(stats)) => stats,
-                    Ok(Err(Error::AbortedTask)) => return Err(Error::AbortedTask),
-                    Ok(Err(e)) => return Err(e),
-                    Err(e) => {
-                        let msg = match e.downcast_ref::<&'static str>() {
-                            Some(s) => *s,
-                            None => match e.downcast_ref::<String>() {
-                                Some(s) => &s[..],
-                                None => "Box<dyn Any>",
-                            },
-                        };
-                        return Err(Error::Export(Box::new(Error::ProcessBatchPanicked(
-                            msg.to_string(),
-                        ))));
-                    }
-                };
-
-                task.status = Status::Succeeded;
-                if let Some(Details::IndexCompaction {
-                    index_uid: _,
-                    pre_compaction_size,
-                    post_compaction_size,
-                }) = task.details.as_mut()
-                {
-                    *pre_compaction_size = Some(Byte::from_u64(pre_size));
-                    *post_compaction_size = Some(Byte::from_u64(post_size));
-                }
-
-                Ok((vec![task], ProcessBatchInfo::default()))
-            }
             Batch::Export { mut task } => {
                 let KindWithContent::Export { url, api_key, payload_size, indexes } = &task.kind
                 else {
@@ -542,92 +496,6 @@ impl IndexScheduler {
         }
     }
 
-    fn apply_compaction(
-        &self,
-        rtxn: &RoTxn,
-        progress: &Progress,
-        index_uid: &str,
-    ) -> Result<(u64, u64)> {
-        // 1. Verify that the index exists
-        if !self.index_mapper.index_exists(rtxn, index_uid)? {
-            return Err(Error::IndexNotFound(index_uid.to_owned()));
-        }
-
-        // 2. We retrieve the index and create a temporary file in the index directory
-        progress.update_progress(IndexCompaction::RetrieveTheIndex);
-        let index = 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.to_string(), index.clone())));
-
-        progress.update_progress(IndexCompaction::CreateTemporaryFile);
-        let src_path = index.path().join("data.mdb");
-        let pre_size = std::fs::metadata(&src_path)?.len();
-
-        let dst_path = TempPath::from_path(index.path().join(DATA_MDB_COPY_NAME));
-        let file = File::create(&dst_path)?;
-        let mut file = tempfile::NamedTempFile::from_parts(file, dst_path);
-
-        // 3. We copy the index data to the temporary file
-        progress.update_progress(IndexCompaction::CopyAndCompactTheIndex);
-        index
-            .copy_to_file(file.as_file_mut(), CompactionOption::Enabled)
-            .map_err(|error| Error::Milli { error, index_uid: Some(index_uid.to_string()) })?;
-        // ...and reset the file position as specified in the documentation
-        file.seek(SeekFrom::Start(0))?;
-
-        // 4. We replace the index data file with the temporary file
-        progress.update_progress(IndexCompaction::PersistTheCompactedIndex);
-        match file.persist(src_path) {
-            Ok(file) => file.sync_all()?,
-            // TODO see if we have a _resource busy_ error and probably handle this by:
-            //      1. closing the index, 2. replacing and 3. reopening it
-            Err(PersistError { error, file: _ }) => return Err(Error::IoError(error)),
-        };
-
-        // 5. Prepare to close the index
-        progress.update_progress(IndexCompaction::CloseTheIndex);
-
-        // unmark that the index is the processing one so we don't keep a handle to it, preventing its closing
-        self.index_mapper.set_currently_updating_index(None);
-
-        self.index_mapper.close_index(rtxn, index_uid)?;
-        drop(index);
-
-        progress.update_progress(IndexCompaction::ReopenTheIndex);
-        // 6. Reopen the index
-        // The index will use the compacted data file when being reopened
-        let index = self.index_mapper.index(rtxn, index_uid)?;
-
-        // if the update processed successfully, we're going to store the new
-        // stats of the index. Since the tasks have already been processed and
-        // this is a non-critical operation. If it fails, we should not fail
-        // the entire batch.
-        let res = || -> Result<_> {
-            let mut wtxn = self.env.write_txn()?;
-            let index_rtxn = index.read_txn()?;
-            let stats = crate::index_mapper::IndexStats::new(&index, &index_rtxn)
-                .map_err(|e| Error::from_milli(e, Some(index_uid.to_string())))?;
-            self.index_mapper.store_stats_of(&mut wtxn, index_uid, &stats)?;
-            wtxn.commit()?;
-            Ok(stats.database_size)
-        }();
-
-        let post_size = match res {
-            Ok(post_size) => post_size,
-            Err(e) => {
-                tracing::error!(
-                    error = &e as &dyn std::error::Error,
-                    "Could not write the stats of the index"
-                );
-                0
-            }
-        };
-
-        Ok((pre_size, post_size))
-    }
-
     /// Swap the index `lhs` with the index `rhs`.
     fn apply_index_swap(
         &self,
@@ -915,10 +783,9 @@ impl IndexScheduler {
 
         let enqueued_tasks = &self.queue.tasks.get_status(rtxn, Status::Enqueued)?;
 
-        // 0. Check if any upgrade or compaction tasks were matched.
+        // 0. Check if any upgrade task was matched.
         //    If so, we cancel all the failed or enqueued upgrade tasks.
         let upgrade_tasks = &self.queue.tasks.get_kind(rtxn, Kind::UpgradeDatabase)?;
-        let compaction_tasks = &self.queue.tasks.get_kind(rtxn, Kind::IndexCompaction)?;
         let is_canceling_upgrade = !matched_tasks.is_disjoint(upgrade_tasks);
         if is_canceling_upgrade {
             let failed_tasks = self.queue.tasks.get_status(rtxn, Status::Failed)?;
@@ -983,33 +850,7 @@ impl IndexScheduler {
             }
         }
 
-        // 3. If we are cancelling a compaction task, remove the tempfiles after incomplete compactions
+        // 3. We now have a list of tasks to cancel, cancel them
-        for compaction_task in &tasks_to_cancel & compaction_tasks {
-            progress.update_progress(TaskCancelationProgress::CleaningCompactionLeftover);
-            let task = self.queue.tasks.get_task(rtxn, compaction_task)?.unwrap();
-            let Some(Details::IndexCompaction {
-                index_uid,
-                pre_compaction_size: _,
-                post_compaction_size: _,
-            }) = task.details
-            else {
-                unreachable!("wrong details for compaction task {compaction_task}")
-            };
-
-            let index_path = match self.index_mapper.index_mapping.get(rtxn, &index_uid)? {
-                Some(index_uuid) => self.index_mapper.index_path(index_uuid),
-                None => continue,
-            };
-
-            if let Err(e) = remove_file(index_path.join(DATA_MDB_COPY_NAME)) {
-                match e.kind() {
-                    ErrorKind::NotFound => (),
-                    _ => return Err(Error::IoError(e)),
-                }
-            }
-        }
-
-        // 4. We now have a list of tasks to cancel, cancel them
         let (task_progress, progress_obj) = AtomicTaskStep::new(tasks_to_cancel.len() as u32);
         progress.update_progress(progress_obj);
 

crates/index-scheduler/src/scheduler/process_export.rs

@@ -16,6 +16,7 @@ use meilisearch_types::milli::vector::parsed_vectors::{ExplicitVectors, VectorOr
 use meilisearch_types::milli::{self, obkv_to_json, Filter, InternalError};
 use meilisearch_types::settings::{self, SecretPolicy};
 use meilisearch_types::tasks::{DetailsExportIndexSettings, ExportIndexSettings};
+use roaring::RoaringBitmap;
 use serde::Deserialize;
 use ureq::{json, Response};
 
@@ -50,6 +51,7 @@ impl IndexScheduler {
         let agent = ureq::AgentBuilder::new().timeout(Duration::from_secs(5)).build();
         let must_stop_processing = self.scheduler.must_stop_processing.clone();
         for (i, (_pattern, uid, export_settings)) in indexes.iter().enumerate() {
+            let err = |err| Error::from_milli(err, Some(uid.to_string()));
             if must_stop_processing.get() {
                 return Err(Error::AbortedTask);
             }
@@ -61,104 +63,31 @@ impl IndexScheduler {
             ));
 
             let ExportIndexSettings { filter, override_settings } = export_settings;
+
             let index = self.index(uid)?;
             let index_rtxn = index.read_txn()?;
-            let bearer = api_key.map(|api_key| format!("Bearer {api_key}"));
+            let filter = filter.as_ref().map(Filter::from_json).transpose().map_err(err)?.flatten();
-
+            let filter_universe =
-            // First, check if the index already exists
+                filter.map(|f| f.evaluate(&index_rtxn, &index)).transpose().map_err(err)?;
-            let url = format!("{base_url}/indexes/{uid}");
+            let whole_universe =
-            let response = retry(&must_stop_processing, || {
+                index.documents_ids(&index_rtxn).map_err(milli::Error::from).map_err(err)?;
-                let mut request = agent.get(&url);
-                if let Some(bearer) = &bearer {
-                    request = request.set("Authorization", bearer);
-                }
-
-                request.send_bytes(Default::default()).map_err(into_backoff_error)
-            });
-            let index_exists = match response {
-                Ok(response) => response.status() == 200,
-                Err(Error::FromRemoteWhenExporting { code, .. }) if code == "index_not_found" => {
-                    false
-                }
-                Err(e) => return Err(e),
-            };
-
-            let primary_key = index
-                .primary_key(&index_rtxn)
-                .map_err(|e| Error::from_milli(e.into(), Some(uid.to_string())))?;
-
-            // Create the index
-            if !index_exists {
-                let url = format!("{base_url}/indexes");
-                retry(&must_stop_processing, || {
-                    let mut request = agent.post(&url);
-                    if let Some(bearer) = &bearer {
-                        request = request.set("Authorization", bearer);
-                    }
-                    let index_param = json!({ "uid": uid, "primaryKey": primary_key });
-                    request.send_json(&index_param).map_err(into_backoff_error)
-                })?;
-            }
-
-            // Patch the index primary key
-            if index_exists && *override_settings {
-                let url = format!("{base_url}/indexes/{uid}");
-                retry(&must_stop_processing, || {
-                    let mut request = agent.patch(&url);
-                    if let Some(bearer) = &bearer {
-                        request = request.set("Authorization", bearer);
-                    }
-                    let index_param = json!({ "primaryKey": primary_key });
-                    request.send_json(&index_param).map_err(into_backoff_error)
-                })?;
-            }
-
-            // Send the index settings
-            if !index_exists || *override_settings {
-                let mut settings =
-                    settings::settings(&index, &index_rtxn, SecretPolicy::RevealSecrets)
-                        .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?;
-                // Remove the experimental chat setting if not enabled
-                if self.features().check_chat_completions("exporting chat settings").is_err() {
-                    settings.chat = Setting::NotSet;
-                }
-                // Retry logic for sending settings
-                let url = format!("{base_url}/indexes/{uid}/settings");
-                retry(&must_stop_processing, || {
-                    let mut request = agent.patch(&url);
-                    if let Some(bearer) = bearer.as_ref() {
-                        request = request.set("Authorization", bearer);
-                    }
-                    request.send_json(settings.clone()).map_err(into_backoff_error)
-                })?;
-            }
-
-            let filter = filter
-                .as_ref()
-                .map(Filter::from_json)
-                .transpose()
-                .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?
-                .flatten();
-
-            let filter_universe = filter
-                .map(|f| f.evaluate(&index_rtxn, &index))
-                .transpose()
-                .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?;
-            let whole_universe = index
-                .documents_ids(&index_rtxn)
-                .map_err(|e| Error::from_milli(e.into(), Some(uid.to_string())))?;
             let universe = filter_universe.unwrap_or(whole_universe);
-
+            let target = TargetInstance { base_url, api_key };
-            let fields_ids_map = index.fields_ids_map(&index_rtxn)?;
+            let ctx = ExportContext {
-            let all_fields: Vec<_> = fields_ids_map.iter().map(|(id, _)| id).collect();
+                index: &index,
-
+                index_rtxn: &index_rtxn,
-            // We don't need to keep this one alive as we will
+                universe: &universe,
-            // spawn many threads to process the documents
+                progress: &progress,
-            drop(index_rtxn);
+                agent: &agent,
-
+                must_stop_processing: &must_stop_processing,
-            let total_documents = universe.len() as u32;
+            };
-            let (step, progress_step) = AtomicDocumentStep::new(total_documents);
+            let options = ExportOptions {
-            progress.update_progress(progress_step);
+                index_uid: uid,
+                payload_size,
+                override_settings: *override_settings,
+                extra_headers: &Default::default(),
+            };
+            let total_documents = self.export_one_index(target, options, ctx)?;
 
             output.insert(
                 IndexUidPattern::new_unchecked(uid.clone()),
@@ -167,36 +96,116 @@ impl IndexScheduler {
                     matched_documents: Some(total_documents as u64),
                 },
             );
+        }
 
-            let limit = payload_size.map(|ps| ps.as_u64() as usize).unwrap_or(20 * 1024 * 1024); // defaults to 20 MiB
+        Ok(output)
-            let documents_url = format!("{base_url}/indexes/{uid}/documents");
+    }
 
+    pub(super) fn export_one_index(
+        &self,
+        target: TargetInstance<'_>,
+        options: ExportOptions<'_>,
+        ctx: ExportContext<'_>,
+    ) -> Result<u64, Error> {
+        let err = |err| Error::from_milli(err, Some(options.index_uid.to_string()));
+
+        let bearer = target.api_key.map(|api_key| format!("Bearer {api_key}"));
+        let url = format!(
+            "{base_url}/indexes/{index_uid}",
+            base_url = target.base_url,
+            index_uid = options.index_uid
+        );
+        let response = retry(ctx.must_stop_processing, || {
+            let mut request = ctx.agent.get(&url);
+            if let Some(bearer) = &bearer {
+                request = request.set("Authorization", bearer);
+            }
+
+            request.send_bytes(Default::default()).map_err(into_backoff_error)
+        });
+        let index_exists = match response {
+            Ok(response) => response.status() == 200,
+            Err(Error::FromRemoteWhenExporting { code, .. }) if code == "index_not_found" => false,
+            Err(e) => return Err(e),
+        };
+        let primary_key =
+            ctx.index.primary_key(&ctx.index_rtxn).map_err(milli::Error::from).map_err(err)?;
+        if !index_exists {
+            let url = format!("{base_url}/indexes", base_url = target.base_url);
+            retry(ctx.must_stop_processing, || {
+                let mut request = ctx.agent.post(&url);
+                if let Some(bearer) = &bearer {
+                    request = request.set("Authorization", bearer);
+                }
+                let index_param = json!({ "uid": options.index_uid, "primaryKey": primary_key });
+                request.send_json(&index_param).map_err(into_backoff_error)
+            })?;
+        }
+        if index_exists && options.override_settings {
+            retry(ctx.must_stop_processing, || {
+                let mut request = ctx.agent.patch(&url);
+                if let Some(bearer) = &bearer {
+                    request = request.set("Authorization", bearer);
+                }
+                let index_param = json!({ "primaryKey": primary_key });
+                request.send_json(&index_param).map_err(into_backoff_error)
+            })?;
+        }
+        if !index_exists || options.override_settings {
+            let mut settings =
+                settings::settings(&ctx.index, &ctx.index_rtxn, SecretPolicy::RevealSecrets)
+                    .map_err(err)?;
+            // Remove the experimental chat setting if not enabled
+            if self.features().check_chat_completions("exporting chat settings").is_err() {
+                settings.chat = Setting::NotSet;
+            }
+            // Retry logic for sending settings
+            let url = format!(
+                "{base_url}/indexes/{index_uid}/settings",
+                base_url = target.base_url,
+                index_uid = options.index_uid
+            );
+            retry(ctx.must_stop_processing, || {
+                let mut request = ctx.agent.patch(&url);
+                if let Some(bearer) = bearer.as_ref() {
+                    request = request.set("Authorization", bearer);
+                }
+                request.send_json(settings.clone()).map_err(into_backoff_error)
+            })?;
+        }
+
+        let fields_ids_map = ctx.index.fields_ids_map(&ctx.index_rtxn)?;
+        let all_fields: Vec<_> = fields_ids_map.iter().map(|(id, _)| id).collect();
+        let total_documents = ctx.universe.len() as u32;
+        let (step, progress_step) = AtomicDocumentStep::new(total_documents);
+        ctx.progress.update_progress(progress_step);
+
+        let limit = options.payload_size.map(|ps| ps.as_u64() as usize).unwrap_or(20 * 1024 * 1024);
+        let documents_url = format!(
+            "{base_url}/indexes/{index_uid}/documents",
+            base_url = target.base_url,
+            index_uid = options.index_uid
+        );
         let results = request_threads()
-                .broadcast(|ctx| {
+            .broadcast(|broadcast| {
-                    let index_rtxn = index
+                let index_rtxn = ctx.index.read_txn().map_err(milli::Error::from).map_err(err)?;
-                        .read_txn()
-                        .map_err(|e| Error::from_milli(e.into(), Some(uid.to_string())))?;
 
                 let mut buffer = Vec::new();
                 let mut tmp_buffer = Vec::new();
                 let mut compressed_buffer = Vec::new();
-                    for (i, docid) in universe.iter().enumerate() {
+                for (i, docid) in ctx.universe.iter().enumerate() {
-                        if i % ctx.num_threads() != ctx.index() {
+                    if i % broadcast.num_threads() != broadcast.index() {
                         continue;
                     }
 
-                        let document = index
+                    let document = ctx.index.document(&index_rtxn, docid).map_err(err)?;
-                            .document(&index_rtxn, docid)
-                            .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?;
 
-                        let mut document = obkv_to_json(&all_fields, &fields_ids_map, document)
+                    let mut document =
-                            .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?;
+                        obkv_to_json(&all_fields, &fields_ids_map, document).map_err(err)?;
 
                     // TODO definitely factorize this code
                     'inject_vectors: {
-                            let embeddings = index
+                        let embeddings = ctx.index.embeddings(&index_rtxn, docid).map_err(err)?;
-                                .embeddings(&index_rtxn, docid)
-                                .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?;
 
                         if embeddings.is_empty() {
                             break 'inject_vectors;
@@ -207,15 +216,12 @@ impl IndexScheduler {
                             .or_insert(serde_json::Value::Object(Default::default()));
 
                         let serde_json::Value::Object(vectors) = vectors else {
-                                return Err(Error::from_milli(
+                            return Err(err(milli::Error::UserError(
-                                    milli::Error::UserError(
                                 milli::UserError::InvalidVectorsMapType {
                                     document_id: {
-                                                if let Ok(Some(Ok(index))) = index
+                                        if let Ok(Some(Ok(index))) = ctx
-                                                    .external_id_of(
+                                            .index
-                                                        &index_rtxn,
+                                            .external_id_of(&index_rtxn, std::iter::once(docid))
-                                                        std::iter::once(docid),
-                                                    )
                                             .map(|it| it.into_iter().next())
                                         {
                                             index
@@ -225,9 +231,7 @@ impl IndexScheduler {
                                     },
                                     value: vectors.clone(),
                                 },
-                                    ),
+                            )));
-                                    Some(uid.to_string()),
-                                ));
                         };
 
                         for (
@@ -236,9 +240,9 @@ impl IndexScheduler {
                         ) in embeddings
                         {
                             let embeddings = ExplicitVectors {
-                                    embeddings: Some(
+                                embeddings: Some(VectorOrArrayOfVectors::from_array_of_vectors(
-                                        VectorOrArrayOfVectors::from_array_of_vectors(embeddings),
+                                    embeddings,
-                                    ),
+                                )),
                                 regenerate: regenerate &&
                                 // Meilisearch does not handle well dumps with fragments, because as the fragments
                                 // are marked as user-provided,
@@ -246,17 +250,16 @@ impl IndexScheduler {
                                 // To prevent this, we mark embeddings has non regenerate in this case.
                                 !has_fragments,
                             };
-                                vectors.insert(
+                            vectors
-                                    embedder_name,
+                                .insert(embedder_name, serde_json::to_value(embeddings).unwrap());
-                                    serde_json::to_value(embeddings).unwrap(),
-                                );
                         }
                     }
 
                     tmp_buffer.clear();
                     serde_json::to_writer(&mut tmp_buffer, &document)
                         .map_err(milli::InternalError::from)
-                            .map_err(|e| Error::from_milli(e.into(), Some(uid.to_string())))?;
+                        .map_err(milli::Error::from)
+                        .map_err(err)?;
 
                     // Make sure we put at least one document in the buffer even
                     // though we might go above the buffer limit before sending
@@ -264,15 +267,11 @@ impl IndexScheduler {
                         // We compress the documents before sending them
                         let mut encoder =
                             GzEncoder::new(&mut compressed_buffer, Compression::default());
-                            encoder
+                        encoder.write_all(&buffer).map_err(milli::Error::from).map_err(err)?;
-                                .write_all(&buffer)
+                        encoder.finish().map_err(milli::Error::from).map_err(err)?;
-                                .map_err(|e| Error::from_milli(e.into(), Some(uid.clone())))?;
-                            encoder
-                                .finish()
-                                .map_err(|e| Error::from_milli(e.into(), Some(uid.clone())))?;
 
-                            retry(&must_stop_processing, || {
+                        retry(ctx.must_stop_processing, || {
-                                let mut request = agent.post(&documents_url);
+                            let mut request = ctx.agent.post(&documents_url);
                             request = request.set("Content-Type", "application/x-ndjson");
                             request = request.set("Content-Encoding", "gzip");
                             if let Some(bearer) = &bearer {
@@ -290,8 +289,8 @@ impl IndexScheduler {
                     }
                 }
 
-                    retry(&must_stop_processing, || {
+                retry(ctx.must_stop_processing, || {
-                        let mut request = agent.post(&documents_url);
+                    let mut request = ctx.agent.post(&documents_url);
                     request = request.set("Content-Type", "application/x-ndjson");
                     if let Some(bearer) = &bearer {
                         request = request.set("Authorization", bearer);
@@ -301,20 +300,12 @@ impl IndexScheduler {
 
                 Ok(())
             })
-                .map_err(|e| {
+            .map_err(|e| err(milli::Error::InternalError(InternalError::PanicInThreadPool(e))))?;
-                    Error::from_milli(
-                        milli::Error::InternalError(InternalError::PanicInThreadPool(e)),
-                        Some(uid.to_string()),
-                    )
-                })?;
         for result in results {
             result?;
         }
-
         step.store(total_documents, atomic::Ordering::Relaxed);
-        }
+        Ok(total_documents as u64)
-
-        Ok(output)
     }
 }
 
@@ -374,4 +365,27 @@ fn ureq_error_into_error(error: ureq::Error) -> Error {
     }
 }
 
+// export_one_index arguments
+pub(super) struct TargetInstance<'a> {
+    pub(super) base_url: &'a str,
+    pub(super) api_key: Option<&'a str>,
+}
+
+pub(super) struct ExportOptions<'a> {
+    pub(super) index_uid: &'a str,
+    pub(super) payload_size: Option<&'a Byte>,
+    pub(super) override_settings: bool,
+    pub(super) extra_headers: &'a hashbrown::HashMap<String, String>,
+}
+
+pub(super) struct ExportContext<'a> {
+    pub(super) index: &'a meilisearch_types::milli::Index,
+    pub(super) index_rtxn: &'a milli::heed::RoTxn<'a>,
+    pub(super) universe: &'a RoaringBitmap,
+    pub(super) progress: &'a Progress,
+    pub(super) agent: &'a ureq::Agent,
+    pub(super) must_stop_processing: &'a MustStopProcessing,
+}
+
+// progress related
 enum ExportIndex {}

crates/index-scheduler/src/scheduler/process_index_operation.rs

@@ -97,7 +97,7 @@ impl IndexScheduler {
                     .embedding_configs()
                     .embedding_configs(index_wtxn)
                     .map_err(|e| Error::from_milli(e.into(), Some(index_uid.clone())))?;
-                let embedders = self.embedders(index_uid.clone(), embedders)?;
+                let embedders = self.embedders(&index_uid, embedders)?;
                 for operation in operations {
                     match operation {
                         DocumentOperation::Replace(_content_uuid) => {
@@ -284,7 +284,7 @@ impl IndexScheduler {
                         .embedding_configs()
                         .embedding_configs(index_wtxn)
                         .map_err(|err| Error::from_milli(err.into(), Some(index_uid.clone())))?;
-                    let embedders = self.embedders(index_uid.clone(), embedders)?;
+                    let embedders = self.embedders(&index_uid, embedders)?;
 
                     progress.update_progress(DocumentEditionProgress::Indexing);
                     congestion = Some(
@@ -434,7 +434,7 @@ impl IndexScheduler {
                         .embedding_configs()
                         .embedding_configs(index_wtxn)
                         .map_err(|err| Error::from_milli(err.into(), Some(index_uid.clone())))?;
-                    let embedders = self.embedders(index_uid.clone(), embedders)?;
+                    let embedders = self.embedders(&index_uid, embedders)?;
 
                     progress.update_progress(DocumentDeletionProgress::Indexing);
                     congestion = Some(

crates/index-scheduler/src/scheduler/process_snapshot_creation.rs

@@ -12,8 +12,6 @@ use crate::processing::{AtomicUpdateFileStep, SnapshotCreationProgress};
 use crate::queue::TaskQueue;
 use crate::{Error, IndexScheduler, Result};
 
-const UPDATE_FILES_DIR_NAME: &str = "update_files";
-
 /// # Safety
 ///
 /// See [`EnvOpenOptions::open`].
@@ -80,32 +78,10 @@ impl IndexScheduler {
     pub(super) fn process_snapshot(
         &self,
         progress: Progress,
-        tasks: Vec<Task>,
+        mut tasks: Vec<Task>,
     ) -> Result<Vec<Task>> {
         progress.update_progress(SnapshotCreationProgress::StartTheSnapshotCreation);
 
-        match self.scheduler.s3_snapshot_options.clone() {
-            Some(options) => {
-                #[cfg(not(unix))]
-                {
-                    let _ = options;
-                    panic!("Non-unix platform does not support S3 snapshotting");
-                }
-                #[cfg(unix)]
-                self.runtime
-                    .as_ref()
-                    .expect("Runtime not initialized")
-                    .block_on(self.process_snapshot_to_s3(progress, options, tasks))
-            }
-            None => self.process_snapshots_to_disk(progress, tasks),
-        }
-    }
-
-    fn process_snapshots_to_disk(
-        &self,
-        progress: Progress,
-        mut tasks: Vec<Task>,
-    ) -> Result<Vec<Task>, Error> {
         fs::create_dir_all(&self.scheduler.snapshots_path)?;
         let temp_snapshot_dir = tempfile::tempdir()?;
 
@@ -152,7 +128,7 @@ impl IndexScheduler {
         let rtxn = self.env.read_txn()?;
 
         // 2.4 Create the update files directory
-        let update_files_dir = temp_snapshot_dir.path().join(UPDATE_FILES_DIR_NAME);
+        let update_files_dir = temp_snapshot_dir.path().join("update_files");
         fs::create_dir_all(&update_files_dir)?;
 
         // 2.5 Only copy the update files of the enqueued tasks
@@ -164,7 +140,7 @@ impl IndexScheduler {
             let task =
                 self.queue.tasks.get_task(&rtxn, task_id)?.ok_or(Error::CorruptedTaskQueue)?;
             if let Some(content_uuid) = task.content_uuid() {
-                let src = self.queue.file_store.update_path(content_uuid);
+                let src = self.queue.file_store.get_update_path(content_uuid);
                 let dst = update_files_dir.join(content_uuid.to_string());
                 fs::copy(src, dst)?;
             }
@@ -230,407 +206,4 @@ impl IndexScheduler {
 
         Ok(tasks)
     }
-
-    #[cfg(unix)]
-    pub(super) async fn process_snapshot_to_s3(
-        &self,
-        progress: Progress,
-        opts: meilisearch_types::milli::update::S3SnapshotOptions,
-        mut tasks: Vec<Task>,
-    ) -> Result<Vec<Task>> {
-        use meilisearch_types::milli::update::S3SnapshotOptions;
-
-        let S3SnapshotOptions {
-            s3_bucket_url,
-            s3_bucket_region,
-            s3_bucket_name,
-            s3_snapshot_prefix,
-            s3_access_key,
-            s3_secret_key,
-            s3_max_in_flight_parts,
-            s3_compression_level: level,
-            s3_signature_duration,
-            s3_multipart_part_size,
-        } = opts;
-
-        let must_stop_processing = self.scheduler.must_stop_processing.clone();
-        let retry_backoff = backoff::ExponentialBackoff::default();
-        let db_name = {
-            let mut base_path = self.env.path().to_owned();
-            base_path.pop();
-            base_path.file_name().and_then(OsStr::to_str).unwrap_or("data.ms").to_string()
-        };
-
-        let (reader, writer) = std::io::pipe()?;
-        let uploader_task = tokio::spawn(multipart_stream_to_s3(
-            s3_bucket_url,
-            s3_bucket_region,
-            s3_bucket_name,
-            s3_snapshot_prefix,
-            s3_access_key,
-            s3_secret_key,
-            s3_max_in_flight_parts,
-            s3_signature_duration,
-            s3_multipart_part_size,
-            must_stop_processing,
-            retry_backoff,
-            db_name,
-            reader,
-        ));
-
-        let index_scheduler = IndexScheduler::private_clone(self);
-        let builder_task = tokio::task::spawn_blocking(move || {
-            stream_tarball_into_pipe(progress, level, writer, index_scheduler)
-        });
-
-        let (uploader_result, builder_result) = tokio::join!(uploader_task, builder_task);
-
-        // Check uploader result first to early return on task abortion.
-        // safety: JoinHandle can return an error if the task was aborted, cancelled, or panicked.
-        uploader_result.unwrap()?;
-        builder_result.unwrap()?;
-
-        for task in &mut tasks {
-            task.status = Status::Succeeded;
-        }
-
-        Ok(tasks)
-    }
-}
-
-/// Streams a tarball of the database content into a pipe.
-#[cfg(unix)]
-fn stream_tarball_into_pipe(
-    progress: Progress,
-    level: u32,
-    writer: std::io::PipeWriter,
-    index_scheduler: IndexScheduler,
-) -> std::result::Result<(), Error> {
-    use std::io::Write as _;
-    use std::path::Path;
-
-    let writer = flate2::write::GzEncoder::new(writer, flate2::Compression::new(level));
-    let mut tarball = tar::Builder::new(writer);
-
-    // 1. Snapshot the version file
-    tarball
-        .append_path_with_name(&index_scheduler.scheduler.version_file_path, VERSION_FILE_NAME)?;
-
-    // 2. Snapshot the index scheduler LMDB env
-    progress.update_progress(SnapshotCreationProgress::SnapshotTheIndexScheduler);
-    let tasks_env_file = index_scheduler.env.try_clone_inner_file()?;
-    let path = Path::new("tasks").join("data.mdb");
-    append_file_to_tarball(&mut tarball, path, tasks_env_file)?;
-
-    // 2.3 Create a read transaction on the index-scheduler
-    let rtxn = index_scheduler.env.read_txn()?;
-
-    // 2.4 Create the update files directory
-    //     And only copy the update files of the enqueued tasks
-    progress.update_progress(SnapshotCreationProgress::SnapshotTheUpdateFiles);
-    let enqueued = index_scheduler.queue.tasks.get_status(&rtxn, Status::Enqueued)?;
-    let (atomic, update_file_progress) = AtomicUpdateFileStep::new(enqueued.len() as u32);
-    progress.update_progress(update_file_progress);
-
-    // We create the update_files directory so that it
-    // always exists even if there are no update files
-    let update_files_dir = Path::new(UPDATE_FILES_DIR_NAME);
-    let src_update_files_dir = {
-        let mut path = index_scheduler.env.path().to_path_buf();
-        path.pop();
-        path.join(UPDATE_FILES_DIR_NAME)
-    };
-    tarball.append_dir(update_files_dir, src_update_files_dir)?;
-
-    for task_id in enqueued {
-        let task = index_scheduler
-            .queue
-            .tasks
-            .get_task(&rtxn, task_id)?
-            .ok_or(Error::CorruptedTaskQueue)?;
-        if let Some(content_uuid) = task.content_uuid() {
-            use std::fs::File;
-
-            let src = index_scheduler.queue.file_store.update_path(content_uuid);
-            let mut update_file = File::open(src)?;
-            let path = update_files_dir.join(content_uuid.to_string());
-            tarball.append_file(path, &mut update_file)?;
-        }
-        atomic.fetch_add(1, Ordering::Relaxed);
-    }
-
-    // 3. Snapshot every indexes
-    progress.update_progress(SnapshotCreationProgress::SnapshotTheIndexes);
-    let index_mapping = index_scheduler.index_mapper.index_mapping;
-    let nb_indexes = index_mapping.len(&rtxn)? as u32;
-    let indexes_dir = Path::new("indexes");
-    let indexes_references: Vec<_> = index_scheduler
-        .index_mapper
-        .index_mapping
-        .iter(&rtxn)?
-        .map(|res| res.map_err(Error::from).map(|(name, uuid)| (name.to_string(), uuid)))
-        .collect::<Result<_, Error>>()?;
-
-    // It's prettier to use a for loop instead of the IndexMapper::try_for_each_index
-    // method, especially when we need to access the UUID, local path and index number.
-    for (i, (name, uuid)) in indexes_references.into_iter().enumerate() {
-        progress.update_progress(VariableNameStep::<SnapshotCreationProgress>::new(
-            &name, i as u32, nb_indexes,
-        ));
-        let path = indexes_dir.join(uuid.to_string()).join("data.mdb");
-        let index = index_scheduler.index_mapper.index(&rtxn, &name)?;
-        let index_file = index.try_clone_inner_file()?;
-        tracing::trace!("Appending index file for {name} in {}", path.display());
-        append_file_to_tarball(&mut tarball, path, index_file)?;
-    }
-
-    drop(rtxn);
-
-    // 4. Snapshot the auth LMDB env
-    progress.update_progress(SnapshotCreationProgress::SnapshotTheApiKeys);
-    let auth_env_file = index_scheduler.scheduler.auth_env.try_clone_inner_file()?;
-    let path = Path::new("auth").join("data.mdb");
-    append_file_to_tarball(&mut tarball, path, auth_env_file)?;
-
-    let mut gzencoder = tarball.into_inner()?;
-    gzencoder.flush()?;
-    gzencoder.try_finish()?;
-    let mut writer = gzencoder.finish()?;
-    writer.flush()?;
-
-    Result::<_, Error>::Ok(())
-}
-
-#[cfg(unix)]
-fn append_file_to_tarball<W, P>(
-    tarball: &mut tar::Builder<W>,
-    path: P,
-    mut auth_env_file: fs::File,
-) -> Result<(), Error>
-where
-    W: std::io::Write,
-    P: AsRef<std::path::Path>,
-{
-    use std::io::{Seek as _, SeekFrom};
-
-    // Note: A previous snapshot operation may have left the cursor
-    //       at the end of the file so we need to seek to the start.
-    auth_env_file.seek(SeekFrom::Start(0))?;
-    tarball.append_file(path, &mut auth_env_file)?;
-    Ok(())
-}
-
-/// Streams the content read from the given reader to S3.
-#[cfg(unix)]
-#[allow(clippy::too_many_arguments)]
-async fn multipart_stream_to_s3(
-    s3_bucket_url: String,
-    s3_bucket_region: String,
-    s3_bucket_name: String,
-    s3_snapshot_prefix: String,
-    s3_access_key: String,
-    s3_secret_key: String,
-    s3_max_in_flight_parts: std::num::NonZero<usize>,
-    s3_signature_duration: std::time::Duration,
-    s3_multipart_part_size: u64,
-    must_stop_processing: super::MustStopProcessing,
-    retry_backoff: backoff::exponential::ExponentialBackoff<backoff::SystemClock>,
-    db_name: String,
-    reader: std::io::PipeReader,
-) -> Result<(), Error> {
-    use std::collections::VecDeque;
-    use std::io;
-    use std::os::fd::OwnedFd;
-    use std::path::PathBuf;
-
-    use bytes::{Bytes, BytesMut};
-    use reqwest::{Client, Response};
-    use rusty_s3::actions::CreateMultipartUpload;
-    use rusty_s3::{Bucket, BucketError, Credentials, S3Action as _, UrlStyle};
-    use tokio::task::JoinHandle;
-
-    let reader = OwnedFd::from(reader);
-    let reader = tokio::net::unix::pipe::Receiver::from_owned_fd(reader)?;
-    let s3_snapshot_prefix = PathBuf::from(s3_snapshot_prefix);
-    let url =
-        s3_bucket_url.parse().map_err(BucketError::ParseError).map_err(Error::S3BucketError)?;
-    let bucket = Bucket::new(url, UrlStyle::Path, s3_bucket_name, s3_bucket_region)
-        .map_err(Error::S3BucketError)?;
-    let credential = Credentials::new(s3_access_key, s3_secret_key);
-
-    // Note for the future (rust 1.91+): use with_added_extension, it's prettier
-    let object_path = s3_snapshot_prefix.join(format!("{db_name}.snapshot"));
-    // Note: It doesn't work on Windows and if a port to this platform is needed,
-    //       use the slash-path crate or similar to get the correct path separator.
-    let object = object_path.display().to_string();
-
-    let action = bucket.create_multipart_upload(Some(&credential), &object);
-    let url = action.sign(s3_signature_duration);
-
-    let client = Client::new();
-    let resp = client.post(url).send().await.map_err(Error::S3HttpError)?;
-    let status = resp.status();
-
-    let body = match resp.error_for_status_ref() {
-        Ok(_) => resp.text().await.map_err(Error::S3HttpError)?,
-        Err(_) => {
-            return Err(Error::S3Error { status, body: resp.text().await.unwrap_or_default() })
-        }
-    };
-
-    let multipart =
-        CreateMultipartUpload::parse_response(&body).map_err(|e| Error::S3XmlError(Box::new(e)))?;
-    tracing::debug!("Starting the upload of the snapshot to {object}");
-
-    // We use this bumpalo for etags strings.
-    let bump = bumpalo::Bump::new();
-    let mut etags = Vec::<&str>::new();
-    let mut in_flight = VecDeque::<(JoinHandle<reqwest::Result<Response>>, Bytes)>::with_capacity(
-        s3_max_in_flight_parts.get(),
-    );
-
-    // Part numbers start at 1 and cannot be larger than 10k
-    for part_number in 1u16.. {
-        if must_stop_processing.get() {
-            return Err(Error::AbortedTask);
-        }
-
-        let part_upload =
-            bucket.upload_part(Some(&credential), &object, part_number, multipart.upload_id());
-        let url = part_upload.sign(s3_signature_duration);
-
-        // Wait for a buffer to be ready if there are in-flight parts that landed
-        let mut buffer = if in_flight.len() >= s3_max_in_flight_parts.get() {
-            let (handle, buffer) = in_flight.pop_front().expect("At least one in flight request");
-            let resp = join_and_map_error(handle).await?;
-            extract_and_append_etag(&bump, &mut etags, resp.headers())?;
-
-            let mut buffer = match buffer.try_into_mut() {
-                Ok(buffer) => buffer,
-                Err(_) => unreachable!("All bytes references were consumed in the task"),
-            };
-            buffer.clear();
-            buffer
-        } else {
-            BytesMut::with_capacity(s3_multipart_part_size as usize)
-        };
-
-        // If we successfully read enough bytes,
-        // we can continue and send the buffer/part
-        while buffer.len() < (s3_multipart_part_size as usize / 2) {
-            // Wait for the pipe to be readable
-
-            reader.readable().await?;
-
-            match reader.try_read_buf(&mut buffer) {
-                Ok(0) => break,
-                // We read some bytes but maybe not enough
-                Ok(_) => continue,
-                // The readiness event is a false positive.
-                Err(ref e) if e.kind() == io::ErrorKind::WouldBlock => continue,
-                Err(e) => return Err(e.into()),
-            }
-        }
-
-        if buffer.is_empty() {
-            // Break the loop if the buffer is
-            // empty after we tried to read bytes
-            break;
-        }
-
-        let body = buffer.freeze();
-        tracing::trace!("Sending part {part_number}");
-        let task = tokio::spawn({
-            let client = client.clone();
-            let body = body.clone();
-            backoff::future::retry(retry_backoff.clone(), move || {
-                let client = client.clone();
-                let url = url.clone();
-                let body = body.clone();
-                async move {
-                    match client.put(url).body(body).send().await {
-                        Ok(resp) if resp.status().is_client_error() => {
-                            resp.error_for_status().map_err(backoff::Error::Permanent)
-                        }
-                        Ok(resp) => Ok(resp),
-                        Err(e) => Err(backoff::Error::transient(e)),
-                    }
-                }
-            })
-        });
-        in_flight.push_back((task, body));
-    }
-
-    for (handle, _buffer) in in_flight {
-        let resp = join_and_map_error(handle).await?;
-        extract_and_append_etag(&bump, &mut etags, resp.headers())?;
-    }
-
-    tracing::debug!("Finalizing the multipart upload");
-
-    let action = bucket.complete_multipart_upload(
-        Some(&credential),
-        &object,
-        multipart.upload_id(),
-        etags.iter().map(AsRef::as_ref),
-    );
-    let url = action.sign(s3_signature_duration);
-    let body = action.body();
-    let resp = backoff::future::retry(retry_backoff, move || {
-        let client = client.clone();
-        let url = url.clone();
-        let body = body.clone();
-        async move {
-            match client.post(url).body(body).send().await {
-                Ok(resp) if resp.status().is_client_error() => {
-                    Err(backoff::Error::Permanent(Error::S3Error {
-                        status: resp.status(),
-                        body: resp.text().await.unwrap_or_default(),
-                    }))
-                }
-                Ok(resp) => Ok(resp),
-                Err(e) => Err(backoff::Error::transient(Error::S3HttpError(e))),
-            }
-        }
-    })
-    .await?;
-
-    let status = resp.status();
-    let body = resp.text().await.map_err(|e| Error::S3Error { status, body: e.to_string() })?;
-    if status.is_success() {
-        Ok(())
-    } else {
-        Err(Error::S3Error { status, body })
-    }
-}
-
-#[cfg(unix)]
-async fn join_and_map_error(
-    join_handle: tokio::task::JoinHandle<Result<reqwest::Response, reqwest::Error>>,
-) -> Result<reqwest::Response> {
-    // safety: Panic happens if the task (JoinHandle) was aborted, cancelled, or panicked
-    let request = join_handle.await.unwrap();
-    let resp = request.map_err(Error::S3HttpError)?;
-    match resp.error_for_status_ref() {
-        Ok(_) => Ok(resp),
-        Err(_) => Err(Error::S3Error {
-            status: resp.status(),
-            body: resp.text().await.unwrap_or_default(),
-        }),
-    }
-}
-
-#[cfg(unix)]
-fn extract_and_append_etag<'b>(
-    bump: &'b bumpalo::Bump,
-    etags: &mut Vec<&'b str>,
-    headers: &reqwest::header::HeaderMap,
-) -> Result<()> {
-    use reqwest::header::ETAG;
-
-    let etag = headers.get(ETAG).ok_or_else(|| Error::S3XmlError("Missing ETag header".into()))?;
-    let etag = etag.to_str().map_err(|e| Error::S3XmlError(Box::new(e)))?;
-    etags.push(bump.alloc_str(etag));
-
-    Ok(())
 }

crates/index-scheduler/src/scheduler/snapshots/test_failure.rs/upgrade_failure/after_processing_everything.snap

@@ -6,7 +6,7 @@ source: crates/index-scheduler/src/scheduler/test_failure.rs
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, batch_uid: 0, status: succeeded, details: { from: (1, 12, 0), to: [current version] }, kind: UpgradeDatabase { from: (1, 12, 0) }}
+0 {uid: 0, batch_uid: 0, status: succeeded, details: { from: (1, 12, 0), to: (1, 21, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
 1 {uid: 1, batch_uid: 1, status: succeeded, details: { primary_key: Some("mouse"), old_new_uid: None, new_index_uid: None }, kind: IndexCreation { index_uid: "catto", primary_key: Some("mouse") }}
 2 {uid: 2, batch_uid: 2, status: succeeded, details: { primary_key: Some("bone"), old_new_uid: None, new_index_uid: None }, kind: IndexCreation { index_uid: "doggo", primary_key: Some("bone") }}
 3 {uid: 3, batch_uid: 3, status: failed, error: ResponseError { code: 200, message: "Index `doggo` already exists.", error_code: "index_already_exists", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#index_already_exists" }, details: { primary_key: Some("bone"), old_new_uid: None, new_index_uid: None }, kind: IndexCreation { index_uid: "doggo", primary_key: Some("bone") }}
@@ -57,7 +57,7 @@ girafo: { number_of_documents: 0, field_distribution: {} }
 [timestamp] [4,]
 ----------------------------------------------------------------------
 ### All Batches:
-0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"[current version]"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"upgradeDatabase":1},"indexUids":{}}, stop reason: "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type.", }
+0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.21.0"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"upgradeDatabase":1},"indexUids":{}}, stop reason: "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type.", }
 1 {uid: 1, details: {"primaryKey":"mouse"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"catto":1}}, stop reason: "created batch containing only task with id 1 of type `indexCreation` that cannot be batched with any other task.", }
 2 {uid: 2, details: {"primaryKey":"bone"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"doggo":1}}, stop reason: "created batch containing only task with id 2 of type `indexCreation` that cannot be batched with any other task.", }
 3 {uid: 3, details: {"primaryKey":"bone"}, stats: {"totalNbTasks":1,"status":{"failed":1},"types":{"indexCreation":1},"indexUids":{"doggo":1}}, stop reason: "created batch containing only task with id 3 of type `indexCreation` that cannot be batched with any other task.", }

crates/index-scheduler/src/scheduler/snapshots/test_failure.rs/upgrade_failure/register_automatic_upgrade_task.snap

@@ -6,7 +6,7 @@ source: crates/index-scheduler/src/scheduler/test_failure.rs
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, status: enqueued, details: { from: (1, 12, 0), to: [current version] }, kind: UpgradeDatabase { from: (1, 12, 0) }}
+0 {uid: 0, status: enqueued, details: { from: (1, 12, 0), to: (1, 21, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued [0,]

crates/index-scheduler/src/scheduler/snapshots/test_failure.rs/upgrade_failure/registered_a_task_while_the_upgrade_task_is_enqueued.snap

@@ -6,7 +6,7 @@ source: crates/index-scheduler/src/scheduler/test_failure.rs
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, status: enqueued, details: { from: (1, 12, 0), to: [current version] }, kind: UpgradeDatabase { from: (1, 12, 0) }}
+0 {uid: 0, status: enqueued, details: { from: (1, 12, 0), to: (1, 21, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
 1 {uid: 1, status: enqueued, details: { primary_key: Some("mouse"), old_new_uid: None, new_index_uid: None }, kind: IndexCreation { index_uid: "catto", primary_key: Some("mouse") }}
 ----------------------------------------------------------------------
 ### Status:

crates/index-scheduler/src/scheduler/snapshots/test_failure.rs/upgrade_failure/upgrade_task_failed.snap

@@ -6,7 +6,7 @@ source: crates/index-scheduler/src/scheduler/test_failure.rs
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, batch_uid: 0, status: failed, error: ResponseError { code: 200, message: "Planned failure for tests.", error_code: "internal", error_type: "internal", error_link: "https://docs.meilisearch.com/errors#internal" }, details: { from: (1, 12, 0), to: [current version] }, kind: UpgradeDatabase { from: (1, 12, 0) }}
+0 {uid: 0, batch_uid: 0, status: failed, error: ResponseError { code: 200, message: "Planned failure for tests.", error_code: "internal", error_type: "internal", error_link: "https://docs.meilisearch.com/errors#internal" }, details: { from: (1, 12, 0), to: (1, 21, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
 1 {uid: 1, status: enqueued, details: { primary_key: Some("mouse"), old_new_uid: None, new_index_uid: None }, kind: IndexCreation { index_uid: "catto", primary_key: Some("mouse") }}
 ----------------------------------------------------------------------
 ### Status:
@@ -37,7 +37,7 @@ catto [1,]
 [timestamp] [0,]
 ----------------------------------------------------------------------
 ### All Batches:
-0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"[current version]"}, stats: {"totalNbTasks":1,"status":{"failed":1},"types":{"upgradeDatabase":1},"indexUids":{}}, stop reason: "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type.", }
+0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.21.0"}, stats: {"totalNbTasks":1,"status":{"failed":1},"types":{"upgradeDatabase":1},"indexUids":{}}, stop reason: "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type.", }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]

crates/index-scheduler/src/scheduler/snapshots/test_failure.rs/upgrade_failure/upgrade_task_failed_again.snap

@@ -6,7 +6,7 @@ source: crates/index-scheduler/src/scheduler/test_failure.rs
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, batch_uid: 0, status: failed, error: ResponseError { code: 200, message: "Planned failure for tests.", error_code: "internal", error_type: "internal", error_link: "https://docs.meilisearch.com/errors#internal" }, details: { from: (1, 12, 0), to: [current version] }, kind: UpgradeDatabase { from: (1, 12, 0) }}
+0 {uid: 0, batch_uid: 0, status: failed, error: ResponseError { code: 200, message: "Planned failure for tests.", error_code: "internal", error_type: "internal", error_link: "https://docs.meilisearch.com/errors#internal" }, details: { from: (1, 12, 0), to: (1, 21, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
 1 {uid: 1, status: enqueued, details: { primary_key: Some("mouse"), old_new_uid: None, new_index_uid: None }, kind: IndexCreation { index_uid: "catto", primary_key: Some("mouse") }}
 2 {uid: 2, status: enqueued, details: { primary_key: Some("bone"), old_new_uid: None, new_index_uid: None }, kind: IndexCreation { index_uid: "doggo", primary_key: Some("bone") }}
 ----------------------------------------------------------------------
@@ -40,7 +40,7 @@ doggo [2,]
 [timestamp] [0,]
 ----------------------------------------------------------------------
 ### All Batches:
-0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"[current version]"}, stats: {"totalNbTasks":1,"status":{"failed":1},"types":{"upgradeDatabase":1},"indexUids":{}}, stop reason: "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type.", }
+0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.21.0"}, stats: {"totalNbTasks":1,"status":{"failed":1},"types":{"upgradeDatabase":1},"indexUids":{}}, stop reason: "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type.", }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]

crates/index-scheduler/src/scheduler/snapshots/test_failure.rs/upgrade_failure/upgrade_task_succeeded.snap

@@ -6,7 +6,7 @@ source: crates/index-scheduler/src/scheduler/test_failure.rs
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, batch_uid: 0, status: succeeded, details: { from: (1, 12, 0), to: [current version] }, kind: UpgradeDatabase { from: (1, 12, 0) }}
+0 {uid: 0, batch_uid: 0, status: succeeded, details: { from: (1, 12, 0), to: (1, 21, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
 1 {uid: 1, status: enqueued, details: { primary_key: Some("mouse"), old_new_uid: None, new_index_uid: None }, kind: IndexCreation { index_uid: "catto", primary_key: Some("mouse") }}
 2 {uid: 2, status: enqueued, details: { primary_key: Some("bone"), old_new_uid: None, new_index_uid: None }, kind: IndexCreation { index_uid: "doggo", primary_key: Some("bone") }}
 3 {uid: 3, status: enqueued, details: { primary_key: Some("bone"), old_new_uid: None, new_index_uid: None }, kind: IndexCreation { index_uid: "doggo", primary_key: Some("bone") }}
@@ -43,7 +43,7 @@ doggo [2,3,]
 [timestamp] [0,]
 ----------------------------------------------------------------------
 ### All Batches:
-0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"[current version]"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"upgradeDatabase":1},"indexUids":{}}, stop reason: "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type.", }
+0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.21.0"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"upgradeDatabase":1},"indexUids":{}}, stop reason: "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type.", }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]

crates/index-scheduler/src/scheduler/test.rs

@@ -742,11 +742,11 @@ fn basic_get_stats() {
         "documentEdition": 0,
         "dumpCreation": 0,
         "export": 0,
-        "indexCompaction": 0,
         "indexCreation": 3,
         "indexDeletion": 0,
         "indexSwap": 0,
         "indexUpdate": 0,
+        "networkTopologyChange": 0,
         "settingsUpdate": 0,
         "snapshotCreation": 0,
         "taskCancelation": 0,
@@ -757,7 +757,7 @@ fn basic_get_stats() {
     "###);
 
     handle.advance_till([Start, BatchCreated]);
-    snapshot!(json_string!(index_scheduler.get_stats().unwrap()), @r###"
+    snapshot!(json_string!(index_scheduler.get_stats().unwrap()), @r#"
     {
       "indexes": {
         "catto": 1,
@@ -777,7 +777,6 @@ fn basic_get_stats() {
         "documentEdition": 0,
         "dumpCreation": 0,
         "export": 0,
-        "indexCompaction": 0,
         "indexCreation": 3,
         "indexDeletion": 0,
         "indexSwap": 0,
@@ -789,7 +788,7 @@ fn basic_get_stats() {
         "upgradeDatabase": 0
       }
     }
-    "###);
+    "#);
 
     handle.advance_till([
         InsideProcessBatch,
@@ -799,7 +798,7 @@ fn basic_get_stats() {
         Start,
         BatchCreated,
     ]);
-    snapshot!(json_string!(index_scheduler.get_stats().unwrap()), @r###"
+    snapshot!(json_string!(index_scheduler.get_stats().unwrap()), @r#"
     {
       "indexes": {
         "catto": 1,
@@ -819,7 +818,6 @@ fn basic_get_stats() {
         "documentEdition": 0,
         "dumpCreation": 0,
         "export": 0,
-        "indexCompaction": 0,
         "indexCreation": 3,
         "indexDeletion": 0,
         "indexSwap": 0,
@@ -831,7 +829,7 @@ fn basic_get_stats() {
         "upgradeDatabase": 0
       }
     }
-    "###);
+    "#);
 
     // now we make one more batch, the started_at field of the new tasks will be past `second_start_time`
     handle.advance_till([
@@ -842,7 +840,7 @@ fn basic_get_stats() {
         Start,
         BatchCreated,
     ]);
-    snapshot!(json_string!(index_scheduler.get_stats().unwrap()), @r###"
+    snapshot!(json_string!(index_scheduler.get_stats().unwrap()), @r#"
     {
       "indexes": {
         "catto": 1,
@@ -862,7 +860,6 @@ fn basic_get_stats() {
         "documentEdition": 0,
         "dumpCreation": 0,
         "export": 0,
-        "indexCompaction": 0,
         "indexCreation": 3,
         "indexDeletion": 0,
         "indexSwap": 0,
@@ -874,7 +871,7 @@ fn basic_get_stats() {
         "upgradeDatabase": 0
       }
     }
-    "###);
+    "#);
 }
 
 #[test]

crates/index-scheduler/src/scheduler/test_embedders.rs

@@ -121,7 +121,7 @@ fn import_vectors() {
         insta::assert_json_snapshot!(simple_hf_config.embedder_options);
         let simple_hf_name = name.clone();
 
-        let configs = index_scheduler.embedders("doggos".to_string(), configs).unwrap();
+        let configs = index_scheduler.embedders("doggos", configs).unwrap();
         let hf_runtime = configs.get(&simple_hf_name).unwrap();
         let hf_embedder = &hf_runtime.embedder;
         let beagle_embed = hf_embedder

crates/index-scheduler/src/test_utils.rs

@@ -126,7 +126,7 @@ impl IndexScheduler {
         std::fs::create_dir_all(&options.auth_path).unwrap();
         let auth_env = open_auth_store_env(&options.auth_path).unwrap();
         let index_scheduler =
-            Self::new_test(options, auth_env, version, None, sender, planned_failures).unwrap();
+            Self::new(options, auth_env, version, None, sender, planned_failures).unwrap();
 
         // To be 100% consistent between all test we're going to start the scheduler right now
         // and ensure it's in the expected starting state.

crates/index-scheduler/src/upgrade/mod.rs

@@ -1,7 +1,7 @@
 use anyhow::bail;
 use meilisearch_types::heed::{Env, RwTxn, WithoutTls};
 use meilisearch_types::tasks::{Details, KindWithContent, Status, Task};
-use meilisearch_types::versioning;
+use meilisearch_types::versioning::{VERSION_MAJOR, VERSION_MINOR, VERSION_PATCH};
 use time::OffsetDateTime;
 use tracing::info;
 
@@ -9,82 +9,76 @@ use crate::queue::TaskQueue;
 use crate::versioning::Versioning;
 
 trait UpgradeIndexScheduler {
-    fn upgrade(&self, env: &Env<WithoutTls>, wtxn: &mut RwTxn) -> anyhow::Result<()>;
+    fn upgrade(
-    /// Whether the migration should be applied, depending on the initial version of the index scheduler before
+        &self,
-    /// any migration was applied
+        env: &Env<WithoutTls>,
-    fn must_upgrade(&self, initial_version: (u32, u32, u32)) -> bool;
+        wtxn: &mut RwTxn,
-    /// A progress-centric description of the migration
+        original: (u32, u32, u32),
-    fn description(&self) -> &'static str;
+    ) -> anyhow::Result<()>;
+    fn target_version(&self) -> (u32, u32, u32);
 }
 
-/// Upgrade the index scheduler to the binary version.
-///
-/// # Warning
-///
-/// The current implementation uses a single wtxn to the index scheduler for the whole duration of the upgrade.
-/// If migrations start taking take a long time, it might prevent tasks from being registered.
-/// If this issue manifests, then it can be mitigated by adding a `fn target_version` to `UpgradeIndexScheduler`,
-/// to be able to write intermediate versions and drop the wtxn between applying migrations.
 pub fn upgrade_index_scheduler(
     env: &Env<WithoutTls>,
     versioning: &Versioning,
-    initial_version: (u32, u32, u32),
+    from: (u32, u32, u32),
+    to: (u32, u32, u32),
 ) -> anyhow::Result<()> {
-    let target_major: u32 = versioning::VERSION_MAJOR;
+    let current_major = to.0;
-    let target_minor: u32 = versioning::VERSION_MINOR;
+    let current_minor = to.1;
-    let target_patch: u32 = versioning::VERSION_PATCH;
+    let current_patch = to.2;
-    let target_version = (target_major, target_minor, target_patch);
-
-    if initial_version == target_version {
-        return Ok(());
-    }
 
     let upgrade_functions: &[&dyn UpgradeIndexScheduler] = &[
-        // List all upgrade functions to apply in order here.
+        // This is the last upgrade function, it will be called when the index is up to date.
+        // any other upgrade function should be added before this one.
+        &ToCurrentNoOp {},
     ];
 
-    let (initial_major, initial_minor, initial_patch) = initial_version;
+    let start = match from {
-
+        (1, 12, _) => 0,
-    if initial_version > target_version {
+        (1, 13, _) => 0,
+        (1, 14, _) => 0,
+        (1, 15, _) => 0,
+        (1, 16, _) => 0,
+        (1, 17, _) => 0,
+        (1, 18, _) => 0,
+        (1, 19, _) => 0,
+        (1, 20, _) => 0,
+        (1, 21, _) => 0,
+        (major, minor, patch) => {
+            if major > current_major
+                || (major == current_major && minor > current_minor)
+                || (major == current_major && minor == current_minor && patch > current_patch)
+            {
                 bail!(
-                "Database version {initial_major}.{initial_minor}.{initial_patch} is higher than the Meilisearch version {target_major}.{target_minor}.{target_patch}. Downgrade is not supported",
+                "Database version {major}.{minor}.{patch} is higher than the Meilisearch version {current_major}.{current_minor}.{current_patch}. Downgrade is not supported",
                 );
-    }
+            } else if major < 1 || (major == current_major && minor < 12) {
-
-    if initial_version < (1, 12, 0) {
                 bail!(
-                "Database version {initial_major}.{initial_minor}.{initial_patch} is too old for the experimental dumpless upgrade feature. Please generate a dump using the v{initial_major}.{initial_minor}.{initial_patch} and import it in the v{target_major}.{target_minor}.{target_patch}",
+                "Database version {major}.{minor}.{patch} is too old for the experimental dumpless upgrade feature. Please generate a dump using the v{major}.{minor}.{patch} and import it in the v{current_major}.{current_minor}.{current_patch}",
             );
+            } else {
+                bail!("Unknown database version: v{major}.{minor}.{patch}");
             }
+        }
+    };
 
     info!("Upgrading the task queue");
-    let mut wtxn = env.write_txn()?;
+    let mut local_from = from;
-    let migration_count = upgrade_functions.len();
+    for upgrade in upgrade_functions[start..].iter() {
-    for (migration_index, upgrade) in upgrade_functions.iter().enumerate() {
+        let target = upgrade.target_version();
-        if upgrade.must_upgrade(initial_version) {
         info!(
-                "[{migration_index}/{migration_count}]Applying migration: {}",
+            "Upgrading from v{}.{}.{} to v{}.{}.{}",
-                upgrade.description()
+            local_from.0, local_from.1, local_from.2, target.0, target.1, target.2
         );
-
+        let mut wtxn = env.write_txn()?;
-            upgrade.upgrade(env, &mut wtxn)?;
+        upgrade.upgrade(env, &mut wtxn, local_from)?;
-
+        versioning.set_version(&mut wtxn, target)?;
-            info!(
+        wtxn.commit()?;
-                "[{}/{migration_count}]Migration applied: {}",
+        local_from = target;
-                migration_index + 1,
-                upgrade.description()
-            )
-        } else {
-            info!(
-                "[{migration_index}/{migration_count}]Skipping unnecessary migration: {}",
-                upgrade.description()
-            )
-        }
     }
 
-    versioning.set_version(&mut wtxn, target_version)?;
+    let mut wtxn = env.write_txn()?;
-    info!("Task queue upgraded, spawning the upgrade database task");
-
     let queue = TaskQueue::new(env, &mut wtxn)?;
     let uid = queue.next_task_id(&wtxn)?;
     queue.register(
@@ -97,14 +91,31 @@ pub fn upgrade_index_scheduler(
             finished_at: None,
             error: None,
             canceled_by: None,
-            details: Some(Details::UpgradeDatabase { from: initial_version, to: target_version }),
+            details: Some(Details::UpgradeDatabase { from, to }),
             status: Status::Enqueued,
-            kind: KindWithContent::UpgradeDatabase { from: initial_version },
+            kind: KindWithContent::UpgradeDatabase { from },
             network: None,
-            custom_metadata: None,
         },
     )?;
     wtxn.commit()?;
 
     Ok(())
 }
+
+#[allow(non_camel_case_types)]
+struct ToCurrentNoOp {}
+
+impl UpgradeIndexScheduler for ToCurrentNoOp {
+    fn upgrade(
+        &self,
+        _env: &Env<WithoutTls>,
+        _wtxn: &mut RwTxn,
+        _original: (u32, u32, u32),
+    ) -> anyhow::Result<()> {
+        Ok(())
+    }
+
+    fn target_version(&self) -> (u32, u32, u32) {
+        (VERSION_MAJOR, VERSION_MINOR, VERSION_PATCH)
+    }
+}

crates/index-scheduler/src/utils.rs

@@ -256,15 +256,14 @@ pub fn swap_index_uid_in_task(task: &mut Task, swap: (&str, &str)) {
     use KindWithContent as K;
     let mut index_uids = vec![];
     match &mut task.kind {
-        K::DocumentAdditionOrUpdate { index_uid, .. }
+        K::DocumentAdditionOrUpdate { index_uid, .. } => index_uids.push(index_uid),
-        | K::DocumentEdition { index_uid, .. }
+        K::DocumentEdition { index_uid, .. } => index_uids.push(index_uid),
-        | K::DocumentDeletion { index_uid, .. }
+        K::DocumentDeletion { index_uid, .. } => index_uids.push(index_uid),
-        | K::DocumentDeletionByFilter { index_uid, .. }
+        K::DocumentDeletionByFilter { index_uid, .. } => index_uids.push(index_uid),
-        | K::DocumentClear { index_uid }
+        K::DocumentClear { index_uid } => index_uids.push(index_uid),
-        | K::SettingsUpdate { index_uid, .. }
+        K::SettingsUpdate { index_uid, .. } => index_uids.push(index_uid),
-        | K::IndexDeletion { index_uid }
+        K::IndexDeletion { index_uid } => index_uids.push(index_uid),
-        | K::IndexCreation { index_uid, .. }
+        K::IndexCreation { index_uid, .. } => index_uids.push(index_uid),
-        | K::IndexCompaction { index_uid, .. } => index_uids.push(index_uid),
         K::IndexUpdate { index_uid, new_index_uid, .. } => {
             index_uids.push(index_uid);
             if let Some(new_uid) = new_index_uid {
@@ -286,6 +285,7 @@ pub fn swap_index_uid_in_task(task: &mut Task, swap: (&str, &str)) {
         | K::DumpCreation { .. }
         | K::Export { .. }
         | K::UpgradeDatabase { .. }
+        | K::NetworkTopologyChange { .. }
         | K::SnapshotCreation => (),
     };
     if let Some(Details::IndexSwap { swaps }) = &mut task.details {
@@ -379,7 +379,6 @@ impl crate::IndexScheduler {
                 status,
                 kind,
                 network: _,
-                custom_metadata: _,
             } = task;
             assert_eq!(uid, task.uid);
             if task.status != Status::Enqueued {
@@ -620,12 +619,8 @@ impl crate::IndexScheduler {
                     Details::UpgradeDatabase { from: _, to: _ } => {
                         assert_eq!(kind.as_kind(), Kind::UpgradeDatabase);
                     }
-                    Details::IndexCompaction {
+                    Details::NetworkTopologyChange { .. } => {
-                        index_uid: _,
+                        assert_eq!(kind.as_kind(), Kind::NetworkTopologyChange);
-                        pre_compaction_size: _,
-                        post_compaction_size: _,
-                    } => {
-                        assert_eq!(kind.as_kind(), Kind::IndexCompaction);
                     }
                 }
             }

crates/index-scheduler/src/versioning.rs

@@ -64,7 +64,14 @@ impl Versioning {
         };
         wtxn.commit()?;
 
-        upgrade_index_scheduler(env, &this, from)?;
+        let bin_major: u32 = versioning::VERSION_MAJOR;
+        let bin_minor: u32 = versioning::VERSION_MINOR;
+        let bin_patch: u32 = versioning::VERSION_PATCH;
+        let to = (bin_major, bin_minor, bin_patch);
+
+        if from != to {
+            upgrade_index_scheduler(env, &this, from, to)?;
+        }
 
         // Once we reach this point it means the upgrade process, if there was one is entirely finished
         // we can safely say we reached the latest version of the index scheduler

crates/json-depth-checker/Cargo.toml

@@ -15,7 +15,7 @@ license.workspace = true
 serde_json = "1.0"
 
 [dev-dependencies]
-criterion = "0.7.0"
+criterion = "0.6.0"
 
 [[bench]]
 name = "depth"

crates/meili-snap/Cargo.toml

@@ -13,7 +13,7 @@ license.workspace = true
 [dependencies]
 # fixed version due to format breakages in v1.40
 insta = { version = "=1.39.0", features = ["json", "redactions"] }
-md5 = "0.8.0"
+md5 = "0.7.0"
 once_cell = "1.21"
-regex-lite = "0.1.8"
+regex-lite = "0.1.6"
-uuid = { version = "1.18.1", features = ["v4"] }
+uuid = { version = "1.17.0", features = ["v4"] }

crates/meilisearch-auth/Cargo.toml

@@ -12,15 +12,15 @@ license.workspace = true
 
 [dependencies]
 base64 = "0.22.1"
-enum-iterator = "2.3.0"
+enum-iterator = "2.1.0"
 hmac = "0.12.1"
 maplit = "1.0.2"
 meilisearch-types = { path = "../meilisearch-types" }
 rand = "0.8.5"
 roaring = { version = "0.10.12", features = ["serde"] }
-serde = { version = "1.0.228", features = ["derive"] }
+serde = { version = "1.0.219", features = ["derive"] }
-serde_json = { version = "1.0.145", features = ["preserve_order"] }
+serde_json = { version = "1.0.140", features = ["preserve_order"] }
 sha2 = "0.10.9"
-thiserror = "2.0.17"
+thiserror = "2.0.12"
-time = { version = "0.3.44", features = ["serde-well-known", "formatting", "parsing", "macros"] }
+time = { version = "0.3.41", features = ["serde-well-known", "formatting", "parsing", "macros"] }
-uuid = { version = "1.18.1", features = ["serde", "v4"] }
+uuid = { version = "1.17.0", features = ["serde", "v4"] }

crates/meilisearch-auth/src/store.rs

@@ -109,7 +109,6 @@ impl HeedAuthStore {
                             Action::IndexesGet,
                             Action::IndexesUpdate,
                             Action::IndexesSwap,
-                            Action::IndexesCompact,
                         ]
                         .iter(),
                     );

crates/meilisearch-types/Cargo.toml

@@ -11,38 +11,38 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-actix-web = { version = "4.12.0", default-features = false }
+actix-web = { version = "4.11.0", default-features = false }
-anyhow = "1.0.100"
+anyhow = "1.0.98"
-bumpalo = "3.19.0"
+bumpalo = "3.18.1"
 bumparaw-collections = "0.1.4"
 byte-unit = { version = "5.1.6", features = ["serde"] }
-convert_case = "0.9.0"
+convert_case = "0.8.0"
-csv = "1.4.0"
+csv = "1.3.1"
-deserr = { version = "0.6.4", features = ["actix-web"] }
+deserr = { version = "0.6.3", features = ["actix-web"] }
 either = { version = "1.15.0", features = ["serde"] }
-enum-iterator = "2.3.0"
+enum-iterator = "2.1.0"
 file-store = { path = "../file-store" }
-flate2 = "1.1.5"
+flate2 = "1.1.2"
 fst = "0.4.7"
-memmap2 = "0.9.9"
+memmap2 = "0.9.7"
 milli = { path = "../milli" }
 roaring = { version = "0.10.12", features = ["serde"] }
 rustc-hash = "2.1.1"
-serde = { version = "1.0.228", features = ["derive"] }
+serde = { version = "1.0.219", features = ["derive"] }
 serde-cs = "0.2.4"
-serde_json = { version = "1.0.145", features = ["preserve_order"] }
+serde_json = { version = "1.0.140", features = ["preserve_order"] }
 tar = "0.4.44"
-tempfile = "3.23.0"
+tempfile = "3.20.0"
-thiserror = "2.0.17"
+thiserror = "2.0.12"
-time = { version = "0.3.44", features = [
+time = { version = "0.3.41", features = [
     "serde-well-known",
     "formatting",
     "parsing",
     "macros",
 ] }
-tokio = "1.48"
+tokio = "1.45"
 utoipa = { version = "5.4.0", features = ["macros"] }
-uuid = { version = "1.18.1", features = ["serde", "v4"] }
+uuid = { version = "1.17.0", features = ["serde", "v4"] }
 
 [dev-dependencies]
 # fixed version due to format breakages in v1.40
@@ -56,9 +56,6 @@ all-tokenizations = ["milli/all-tokenizations"]
 # chinese specialized tokenization
 chinese = ["milli/chinese"]
 chinese-pinyin = ["milli/chinese-pinyin"]
-
-enterprise = ["milli/enterprise"]
-
 # hebrew specialized tokenization
 hebrew = ["milli/hebrew"]
 # japanese specialized tokenization

crates/meilisearch-types/src/community_edition.rs

@@ -1,16 +0,0 @@
-pub mod network {
-    use milli::update::new::indexer::current_edition::sharding::Shards;
-
-    use crate::network::Network;
-
-    impl Network {
-        pub fn shards(&self) -> Option<Shards> {
-            None
-        }
-
-        pub fn sharding(&self) -> bool {
-            // always false in CE
-            false
-        }
-    }
-}

crates/meilisearch-types/src/enterprise_edition/network.rs

@@ -3,27 +3,99 @@
 // Use of this source code is governed by the Business Source License 1.1,
 // as found in the LICENSE-EE file or at <https://mariadb.com/bsl11>
 
-use milli::update::new::indexer::enterprise_edition::sharding::Shards;
+use std::collections::BTreeMap;
 
-use crate::network::Network;
+use deserr::Deserr;
+use milli::update::new::indexer::enterprise_edition::sharding::{Shard, Shards};
+use milli::update::Setting;
+use serde::{Deserialize, Serialize};
+use utoipa::ToSchema;
 
-impl Network {
+use crate::deserr::DeserrJsonError;
+use crate::error::deserr_codes::{
+    InvalidNetworkRemotes, InvalidNetworkSearchApiKey, InvalidNetworkSelf, InvalidNetworkSharding,
+    InvalidNetworkUrl, InvalidNetworkWriteApiKey,
+};
+
+#[derive(Clone, Debug, Deserr, ToSchema, Serialize, Deserialize, PartialEq, Eq)]
+#[deserr(error = DeserrJsonError, rename_all = camelCase, deny_unknown_fields)]
+#[serde(rename_all = "camelCase")]
+#[schema(rename_all = "camelCase")]
+pub struct Network {
+    #[schema(value_type = Option<BTreeMap<String, Remote>>, example = json!("http://localhost:7700"))]
+    #[deserr(default, error = DeserrJsonError<InvalidNetworkRemotes>)]
+    #[serde(default)]
+    pub remotes: Setting<BTreeMap<String, Option<Remote>>>,
+    #[schema(value_type = Option<String>, example = json!("ms-00"), rename = "self")]
+    #[serde(default, rename = "self")]
+    #[deserr(default, rename = "self", error = DeserrJsonError<InvalidNetworkSelf>)]
+    pub local: Setting<String>,
+    #[schema(value_type = Option<bool>, example = json!(true))]
+    #[serde(default)]
+    #[deserr(default, error = DeserrJsonError<InvalidNetworkSharding>)]
+    pub sharding: Setting<bool>,
+}
+
+#[derive(Clone, Debug, Deserr, ToSchema, Serialize, Deserialize, PartialEq, Eq)]
+#[deserr(error = DeserrJsonError<InvalidNetworkRemotes>, rename_all = camelCase, deny_unknown_fields)]
+#[serde(rename_all = "camelCase")]
+#[schema(rename_all = "camelCase")]
+pub struct Remote {
+    #[schema(value_type = Option<String>, example = json!({
+        "ms-0": Remote { url: Setting::Set("http://localhost:7700".into()), search_api_key: Setting::Reset, write_api_key: Setting::Reset },
+        "ms-1": Remote { url: Setting::Set("http://localhost:7701".into()), search_api_key: Setting::Set("foo".into()), write_api_key: Setting::Set("bar".into()) },
+        "ms-2": Remote { url: Setting::Set("http://localhost:7702".into()), search_api_key: Setting::Set("bar".into()), write_api_key: Setting::Set("foo".into()) },
+    }))]
+    #[deserr(default, error = DeserrJsonError<InvalidNetworkUrl>)]
+    #[serde(default)]
+    pub url: Setting<String>,
+    #[schema(value_type = Option<String>, example = json!("XWnBI8QHUc-4IlqbKPLUDuhftNq19mQtjc6JvmivzJU"))]
+    #[deserr(default, error = DeserrJsonError<InvalidNetworkSearchApiKey>)]
+    #[serde(default)]
+    pub search_api_key: Setting<String>,
+    #[schema(value_type = Option<String>, example = json!("XWnBI8QHUc-4IlqbKPLUDuhftNq19mQtjc6JvmivzJU"))]
+    #[deserr(default, error = DeserrJsonError<InvalidNetworkWriteApiKey>)]
+    #[serde(default)]
+    pub write_api_key: Setting<String>,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq, Default)]
+#[serde(rename_all = "camelCase")]
+pub struct DbNetwork {
+    #[serde(default, rename = "self")]
+    pub local: Option<String>,
+    #[serde(default)]
+    pub remotes: BTreeMap<String, DbRemote>,
+    #[serde(default)]
+    pub sharding: bool,
+}
+
+impl DbNetwork {
     pub fn shards(&self) -> Option<Shards> {
         if self.sharding {
-            let this = self.local.as_deref().expect("Inconsistent `sharding` and `self`");
+            let this = self.local.as_deref();
-            let others = self
+
-                .remotes
+            Some(Shards(
+                self.remotes
                     .keys()
-                .filter(|name| name.as_str() != this)
+                    .map(|name| Shard {
-                .map(|name| name.to_owned())
+                        is_own: Some(name.as_str()) == this,
-                .collect();
+                        name: name.to_owned(),
-            Some(Shards { own: vec![this.to_owned()], others })
+                    })
+                    .collect(),
+            ))
         } else {
             None
         }
     }
-
+}
-    pub fn sharding(&self) -> bool {
+
-        self.sharding
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq)]
-    }
+#[serde(rename_all = "camelCase")]
+pub struct DbRemote {
+    pub url: String,
+    #[serde(default)]
+    pub search_api_key: Option<String>,
+    #[serde(default)]
+    pub write_api_key: Option<String>,
 }

crates/meilisearch-types/src/error.rs

@@ -254,12 +254,10 @@ InvalidSearchHybridQuery                       , InvalidRequest       , BAD_REQU
 InvalidIndexLimit                              , InvalidRequest       , BAD_REQUEST ;
 InvalidIndexOffset                             , InvalidRequest       , BAD_REQUEST ;
 InvalidIndexPrimaryKey                         , InvalidRequest       , BAD_REQUEST ;
-InvalidIndexCustomMetadata                     , InvalidRequest       , BAD_REQUEST ;
 InvalidIndexUid                                , InvalidRequest       , BAD_REQUEST ;
 InvalidMultiSearchFacets                       , InvalidRequest       , BAD_REQUEST ;
 InvalidMultiSearchFacetsByIndex                , InvalidRequest       , BAD_REQUEST ;
 InvalidMultiSearchFacetOrder                   , InvalidRequest       , BAD_REQUEST ;
-InvalidMultiSearchQueryPersonalization         , InvalidRequest       , BAD_REQUEST ;
 InvalidMultiSearchFederated                    , InvalidRequest       , BAD_REQUEST ;
 InvalidMultiSearchFederationOptions            , InvalidRequest       , BAD_REQUEST ;
 InvalidMultiSearchMaxValuesPerFacet            , InvalidRequest       , BAD_REQUEST ;
@@ -317,8 +315,6 @@ InvalidSearchShowRankingScoreDetails           , InvalidRequest       , BAD_REQU
 InvalidSimilarShowRankingScoreDetails          , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchSort                              , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchDistinct                          , InvalidRequest       , BAD_REQUEST ;
-InvalidSearchPersonalize                       , InvalidRequest       , BAD_REQUEST ;
-InvalidSearchPersonalizeUserContext            , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchMediaAndVector                    , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsDisplayedAttributes             , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsDistinctAttribute               , InvalidRequest       , BAD_REQUEST ;
@@ -394,9 +390,6 @@ TooManyVectors                                 , InvalidRequest       , BAD_REQU
 UnretrievableDocument                          , Internal             , BAD_REQUEST ;
 UnretrievableErrorCode                         , InvalidRequest       , BAD_REQUEST ;
 UnsupportedMediaType                           , InvalidRequest       , UNSUPPORTED_MEDIA_TYPE ;
-InvalidS3SnapshotRequest                       , Internal             , BAD_REQUEST ;
-InvalidS3SnapshotParameters                    , Internal             , BAD_REQUEST ;
-S3SnapshotServerError                          , Internal             , BAD_GATEWAY ;
 
 // Experimental features
 VectorEmbeddingError                           , InvalidRequest       , BAD_REQUEST ;
@@ -433,7 +426,6 @@ InvalidChatCompletionSearchQueryParamPrompt    , InvalidRequest       , BAD_REQU
 InvalidChatCompletionSearchFilterParamPrompt   , InvalidRequest       , BAD_REQUEST ;
 InvalidChatCompletionSearchIndexUidParamPrompt , InvalidRequest       , BAD_REQUEST ;
 InvalidChatCompletionPreQueryPrompt            , InvalidRequest       , BAD_REQUEST ;
-RequiresEnterpriseEdition                      , InvalidRequest       , UNAVAILABLE_FOR_LEGAL_REASONS ;
 // Webhooks
 InvalidWebhooks                                , InvalidRequest       , BAD_REQUEST ;
 InvalidWebhookUrl                              , InvalidRequest       , BAD_REQUEST ;
@@ -537,6 +529,8 @@ impl ErrorCode for milli::Error {
                     | UserError::DocumentEditionCompilationError(_) => {
                         Code::EditDocumentsByFunctionError
                     }
+                    UserError::NetworkShardingWithoutSelf => Code::InvalidNetworkSharding,
+                    UserError::NetworkMissingUrl(_) => Code::MissingNetworkUrl,
                     UserError::CelluliteError(err) => match err {
                         cellulite::Error::BuildCanceled
                         | cellulite::Error::VersionMismatchOnBuild(_)
@@ -687,18 +681,6 @@ impl fmt::Display for deserr_codes::InvalidNetworkSearchApiKey {
     }
 }
 
-impl fmt::Display for deserr_codes::InvalidSearchPersonalize {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        write!(f, "the value of `personalize` is invalid, expected a JSON object with `userContext` string.")
-    }
-}
-
-impl fmt::Display for deserr_codes::InvalidSearchPersonalizeUserContext {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        write!(f, "the value of `userContext` is invalid, expected a string.")
-    }
-}
-
 #[macro_export]
 macro_rules! internal_error {
     ($target:ty : $($other:path), *) => {

crates/meilisearch-types/src/keys.rs

@@ -380,9 +380,6 @@ pub enum Action {
     #[serde(rename = "webhooks.*")]
     #[deserr(rename = "webhooks.*")]
     WebhooksAll,
-    #[serde(rename = "indexes.compact")]
-    #[deserr(rename = "indexes.compact")]
-    IndexesCompact,
 }
 
 impl Action {
@@ -401,7 +398,6 @@ impl Action {
             INDEXES_UPDATE => Some(Self::IndexesUpdate),
             INDEXES_DELETE => Some(Self::IndexesDelete),
             INDEXES_SWAP => Some(Self::IndexesSwap),
-            INDEXES_COMPACT => Some(Self::IndexesCompact),
             TASKS_ALL => Some(Self::TasksAll),
             TASKS_CANCEL => Some(Self::TasksCancel),
             TASKS_DELETE => Some(Self::TasksDelete),
@@ -466,7 +462,6 @@ impl Action {
             IndexesUpdate => false,
             IndexesDelete => false,
             IndexesSwap => false,
-            IndexesCompact => false,
             TasksCancel => false,
             TasksDelete => false,
             TasksGet => true,
@@ -518,7 +513,6 @@ pub mod actions {
     pub const INDEXES_UPDATE: u8 = IndexesUpdate.repr();
     pub const INDEXES_DELETE: u8 = IndexesDelete.repr();
     pub const INDEXES_SWAP: u8 = IndexesSwap.repr();
-    pub const INDEXES_COMPACT: u8 = IndexesCompact.repr();
     pub const TASKS_ALL: u8 = TasksAll.repr();
     pub const TASKS_CANCEL: u8 = TasksCancel.repr();
     pub const TASKS_DELETE: u8 = TasksDelete.repr();
@@ -620,7 +614,6 @@ pub(crate) mod test {
         assert!(WebhooksDelete.repr() == 47 && WEBHOOKS_DELETE == 47);
         assert!(WebhooksCreate.repr() == 48 && WEBHOOKS_CREATE == 48);
         assert!(WebhooksAll.repr() == 49 && WEBHOOKS_ALL == 49);
-        assert!(IndexesCompact.repr() == 50 && INDEXES_COMPACT == 50);
     }
 
     #[test]

crates/meilisearch-types/src/lib.rs

@@ -2,17 +2,10 @@
 
 pub mod batch_view;
 pub mod batches;
-#[cfg(not(feature = "enterprise"))]
-pub mod community_edition;
 pub mod compression;
 pub mod deserr;
 pub mod document_formats;
-#[cfg(feature = "enterprise")]
 pub mod enterprise_edition;
-#[cfg(not(feature = "enterprise"))]
-pub use community_edition as current_edition;
-#[cfg(feature = "enterprise")]
-pub use enterprise_edition as current_edition;
 pub mod error;
 pub mod facet_values_sort;
 pub mod features;
@@ -20,7 +13,6 @@ pub mod index_uid;
 pub mod index_uid_pattern;
 pub mod keys;
 pub mod locales;
-pub mod network;
 pub mod settings;
 pub mod star_or;
 pub mod task_view;

crates/meilisearch-types/src/network.rs

@@ -1,24 +0,0 @@
-use std::collections::BTreeMap;
-
-use serde::{Deserialize, Serialize};
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq, Default)]
-#[serde(rename_all = "camelCase")]
-pub struct Network {
-    #[serde(default, rename = "self")]
-    pub local: Option<String>,
-    #[serde(default)]
-    pub remotes: BTreeMap<String, Remote>,
-    #[serde(default)]
-    pub sharding: bool,
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq)]
-#[serde(rename_all = "camelCase")]
-pub struct Remote {
-    pub url: String,
-    #[serde(default)]
-    pub search_api_key: Option<String>,
-    #[serde(default)]
-    pub write_api_key: Option<String>,
-}

crates/meilisearch-types/src/settings.rs

@@ -346,26 +346,24 @@ impl<T> Settings<T> {
                 continue;
             };
 
-            hide_secret(api_key, 0);
+            Self::hide_secret(api_key);
         }
     }
-}
 
-/// Redact a secret string, starting from the `secret_offset`th byte.
+    fn hide_secret(secret: &mut String) {
-pub fn hide_secret(secret: &mut String, secret_offset: usize) {
+        match secret.len() {
-    match secret.len().checked_sub(secret_offset) {
+            x if x < 10 => {
-        None => (),
+                secret.replace_range(.., "XXX...");
-        Some(x) if x < 10 => {
-            secret.replace_range(secret_offset.., "XXX...");
             }
-        Some(x) if x < 20 => {
+            x if x < 20 => {
-            secret.replace_range((secret_offset + 2).., "XXXX...");
+                secret.replace_range(2.., "XXXX...");
             }
-        Some(x) if x < 30 => {
+            x if x < 30 => {
-            secret.replace_range((secret_offset + 3).., "XXXXX...");
+                secret.replace_range(3.., "XXXXX...");
+            }
+            _x => {
+                secret.replace_range(5.., "XXXXXX...");
             }
-        Some(_x) => {
-            secret.replace_range((secret_offset + 5).., "XXXXXX...");
         }
     }
 }

crates/meilisearch-types/src/task_view.rs

@@ -7,6 +7,7 @@ use time::{Duration, OffsetDateTime};
 use utoipa::ToSchema;
 
 use crate::batches::BatchId;
+use crate::enterprise_edition::network::Network;
 use crate::error::ResponseError;
 use crate::settings::{Settings, Unchecked};
 use crate::tasks::{
@@ -55,9 +56,6 @@ pub struct TaskView {
 
     #[serde(default, skip_serializing_if = "Option::is_none")]
     pub network: Option<TaskNetwork>,
-
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub custom_metadata: Option<String>,
 }
 
 impl TaskView {
@@ -76,7 +74,6 @@ impl TaskView {
             started_at: task.started_at,
             finished_at: task.finished_at,
             network: task.network.clone(),
-            custom_metadata: task.custom_metadata.clone(),
         }
     }
 }
@@ -146,11 +143,9 @@ pub struct DetailsView {
     pub old_index_uid: Option<String>,
     #[serde(skip_serializing_if = "Option::is_none")]
     pub new_index_uid: Option<String>,
-    // index compaction
+    // network
     #[serde(skip_serializing_if = "Option::is_none")]
-    pub pre_compaction_size: Option<String>,
+    pub network: Option<Network>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub post_compaction_size: Option<String>,
 }
 
 impl DetailsView {
@@ -323,23 +318,9 @@ impl DetailsView {
                 // We should never be able to batch multiple renames at the same time.
                 (Some(left), Some(_right)) => Some(left),
             },
-            pre_compaction_size: match (
+            network: match (&self.network, &other.network) {
-                self.pre_compaction_size.clone(),
-                other.pre_compaction_size.clone(),
-            ) {
                 (None, None) => None,
-                (None, Some(size)) | (Some(size), None) => Some(size),
+                (_, Some(network)) | (Some(network), None) => Some(network.clone()),
-                // We should never be able to batch multiple compactions at the same time.
-                (Some(left), Some(_right)) => Some(left),
-            },
-            post_compaction_size: match (
-                self.post_compaction_size.clone(),
-                other.post_compaction_size.clone(),
-            ) {
-                (None, None) => None,
-                (None, Some(size)) | (Some(size), None) => Some(size),
-                // We should never be able to batch multiple compactions at the same time.
-                (Some(left), Some(_right)) => Some(left),
             },
         }
     }
@@ -442,14 +423,8 @@ impl From<Details> for DetailsView {
                 upgrade_to: Some(format!("v{}.{}.{}", to.0, to.1, to.2)),
                 ..Default::default()
             },
-            Details::IndexCompaction { pre_compaction_size, post_compaction_size, .. } => {
+            Details::NetworkTopologyChange { network: new_network } => {
-                DetailsView {
+                DetailsView { network: new_network, ..Default::default() }
-                    pre_compaction_size: pre_compaction_size
-                        .map(|size| size.get_appropriate_unit(UnitType::Both).to_string()),
-                    post_compaction_size: post_compaction_size
-                        .map(|size| size.get_appropriate_unit(UnitType::Both).to_string()),
-                    ..Default::default()
-                }
             }
         }
     }

crates/meilisearch-types/src/tasks.rs

@@ -15,6 +15,7 @@ use utoipa::{schema, ToSchema};
 use uuid::Uuid;
 
 use crate::batches::BatchId;
+use crate::enterprise_edition::network::Network;
 use crate::error::ResponseError;
 use crate::index_uid_pattern::IndexUidPattern;
 use crate::keys::Key;
@@ -45,9 +46,6 @@ pub struct Task {
 
     #[serde(default, skip_serializing_if = "Option::is_none")]
     pub network: Option<TaskNetwork>,
-
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub custom_metadata: Option<String>,
 }
 
 impl Task {
@@ -61,6 +59,7 @@ impl Task {
             | TaskDeletion { .. }
             | Export { .. }
             | UpgradeDatabase { .. }
+            | NetworkTopologyChange { .. }
             | IndexSwap { .. } => None,
             DocumentAdditionOrUpdate { index_uid, .. }
             | DocumentEdition { index_uid, .. }
@@ -70,8 +69,7 @@ impl Task {
             | SettingsUpdate { index_uid, .. }
             | IndexCreation { index_uid, .. }
             | IndexUpdate { index_uid, .. }
-            | IndexDeletion { index_uid }
+            | IndexDeletion { index_uid } => Some(index_uid),
-            | IndexCompaction { index_uid } => Some(index_uid),
         }
     }
 
@@ -99,7 +97,7 @@ impl Task {
             | KindWithContent::SnapshotCreation
             | KindWithContent::Export { .. }
             | KindWithContent::UpgradeDatabase { .. }
-            | KindWithContent::IndexCompaction { .. } => None,
+            | KindWithContent::NetworkTopologyChange { .. } => None,
         }
     }
 }
@@ -175,8 +173,9 @@ pub enum KindWithContent {
     UpgradeDatabase {
         from: (u32, u32, u32),
     },
-    IndexCompaction {
+    NetworkTopologyChange {
-        index_uid: String,
+        network: Option<Network>,
+        origin: Option<Origin>,
     },
 }
 
@@ -214,7 +213,7 @@ impl KindWithContent {
             KindWithContent::SnapshotCreation => Kind::SnapshotCreation,
             KindWithContent::Export { .. } => Kind::Export,
             KindWithContent::UpgradeDatabase { .. } => Kind::UpgradeDatabase,
-            KindWithContent::IndexCompaction { .. } => Kind::IndexCompaction,
+            KindWithContent::NetworkTopologyChange { .. } => Kind::NetworkTopologyChange,
         }
     }
 
@@ -227,6 +226,7 @@ impl KindWithContent {
             | TaskCancelation { .. }
             | TaskDeletion { .. }
             | Export { .. }
+            | NetworkTopologyChange { .. }
             | UpgradeDatabase { .. } => vec![],
             DocumentAdditionOrUpdate { index_uid, .. }
             | DocumentEdition { index_uid, .. }
@@ -235,8 +235,7 @@ impl KindWithContent {
             | DocumentClear { index_uid }
             | SettingsUpdate { index_uid, .. }
             | IndexCreation { index_uid, .. }
-            | IndexDeletion { index_uid }
+            | IndexDeletion { index_uid } => vec![index_uid],
-            | IndexCompaction { index_uid } => vec![index_uid],
             IndexUpdate { index_uid, new_index_uid, .. } => {
                 let mut indexes = vec![index_uid.as_str()];
                 if let Some(new_uid) = new_index_uid {
@@ -335,11 +334,9 @@ impl KindWithContent {
                     versioning::VERSION_PATCH,
                 ),
             }),
-            KindWithContent::IndexCompaction { index_uid } => Some(Details::IndexCompaction {
+            KindWithContent::NetworkTopologyChange { network: new_network, origin: _ } => {
-                index_uid: index_uid.clone(),
+                Some(Details::NetworkTopologyChange { network: new_network.clone() })
-                pre_compaction_size: None,
+            }
-                post_compaction_size: None,
-            }),
         }
     }
 
@@ -422,11 +419,9 @@ impl KindWithContent {
                     versioning::VERSION_PATCH,
                 ),
             }),
-            KindWithContent::IndexCompaction { index_uid } => Some(Details::IndexCompaction {
+            KindWithContent::NetworkTopologyChange { network: new_network, origin: _s } => {
-                index_uid: index_uid.clone(),
+                Some(Details::NetworkTopologyChange { network: new_network.clone() })
-                pre_compaction_size: None,
+            }
-                post_compaction_size: None,
-            }),
         }
     }
 }
@@ -489,11 +484,9 @@ impl From<&KindWithContent> for Option<Details> {
                     versioning::VERSION_PATCH,
                 ),
             }),
-            KindWithContent::IndexCompaction { index_uid } => Some(Details::IndexCompaction {
+            KindWithContent::NetworkTopologyChange { network: new_network, origin: _ } => {
-                index_uid: index_uid.clone(),
+                Some(Details::NetworkTopologyChange { network: new_network.clone() })
-                pre_compaction_size: None,
+            }
-                post_compaction_size: None,
-            }),
         }
     }
 }
@@ -604,7 +597,7 @@ pub enum Kind {
     SnapshotCreation,
     Export,
     UpgradeDatabase,
-    IndexCompaction,
+    NetworkTopologyChange,
 }
 
 impl Kind {
@@ -616,15 +609,15 @@ impl Kind {
             | Kind::SettingsUpdate
             | Kind::IndexCreation
             | Kind::IndexDeletion
-            | Kind::IndexUpdate
+            | Kind::IndexUpdate => true,
-            | Kind::IndexCompaction => true,
             Kind::IndexSwap
             | Kind::TaskCancelation
             | Kind::TaskDeletion
             | Kind::DumpCreation
             | Kind::Export
             | Kind::UpgradeDatabase
-            | Kind::SnapshotCreation => false,
+            | Kind::SnapshotCreation
+            | Kind::NetworkTopologyChange => false,
         }
     }
 }
@@ -645,7 +638,7 @@ impl Display for Kind {
             Kind::SnapshotCreation => write!(f, "snapshotCreation"),
             Kind::Export => write!(f, "export"),
             Kind::UpgradeDatabase => write!(f, "upgradeDatabase"),
-            Kind::IndexCompaction => write!(f, "indexCompaction"),
+            Kind::NetworkTopologyChange => write!(f, "networkTopologyChange"),
         }
     }
 }
@@ -681,8 +674,8 @@ impl FromStr for Kind {
             Ok(Kind::Export)
         } else if kind.eq_ignore_ascii_case("upgradeDatabase") {
             Ok(Kind::UpgradeDatabase)
-        } else if kind.eq_ignore_ascii_case("indexCompaction") {
+        } else if kind.eq_ignore_ascii_case("networkTopologyChange") {
-            Ok(Kind::IndexCompaction)
+            Ok(Kind::NetworkTopologyChange)
         } else {
             Err(ParseTaskKindError(kind.to_owned()))
         }
@@ -768,10 +761,8 @@ pub enum Details {
         from: (u32, u32, u32),
         to: (u32, u32, u32),
     },
-    IndexCompaction {
+    NetworkTopologyChange {
-        index_uid: String,
+        network: Option<Network>,
-        pre_compaction_size: Option<Byte>,
-        post_compaction_size: Option<Byte>,
     },
 }
 
@@ -835,15 +826,12 @@ impl Details {
             Self::ClearAll { deleted_documents } => *deleted_documents = Some(0),
             Self::TaskCancelation { canceled_tasks, .. } => *canceled_tasks = Some(0),
             Self::TaskDeletion { deleted_tasks, .. } => *deleted_tasks = Some(0),
-            Self::IndexCompaction { pre_compaction_size, post_compaction_size, .. } => {
-                *pre_compaction_size = None;
-                *post_compaction_size = None;
-            }
             Self::SettingsUpdate { .. }
             | Self::IndexInfo { .. }
             | Self::Dump { .. }
             | Self::Export { .. }
             | Self::UpgradeDatabase { .. }
+            | Self::NetworkTopologyChange { .. }
             | Self::IndexSwap { .. } => (),
         }
 

crates/meilisearch-types/src/webhooks.rs

@@ -11,24 +11,6 @@ pub struct Webhook {
     pub headers: BTreeMap<String, String>,
 }
 
-impl Webhook {
-    pub fn redact_authorization_header(&mut self) {
-        // headers are case insensitive, so to make the redaction robust we iterate over qualifying headers
-        // rather than getting one canonical `Authorization` header.
-        for value in self
-            .headers
-            .iter_mut()
-            .filter_map(|(name, value)| name.eq_ignore_ascii_case("authorization").then_some(value))
-        {
-            if value.starts_with("Bearer ") {
-                crate::settings::hide_secret(value, "Bearer ".len());
-            } else {
-                crate::settings::hide_secret(value, 0);
-            }
-        }
-    }
-}
-
 #[derive(Debug, Serialize, Default, Clone, PartialEq)]
 #[serde(rename_all = "camelCase")]
 pub struct WebhooksView {

crates/meilisearch/Cargo.toml

@@ -14,91 +14,91 @@ default-run = "meilisearch"
 
 [dependencies]
 actix-cors = "0.7.1"
-actix-http = { version = "3.11.2", default-features = false, features = [
+actix-http = { version = "3.11.0", default-features = false, features = [
     "compress-brotli",
     "compress-gzip",
     "rustls-0_23",
 ] }
 actix-utils = "3.0.1"
-actix-web = { version = "4.12.0", default-features = false, features = [
+actix-web = { version = "4.11.0", default-features = false, features = [
     "macros",
     "compress-brotli",
     "compress-gzip",
     "cookies",
     "rustls-0_23",
 ] }
-anyhow = { version = "1.0.100", features = ["backtrace"] }
+anyhow = { version = "1.0.98", features = ["backtrace"] }
-bstr = "1.12.1"
+bstr = "1.12.0"
 byte-unit = { version = "5.1.6", features = ["serde"] }
-bytes = "1.11.0"
+bytes = "1.10.1"
-bumpalo = "3.19.0"
+bumpalo = "3.18.1"
-clap = { version = "4.5.52", features = ["derive", "env"] }
+clap = { version = "4.5.40", features = ["derive", "env"] }
 crossbeam-channel = "0.5.15"
-deserr = { version = "0.6.4", features = ["actix-web"] }
+deserr = { version = "0.6.3", features = ["actix-web"] }
 dump = { path = "../dump" }
 either = "1.15.0"
 file-store = { path = "../file-store" }
-flate2 = "1.1.5"
+flate2 = "1.1.2"
 fst = "0.4.7"
 futures = "0.3.31"
 futures-util = "0.3.31"
 index-scheduler = { path = "../index-scheduler" }
-indexmap = { version = "2.12.0", features = ["serde"] }
+indexmap = { version = "2.9.0", features = ["serde"] }
-is-terminal = "0.4.17"
+is-terminal = "0.4.16"
 itertools = "0.14.0"
 jsonwebtoken = "9.3.1"
 lazy_static = "1.5.0"
 meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
-memmap2 = "0.9.9"
+memmap2 = "0.9.7"
-mimalloc = { version = "0.1.48", default-features = false }
+mimalloc = { version = "0.1.47", default-features = false }
 mime = "0.3.17"
 num_cpus = "1.17.0"
 obkv = "0.3.0"
 once_cell = "1.21.3"
-ordered-float = "5.1.0"
+ordered-float = "5.0.0"
-parking_lot = "0.12.5"
+parking_lot = "0.12.4"
 permissive-json-pointer = { path = "../permissive-json-pointer" }
 pin-project-lite = "0.2.16"
 platform-dirs = "0.3.0"
 prometheus = { version = "0.14.0", features = ["process"] }
 rand = "0.8.5"
-rayon = "1.11.0"
+rayon = "1.10.0"
-regex = "1.12.2"
+regex = "1.11.1"
-reqwest = { version = "0.12.24", features = [
+reqwest = { version = "0.12.20", features = [
     "rustls-tls",
     "json",
 ], default-features = false }
-rustls = { version = "0.23.35", features = ["ring"], default-features = false }
+rustls = { version = "0.23.28", features = ["ring"], default-features = false }
-rustls-pki-types = { version = "1.13.0", features = ["alloc"] }
+rustls-pki-types = { version = "1.12.0", features = ["alloc"] }
 rustls-pemfile = "2.2.0"
 segment = { version = "0.2.6" }
-serde = { version = "1.0.228", features = ["derive"] }
+serde = { version = "1.0.219", features = ["derive"] }
-serde_json = { version = "1.0.145", features = ["preserve_order"] }
+serde_json = { version = "1.0.140", features = ["preserve_order"] }
 sha2 = "0.10.9"
 siphasher = "1.0.1"
 slice-group-by = "0.3.1"
-static-files = { version = "0.3.1", optional = true }
+static-files = { version = "0.2.5", optional = true }
-sysinfo = "0.37.2"
+sysinfo = "0.35.2"
 tar = "0.4.44"
-tempfile = "3.23.0"
+tempfile = "3.20.0"
-thiserror = "2.0.17"
+thiserror = "2.0.12"
-time = { version = "0.3.44", features = [
+time = { version = "0.3.41", features = [
     "serde-well-known",
     "formatting",
     "parsing",
     "macros",
 ] }
-tokio = { version = "1.48.0", features = ["full"] }
+tokio = { version = "1.45.1", features = ["full"] }
-toml = "0.9.8"
+toml = "0.8.23"
-uuid = { version = "1.18.1", features = ["serde", "v4", "v7"] }
+uuid = { version = "1.17.0", features = ["serde", "v4"] }
 serde_urlencoded = "0.7.1"
 termcolor = "1.4.1"
-url = { version = "2.5.7", features = ["serde"] }
+url = { version = "2.5.4", features = ["serde"] }
 tracing = "0.1.41"
 tracing-subscriber = { version = "0.3.20", features = ["json"] }
 tracing-trace = { version = "0.1.0", path = "../tracing-trace" }
-tracing-actix-web = "0.7.19"
+tracing-actix-web = "0.7.18"
 build-info = { version = "1.7.0", path = "../build-info" }
 roaring = "0.10.12"
 mopa-maintained = "0.2.3"
@@ -114,35 +114,35 @@ utoipa = { version = "5.4.0", features = [
 utoipa-scalar = { version = "0.3.0", optional = true, features = ["actix-web"] }
 async-openai = { git = "https://github.com/meilisearch/async-openai", branch = "better-error-handling" }
 secrecy = "0.10.3"
-actix-web-lab = { version = "0.24.3", default-features = false }
+actix-web-lab = { version = "0.24.1", default-features = false }
 urlencoding = "2.1.3"
 backoff = { version = "0.4.0", features = ["tokio"] }
-humantime = { version = "2.3.0", default-features = false }
+
 
 [dev-dependencies]
-actix-rt = "2.11.0"
+actix-rt = "2.10.0"
-brotli = "8.0.2"
+brotli = "8.0.1"
 # fixed version due to format breakages in v1.40
 insta = { version = "=1.39.0", features = ["redactions"] }
 manifest-dir-macros = "0.1.18"
 maplit = "1.0.2"
 meili-snap = { path = "../meili-snap" }
 temp-env = "0.3.6"
-wiremock = "0.6.5"
+wiremock = "0.6.3"
 yaup = "0.3.1"
 
 [build-dependencies]
-anyhow = { version = "1.0.100", optional = true }
+anyhow = { version = "1.0.98", optional = true }
-cargo_toml = { version = "0.22.3", optional = true }
+cargo_toml = { version = "0.22.1", optional = true }
 hex = { version = "0.4.3", optional = true }
-reqwest = { version = "0.12.24", features = [
+reqwest = { version = "0.12.20", features = [
     "blocking",
     "rustls-tls",
 ], default-features = false, optional = true }
 sha-1 = { version = "0.10.1", optional = true }
-static-files = { version = "0.3.1", optional = true }
+static-files = { version = "0.2.5", optional = true }
-tempfile = { version = "3.23.0", optional = true }
+tempfile = { version = "3.20.0", optional = true }
-zip = { version = "6.0.0", optional = true }
+zip = { version = "4.1.0", optional = true }
 
 [features]
 default = ["meilisearch-types/all-tokenizations", "mini-dashboard"]
@@ -160,7 +160,6 @@ mini-dashboard = [
 ]
 chinese = ["meilisearch-types/chinese"]
 chinese-pinyin = ["meilisearch-types/chinese-pinyin"]
-enterprise = ["meilisearch-types/enterprise"]
 hebrew = ["meilisearch-types/hebrew"]
 japanese = ["meilisearch-types/japanese"]
 korean = ["meilisearch-types/korean"]

crates/meilisearch/src/analytics/segment_analytics.rs

@@ -195,7 +195,7 @@ struct Infos {
     experimental_enable_logs_route: bool,
     experimental_reduce_indexing_memory_usage: bool,
     experimental_max_number_of_batched_tasks: usize,
-    experimental_limit_batched_tasks_total_size: Option<u64>,
+    experimental_limit_batched_tasks_total_size: u64,
     experimental_network: bool,
     experimental_multimodal: bool,
     experimental_chat_completions: bool,
@@ -205,10 +205,7 @@ struct Infos {
     experimental_no_snapshot_compaction: bool,
     experimental_no_edition_2024_for_dumps: bool,
     experimental_no_edition_2024_for_settings: bool,
-    experimental_no_edition_2024_for_prefix_post_processing: bool,
-    experimental_no_edition_2024_for_facet_post_processing: bool,
     experimental_vector_store_setting: bool,
-    experimental_personalization: bool,
     gpu_enabled: bool,
     db_path: bool,
     import_dump: bool,
@@ -218,7 +215,6 @@ struct Infos {
     import_snapshot: bool,
     schedule_snapshot: Option<u64>,
     snapshot_dir: bool,
-    uses_s3_snapshots: bool,
     ignore_missing_snapshot: bool,
     ignore_snapshot_if_db_exists: bool,
     http_addr: bool,
@@ -287,8 +283,6 @@ impl Infos {
             indexer_options,
             config_file_path,
             no_analytics: _,
-            experimental_personalization_api_key,
-            s3_snapshot_options,
         } = options;
 
         let schedule_snapshot = match schedule_snapshot {
@@ -302,8 +296,6 @@ impl Infos {
             skip_index_budget: _,
             experimental_no_edition_2024_for_settings,
             experimental_no_edition_2024_for_dumps,
-            experimental_no_edition_2024_for_prefix_post_processing,
-            experimental_no_edition_2024_for_facet_post_processing,
         } = indexer_options;
 
         let RuntimeTogglableFeatures {
@@ -352,14 +344,13 @@ impl Infos {
             import_snapshot: import_snapshot.is_some(),
             schedule_snapshot,
             snapshot_dir: snapshot_dir != PathBuf::from("snapshots/"),
-            uses_s3_snapshots: s3_snapshot_options.is_some(),
             ignore_missing_snapshot,
             ignore_snapshot_if_db_exists,
             http_addr: http_addr != default_http_addr(),
             http_payload_size_limit,
             experimental_max_number_of_batched_tasks,
             experimental_limit_batched_tasks_total_size:
-                experimental_limit_batched_tasks_total_size.map(|size| size.as_u64()),
+                experimental_limit_batched_tasks_total_size.into(),
             task_queue_webhook: task_webhook_url.is_some(),
             task_webhook_authorization_header: task_webhook_authorization_header.is_some(),
             log_level: log_level.to_string(),
@@ -374,9 +365,6 @@ impl Infos {
             ssl_resumption,
             ssl_tickets,
             experimental_no_edition_2024_for_settings,
-            experimental_no_edition_2024_for_prefix_post_processing,
-            experimental_no_edition_2024_for_facet_post_processing,
-            experimental_personalization: experimental_personalization_api_key.is_some(),
         }
     }
 }

crates/meilisearch/src/error.rs

@@ -38,8 +38,6 @@ pub enum MeilisearchHttpError {
     PaginationInFederatedQuery(usize, &'static str),
     #[error("Inside `.queries[{0}]`: Using facet options is not allowed in federated queries.\n - Hint: remove `facets` from query #{0} or remove `federation` from the request\n - Hint: pass `federation.facetsByIndex.{1}: {2:?}` for facets in federated search")]
     FacetsInFederatedQuery(usize, String, Vec<String>),
-    #[error("Inside `.queries[{0}]`: Using `.personalize` is not allowed in federated queries.\n - Hint: remove `personalize` from query #{0} or remove `federation` from the request")]
-    PersonalizationInFederatedQuery(usize),
     #[error("Inconsistent order for values in facet `{facet}`: index `{previous_uid}` orders {previous_facet_order}, but index `{current_uid}` orders {index_facet_order}.\n - Hint: Remove `federation.mergeFacets` or change `faceting.sortFacetValuesBy` to be consistent in settings.")]
     InconsistentFacetOrder {
         facet: String,
@@ -139,9 +137,6 @@ impl ErrorCode for MeilisearchHttpError {
             MeilisearchHttpError::InconsistentFacetOrder { .. } => {
                 Code::InvalidMultiSearchFacetOrder
             }
-            MeilisearchHttpError::PersonalizationInFederatedQuery(_) => {
-                Code::InvalidMultiSearchQueryPersonalization
-            }
             MeilisearchHttpError::InconsistentOriginHeaders { .. } => {
                 Code::InconsistentDocumentChangeHeaders
             }

crates/meilisearch/src/lib.rs

@@ -11,7 +11,6 @@ pub mod middleware;
 pub mod option;
 #[cfg(test)]
 mod option_test;
-pub mod personalization;
 pub mod routes;
 pub mod search;
 pub mod search_queue;
@@ -59,7 +58,6 @@ use tracing::{error, info_span};
 use tracing_subscriber::filter::Targets;
 
 use crate::error::MeilisearchHttpError;
-use crate::personalization::PersonalizationService;
 
 /// Default number of simultaneously opened indexes.
 ///
@@ -130,8 +128,12 @@ pub type LogStderrType = tracing_subscriber::filter::Filtered<
 >;
 
 pub fn create_app(
-    services: ServicesData,
+    index_scheduler: Data<IndexScheduler>,
+    auth_controller: Data<AuthController>,
+    search_queue: Data<SearchQueue>,
     opt: Opt,
+    logs: (LogRouteHandle, LogStderrHandle),
+    analytics: Data<Analytics>,
     enable_dashboard: bool,
 ) -> actix_web::App<
     impl ServiceFactory<
@@ -143,7 +145,17 @@ pub fn create_app(
     >,
 > {
     let app = actix_web::App::new()
-        .configure(|s| configure_data(s, services, &opt))
+        .configure(|s| {
+            configure_data(
+                s,
+                index_scheduler.clone(),
+                auth_controller.clone(),
+                search_queue.clone(),
+                &opt,
+                logs,
+                analytics.clone(),
+            )
+        })
         .configure(routes::configure)
         .configure(|s| dashboard(s, enable_dashboard));
 
@@ -221,26 +233,12 @@ pub fn setup_meilisearch(
         task_db_size: opt.max_task_db_size.as_u64() as usize,
         index_base_map_size: opt.max_index_size.as_u64() as usize,
         enable_mdb_writemap: opt.experimental_reduce_indexing_memory_usage,
-        indexer_config: Arc::new({
+        indexer_config: Arc::new((&opt.indexer_options).try_into()?),
-            let s3_snapshot_options =
-                opt.s3_snapshot_options.clone().map(|opt| opt.try_into()).transpose()?;
-            IndexerConfig { s3_snapshot_options, ..(&opt.indexer_options).try_into()? }
-        }),
         autobatching_enabled: true,
         cleanup_enabled: !opt.experimental_replication_parameters,
         max_number_of_tasks: 1_000_000,
         max_number_of_batched_tasks: opt.experimental_max_number_of_batched_tasks,
-        batched_tasks_size_limit: opt.experimental_limit_batched_tasks_total_size.map_or_else(
+        batched_tasks_size_limit: opt.experimental_limit_batched_tasks_total_size.into(),
-            || {
-                opt.indexer_options
-                    .max_indexing_memory
-                    // By default, we use half of the available memory to determine the size of batched tasks
-                    .map_or(u64::MAX, |mem| mem.as_u64() / 2)
-                    // And never exceed 10 GiB when we infer the limit
-                    .min(10 * 1024 * 1024 * 1024)
-            },
-            |size| size.as_u64(),
-        ),
         index_growth_amount: byte_unit::Byte::from_str("10GiB").unwrap().as_u64() as usize,
         index_count: DEFAULT_INDEX_COUNT,
         instance_features: opt.to_instance_features(),
@@ -536,11 +534,7 @@ fn import_dump(
     let indexer_config = if base_config.max_threads.is_none() {
         let (thread_pool, _) = default_thread_pool_and_threads();
 
-        let _config = IndexerConfig {
+        let _config = IndexerConfig { thread_pool, ..*base_config };
-            thread_pool,
-            s3_snapshot_options: base_config.s3_snapshot_options.clone(),
-            ..*base_config
-        };
         backup_config = _config;
         &backup_config
     } else {
@@ -597,7 +591,7 @@ fn import_dump(
             let reader = DocumentsBatchReader::from_reader(reader)?;
 
             let embedder_configs = index.embedding_configs().embedding_configs(&wtxn)?;
-            let embedders = index_scheduler.embedders(uid.to_string(), embedder_configs)?;
+            let embedders = index_scheduler.embedders(&uid, embedder_configs)?;
 
             let builder = milli::update::IndexDocuments::new(
                 &mut wtxn,
@@ -625,7 +619,7 @@ fn import_dump(
 
             let mut indexer = indexer::DocumentOperation::new();
             let embedders = index.embedding_configs().embedding_configs(&rtxn)?;
-            let embedders = index_scheduler.embedders(uid.clone(), embedders)?;
+            let embedders = index_scheduler.embedders(&uid, embedders)?;
 
             let mmap = unsafe { memmap2::Mmap::map(index_reader.documents_file())? };
 
@@ -688,26 +682,23 @@ fn import_dump(
     Ok(index_scheduler_dump.finish()?)
 }
 
-pub fn configure_data(config: &mut web::ServiceConfig, services: ServicesData, opt: &Opt) {
+pub fn configure_data(
-    let ServicesData {
+    config: &mut web::ServiceConfig,
-        index_scheduler,
+    index_scheduler: Data<IndexScheduler>,
-        auth,
+    auth: Data<AuthController>,
-        search_queue,
+    search_queue: Data<SearchQueue>,
-        personalization_service,
+    opt: &Opt,
-        logs_route_handle,
+    (logs_route, logs_stderr): (LogRouteHandle, LogStderrHandle),
-        logs_stderr_handle,
+    analytics: Data<Analytics>,
-        analytics,
+) {
-    } = services;
-
     let http_payload_size_limit = opt.http_payload_size_limit.as_u64() as usize;
     config
         .app_data(index_scheduler)
         .app_data(auth)
         .app_data(search_queue)
         .app_data(analytics)
-        .app_data(personalization_service)
+        .app_data(web::Data::new(logs_route))
-        .app_data(logs_route_handle)
+        .app_data(web::Data::new(logs_stderr))
-        .app_data(logs_stderr_handle)
         .app_data(web::Data::new(opt.clone()))
         .app_data(
             web::JsonConfig::default()
@@ -768,14 +759,3 @@ pub fn dashboard(config: &mut web::ServiceConfig, enable_frontend: bool) {
 pub fn dashboard(config: &mut web::ServiceConfig, _enable_frontend: bool) {
     config.service(web::resource("/").route(web::get().to(routes::running)));
 }
-
-#[derive(Clone)]
-pub struct ServicesData {
-    pub index_scheduler: Data<IndexScheduler>,
-    pub auth: Data<AuthController>,
-    pub search_queue: Data<SearchQueue>,
-    pub personalization_service: Data<PersonalizationService>,
-    pub logs_route_handle: Data<LogRouteHandle>,
-    pub logs_stderr_handle: Data<LogStderrHandle>,
-    pub analytics: Data<Analytics>,
-}

crates/meilisearch/src/main.rs

@@ -14,11 +14,10 @@ use index_scheduler::IndexScheduler;
 use is_terminal::IsTerminal;
 use meilisearch::analytics::Analytics;
 use meilisearch::option::LogMode;
-use meilisearch::personalization::PersonalizationService;
 use meilisearch::search_queue::SearchQueue;
 use meilisearch::{
     analytics, create_app, setup_meilisearch, LogRouteHandle, LogRouteType, LogStderrHandle,
-    LogStderrType, Opt, ServicesData, SubscriberForSecondLayer,
+    LogStderrType, Opt, SubscriberForSecondLayer,
 };
 use meilisearch_auth::{generate_master_key, AuthController, MASTER_KEY_MIN_SIZE};
 use termcolor::{Color, ColorChoice, ColorSpec, StandardStream, WriteColor};
@@ -153,15 +152,8 @@ async fn run_http(
     let enable_dashboard = &opt.env == "development";
     let opt_clone = opt.clone();
     let index_scheduler = Data::from(index_scheduler);
-    let auth = Data::from(auth_controller);
+    let auth_controller = Data::from(auth_controller);
     let analytics = Data::from(analytics);
-    // Create personalization service with API key from options
-    let personalization_service = Data::new(
-        opt.experimental_personalization_api_key
-            .clone()
-            .map(PersonalizationService::cohere)
-            .unwrap_or_else(PersonalizationService::disabled),
-    );
     let search_queue = SearchQueue::new(
         opt.experimental_search_queue_size,
         available_parallelism()
@@ -173,22 +165,18 @@ async fn run_http(
         usize::from(opt.experimental_drop_search_after) as u64
     ));
     let search_queue = Data::new(search_queue);
-    let (logs_route_handle, logs_stderr_handle) = logs;
-    let logs_route_handle = Data::new(logs_route_handle);
-    let logs_stderr_handle = Data::new(logs_stderr_handle);
 
-    let services = ServicesData {
+    let http_server = HttpServer::new(move || {
-        index_scheduler,
+        create_app(
-        auth,
+            index_scheduler.clone(),
-        search_queue,
+            auth_controller.clone(),
-        personalization_service,
+            search_queue.clone(),
-        logs_route_handle,
+            opt.clone(),
-        logs_stderr_handle,
+            logs.clone(),
-        analytics,
+            analytics.clone(),
-    };
+            enable_dashboard,
-
+        )
-    let http_server =
+    })
-        HttpServer::new(move || create_app(services.clone(), opt.clone(), enable_dashboard))
     // Disable signals allows the server to terminate immediately when a user enter CTRL-C
     .disable_signals()
     .keep_alive(KeepAlive::Os);

crates/meilisearch/src/metrics.rs

@@ -1,8 +1,7 @@
 use lazy_static::lazy_static;
 use prometheus::{
-    opts, register_gauge, register_gauge_vec, register_histogram_vec, register_int_counter_vec,
+    opts, register_gauge, register_histogram_vec, register_int_counter_vec, register_int_gauge,
-    register_int_gauge, register_int_gauge_vec, Gauge, GaugeVec, HistogramVec, IntCounterVec,
+    register_int_gauge_vec, Gauge, HistogramVec, IntCounterVec, IntGauge, IntGaugeVec,
-    IntGauge, IntGaugeVec,
 };
 
 lazy_static! {
@@ -74,20 +73,6 @@ lazy_static! {
         &["kind", "value"]
     )
     .expect("Can't create a metric");
-    pub static ref MEILISEARCH_BATCH_RUNNING_PROGRESS_TRACE: GaugeVec = register_gauge_vec!(
-        opts!("meilisearch_batch_running_progress_trace", "The currently running progress trace"),
-        &["batch_uid", "step_name"]
-    )
-    .expect("Can't create a metric");
-    pub static ref MEILISEARCH_LAST_FINISHED_BATCHES_PROGRESS_TRACE_MS: IntGaugeVec =
-        register_int_gauge_vec!(
-            opts!(
-                "meilisearch_last_finished_batches_progress_trace_ms",
-                "The last few batches progress trace in milliseconds"
-            ),
-            &["batch_uid", "step_name"]
-        )
-        .expect("Can't create a metric");
     pub static ref MEILISEARCH_LAST_UPDATE: IntGauge =
         register_int_gauge!(opts!("meilisearch_last_update", "Meilisearch Last Update"))
             .expect("Can't create a metric");
@@ -129,9 +114,4 @@ lazy_static! {
             "Meilisearch Task Queue Size Until Stop Registering",
         ))
         .expect("Can't create a metric");
-    pub static ref MEILISEARCH_PERSONALIZED_SEARCH_REQUESTS: IntGauge = register_int_gauge!(opts!(
-        "meilisearch_personalized_search_requests",
-        "Meilisearch number of search requests with personalization"
-    ))
-    .expect("Can't create a metric");
 }

crates/meilisearch/src/option.rs

@@ -7,13 +7,12 @@ use std::ops::Deref;
 use std::path::PathBuf;
 use std::str::FromStr;
 use std::sync::Arc;
-use std::time::Duration;
 use std::{env, fmt, fs};
 
 use byte_unit::{Byte, ParseError, UnitType};
 use clap::Parser;
 use meilisearch_types::features::InstanceTogglableFeatures;
-use meilisearch_types::milli::update::{IndexerConfig, S3SnapshotOptions};
+use meilisearch_types::milli::update::IndexerConfig;
 use meilisearch_types::milli::ThreadPoolNoAbortBuilder;
 use rustls::server::{ServerSessionMemoryCache, WebPkiClientVerifier};
 use rustls::RootCertStore;
@@ -56,10 +55,6 @@ const MEILI_EXPERIMENTAL_ENABLE_LOGS_ROUTE: &str = "MEILI_EXPERIMENTAL_ENABLE_LO
 const MEILI_EXPERIMENTAL_CONTAINS_FILTER: &str = "MEILI_EXPERIMENTAL_CONTAINS_FILTER";
 const MEILI_EXPERIMENTAL_NO_EDITION_2024_FOR_SETTINGS: &str =
     "MEILI_EXPERIMENTAL_NO_EDITION_2024_FOR_SETTINGS";
-const MEILI_EXPERIMENTAL_NO_EDITION_2024_FOR_FACET_POST_PROCESSING: &str =
-    "MEILI_EXPERIMENTAL_NO_EDITION_2024_FOR_FACET_POST_PROCESSING";
-const MEILI_EXPERIMENTAL_NO_EDITION_2024_FOR_PREFIX_POST_PROCESSING: &str =
-    "MEILI_EXPERIMENTAL_NO_EDITION_2024_FOR_PREFIX_POST_PROCESSING";
 const MEILI_EXPERIMENTAL_ENABLE_METRICS: &str = "MEILI_EXPERIMENTAL_ENABLE_METRICS";
 const MEILI_EXPERIMENTAL_SEARCH_QUEUE_SIZE: &str = "MEILI_EXPERIMENTAL_SEARCH_QUEUE_SIZE";
 const MEILI_EXPERIMENTAL_DROP_SEARCH_AFTER: &str = "MEILI_EXPERIMENTAL_DROP_SEARCH_AFTER";
@@ -75,22 +70,6 @@ const MEILI_EXPERIMENTAL_EMBEDDING_CACHE_ENTRIES: &str =
 const MEILI_EXPERIMENTAL_NO_SNAPSHOT_COMPACTION: &str = "MEILI_EXPERIMENTAL_NO_SNAPSHOT_COMPACTION";
 const MEILI_EXPERIMENTAL_NO_EDITION_2024_FOR_DUMPS: &str =
     "MEILI_EXPERIMENTAL_NO_EDITION_2024_FOR_DUMPS";
-const MEILI_EXPERIMENTAL_PERSONALIZATION_API_KEY: &str =
-    "MEILI_EXPERIMENTAL_PERSONALIZATION_API_KEY";
-
-// Related to S3 snapshots
-const MEILI_S3_BUCKET_URL: &str = "MEILI_S3_BUCKET_URL";
-const MEILI_S3_BUCKET_REGION: &str = "MEILI_S3_BUCKET_REGION";
-const MEILI_S3_BUCKET_NAME: &str = "MEILI_S3_BUCKET_NAME";
-const MEILI_S3_SNAPSHOT_PREFIX: &str = "MEILI_S3_SNAPSHOT_PREFIX";
-const MEILI_S3_ACCESS_KEY: &str = "MEILI_S3_ACCESS_KEY";
-const MEILI_S3_SECRET_KEY: &str = "MEILI_S3_SECRET_KEY";
-const MEILI_EXPERIMENTAL_S3_MAX_IN_FLIGHT_PARTS: &str = "MEILI_EXPERIMENTAL_S3_MAX_IN_FLIGHT_PARTS";
-const MEILI_EXPERIMENTAL_S3_COMPRESSION_LEVEL: &str = "MEILI_EXPERIMENTAL_S3_COMPRESSION_LEVEL";
-const MEILI_EXPERIMENTAL_S3_SIGNATURE_DURATION_SECONDS: &str =
-    "MEILI_EXPERIMENTAL_S3_SIGNATURE_DURATION_SECONDS";
-const MEILI_EXPERIMENTAL_S3_MULTIPART_PART_SIZE: &str = "MEILI_EXPERIMENTAL_S3_MULTIPART_PART_SIZE";
-
 const DEFAULT_CONFIG_FILE_PATH: &str = "./config.toml";
 const DEFAULT_DB_PATH: &str = "./data.ms";
 const DEFAULT_HTTP_ADDR: &str = "localhost:7700";
@@ -100,10 +79,6 @@ const DEFAULT_SNAPSHOT_DIR: &str = "snapshots/";
 const DEFAULT_SNAPSHOT_INTERVAL_SEC: u64 = 86400;
 const DEFAULT_SNAPSHOT_INTERVAL_SEC_STR: &str = "86400";
 const DEFAULT_DUMP_DIR: &str = "dumps/";
-const DEFAULT_S3_SNAPSHOT_MAX_IN_FLIGHT_PARTS: NonZeroUsize = NonZeroUsize::new(10).unwrap();
-const DEFAULT_S3_SNAPSHOT_COMPRESSION_LEVEL: u32 = 0;
-const DEFAULT_S3_SNAPSHOT_SIGNATURE_DURATION_SECONDS: u64 = 8 * 3600; // 8 hours
-const DEFAULT_S3_SNAPSHOT_MULTIPART_PART_SIZE: Byte = Byte::from_u64(375 * 1024 * 1024); // 375 MiB
 
 const MEILI_MAX_INDEXING_MEMORY: &str = "MEILI_MAX_INDEXING_MEMORY";
 const MEILI_MAX_INDEXING_THREADS: &str = "MEILI_MAX_INDEXING_THREADS";
@@ -473,14 +448,11 @@ pub struct Opt {
     #[serde(default = "default_limit_batched_tasks")]
     pub experimental_max_number_of_batched_tasks: usize,
 
-    /// Experimentally controls the maximum total size, in bytes, of tasks that will be processed
+    /// Experimentally reduces the maximum total size, in bytes, of tasks that will be processed at once,
-    /// simultaneously. When unspecified, defaults to half of the maximum indexing memory and
+    /// see: <https://github.com/orgs/meilisearch/discussions/801>
-    /// clamped to 10 GiB.
+    #[clap(long, env = MEILI_EXPERIMENTAL_LIMIT_BATCHED_TASKS_TOTAL_SIZE, default_value_t = default_limit_batched_tasks_total_size())]
-    ///
+    #[serde(default = "default_limit_batched_tasks_total_size")]
-    /// See: <https://github.com/orgs/meilisearch/discussions/801>
+    pub experimental_limit_batched_tasks_total_size: Byte,
-    #[clap(long, env = MEILI_EXPERIMENTAL_LIMIT_BATCHED_TASKS_TOTAL_SIZE)]
-    #[serde(default)]
-    pub experimental_limit_batched_tasks_total_size: Option<Byte>,
 
     /// Enables experimental caching of search query embeddings. The value represents the maximal number of entries in the cache of each
     /// distinct embedder.
@@ -499,20 +471,10 @@ pub struct Opt {
     #[serde(default)]
     pub experimental_no_snapshot_compaction: bool,
 
-    /// Experimental personalization API key feature.
-    ///
-    /// Sets the API key for personalization features.
-    #[clap(long, env = MEILI_EXPERIMENTAL_PERSONALIZATION_API_KEY)]
-    pub experimental_personalization_api_key: Option<String>,
-
     #[serde(flatten)]
     #[clap(flatten)]
     pub indexer_options: IndexerOpts,
 
-    #[serde(flatten)]
-    #[clap(flatten)]
-    pub s3_snapshot_options: Option<S3SnapshotOpts>,
-
     /// Set the path to a configuration file that should be used to setup the engine.
     /// Format must be TOML.
     #[clap(long)]
@@ -614,8 +576,6 @@ impl Opt {
             experimental_limit_batched_tasks_total_size,
             experimental_embedding_cache_entries,
             experimental_no_snapshot_compaction,
-            experimental_personalization_api_key,
-            s3_snapshot_options,
         } = self;
         export_to_env_if_not_present(MEILI_DB_PATH, db_path);
         export_to_env_if_not_present(MEILI_HTTP_ADDR, http_addr);
@@ -704,12 +664,10 @@ impl Opt {
             MEILI_EXPERIMENTAL_MAX_NUMBER_OF_BATCHED_TASKS,
             experimental_max_number_of_batched_tasks.to_string(),
         );
-        if let Some(limit) = experimental_limit_batched_tasks_total_size {
         export_to_env_if_not_present(
             MEILI_EXPERIMENTAL_LIMIT_BATCHED_TASKS_TOTAL_SIZE,
-                limit.to_string(),
+            experimental_limit_batched_tasks_total_size.to_string(),
         );
-        }
         export_to_env_if_not_present(
             MEILI_EXPERIMENTAL_EMBEDDING_CACHE_ENTRIES,
             experimental_embedding_cache_entries.to_string(),
@@ -718,22 +676,7 @@ impl Opt {
             MEILI_EXPERIMENTAL_NO_SNAPSHOT_COMPACTION,
             experimental_no_snapshot_compaction.to_string(),
         );
-        if let Some(experimental_personalization_api_key) = experimental_personalization_api_key {
-            export_to_env_if_not_present(
-                MEILI_EXPERIMENTAL_PERSONALIZATION_API_KEY,
-                experimental_personalization_api_key,
-            );
-        }
         indexer_options.export_to_env();
-        if let Some(s3_snapshot_options) = s3_snapshot_options {
-            #[cfg(not(unix))]
-            {
-                let _ = s3_snapshot_options;
-                panic!("S3 snapshot options are not supported on Windows");
-            }
-            #[cfg(unix)]
-            s3_snapshot_options.export_to_env();
-        }
     }
 
     pub fn get_ssl_config(&self) -> anyhow::Result<Option<rustls::ServerConfig>> {
@@ -829,22 +772,6 @@ pub struct IndexerOpts {
     #[clap(long, env = MEILI_EXPERIMENTAL_NO_EDITION_2024_FOR_DUMPS)]
     #[serde(default)]
     pub experimental_no_edition_2024_for_dumps: bool,
-
-    /// Experimental no edition 2024 to compute prefixes. For more information,
-    /// see: <https://github.com/orgs/meilisearch/discussions/862>
-    ///
-    /// Enables the experimental no edition 2024 to compute prefixes.
-    #[clap(long, env = MEILI_EXPERIMENTAL_NO_EDITION_2024_FOR_PREFIX_POST_PROCESSING)]
-    #[serde(default)]
-    pub experimental_no_edition_2024_for_prefix_post_processing: bool,
-
-    /// Experimental no edition 2024 to compute facets. For more information,
-    /// see: <https://github.com/orgs/meilisearch/discussions/862>
-    ///
-    /// Enables the experimental no edition 2024 to compute facets.
-    #[clap(long, env = MEILI_EXPERIMENTAL_NO_EDITION_2024_FOR_FACET_POST_PROCESSING)]
-    #[serde(default)]
-    pub experimental_no_edition_2024_for_facet_post_processing: bool,
 }
 
 impl IndexerOpts {
@@ -856,8 +783,6 @@ impl IndexerOpts {
             skip_index_budget: _,
             experimental_no_edition_2024_for_settings,
             experimental_no_edition_2024_for_dumps,
-            experimental_no_edition_2024_for_prefix_post_processing,
-            experimental_no_edition_2024_for_facet_post_processing,
         } = self;
         if let Some(max_indexing_memory) = max_indexing_memory.0 {
             export_to_env_if_not_present(
@@ -883,18 +808,6 @@ impl IndexerOpts {
                 experimental_no_edition_2024_for_dumps.to_string(),
             );
         }
-        if experimental_no_edition_2024_for_prefix_post_processing {
-            export_to_env_if_not_present(
-                MEILI_EXPERIMENTAL_NO_EDITION_2024_FOR_PREFIX_POST_PROCESSING,
-                experimental_no_edition_2024_for_prefix_post_processing.to_string(),
-            );
-        }
-        if experimental_no_edition_2024_for_facet_post_processing {
-            export_to_env_if_not_present(
-                MEILI_EXPERIMENTAL_NO_EDITION_2024_FOR_FACET_POST_PROCESSING,
-                experimental_no_edition_2024_for_facet_post_processing.to_string(),
-            );
-        }
     }
 }
 
@@ -902,16 +815,6 @@ impl TryFrom<&IndexerOpts> for IndexerConfig {
     type Error = anyhow::Error;
 
     fn try_from(other: &IndexerOpts) -> Result<Self, Self::Error> {
-        let IndexerOpts {
-            max_indexing_memory,
-            max_indexing_threads,
-            skip_index_budget,
-            experimental_no_edition_2024_for_settings,
-            experimental_no_edition_2024_for_dumps,
-            experimental_no_edition_2024_for_prefix_post_processing,
-            experimental_no_edition_2024_for_facet_post_processing,
-        } = other;
-
         let thread_pool = ThreadPoolNoAbortBuilder::new_for_indexing()
             .num_threads(other.max_indexing_threads.unwrap_or_else(|| num_cpus::get() / 2))
             .build()?;
@@ -919,163 +822,17 @@ impl TryFrom<&IndexerOpts> for IndexerConfig {
         Ok(Self {
             thread_pool,
             log_every_n: Some(DEFAULT_LOG_EVERY_N),
-            max_memory: max_indexing_memory.map(|b| b.as_u64() as usize),
+            max_memory: other.max_indexing_memory.map(|b| b.as_u64() as usize),
-            max_threads: max_indexing_threads.0,
+            max_threads: *other.max_indexing_threads,
             max_positions_per_attributes: None,
-            skip_index_budget: *skip_index_budget,
+            skip_index_budget: other.skip_index_budget,
-            experimental_no_edition_2024_for_settings: *experimental_no_edition_2024_for_settings,
+            experimental_no_edition_2024_for_settings: other
-            experimental_no_edition_2024_for_dumps: *experimental_no_edition_2024_for_dumps,
+                .experimental_no_edition_2024_for_settings,
+            experimental_no_edition_2024_for_dumps: other.experimental_no_edition_2024_for_dumps,
             chunk_compression_type: Default::default(),
             chunk_compression_level: Default::default(),
             documents_chunk_size: Default::default(),
             max_nb_chunks: Default::default(),
-            experimental_no_edition_2024_for_prefix_post_processing:
-                *experimental_no_edition_2024_for_prefix_post_processing,
-            experimental_no_edition_2024_for_facet_post_processing:
-                *experimental_no_edition_2024_for_facet_post_processing,
-            s3_snapshot_options: None,
-        })
-    }
-}
-
-#[derive(Debug, Clone, Parser, Deserialize)]
-// This group is a bit tricky but makes it possible to require all listed fields if one of them
-// is specified. It lets us keep an Option for the S3SnapshotOpts configuration.
-// <https://github.com/clap-rs/clap/issues/5092#issuecomment-2616986075>
-#[group(requires_all = ["s3_bucket_url", "s3_bucket_region", "s3_bucket_name", "s3_snapshot_prefix", "s3_access_key", "s3_secret_key"])]
-pub struct S3SnapshotOpts {
-    /// The S3 bucket URL in the format https://s3.<region>.amazonaws.com.
-    #[clap(long, env = MEILI_S3_BUCKET_URL, required = false)]
-    #[serde(default)]
-    pub s3_bucket_url: String,
-
-    /// The region in the format us-east-1.
-    #[clap(long, env = MEILI_S3_BUCKET_REGION, required = false)]
-    #[serde(default)]
-    pub s3_bucket_region: String,
-
-    /// The bucket name.
-    #[clap(long, env = MEILI_S3_BUCKET_NAME, required = false)]
-    #[serde(default)]
-    pub s3_bucket_name: String,
-
-    /// The prefix path where to put the snapshot, uses normal slashes (/).
-    #[clap(long, env = MEILI_S3_SNAPSHOT_PREFIX, required = false)]
-    #[serde(default)]
-    pub s3_snapshot_prefix: String,
-
-    /// The S3 access key.
-    #[clap(long, env = MEILI_S3_ACCESS_KEY, required = false)]
-    #[serde(default)]
-    pub s3_access_key: String,
-
-    /// The S3 secret key.
-    #[clap(long, env = MEILI_S3_SECRET_KEY, required = false)]
-    #[serde(default)]
-    pub s3_secret_key: String,
-
-    /// The maximum number of parts that can be uploaded in parallel.
-    ///
-    /// For more information, see <https://github.com/orgs/meilisearch/discussions/869>.
-    #[clap(long, env = MEILI_EXPERIMENTAL_S3_MAX_IN_FLIGHT_PARTS, default_value_t = default_experimental_s3_snapshot_max_in_flight_parts())]
-    #[serde(default = "default_experimental_s3_snapshot_max_in_flight_parts")]
-    pub experimental_s3_max_in_flight_parts: NonZeroUsize,
-
-    /// The compression level. Defaults to no compression (0).
-    ///
-    /// For more information, see <https://github.com/orgs/meilisearch/discussions/869>.
-    #[clap(long, env = MEILI_EXPERIMENTAL_S3_COMPRESSION_LEVEL, default_value_t = default_experimental_s3_snapshot_compression_level())]
-    #[serde(default = "default_experimental_s3_snapshot_compression_level")]
-    pub experimental_s3_compression_level: u32,
-
-    /// The signature duration for the multipart upload.
-    ///
-    /// For more information, see <https://github.com/orgs/meilisearch/discussions/869>.
-    #[clap(long, env = MEILI_EXPERIMENTAL_S3_SIGNATURE_DURATION_SECONDS, default_value_t = default_experimental_s3_snapshot_signature_duration_seconds())]
-    #[serde(default = "default_experimental_s3_snapshot_signature_duration_seconds")]
-    pub experimental_s3_signature_duration_seconds: u64,
-
-    /// The size of the the multipart parts.
-    ///
-    /// Must not be less than 10MiB and larger than 8GiB. Yes,
-    /// twice the boundaries of the AWS S3 multipart upload
-    /// because we use it a bit differently internally.
-    ///
-    /// For more information, see <https://github.com/orgs/meilisearch/discussions/869>.
-    #[clap(long, env = MEILI_EXPERIMENTAL_S3_MULTIPART_PART_SIZE, default_value_t = default_experimental_s3_snapshot_multipart_part_size())]
-    #[serde(default = "default_experimental_s3_snapshot_multipart_part_size")]
-    pub experimental_s3_multipart_part_size: Byte,
-}
-
-impl S3SnapshotOpts {
-    /// Exports the values to their corresponding env vars if they are not set.
-    pub fn export_to_env(self) {
-        let S3SnapshotOpts {
-            s3_bucket_url,
-            s3_bucket_region,
-            s3_bucket_name,
-            s3_snapshot_prefix,
-            s3_access_key,
-            s3_secret_key,
-            experimental_s3_max_in_flight_parts,
-            experimental_s3_compression_level,
-            experimental_s3_signature_duration_seconds,
-            experimental_s3_multipart_part_size,
-        } = self;
-
-        export_to_env_if_not_present(MEILI_S3_BUCKET_URL, s3_bucket_url);
-        export_to_env_if_not_present(MEILI_S3_BUCKET_REGION, s3_bucket_region);
-        export_to_env_if_not_present(MEILI_S3_BUCKET_NAME, s3_bucket_name);
-        export_to_env_if_not_present(MEILI_S3_SNAPSHOT_PREFIX, s3_snapshot_prefix);
-        export_to_env_if_not_present(MEILI_S3_ACCESS_KEY, s3_access_key);
-        export_to_env_if_not_present(MEILI_S3_SECRET_KEY, s3_secret_key);
-        export_to_env_if_not_present(
-            MEILI_EXPERIMENTAL_S3_MAX_IN_FLIGHT_PARTS,
-            experimental_s3_max_in_flight_parts.to_string(),
-        );
-        export_to_env_if_not_present(
-            MEILI_EXPERIMENTAL_S3_COMPRESSION_LEVEL,
-            experimental_s3_compression_level.to_string(),
-        );
-        export_to_env_if_not_present(
-            MEILI_EXPERIMENTAL_S3_SIGNATURE_DURATION_SECONDS,
-            experimental_s3_signature_duration_seconds.to_string(),
-        );
-        export_to_env_if_not_present(
-            MEILI_EXPERIMENTAL_S3_MULTIPART_PART_SIZE,
-            experimental_s3_multipart_part_size.to_string(),
-        );
-    }
-}
-
-impl TryFrom<S3SnapshotOpts> for S3SnapshotOptions {
-    type Error = anyhow::Error;
-
-    fn try_from(other: S3SnapshotOpts) -> Result<Self, Self::Error> {
-        let S3SnapshotOpts {
-            s3_bucket_url,
-            s3_bucket_region,
-            s3_bucket_name,
-            s3_snapshot_prefix,
-            s3_access_key,
-            s3_secret_key,
-            experimental_s3_max_in_flight_parts,
-            experimental_s3_compression_level,
-            experimental_s3_signature_duration_seconds,
-            experimental_s3_multipart_part_size,
-        } = other;
-
-        Ok(S3SnapshotOptions {
-            s3_bucket_url,
-            s3_bucket_region,
-            s3_bucket_name,
-            s3_snapshot_prefix,
-            s3_access_key,
-            s3_secret_key,
-            s3_max_in_flight_parts: experimental_s3_max_in_flight_parts,
-            s3_compression_level: experimental_s3_compression_level,
-            s3_signature_duration: Duration::from_secs(experimental_s3_signature_duration_seconds),
-            s3_multipart_part_size: experimental_s3_multipart_part_size.as_u64(),
         })
     }
 }
@@ -1278,6 +1035,10 @@ fn default_limit_batched_tasks() -> usize {
     usize::MAX
 }
 
+fn default_limit_batched_tasks_total_size() -> Byte {
+    Byte::from_u64(u64::MAX)
+}
+
 fn default_embedding_cache_entries() -> usize {
     0
 }
@@ -1290,22 +1051,6 @@ fn default_snapshot_interval_sec() -> &'static str {
     DEFAULT_SNAPSHOT_INTERVAL_SEC_STR
 }
 
-fn default_experimental_s3_snapshot_max_in_flight_parts() -> NonZeroUsize {
-    DEFAULT_S3_SNAPSHOT_MAX_IN_FLIGHT_PARTS
-}
-
-fn default_experimental_s3_snapshot_compression_level() -> u32 {
-    DEFAULT_S3_SNAPSHOT_COMPRESSION_LEVEL
-}
-
-fn default_experimental_s3_snapshot_signature_duration_seconds() -> u64 {
-    DEFAULT_S3_SNAPSHOT_SIGNATURE_DURATION_SECONDS
-}
-
-fn default_experimental_s3_snapshot_multipart_part_size() -> Byte {
-    DEFAULT_S3_SNAPSHOT_MULTIPART_PART_SIZE
-}
-
 fn default_dump_dir() -> PathBuf {
     PathBuf::from(DEFAULT_DUMP_DIR)
 }

crates/meilisearch/src/personalization/mod.rs

@@ -1,366 +0,0 @@
-use std::time::Duration;
-
-use meilisearch_types::error::{Code, ErrorCode, ResponseError};
-use meilisearch_types::milli::TimeBudget;
-use rand::Rng;
-use reqwest::Client;
-use serde::{Deserialize, Serialize};
-use tracing::{debug, info, warn};
-
-use crate::search::{Personalize, SearchResult};
-
-const COHERE_API_URL: &str = "https://api.cohere.ai/v1/rerank";
-const MAX_RETRIES: u32 = 10;
-
-#[derive(Debug, thiserror::Error)]
-enum PersonalizationError {
-    #[error("Personalization service: HTTP request failed: {0}")]
-    Request(#[from] reqwest::Error),
-    #[error("Personalization service: Failed to parse response: {0}")]
-    Parse(String),
-    #[error("Personalization service: Cohere API error: {0}")]
-    Api(String),
-    #[error("Personalization service: Unauthorized: invalid API key")]
-    Unauthorized,
-    #[error("Personalization service: Rate limited: too many requests")]
-    RateLimited,
-    #[error("Personalization service: Bad request: {0}")]
-    BadRequest(String),
-    #[error("Personalization service: Internal server error: {0}")]
-    InternalServerError(String),
-    #[error("Personalization service: Network error: {0}")]
-    Network(String),
-    #[error("Personalization service: Deadline exceeded")]
-    DeadlineExceeded,
-    #[error(transparent)]
-    FeatureNotEnabled(#[from] index_scheduler::error::FeatureNotEnabledError),
-}
-
-impl ErrorCode for PersonalizationError {
-    fn error_code(&self) -> Code {
-        match self {
-            PersonalizationError::FeatureNotEnabled { .. } => Code::FeatureNotEnabled,
-            PersonalizationError::Unauthorized => Code::RemoteInvalidApiKey,
-            PersonalizationError::RateLimited => Code::TooManySearchRequests,
-            PersonalizationError::BadRequest(_) => Code::RemoteBadRequest,
-            PersonalizationError::InternalServerError(_) => Code::RemoteRemoteError,
-            PersonalizationError::Network(_) | PersonalizationError::Request(_) => {
-                Code::RemoteCouldNotSendRequest
-            }
-            PersonalizationError::Parse(_) | PersonalizationError::Api(_) => {
-                Code::RemoteBadResponse
-            }
-            PersonalizationError::DeadlineExceeded => Code::Internal, // should not be returned to the client
-        }
-    }
-}
-
-pub struct CohereService {
-    client: Client,
-    api_key: String,
-}
-
-impl CohereService {
-    pub fn new(api_key: String) -> Self {
-        info!("Personalization service initialized with Cohere API");
-        let client = Client::builder()
-            .timeout(Duration::from_secs(30))
-            .build()
-            .expect("Failed to create HTTP client");
-        Self { client, api_key }
-    }
-
-    pub async fn rerank_search_results(
-        &self,
-        search_result: SearchResult,
-        personalize: &Personalize,
-        query: Option<&str>,
-        time_budget: TimeBudget,
-    ) -> Result<SearchResult, ResponseError> {
-        if time_budget.exceeded() {
-            warn!("Could not rerank due to deadline");
-            // If the deadline is exceeded, return the original search result instead of an error
-            return Ok(search_result);
-        }
-
-        // Extract user context from personalization
-        let user_context = personalize.user_context.as_str();
-
-        // Build the prompt by merging query and user context
-        let prompt = match query {
-            Some(q) => format!("User Context: {user_context}\nQuery: {q}"),
-            None => format!("User Context: {user_context}"),
-        };
-
-        // Extract documents for reranking
-        let documents: Vec<String> = search_result
-            .hits
-            .iter()
-            .map(|hit| {
-                // Convert the document to a string representation for reranking
-                serde_json::to_string(&hit.document).unwrap_or_else(|_| "{}".to_string())
-            })
-            .collect();
-
-        if documents.is_empty() {
-            return Ok(search_result);
-        }
-
-        // Call Cohere's rerank API with retry logic
-        let reranked_indices =
-            match self.call_rerank_with_retry(&prompt, &documents, time_budget).await {
-                Ok(indices) => indices,
-                Err(PersonalizationError::DeadlineExceeded) => {
-                    // If the deadline is exceeded, return the original search result instead of an error
-                    return Ok(search_result);
-                }
-                Err(e) => return Err(e.into()),
-            };
-
-        debug!("Cohere rerank successful, reordering {} results", search_result.hits.len());
-
-        // Reorder the hits based on Cohere's reranking
-        let mut reranked_hits = Vec::new();
-        for index in reranked_indices.iter() {
-            if let Some(hit) = search_result.hits.get(*index) {
-                reranked_hits.push(hit.clone());
-            }
-        }
-
-        Ok(SearchResult { hits: reranked_hits, ..search_result })
-    }
-
-    async fn call_rerank_with_retry(
-        &self,
-        query: &str,
-        documents: &[String],
-        time_budget: TimeBudget,
-    ) -> Result<Vec<usize>, PersonalizationError> {
-        let request_body = CohereRerankRequest {
-            query: query.to_string(),
-            documents: documents.to_vec(),
-            model: "rerank-english-v3.0".to_string(),
-        };
-
-        // Retry loop similar to vector extraction
-        for attempt in 0..MAX_RETRIES {
-            let response_result = self.send_rerank_request(&request_body).await;
-
-            let retry_duration = match self.handle_response(response_result).await {
-                Ok(indices) => return Ok(indices),
-                Err(retry) => {
-                    warn!("Cohere rerank attempt #{} failed: {}", attempt, retry.error);
-
-                    if time_budget.exceeded() {
-                        warn!("Could not rerank due to deadline");
-                        return Err(PersonalizationError::DeadlineExceeded);
-                    } else {
-                        match retry.into_duration(attempt) {
-                            Ok(d) => d,
-                            Err(error) => return Err(error),
-                        }
-                    }
-                }
-            };
-
-            // randomly up to double the retry duration
-            let retry_duration = retry_duration
-                + rand::thread_rng().gen_range(std::time::Duration::ZERO..retry_duration);
-
-            warn!("Retrying after {}ms", retry_duration.as_millis());
-            tokio::time::sleep(retry_duration).await;
-        }
-
-        // Final attempt without retry
-        let response_result = self.send_rerank_request(&request_body).await;
-
-        match self.handle_response(response_result).await {
-            Ok(indices) => Ok(indices),
-            Err(retry) => Err(retry.into_error()),
-        }
-    }
-
-    async fn send_rerank_request(
-        &self,
-        request_body: &CohereRerankRequest,
-    ) -> Result<reqwest::Response, reqwest::Error> {
-        self.client
-            .post(COHERE_API_URL)
-            .header("Authorization", format!("Bearer {}", self.api_key))
-            .header("Content-Type", "application/json")
-            .json(request_body)
-            .send()
-            .await
-    }
-
-    async fn handle_response(
-        &self,
-        response_result: Result<reqwest::Response, reqwest::Error>,
-    ) -> Result<Vec<usize>, Retry> {
-        let response = match response_result {
-            Ok(r) => r,
-            Err(e) if e.is_timeout() => {
-                return Err(Retry::retry_later(PersonalizationError::Network(format!(
-                    "Request timeout: {}",
-                    e
-                ))));
-            }
-            Err(e) => {
-                return Err(Retry::retry_later(PersonalizationError::Network(format!(
-                    "Network error: {}",
-                    e
-                ))));
-            }
-        };
-
-        let status = response.status();
-        let status_code = status.as_u16();
-
-        if status.is_success() {
-            let rerank_response: CohereRerankResponse = match response.json().await {
-                Ok(r) => r,
-                Err(e) => {
-                    return Err(Retry::retry_later(PersonalizationError::Parse(format!(
-                        "Failed to parse response: {}",
-                        e
-                    ))));
-                }
-            };
-
-            // Extract indices from rerank results
-            let indices: Vec<usize> =
-                rerank_response.results.iter().map(|result| result.index as usize).collect();
-
-            return Ok(indices);
-        }
-
-        // Handle error status codes
-        let error_body = response.text().await.unwrap_or_else(|_| "Unknown error".to_string());
-
-        let retry = match status_code {
-            401 => Retry::give_up(PersonalizationError::Unauthorized),
-            429 => Retry::rate_limited(PersonalizationError::RateLimited),
-            400 => Retry::give_up(PersonalizationError::BadRequest(error_body)),
-            500..=599 => Retry::retry_later(PersonalizationError::InternalServerError(format!(
-                "Status {}: {}",
-                status_code, error_body
-            ))),
-            402..=499 => Retry::give_up(PersonalizationError::Api(format!(
-                "Status {}: {}",
-                status_code, error_body
-            ))),
-            _ => Retry::retry_later(PersonalizationError::Api(format!(
-                "Unexpected status {}: {}",
-                status_code, error_body
-            ))),
-        };
-
-        Err(retry)
-    }
-}
-
-#[derive(Serialize)]
-struct CohereRerankRequest {
-    query: String,
-    documents: Vec<String>,
-    model: String,
-}
-
-#[derive(Deserialize)]
-struct CohereRerankResponse {
-    results: Vec<CohereRerankResult>,
-}
-
-#[derive(Deserialize)]
-struct CohereRerankResult {
-    index: u32,
-}
-
-// Retry strategy similar to vector extraction
-struct Retry {
-    error: PersonalizationError,
-    strategy: RetryStrategy,
-}
-
-enum RetryStrategy {
-    GiveUp,
-    Retry,
-    RetryAfterRateLimit,
-}
-
-impl Retry {
-    fn give_up(error: PersonalizationError) -> Self {
-        Self { error, strategy: RetryStrategy::GiveUp }
-    }
-
-    fn retry_later(error: PersonalizationError) -> Self {
-        Self { error, strategy: RetryStrategy::Retry }
-    }
-
-    fn rate_limited(error: PersonalizationError) -> Self {
-        Self { error, strategy: RetryStrategy::RetryAfterRateLimit }
-    }
-
-    fn into_duration(self, attempt: u32) -> Result<Duration, PersonalizationError> {
-        match self.strategy {
-            RetryStrategy::GiveUp => Err(self.error),
-            RetryStrategy::Retry => {
-                // Exponential backoff: 10^attempt milliseconds
-                Ok(Duration::from_millis((10u64).pow(attempt)))
-            }
-            RetryStrategy::RetryAfterRateLimit => {
-                // Longer backoff for rate limits: 100ms + exponential
-                Ok(Duration::from_millis(100 + (10u64).pow(attempt)))
-            }
-        }
-    }
-
-    fn into_error(self) -> PersonalizationError {
-        self.error
-    }
-}
-
-pub enum PersonalizationService {
-    Cohere(CohereService),
-    Disabled,
-}
-
-impl PersonalizationService {
-    pub fn cohere(api_key: String) -> Self {
-        // If the API key is empty, consider the personalization service as disabled
-        if api_key.trim().is_empty() {
-            Self::disabled()
-        } else {
-            Self::Cohere(CohereService::new(api_key))
-        }
-    }
-
-    pub fn disabled() -> Self {
-        debug!("Personalization service disabled");
-        Self::Disabled
-    }
-
-    pub async fn rerank_search_results(
-        &self,
-        search_result: SearchResult,
-        personalize: &Personalize,
-        query: Option<&str>,
-        time_budget: TimeBudget,
-    ) -> Result<SearchResult, ResponseError> {
-        match self {
-            Self::Cohere(cohere_service) => {
-                cohere_service
-                    .rerank_search_results(search_result, personalize, query, time_budget)
-                    .await
-            }
-            Self::Disabled => Err(PersonalizationError::FeatureNotEnabled(
-                index_scheduler::error::FeatureNotEnabledError {
-                    disabled_action: "reranking search results",
-                    feature: "personalization",
-                    issue_link: "https://github.com/orgs/meilisearch/discussions/866",
-                },
-            )
-            .into()),
-        }
-    }
-}

crates/meilisearch/src/routes/chats/chat_completions.rs

@@ -282,8 +282,7 @@ async fn process_search_request(
     if let Some(search_rules) = auth_filter.get_index_search_rules(&index_uid) {
         add_search_rules(&mut query.filter, search_rules);
     }
-    let search_kind =
+    let search_kind = search_kind(&query, index_scheduler.get_ref(), &index_uid, &index)?;
-        search_kind(&query, index_scheduler.get_ref(), index_uid.to_string(), &index)?;
 
     let permit = search_queue.try_get_search_permit().await?;
     let features = index_scheduler.features();
@@ -300,7 +299,7 @@ async fn process_search_request(
         let (search, _is_finite_pagination, _max_total_hits, _offset) =
             prepare_search(&index_cloned, &rtxn, &query, &search_kind, time_budget, features)?;
 
-        match search_from_kind(index_uid, search_kind, search) {
+        match search_from_kind(&index_uid, search_kind, search) {
             Ok((search_results, _)) => Ok((rtxn, Ok(search_results))),
             Err(MeilisearchHttpError::Milli {
                 error: meilisearch_types::milli::Error::UserError(user_error),

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

@@ -1,39 +0,0 @@
-pub mod proxy {
-
-    use std::fs::File;
-
-    use actix_web::HttpRequest;
-    use index_scheduler::IndexScheduler;
-
-    use crate::error::MeilisearchHttpError;
-
-    pub enum Body<T: serde::Serialize> {
-        NdJsonPayload,
-        Inline(T),
-        None,
-    }
-
-    impl Body<()> {
-        pub fn with_ndjson_payload(_file: File) -> Self {
-            Self::NdJsonPayload
-        }
-
-        pub fn none() -> Self {
-            Self::None
-        }
-    }
-
-    pub const PROXY_ORIGIN_REMOTE_HEADER: &str = "Meili-Proxy-Origin-Remote";
-    pub const PROXY_ORIGIN_TASK_UID_HEADER: &str = "Meili-Proxy-Origin-TaskUid";
-
-    pub async fn proxy<T: serde::Serialize>(
-        _index_scheduler: &IndexScheduler,
-        _index_uid: &str,
-        _req: &HttpRequest,
-        _network: meilisearch_types::network::Network,
-        _body: Body<T>,
-        _task: &meilisearch_types::tasks::Task,
-    ) -> Result<(), MeilisearchHttpError> {
-        Ok(())
-    }
-}

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

@@ -1,84 +0,0 @@
-use actix_web::web::{self, Data};
-use actix_web::{HttpRequest, HttpResponse};
-use index_scheduler::IndexScheduler;
-use meilisearch_types::error::ResponseError;
-use meilisearch_types::index_uid::IndexUid;
-use meilisearch_types::keys::actions;
-use meilisearch_types::tasks::KindWithContent;
-use tracing::debug;
-use utoipa::OpenApi;
-
-use super::ActionPolicy;
-use crate::analytics::Analytics;
-use crate::extractors::authentication::GuardedData;
-use crate::extractors::sequential_extractor::SeqHandler;
-use crate::routes::SummarizedTaskView;
-
-#[derive(OpenApi)]
-#[openapi(
-    paths(compact),
-    tags(
-        (
-            name = "Compact an index",
-            description = "The /compact route uses compacts the database to reorganize and make it smaller and more efficient.",
-            external_docs(url = "https://www.meilisearch.com/docs/reference/api/compact"),
-        ),
-    ),
-)]
-pub struct CompactApi;
-
-pub fn configure(cfg: &mut web::ServiceConfig) {
-    cfg.service(web::resource("").route(web::post().to(SeqHandler(compact))));
-}
-
-/// Compact an index
-#[utoipa::path(
-    post,
-    path = "{indexUid}/compact",
-    tag = "Compact an index",
-    security(("Bearer" = ["search", "*"])),
-    params(("indexUid" = String, Path, example = "movies", description = "Index Unique Identifier", nullable = false)),
-    responses(
-        (status = ACCEPTED, description = "Task successfully enqueued", body = SummarizedTaskView, content_type = "application/json", example = json!(
-            {
-                "taskUid": 147,
-                "indexUid": null,
-                "status": "enqueued",
-                "type": "documentDeletion",
-                "enqueuedAt": "2024-08-08T17:05:55.791772Z"
-            }
-        )),
-        (status = 401, description = "The authorization header is missing", body = ResponseError, content_type = "application/json", example = json!(
-            {
-                "message": "The Authorization header is missing. It must use the bearer authorization method.",
-                "code": "missing_authorization_header",
-                "type": "auth",
-                "link": "https://docs.meilisearch.com/errors#missing_authorization_header"
-            }
-        )),
-    )
-)]
-pub async fn compact(
-    index_scheduler: GuardedData<ActionPolicy<{ actions::INDEXES_COMPACT }>, Data<IndexScheduler>>,
-    index_uid: web::Path<String>,
-    req: HttpRequest,
-    analytics: web::Data<Analytics>,
-) -> Result<HttpResponse, ResponseError> {
-    let index_uid = IndexUid::try_from(index_uid.into_inner())?;
-
-    analytics.publish(IndexCompacted::default(), &req);
-
-    let task = KindWithContent::IndexCompaction { index_uid: index_uid.to_string() };
-    let task =
-        match tokio::task::spawn_blocking(move || index_scheduler.register(task, None, false))
-            .await?
-        {
-            Ok(task) => task,
-            Err(e) => return Err(e.into()),
-        };
-
-    debug!(returns = ?task, "Compact the {index_uid} index");
-    Ok(HttpResponse::Accepted().json(SummarizedTaskView::from(task)))
-}
-
-crate::empty_analytics!(IndexCompacted, "Index Compacted");

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

@@ -45,7 +45,7 @@ use crate::extractors::authentication::policies::*;
 use crate::extractors::authentication::GuardedData;
 use crate::extractors::payload::Payload;
 use crate::extractors::sequential_extractor::SeqHandler;
-use crate::routes::indexes::current_edition::proxy::{proxy, Body};
+use crate::routes::indexes::enterprise_edition::proxy::{check_leader, proxy, Body};
 use crate::routes::indexes::search::fix_sort_query_parameters;
 use crate::routes::{
     get_task_id, is_dry_run, PaginationView, SummarizedTaskView, PAGINATION_DEFAULT_LIMIT,
@@ -333,15 +333,14 @@ impl Aggregate for DocumentsDeletionAggregator {
 pub async fn delete_document(
     index_scheduler: GuardedData<ActionPolicy<{ actions::DOCUMENTS_DELETE }>, Data<IndexScheduler>>,
     path: web::Path<DocumentParam>,
-    params: AwebQueryParameter<CustomMetadataQuery, DeserrQueryParamError>,
     req: HttpRequest,
     opt: web::Data<Opt>,
     analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
-    let CustomMetadataQuery { custom_metadata } = params.into_inner();
     let DocumentParam { index_uid, document_id } = path.into_inner();
     let index_uid = IndexUid::try_from(index_uid)?;
     let network = index_scheduler.network();
+    let origin = check_leader(&req, &network)?;
 
     analytics.publish(
         DocumentsDeletionAggregator {
@@ -361,14 +360,11 @@ pub async fn delete_document(
     let dry_run = is_dry_run(&req, &opt)?;
     let task = {
         let index_scheduler = index_scheduler.clone();
-        tokio::task::spawn_blocking(move || {
+        tokio::task::spawn_blocking(move || index_scheduler.register(task, uid, dry_run)).await??
-            index_scheduler.register_with_custom_metadata(task, uid, custom_metadata, dry_run)
-        })
-        .await??
     };
 
-    if network.sharding() && !dry_run {
+    if network.sharding && !dry_run {
-        proxy(&index_scheduler, &index_uid, &req, network, Body::none(), &task).await?;
+        proxy(&index_scheduler, &index_uid, &req, origin, network, Body::none(), &task).await?;
     }
 
     let task: SummarizedTaskView = task.into();
@@ -683,19 +679,6 @@ pub struct UpdateDocumentsQuery {
     #[param(value_type = char, default = ",", example = ";")]
     #[deserr(default, try_from(char) = from_char_csv_delimiter -> DeserrQueryParamError<InvalidDocumentCsvDelimiter>, error = DeserrQueryParamError<InvalidDocumentCsvDelimiter>)]
     pub csv_delimiter: Option<u8>,
-
-    #[param(example = "custom")]
-    #[deserr(default, error = DeserrQueryParamError<InvalidIndexCustomMetadata>)]
-    pub custom_metadata: Option<String>,
-}
-
-#[derive(Deserialize, Debug, Deserr, IntoParams)]
-#[deserr(error = DeserrQueryParamError, rename_all = camelCase, deny_unknown_fields)]
-#[into_params(parameter_in = Query, rename_all = "camelCase")]
-pub struct CustomMetadataQuery {
-    #[param(example = "custom")]
-    #[deserr(default, error = DeserrQueryParamError<InvalidIndexCustomMetadata>)]
-    pub custom_metadata: Option<String>,
 }
 
 fn from_char_csv_delimiter(
@@ -837,7 +820,6 @@ pub async fn replace_documents(
         body,
         IndexDocumentsMethod::ReplaceDocuments,
         uid,
-        params.custom_metadata,
         dry_run,
         allow_index_creation,
         &req,
@@ -940,7 +922,6 @@ pub async fn update_documents(
         body,
         IndexDocumentsMethod::UpdateDocuments,
         uid,
-        params.custom_metadata,
         dry_run,
         allow_index_creation,
         &req,
@@ -960,13 +941,13 @@ async fn document_addition(
     body: Payload,
     method: IndexDocumentsMethod,
     task_id: Option<TaskId>,
-    custom_metadata: Option<String>,
     dry_run: bool,
     allow_index_creation: bool,
     req: &HttpRequest,
 ) -> Result<SummarizedTaskView, MeilisearchHttpError> {
     let mime_type = extract_mime_type(req)?;
     let network = index_scheduler.network();
+    let origin = check_leader(&req, &network)?;
 
     let format = match (
         mime_type.as_ref().map(|m| (m.type_().as_str(), m.subtype().as_str())),
@@ -1086,9 +1067,7 @@ async fn document_addition(
     };
 
     let scheduler = index_scheduler.clone();
-    let task = match tokio::task::spawn_blocking(move || {
+    let task = match tokio::task::spawn_blocking(move || scheduler.register(task, task_id, dry_run))
-        scheduler.register_with_custom_metadata(task, task_id, custom_metadata, dry_run)
-    })
         .await?
     {
         Ok(task) => task,
@@ -1098,12 +1077,13 @@ async fn document_addition(
         }
     };
 
-    if network.sharding() {
+    if network.sharding {
         if let Some(file) = file {
             proxy(
                 &index_scheduler,
                 &index_uid,
                 req,
+                origin,
                 network,
                 Body::with_ndjson_payload(file),
                 &task,
@@ -1153,7 +1133,7 @@ async fn copy_body_to_file(
 /// Delete a set of documents based on an array of document ids.
 #[utoipa::path(
     post,
-    path = "{indexUid}/documents/delete-batch",
+    path = "{indexUid}/delete-batch",
     tag = "Documents",
     security(("Bearer" = ["documents.delete", "documents.*", "*"])),
     params(
@@ -1184,16 +1164,14 @@ pub async fn delete_documents_batch(
     index_scheduler: GuardedData<ActionPolicy<{ actions::DOCUMENTS_DELETE }>, Data<IndexScheduler>>,
     index_uid: web::Path<String>,
     body: web::Json<Vec<Value>>,
-    params: AwebQueryParameter<CustomMetadataQuery, DeserrQueryParamError>,
     req: HttpRequest,
     opt: web::Data<Opt>,
     analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     debug!(parameters = ?body, "Delete documents by batch");
-    let CustomMetadataQuery { custom_metadata } = params.into_inner();
-
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
     let network = index_scheduler.network();
+    let origin = check_leader(&req, &network)?;
 
     analytics.publish(
         DocumentsDeletionAggregator {
@@ -1216,14 +1194,12 @@ pub async fn delete_documents_batch(
     let dry_run = is_dry_run(&req, &opt)?;
     let task = {
         let index_scheduler = index_scheduler.clone();
-        tokio::task::spawn_blocking(move || {
+        tokio::task::spawn_blocking(move || index_scheduler.register(task, uid, dry_run)).await??
-            index_scheduler.register_with_custom_metadata(task, uid, custom_metadata, dry_run)
-        })
-        .await??
     };
 
-    if network.sharding() && !dry_run {
+    if network.sharding && !dry_run {
-        proxy(&index_scheduler, &index_uid, &req, network, Body::Inline(body), &task).await?;
+        proxy(&index_scheduler, &index_uid, &req, origin, network, Body::Inline(body), &task)
+            .await?;
     }
 
     let task: SummarizedTaskView = task.into();
@@ -1273,19 +1249,17 @@ pub struct DocumentDeletionByFilter {
 pub async fn delete_documents_by_filter(
     index_scheduler: GuardedData<ActionPolicy<{ actions::DOCUMENTS_DELETE }>, Data<IndexScheduler>>,
     index_uid: web::Path<String>,
-    params: AwebQueryParameter<CustomMetadataQuery, DeserrQueryParamError>,
     body: AwebJson<DocumentDeletionByFilter, DeserrJsonError>,
     req: HttpRequest,
     opt: web::Data<Opt>,
     analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     debug!(parameters = ?body, "Delete documents by filter");
-    let CustomMetadataQuery { custom_metadata } = params.into_inner();
-
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
     let index_uid = index_uid.into_inner();
     let filter = body.into_inner();
     let network = index_scheduler.network();
+    let origin = check_leader(&req, &network)?;
 
     analytics.publish(
         DocumentsDeletionAggregator {
@@ -1314,14 +1288,12 @@ pub async fn delete_documents_by_filter(
     let dry_run = is_dry_run(&req, &opt)?;
     let task = {
         let index_scheduler = index_scheduler.clone();
-        tokio::task::spawn_blocking(move || {
+        tokio::task::spawn_blocking(move || index_scheduler.register(task, uid, dry_run)).await??
-            index_scheduler.register_with_custom_metadata(task, uid, custom_metadata, dry_run)
-        })
-        .await??
     };
 
-    if network.sharding() && !dry_run {
+    if network.sharding && !dry_run {
-        proxy(&index_scheduler, &index_uid, &req, network, Body::Inline(filter), &task).await?;
+        proxy(&index_scheduler, &index_uid, &req, origin, network, Body::Inline(filter), &task)
+            .await?;
     }
 
     let task: SummarizedTaskView = task.into();
@@ -1407,40 +1379,39 @@ impl Aggregate for EditDocumentsByFunctionAggregator {
 pub async fn edit_documents_by_function(
     index_scheduler: GuardedData<ActionPolicy<{ actions::DOCUMENTS_ALL }>, Data<IndexScheduler>>,
     index_uid: web::Path<String>,
-    params: AwebQueryParameter<CustomMetadataQuery, DeserrQueryParamError>,
+    params: AwebJson<DocumentEditionByFunction, DeserrJsonError>,
-    body: AwebJson<DocumentEditionByFunction, DeserrJsonError>,
     req: HttpRequest,
     opt: web::Data<Opt>,
     analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
-    debug!(parameters = ?body, "Edit documents by function");
+    debug!(parameters = ?params, "Edit documents by function");
-    let CustomMetadataQuery { custom_metadata } = params.into_inner();
 
     index_scheduler
         .features()
         .check_edit_documents_by_function("Using the documents edit route")?;
 
     let network = index_scheduler.network();
+    let origin = check_leader(&req, &network)?;
 
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
     let index_uid = index_uid.into_inner();
-    let body = body.into_inner();
+    let params = params.into_inner();
 
     analytics.publish(
         EditDocumentsByFunctionAggregator {
-            filtered: body.filter.is_some(),
+            filtered: params.filter.is_some(),
-            with_context: body.context.is_some(),
+            with_context: params.context.is_some(),
             index_creation: index_scheduler.index(&index_uid).is_err(),
         },
         &req,
     );
 
     let engine = milli::rhai::Engine::new();
-    if let Err(e) = engine.compile(&body.function) {
+    if let Err(e) = engine.compile(&params.function) {
         return Err(ResponseError::from_msg(e.to_string(), Code::BadRequest));
     }
 
-    if let Some(ref filter) = body.filter {
+    if let Some(ref filter) = params.filter {
         // we ensure the filter is well formed before enqueuing it
         crate::search::parse_filter(
             filter,
@@ -1451,8 +1422,8 @@ pub async fn edit_documents_by_function(
     }
     let task = KindWithContent::DocumentEdition {
         index_uid: index_uid.clone(),
-        filter_expr: body.filter.clone(),
+        filter_expr: params.filter.clone(),
-        context: match body.context.clone() {
+        context: match params.context.clone() {
             Some(Value::Object(m)) => Some(m),
             None => None,
             _ => {
@@ -1462,21 +1433,19 @@ pub async fn edit_documents_by_function(
                 ))
             }
         },
-        function: body.function.clone(),
+        function: params.function.clone(),
     };
 
     let uid = get_task_id(&req, &opt)?;
     let dry_run = is_dry_run(&req, &opt)?;
     let task = {
         let index_scheduler = index_scheduler.clone();
-        tokio::task::spawn_blocking(move || {
+        tokio::task::spawn_blocking(move || index_scheduler.register(task, uid, dry_run)).await??
-            index_scheduler.register_with_custom_metadata(task, uid, custom_metadata, dry_run)
-        })
-        .await??
     };
 
-    if network.sharding() && !dry_run {
+    if network.sharding && !dry_run {
-        proxy(&index_scheduler, &index_uid, &req, network, Body::Inline(body), &task).await?;
+        proxy(&index_scheduler, &index_uid, &req, origin, network, Body::Inline(params), &task)
+            .await?;
     }
 
     let task: SummarizedTaskView = task.into();
@@ -1517,14 +1486,13 @@ pub async fn edit_documents_by_function(
 pub async fn clear_all_documents(
     index_scheduler: GuardedData<ActionPolicy<{ actions::DOCUMENTS_DELETE }>, Data<IndexScheduler>>,
     index_uid: web::Path<String>,
-    params: AwebQueryParameter<CustomMetadataQuery, DeserrQueryParamError>,
     req: HttpRequest,
     opt: web::Data<Opt>,
     analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
     let network = index_scheduler.network();
-    let CustomMetadataQuery { custom_metadata } = params.into_inner();
+    let origin = check_leader(&req, &network)?;
 
     analytics.publish(
         DocumentsDeletionAggregator {
@@ -1543,14 +1511,11 @@ pub async fn clear_all_documents(
     let task = {
         let index_scheduler = index_scheduler.clone();
 
-        tokio::task::spawn_blocking(move || {
+        tokio::task::spawn_blocking(move || index_scheduler.register(task, uid, dry_run)).await??
-            index_scheduler.register_with_custom_metadata(task, uid, custom_metadata, dry_run)
-        })
-        .await??
     };
 
-    if network.sharding() && !dry_run {
+    if network.sharding && !dry_run {
-        proxy(&index_scheduler, &index_uid, &req, network, Body::none(), &task).await?;
+        proxy(&index_scheduler, &index_uid, &req, origin, network, Body::none(), &task).await?;
     }
 
     let task: SummarizedTaskView = task.into();

crates/meilisearch/src/routes/indexes/enterprise_edition/proxy.rs

@@ -38,6 +38,27 @@ impl Body<()> {
     }
 }
 
+pub fn check_leader(
+    req: &HttpRequest,
+    network: &meilisearch_types::enterprise_edition::network::DbNetwork,
+) -> Result<Option<Origin>, MeilisearchHttpError> {
+    match origin_from_req(req)? {
+        Some(origin) => Ok(Some(origin)),
+        None => {
+            let this = network
+                .local
+                .as_deref()
+                .expect("inconsistent `network.sharding` and `network.self`");
+
+            let is_leader = this == todo!();
+            if !is_leader {
+                return Err(MeilisearchHttpError::NotLeader { leader: todo!() });
+            }
+            Ok(None)
+        }
+    }
+}
+
 /// If necessary, proxies the passed request to the network and update the task description.
 ///
 /// This function reads the custom headers from the request to determine if must proxy the request or if the request
@@ -52,11 +73,12 @@ pub async fn proxy<T: serde::Serialize>(
     index_scheduler: &IndexScheduler,
     index_uid: &str,
     req: &HttpRequest,
-    network: meilisearch_types::network::Network,
+    origin: Option<Origin>,
+    network: meilisearch_types::enterprise_edition::network::DbNetwork,
     body: Body<T>,
     task: &meilisearch_types::tasks::Task,
 ) -> Result<(), MeilisearchHttpError> {
-    match origin_from_req(req)? {
+    match origin {
         Some(origin) => {
             index_scheduler.set_task_network(task.uid, TaskNetwork::Origin { origin })?
         }

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

@@ -260,7 +260,7 @@ pub async fn search(
     }
 
     let index = index_scheduler.index(&index_uid)?;
-    let search_kind = search_kind(&search_query, &index_scheduler, index_uid.to_string(), &index)?;
+    let search_kind = search_kind(&search_query, &index_scheduler, &index_uid, &index)?;
     let permit = search_queue.try_get_search_permit().await?;
     let search_result = tokio::task::spawn_blocking(move || {
         perform_facet_search(
@@ -343,7 +343,6 @@ impl From<FacetSearchQuery> for SearchQuery {
             hybrid,
             ranking_score_threshold,
             locales,
-            personalize: None,
         }
     }
 }

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

@@ -28,18 +28,8 @@ use crate::extractors::sequential_extractor::SeqHandler;
 use crate::routes::is_dry_run;
 use crate::Opt;
 
-pub mod compact;
 pub mod documents;
-
-#[cfg(not(feature = "enterprise"))]
-mod community_edition;
-#[cfg(feature = "enterprise")]
 mod enterprise_edition;
-#[cfg(not(feature = "enterprise"))]
-use community_edition as current_edition;
-#[cfg(feature = "enterprise")]
-use enterprise_edition as current_edition;
-
 pub mod facet_search;
 pub mod search;
 mod search_analytics;
@@ -50,7 +40,7 @@ mod settings_analytics;
 pub mod similar;
 mod similar_analytics;
 
-pub use current_edition::proxy::{PROXY_ORIGIN_REMOTE_HEADER, PROXY_ORIGIN_TASK_UID_HEADER};
+pub use enterprise_edition::proxy::{PROXY_ORIGIN_REMOTE_HEADER, PROXY_ORIGIN_TASK_UID_HEADER};
 
 #[derive(OpenApi)]
 #[openapi(
@@ -59,9 +49,8 @@ pub use current_edition::proxy::{PROXY_ORIGIN_REMOTE_HEADER, PROXY_ORIGIN_TASK_U
         (path = "/", api = facet_search::FacetSearchApi),
         (path = "/", api = similar::SimilarApi),
         (path = "/", api = settings::SettingsApi),
-        (path = "/", api = compact::CompactApi),
     ),
-    paths(list_indexes, create_index, get_index, update_index, delete_index, get_index_stats, compact::compact),
+    paths(list_indexes, create_index, get_index, update_index, delete_index, get_index_stats),
     tags(
         (
             name = "Indexes",
@@ -91,8 +80,7 @@ pub fn configure(cfg: &mut web::ServiceConfig) {
             .service(web::scope("/search").configure(search::configure))
             .service(web::scope("/facet-search").configure(facet_search::configure))
             .service(web::scope("/similar").configure(similar::configure))
-            .service(web::scope("/settings").configure(settings::configure))
+            .service(web::scope("/settings").configure(settings::configure)),
-            .service(web::scope("/compact").configure(compact::configure)),
     );
 }
 

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

@@ -13,7 +13,6 @@ use meilisearch_types::serde_cs::vec::CS;
 use serde_json::Value;
 use tracing::debug;
 use utoipa::{IntoParams, OpenApi};
-use uuid::Uuid;
 
 use crate::analytics::Analytics;
 use crate::error::MeilisearchHttpError;
@@ -22,12 +21,11 @@ use crate::extractors::authentication::GuardedData;
 use crate::extractors::sequential_extractor::SeqHandler;
 use crate::metrics::MEILISEARCH_DEGRADED_SEARCH_REQUESTS;
 use crate::routes::indexes::search_analytics::{SearchAggregator, SearchGET, SearchPOST};
-use crate::routes::parse_include_metadata_header;
 use crate::search::{
-    add_search_rules, perform_search, HybridQuery, MatchingStrategy, Personalize,
+    add_search_rules, perform_search, HybridQuery, MatchingStrategy, RankingScoreThreshold,
-    RankingScoreThreshold, RetrieveVectors, SearchKind, SearchParams, SearchQuery, SearchResult,
+    RetrieveVectors, SearchKind, SearchQuery, SearchResult, SemanticRatio, DEFAULT_CROP_LENGTH,
-    SemanticRatio, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG,
+    DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG,
-    DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET, DEFAULT_SEMANTIC_RATIO,
+    DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET, DEFAULT_SEMANTIC_RATIO,
 };
 use crate::search_queue::SearchQueue;
 
@@ -134,8 +132,6 @@ pub struct SearchQueryGet {
     #[deserr(default, error = DeserrQueryParamError<InvalidSearchLocales>)]
     #[param(value_type = Vec<Locale>, explode = false)]
     pub locales: Option<CS<Locale>>,
-    #[deserr(default, error = DeserrQueryParamError<InvalidSearchPersonalizeUserContext>)]
-    pub personalize_user_context: Option<String>,
 }
 
 #[derive(Debug, Clone, Copy, PartialEq, deserr::Deserr)]
@@ -207,9 +203,6 @@ impl TryFrom<SearchQueryGet> for SearchQuery {
             ));
         }
 
-        let personalize =
-            other.personalize_user_context.map(|user_context| Personalize { user_context });
-
         Ok(Self {
             q: other.q,
             // `media` not supported for `GET`
@@ -239,7 +232,6 @@ impl TryFrom<SearchQueryGet> for SearchQuery {
             hybrid,
             ranking_score_threshold: other.ranking_score_threshold.map(|o| o.0),
             locales: other.locales.map(|o| o.into_iter().collect()),
-            personalize,
         })
     }
 }
@@ -328,14 +320,12 @@ pub fn fix_sort_query_parameters(sort_query: &str) -> Vec<String> {
 pub async fn search_with_url_query(
     index_scheduler: GuardedData<ActionPolicy<{ actions::SEARCH }>, Data<IndexScheduler>>,
     search_queue: web::Data<SearchQueue>,
-    personalization_service: web::Data<crate::personalization::PersonalizationService>,
     index_uid: web::Path<String>,
     params: AwebQueryParameter<SearchQueryGet, DeserrQueryParamError>,
     req: HttpRequest,
     analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
-    let request_uid = Uuid::now_v7();
+    debug!(parameters = ?params, "Search get");
-    debug!(request_uid = ?request_uid, parameters = ?params, "Search get");
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
 
     let mut query: SearchQuery = params.into_inner().try_into()?;
@@ -349,56 +339,30 @@ pub async fn search_with_url_query(
 
     let index = index_scheduler.index(&index_uid)?;
 
-    // Extract personalization and query string before moving query
+    let search_kind = search_kind(&query, index_scheduler.get_ref(), &index_uid, &index)?;
-    let personalize = query.personalize.take();
-
-    let search_kind =
-        search_kind(&query, index_scheduler.get_ref(), index_uid.to_string(), &index)?;
     let retrieve_vector = RetrieveVectors::new(query.retrieve_vectors);
-
-    // Save the query string for personalization if requested
-    let personalize_query = personalize.is_some().then(|| query.q.clone()).flatten();
-
     let permit = search_queue.try_get_search_permit().await?;
-    let include_metadata = parse_include_metadata_header(&req);
-
     let search_result = tokio::task::spawn_blocking(move || {
         perform_search(
-            SearchParams {
+            &index_uid,
-                index_uid: index_uid.to_string(),
+            &index,
             query,
             search_kind,
-                retrieve_vectors: retrieve_vector,
+            retrieve_vector,
-                features: index_scheduler.features(),
+            index_scheduler.features(),
-                request_uid,
-                include_metadata,
-            },
-            &index,
         )
     })
     .await;
     permit.drop().await;
     let search_result = search_result?;
-    if let Ok((search_result, _)) = search_result.as_ref() {
+    if let Ok(ref search_result) = search_result {
         aggregate.succeed(search_result);
     }
     analytics.publish(aggregate, &req);
 
-    let (mut search_result, time_budget) = search_result?;
+    let search_result = search_result?;
 
-    // Apply personalization if requested
+    debug!(returns = ?search_result, "Search get");
-    if let Some(personalize) = personalize.as_ref() {
-        search_result = personalization_service
-            .rerank_search_results(
-                search_result,
-                personalize,
-                personalize_query.as_deref(),
-                time_budget,
-            )
-            .await?;
-    }
-
-    debug!(request_uid = ?request_uid, returns = ?search_result, "Search get");
     Ok(HttpResponse::Ok().json(search_result))
 }
 
@@ -461,17 +425,15 @@ pub async fn search_with_url_query(
 pub async fn search_with_post(
     index_scheduler: GuardedData<ActionPolicy<{ actions::SEARCH }>, Data<IndexScheduler>>,
     search_queue: web::Data<SearchQueue>,
-    personalization_service: web::Data<crate::personalization::PersonalizationService>,
     index_uid: web::Path<String>,
     params: AwebJson<SearchQuery, DeserrJsonError>,
     req: HttpRequest,
     analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
-    let request_uid = Uuid::now_v7();
 
     let mut query = params.into_inner();
-    debug!(request_uid = ?request_uid, parameters = ?query, "Search post");
+    debug!(parameters = ?query, "Search post");
 
     // Tenant token search_rules.
     if let Some(search_rules) = index_scheduler.filters().get_index_search_rules(&index_uid) {
@@ -482,37 +444,24 @@ pub async fn search_with_post(
 
     let index = index_scheduler.index(&index_uid)?;
 
-    // Extract personalization and query string before moving query
+    let search_kind = search_kind(&query, index_scheduler.get_ref(), &index_uid, &index)?;
-    let personalize = query.personalize.take();
-
-    let search_kind =
-        search_kind(&query, index_scheduler.get_ref(), index_uid.to_string(), &index)?;
     let retrieve_vectors = RetrieveVectors::new(query.retrieve_vectors);
 
-    let include_metadata = parse_include_metadata_header(&req);
-
-    // Save the query string for personalization if requested
-    let personalize_query = personalize.is_some().then(|| query.q.clone()).flatten();
-
     let permit = search_queue.try_get_search_permit().await?;
     let search_result = tokio::task::spawn_blocking(move || {
         perform_search(
-            SearchParams {
+            &index_uid,
-                index_uid: index_uid.to_string(),
+            &index,
             query,
             search_kind,
             retrieve_vectors,
-                features: index_scheduler.features(),
+            index_scheduler.features(),
-                request_uid,
-                include_metadata,
-            },
-            &index,
         )
     })
     .await;
     permit.drop().await;
     let search_result = search_result?;
-    if let Ok((ref search_result, _)) = search_result {
+    if let Ok(ref search_result) = search_result {
         aggregate.succeed(search_result);
         if search_result.degraded {
             MEILISEARCH_DEGRADED_SEARCH_REQUESTS.inc();
@@ -520,28 +469,16 @@ pub async fn search_with_post(
     }
     analytics.publish(aggregate, &req);
 
-    let (mut search_result, time_budget) = search_result?;
+    let search_result = search_result?;
 
-    // Apply personalization if requested
+    debug!(returns = ?search_result, "Search post");
-    if let Some(personalize) = personalize.as_ref() {
-        search_result = personalization_service
-            .rerank_search_results(
-                search_result,
-                personalize,
-                personalize_query.as_deref(),
-                time_budget,
-            )
-            .await?;
-    }
-
-    debug!(request_uid = ?request_uid, returns = ?search_result, "Search post");
     Ok(HttpResponse::Ok().json(search_result))
 }
 
 pub fn search_kind(
     query: &SearchQuery,
     index_scheduler: &IndexScheduler,
-    index_uid: String,
+    index_uid: &str,
     index: &milli::Index,
 ) -> Result<SearchKind, ResponseError> {
     let is_placeholder_query =

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

@@ -7,7 +7,6 @@ use serde_json::{json, Value};
 
 use crate::aggregate_methods;
 use crate::analytics::{Aggregate, AggregateMethod};
-use crate::metrics::MEILISEARCH_PERSONALIZED_SEARCH_REQUESTS;
 use crate::search::{
     SearchQuery, SearchResult, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER,
     DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT,
@@ -96,9 +95,6 @@ pub struct SearchAggregator<Method: AggregateMethod> {
     show_ranking_score_details: bool,
     ranking_score_threshold: bool,
 
-    // personalization
-    total_personalized: usize,
-
     marker: std::marker::PhantomData<Method>,
 }
 
@@ -133,7 +129,6 @@ impl<Method: AggregateMethod> SearchAggregator<Method> {
             hybrid,
             ranking_score_threshold,
             locales,
-            personalize,
         } = query;
 
         let mut ret = Self::default();
@@ -209,12 +204,6 @@ impl<Method: AggregateMethod> SearchAggregator<Method> {
             ret.locales = locales.iter().copied().collect();
         }
 
-        // personalization
-        if personalize.is_some() {
-            ret.total_personalized = 1;
-            MEILISEARCH_PERSONALIZED_SEARCH_REQUESTS.inc();
-        }
-
         ret.highlight_pre_tag = *highlight_pre_tag != DEFAULT_HIGHLIGHT_PRE_TAG();
         ret.highlight_post_tag = *highlight_post_tag != DEFAULT_HIGHLIGHT_POST_TAG();
         ret.crop_marker = *crop_marker != DEFAULT_CROP_MARKER();
@@ -245,8 +234,6 @@ impl<Method: AggregateMethod> SearchAggregator<Method> {
             facet_stats: _,
             degraded,
             used_negative_operator,
-            request_uid: _,
-            metadata: _,
         } = result;
 
         self.total_succeeded = self.total_succeeded.saturating_add(1);
@@ -307,7 +294,6 @@ impl<Method: AggregateMethod> Aggregate for SearchAggregator<Method> {
             total_used_negative_operator,
             ranking_score_threshold,
             mut locales,
-            total_personalized,
             marker: _,
         } = *new;
 
@@ -393,9 +379,6 @@ impl<Method: AggregateMethod> Aggregate for SearchAggregator<Method> {
         // locales
         self.locales.append(&mut locales);
 
-        // personalization
-        self.total_personalized = self.total_personalized.saturating_add(total_personalized);
-
         self
     }
 
@@ -441,7 +424,6 @@ impl<Method: AggregateMethod> Aggregate for SearchAggregator<Method> {
             total_used_negative_operator,
             ranking_score_threshold,
             locales,
-            total_personalized,
             marker: _,
         } = *self;
 
@@ -515,9 +497,6 @@ impl<Method: AggregateMethod> Aggregate for SearchAggregator<Method> {
                 "show_ranking_score_details": show_ranking_score_details,
                 "ranking_score_threshold": ranking_score_threshold,
             },
-            "personalization": {
-                "total_personalized": total_personalized,
-            },
         })
     }
 }