WIP missing DeCboRoaringBitmapCodec::bytes_encode implem

Add support for conditional compilation of the EE

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

@@ -14,10 +14,105 @@ on:
   workflow_dispatch:
 
 jobs:
-  docker:
-    runs-on: docker
+  build:
+    runs-on: ${{ matrix.runner }}
+
+    strategy:
+      matrix:
+        platform: [amd64, arm64]
+        edition: [community, enterprise]
+        include:
+          - platform: amd64
+            runner: ubuntu-24.04
+          - platform: arm64
+            runner: ubuntu-24.04-arm
+          - edition: community
+            registry: getmeili/meilisearch
+            feature-flag: ""
+          - edition: enterprise
+            registry: getmeili/meilisearch-enterprise
+            feature-flag: "--features enterprise"
+
+    permissions: {}
+    steps:
+      - uses: actions/checkout@v5
+
+      - name: Prepare
+        run: |
+          platform=linux/${{ 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
 
@@ -58,26 +153,30 @@ jobs:
 
           echo "date=$commit_date" >> $GITHUB_OUTPUT
 
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-
       - name: Install cosign
         uses: sigstore/cosign-installer@d7543c93d881b35a8faa02e8e3605f69b7a1ce62 # tag=v3.10.0
 
+      - name: Download digests
+        uses: actions/download-artifact@v4
+        with:
+          path: ${{ runner.temp }}/digests
+          pattern: digests-${{ matrix.edition }}-*
+          merge-multiple: true
+
       - name: Login to Docker Hub
         uses: docker/login-action@v3
         with:
           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: getmeili/meilisearch
+          images: ${{ matrix.registry }}
           # Prevent `latest` to be updated for each new tag pushed.
           # We need latest and `vX.Y` tags to only be pushed for the stable Meilisearch releases.
           flavor: latest=false
@@ -88,26 +187,24 @@ jobs:
             type=semver,pattern=v{{major}},enable=${{ 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: Build and push
-        uses: docker/build-push-action@v6
-        id: build-and-push
-        with:
-          push: true
-          platforms: linux/amd64,linux/arm64
-          tags: ${{ steps.meta.outputs.tags }}
-          build-args: |
-            COMMIT_SHA=${{ github.sha }}
-            COMMIT_DATE=${{ steps.build-metadata.outputs.date }}
-            GIT_TAG=${{ github.ref_name }}
+      - name: Create manifest list and push
+        working-directory: ${{ runner.temp }}/digests
+        run: |
+          docker buildx imagetools create $(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "$DOCKER_METADATA_OUTPUT_JSON") \
+            $(printf '${{ matrix.registry }}@sha256:%s ' *)
+
+      - name: Inspect image to fetch digest to sign
+        run: |
+          digest=$(docker buildx imagetools inspect --format='{{ json .Manifest }}' ${{ matrix.registry }}:${{ steps.meta.outputs.version }} | jq -r '.digest')
+          echo "DIGEST=${digest}" >> $GITHUB_ENV
 
       - 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}@${DIGEST} "
+            images+="${tag}@${{ env.DIGEST }} "
           done
           cosign sign --yes ${images}
 
@@ -121,22 +218,3 @@ jobs:
           repository: meilisearch/meilisearch-cloud
           event-type: cloud-docker-build
           client-payload: '{ "meilisearch_version": "${{ github.ref_name }}", "stable": "${{ steps.check-tag-format.outputs.stable }}" }'
-
-      # Send notification to Swarmia to notify of a deployment: https://app.swarmia.com
-      # - name: 'Setup jq'
-      #   uses: dcarbone/install-jq-action
-      # - name: Send deployment to Swarmia
-      #   if: github.event_name == 'push' && success()
-      #   run: |
-      #     JSON_STRING=$( jq --null-input --compact-output \
-      #     --arg version "${{ github.ref_name }}" \
-      #     --arg appName "meilisearch" \
-      #     --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

@@ -32,157 +32,61 @@ jobs:
         if: github.event_name == 'release' && steps.check-tag-format.outputs.stable == 'true'
         run: bash .github/scripts/check-release.sh
 
-  publish-linux:
-    name: Publish binary for Linux
-    runs-on: ubuntu-latest
-    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
-      # No need to upload binaries for dry run (cron or workflow_dispatch)
-      - 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/meilisearch
-          asset_name: meilisearch-linux-amd64
-          tag: ${{ github.ref }}
-
-  publish-macos-windows:
-    name: Publish binary for ${{ matrix.os }}
+  publish-binaries:
+    name: Publish binary for ${{ matrix.release }} ${{ matrix.edition }} edition
     runs-on: ${{ matrix.os }}
-    needs: check-version
     strategy:
       fail-fast: false
       matrix:
-        os: [macos-13, windows-2022]
+        edition: [community, enterprise]
+        release:
+          [macos-amd64, macos-aarch64, windows, linux-amd64, linux-aarch64]
         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
+          - 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: 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
     steps:
       - uses: actions/checkout@v5
       - uses: dtolnay/rust-toolchain@1.89
       - name: Build
-        run: cargo build --release --locked
+        run: cargo build --release --locked ${{ matrix.feature-flag }} ${{ matrix.extra-args }}
       # No need to upload binaries for dry run (cron or workflow_dispatch)
       - 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 or workflow_dispatch)
-        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 or workflow_dispatch)
-        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: ${{ matrix.asset_name }}
+          file: target/${{ matrix.binary_path }}
+          asset_name: meilisearch-${{ matrix.edition-suffix }}${{ matrix.asset_name }}
           tag: ${{ github.ref }}
 
   publish-openapi-file:

.github/workflows/sdks-tests.yml

@@ -68,7 +68,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
+        image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -92,7 +92,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
+        image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -122,7 +122,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
+        image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -149,7 +149,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
+        image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -184,7 +184,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
+        image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -213,7 +213,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
+        image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -238,7 +238,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
+        image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -263,7 +263,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
+        image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -284,7 +284,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
+        image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -307,7 +307,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
+        image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -338,7 +338,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
+        image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -370,7 +370,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
+        image: getmeili/meilisearch-enterprise:${{ 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

@@ -15,8 +15,12 @@ env:
 
 jobs:
   test-linux:
-    name: Tests on ubuntu-22.04
-    runs-on: ubuntu-latest
+    name: Tests on Ubuntu
+    runs-on: ${{ matrix.runner }}
+    strategy:
+      matrix:
+        runner: [ubuntu-24.04, ubuntu-24.04-arm]
+        features: ["", "--features enterprise"]
     container:
       # Use ubuntu-22.04 to compile with glibc 2.35
       image: ubuntu:22.04
@@ -39,7 +43,7 @@ jobs:
         uses: actions-rs/cargo@v1
         with:
           command: test
-          args: --locked --release --all
+          args: --locked --release --all ${{ matrix.features }}
 
   test-others:
     name: Tests on ${{ matrix.os }}
@@ -47,7 +51,8 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        os: [macos-13, windows-2022]
+        os: [macos-14, windows-2022]
+        features: ["", "--features enterprise"]
     steps:
       - uses: actions/checkout@v5
       - name: Cache dependencies
@@ -62,7 +67,7 @@ jobs:
         uses: actions-rs/cargo@v1
         with:
           command: test
-          args: --locked --release --all
+          args: --locked --release --all ${{ matrix.features }}
 
   test-all-features:
     name: Tests almost all features
@@ -88,6 +93,9 @@ jobs:
   ollama-ubuntu:
     name: Test with Ollama
     runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        features: ["", "--features enterprise"]
     env:
       MEILI_TEST_OLLAMA_SERVER: "http://localhost:11434"
     steps:
@@ -115,7 +123,7 @@ jobs:
         uses: actions-rs/cargo@v1
         with:
           command: test
-          args: --locked --release --all --features test-ollama ollama
+          args: --locked --release --all --features test-ollama ollama ${{ matrix.features }}
 
   test-disabled-tokenization:
     name: Test disabled tokenization
@@ -143,16 +151,12 @@ jobs:
   # We run tests in debug also, to make sure that the debug_assertions are hit
   test-debug:
     name: Run tests in debug
-    runs-on: ubuntu-latest
-    container:
-      # Use ubuntu-22.04 to compile with glibc 2.35
-      image: ubuntu:22.04
+    runs-on: ubuntu-22.04
+    strategy:
+      matrix:
+        features: ["", "--features enterprise"]
     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: Cache dependencies
         uses: Swatinem/rust-cache@v2.8.0
@@ -160,11 +164,14 @@ jobs:
         uses: actions-rs/cargo@v1
         with:
           command: test
-          args: --locked --all
+          args: --locked --all ${{ matrix.features }}
 
   clippy:
     name: Run Clippy
     runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        features: ["", "--features enterprise"]
     steps:
       - uses: actions/checkout@v5
       - uses: dtolnay/rust-toolchain@1.89
@@ -177,7 +184,7 @@ jobs:
         uses: actions-rs/cargo@v1
         with:
           command: clippy
-          args: --all-targets -- --deny warnings
+          args: --all-targets ${{ matrix.features }} -- --deny warnings
 
   fmt:
     name: Run Rustfmt

Cargo.toml

@@ -23,7 +23,7 @@ members = [
 ]
 
 [workspace.package]
-version = "1.24.0"
+version = "1.27.0"
 authors = [
     "Quentin de Quelen <quentin@dequelen.me>",
     "Clément Renault <clement@meilisearch.com>",
@@ -50,3 +50,5 @@ opt-level = 3
 opt-level = 3
 [profile.dev.package.roaring]
 opt-level = 3
+[profile.dev.package.gemm-f16]
+opt-level = 3

Cross.toml

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

Dockerfile

@@ -8,16 +8,14 @@ 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="$(apk --print-arch)"; \
-        if [ "$apkArch" = "aarch64" ]; then \
-            export JEMALLOC_SYS_WITH_LG_PAGE=16; \
-        fi && \
-        cargo build --release -p meilisearch -p meilitool
+        cargo build --release -p meilisearch -p meilitool ${EXTRA_ARGS}
 
 # Run
 FROM    alpine:3.22

README.md

@@ -39,6 +39,7 @@
 ## 🖥 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.

crates/benchmarks/Cargo.toml

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

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 = "0.3.41", features = ["parsing"] }
+time = { version = "0.3.44", features = ["parsing"] }
 
 [build-dependencies]
-anyhow = "1.0.98"
+anyhow = "1.0.100"
 vergen-git2 = "1.0.7"

crates/dump/Cargo.toml

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

@@ -96,6 +96,8 @@ 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.
@@ -178,6 +180,7 @@ impl From<Task> for TaskDump {
             started_at: task.started_at,
             finished_at: task.finished_at,
             network: task.network,
+            custom_metadata: task.custom_metadata,
         }
     }
 }
@@ -259,13 +262,13 @@ 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::{Network, Remote};
     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};
@@ -396,6 +399,7 @@ 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,
             ),
@@ -421,6 +425,7 @@ 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(),
@@ -441,6 +446,7 @@ pub(crate) mod test {
                     started_at: None,
                     finished_at: None,
                     network: None,
+                    custom_metadata: None,
                 },
                 None,
             ),

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

@@ -164,6 +164,7 @@ 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::enterprise_edition::network::Network;
+pub type Network = meilisearch_types::network::Network;
 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::Network;
 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};

crates/file-store/Cargo.toml

@@ -11,7 +11,7 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-tempfile = "3.20.0"
-thiserror = "2.0.12"
+tempfile = "3.23.0"
+thiserror = "2.0.17"
 tracing = "0.1.41"
-uuid = { version = "1.17.0", features = ["serde", "v4"] }
+uuid = { version = "1.18.1", 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.get_update_path(uuid);
+        let path = self.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 get_update_path(&self, uuid: Uuid) -> PathBuf {
+    pub fn 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 = "0.6.0", features = ["html_reports"] }
+criterion = { version = "0.7.0", features = ["html_reports"] }
 
 [[bench]]
 name = "benchmarks"

crates/fuzzers/Cargo.toml

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

crates/index-scheduler/Cargo.toml

@@ -11,31 +11,33 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-anyhow = "1.0.98"
+anyhow = "1.0.100"
 bincode = "1.3.3"
 byte-unit = "5.1.6"
-bumpalo = "3.18.1"
+bytes = "1.11.0"
+bumpalo = "3.19.0"
 bumparaw-collections = "0.1.4"
-convert_case = "0.8.0"
-csv = "1.3.1"
+convert_case = "0.9.0"
+csv = "1.4.0"
 derive_builder = "0.20.2"
 dump = { path = "../dump" }
-enum-iterator = "2.1.0"
+enum-iterator = "2.3.0"
 file-store = { path = "../file-store" }
-flate2 = "1.1.2"
-indexmap = "2.9.0"
+flate2 = "1.1.5"
+indexmap = "2.12.0"
 meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
-memmap2 = "0.9.7"
+memmap2 = "0.9.9"
 page_size = "0.6.0"
-rayon = "1.10.0"
+rayon = "1.11.0"
 roaring = { version = "0.10.12", features = ["serde"] }
-serde = { version = "1.0.219", features = ["derive"] }
-serde_json = { version = "1.0.140", features = ["preserve_order"] }
+serde = { version = "1.0.228", features = ["derive"] }
+serde_json = { version = "1.0.145", features = ["preserve_order"] }
+tar = "0.4.44"
 synchronoise = "1.0.1"
-tempfile = "3.20.0"
-thiserror = "2.0.12"
-time = { version = "0.3.41", features = [
+tempfile = "3.23.0"
+thiserror = "2.0.17"
+time = { version = "0.3.44", features = [
     "serde-well-known",
     "formatting",
     "parsing",
@@ -43,8 +45,11 @@ time = { version = "0.3.41", features = [
 ] }
 tracing = "0.1.41"
 ureq = "2.12.1"
-uuid = { version = "1.17.0", features = ["serde", "v4"] }
+uuid = { version = "1.18.1", features = ["serde", "v4"] }
 backoff = "0.4.0"
+reqwest = { version = "0.12.24", features = ["rustls-tls", "http2"], default-features = false }
+rusty-s3 = "0.8.1"
+tokio = { version = "1.48.0", features = ["full"] }
 
 [dev-dependencies]
 big_s = "1.0.2"

crates/index-scheduler/src/dump.rs

@@ -150,6 +150,7 @@ 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,

crates/index-scheduler/src/error.rs

@@ -5,6 +5,7 @@ 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;
@@ -127,6 +128,14 @@ 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)]
@@ -226,6 +235,10 @@ impl Error {
             | Error::TaskCancelationWithEmptyQuery
             | Error::FromRemoteWhenExporting { .. }
             | Error::AbortedTask
+            | Error::S3Error { .. }
+            | Error::S3HttpError(_)
+            | Error::S3XmlError(_)
+            | Error::S3BucketError(_)
             | Error::Dump(_)
             | Error::Heed(_)
             | Error::Milli { .. }
@@ -293,8 +306,14 @@ 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::Network;
 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;

crates/index-scheduler/src/insta_snapshot.rs

@@ -36,6 +36,7 @@ pub fn snapshot_index_scheduler(scheduler: &IndexScheduler) -> String {
         run_loop_iteration: _,
         embedders: _,
         chat_settings: _,
+        runtime: _,
     } = scheduler;
 
     let rtxn = env.read_txn().unwrap();
@@ -231,6 +232,7 @@ pub fn snapshot_task(task: &Task) -> String {
         status,
         kind,
         network,
+        custom_metadata,
     } = task;
     snap.push('{');
     snap.push_str(&format!("uid: {uid}, "));
@@ -251,6 +253,9 @@ 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

crates/index-scheduler/src/lib.rs

@@ -54,7 +54,6 @@ pub use features::RoFeatures;
 use flate2::bufread::GzEncoder;
 use flate2::Compression;
 use meilisearch_types::batches::Batch;
-use meilisearch_types::enterprise_edition::network::Network;
 use meilisearch_types::features::{
     ChatCompletionSettings, InstanceTogglableFeatures, RuntimeTogglableFeatures,
 };
@@ -67,6 +66,7 @@ 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};
@@ -216,6 +216,9 @@ pub struct IndexScheduler {
     /// A counter that is incremented before every call to [`tick`](IndexScheduler::tick)
     #[cfg(test)]
     run_loop_iteration: Arc<RwLock<usize>>,
+
+    /// The tokio runtime used for asynchronous tasks.
+    runtime: Option<tokio::runtime::Handle>,
 }
 
 impl IndexScheduler {
@@ -242,6 +245,7 @@ impl IndexScheduler {
             run_loop_iteration: self.run_loop_iteration.clone(),
             features: self.features.clone(),
             chat_settings: self.chat_settings,
+            runtime: self.runtime.clone(),
         }
     }
 
@@ -255,13 +259,23 @@ 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),
-        #[cfg(test)] test_breakpoint_sdr: crossbeam_channel::Sender<(test_utils::Breakpoint, bool)>,
-        #[cfg(test)] planned_failures: Vec<(usize, test_utils::FailureLocation)>,
+        runtime: Option<tokio::runtime::Handle>,
+    ) -> Result<Self> {
+        let this = Self::new_without_run(options, auth_env, from_db_version, runtime)?;
+
+        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)?;
@@ -316,8 +330,7 @@ impl IndexScheduler {
 
         wtxn.commit()?;
 
-        // allow unreachable_code to get rids of the warning in the case of a test build.
-        let this = Self {
+        Ok(Self {
             processing_tasks: Arc::new(RwLock::new(ProcessingTasks::new())),
             version,
             queue,
@@ -333,15 +346,32 @@ impl IndexScheduler {
             webhooks: Arc::new(webhooks),
             embedders: Default::default(),
 
-            #[cfg(test)]
-            test_breakpoint_sdr,
-            #[cfg(test)]
-            planned_failures,
+            #[cfg(test)] // Will be replaced in `new_tests` in test environments
+            test_breakpoint_sdr: crossbeam_channel::bounded(0).0,
+            #[cfg(test)] // Will be replaced in `new_tests` in test environments
+            planned_failures: Default::default(),
             #[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)
@@ -726,6 +756,19 @@ 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())
@@ -736,7 +779,7 @@ impl IndexScheduler {
         }
 
         let mut wtxn = self.env.write_txn()?;
-        let task = self.queue.register(&mut wtxn, &kind, task_id, dry_run)?;
+        let task = self.queue.register(&mut wtxn, &kind, task_id, custom_metadata, dry_run)?;
 
         // If the registered task is a task cancelation
         // we inform the processing tasks to stop (if necessary).

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

@@ -257,6 +257,7 @@ 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)?;
@@ -280,6 +281,7 @@ 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.
@@ -344,6 +346,7 @@ impl Queue {
                 tasks: to_delete,
             },
             None,
+            None,
             false,
         )?;
 

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

@@ -25,6 +25,7 @@ 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;
@@ -87,11 +88,14 @@ 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) -> Scheduler {
-        Scheduler {
+    pub(crate) fn private_clone(&self) -> Self {
+        Self {
             must_stop_processing: self.must_stop_processing.clone(),
             wake_up: self.wake_up.clone(),
             autobatching_enabled: self.autobatching_enabled,
@@ -103,23 +107,52 @@ 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: options.autobatching_enabled,
-            max_number_of_batched_tasks: options.max_number_of_batched_tasks,
-            batched_tasks_size_limit: options.batched_tasks_size_limit,
-            dumps_path: options.dumps_path.clone(),
-            snapshots_path: options.snapshots_path.clone(),
+            autobatching_enabled: *autobatching_enabled,
+            max_number_of_batched_tasks: *max_number_of_batched_tasks,
+            batched_tasks_size_limit: *batched_tasks_size_limit,
+            dumps_path: dumps_path.clone(),
+            snapshots_path: snapshots_path.clone(),
             auth_env,
-            version_file_path: options.version_file_path.clone(),
-            embedding_cache_cap: options.embedding_cache_cap,
-            experimental_no_snapshot_compaction: options.experimental_no_snapshot_compaction,
+            version_file_path: version_file_path.clone(),
+            embedding_cache_cap: *embedding_cache_cap,
+            experimental_no_snapshot_compaction: *experimental_no_snapshot_compaction,
+            s3_snapshot_options: indexer_config.s3_snapshot_options.clone(),
         }
     }
 }

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

@@ -12,6 +12,8 @@ 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`].
@@ -78,10 +80,32 @@ impl IndexScheduler {
     pub(super) fn process_snapshot(
         &self,
         progress: Progress,
-        mut tasks: Vec<Task>,
+        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()?;
 
@@ -128,7 +152,7 @@ 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");
+        let update_files_dir = temp_snapshot_dir.path().join(UPDATE_FILES_DIR_NAME);
         fs::create_dir_all(&update_files_dir)?;
 
         // 2.5 Only copy the update files of the enqueued tasks
@@ -140,7 +164,7 @@ 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.get_update_path(content_uuid);
+                let src = self.queue.file_store.update_path(content_uuid);
                 let dst = update_files_dir.join(content_uuid.to_string());
                 fs::copy(src, dst)?;
             }
@@ -206,4 +230,407 @@ 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: (1, 24, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
+0 {uid: 0, batch_uid: 0, status: succeeded, details: { from: (1, 12, 0), to: (1, 27, 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":"v1.24.0"}, 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.", }
+0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.27.0"}, 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: (1, 24, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
+0 {uid: 0, status: enqueued, details: { from: (1, 12, 0), to: (1, 27, 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: (1, 24, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
+0 {uid: 0, status: enqueued, details: { from: (1, 12, 0), to: (1, 27, 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: (1, 24, 0) }, 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, 27, 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":"v1.24.0"}, 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.", }
+0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.27.0"}, 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: (1, 24, 0) }, 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, 27, 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":"v1.24.0"}, 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.", }
+0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.27.0"}, 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: (1, 24, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
+0 {uid: 0, batch_uid: 0, status: succeeded, details: { from: (1, 12, 0), to: (1, 27, 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":"v1.24.0"}, 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.", }
+0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.27.0"}, 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/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(options, auth_env, version, sender, planned_failures).unwrap();
+            Self::new_test(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

@@ -48,6 +48,9 @@ pub fn upgrade_index_scheduler(
         (1, 22, _) => 0,
         (1, 23, _) => 0,
         (1, 24, _) => 0,
+        (1, 25, _) => 0,
+        (1, 26, _) => 0,
+        (1, 27, _) => 0,
         (major, minor, patch) => {
             if major > current_major
                 || (major == current_major && minor > current_minor)
@@ -98,6 +101,7 @@ pub fn upgrade_index_scheduler(
             status: Status::Enqueued,
             kind: KindWithContent::UpgradeDatabase { from },
             network: None,
+            custom_metadata: None,
         },
     )?;
     wtxn.commit()?;

crates/index-scheduler/src/utils.rs

@@ -379,6 +379,7 @@ impl crate::IndexScheduler {
                 status,
                 kind,
                 network: _,
+                custom_metadata: _,
             } = task;
             assert_eq!(uid, task.uid);
             if task.status != Status::Enqueued {

crates/json-depth-checker/Cargo.toml

@@ -15,7 +15,7 @@ license.workspace = true
 serde_json = "1.0"
 
 [dev-dependencies]
-criterion = "0.6.0"
+criterion = "0.7.0"
 
 [[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 = "0.7.0"
+md5 = "0.8.0"
 once_cell = "1.21"
-regex-lite = "0.1.6"
-uuid = { version = "1.17.0", features = ["v4"] }
+regex-lite = "0.1.8"
+uuid = { version = "1.18.1", features = ["v4"] }

crates/meilisearch-auth/Cargo.toml

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

crates/meilisearch-types/Cargo.toml

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

@@ -0,0 +1,16 @@
+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

@@ -3,21 +3,9 @@
 // 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 milli::update::new::indexer::enterprise_edition::sharding::Shards;
-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,
-}
+use crate::network::Network;
 
 impl Network {
     pub fn shards(&self) -> Option<Shards> {
@@ -34,14 +22,8 @@ impl Network {
             None
         }
     }
-}
 
-#[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>,
+    pub fn sharding(&self) -> bool {
+        self.sharding
+    }
 }

crates/meilisearch-types/src/error.rs

@@ -254,10 +254,12 @@ 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 ;
@@ -315,6 +317,8 @@ 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 ;
@@ -390,6 +394,9 @@ 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 ;
@@ -426,6 +433,7 @@ 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 ;
@@ -679,6 +687,18 @@ 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/lib.rs

@@ -2,10 +2,17 @@
 
 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;
@@ -13,6 +20,7 @@ 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

@@ -0,0 +1,23 @@
+use serde::{Deserialize, Serialize};
+use std::collections::BTreeMap;
+
+#[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

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

crates/meilisearch-types/src/task_view.rs

@@ -55,6 +55,9 @@ 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 {
@@ -73,6 +76,7 @@ impl TaskView {
             started_at: task.started_at,
             finished_at: task.finished_at,
             network: task.network.clone(),
+            custom_metadata: task.custom_metadata.clone(),
         }
     }
 }

crates/meilisearch-types/src/tasks.rs

@@ -45,6 +45,9 @@ 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 {

crates/meilisearch-types/src/webhooks.rs

@@ -11,6 +11,24 @@ 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 = "3.11.0", default-features = false, features = [
+actix-http = { version = "3.11.2", default-features = false, features = [
     "compress-brotli",
     "compress-gzip",
     "rustls-0_23",
 ] }
 actix-utils = "3.0.1"
-actix-web = { version = "4.11.0", default-features = false, features = [
+actix-web = { version = "4.12.0", default-features = false, features = [
     "macros",
     "compress-brotli",
     "compress-gzip",
     "cookies",
     "rustls-0_23",
 ] }
-anyhow = { version = "1.0.98", features = ["backtrace"] }
-bstr = "1.12.0"
+anyhow = { version = "1.0.100", features = ["backtrace"] }
+bstr = "1.12.1"
 byte-unit = { version = "5.1.6", features = ["serde"] }
-bytes = "1.10.1"
-bumpalo = "3.18.1"
-clap = { version = "4.5.40", features = ["derive", "env"] }
+bytes = "1.11.0"
+bumpalo = "3.19.0"
+clap = { version = "4.5.52", features = ["derive", "env"] }
 crossbeam-channel = "0.5.15"
-deserr = { version = "0.6.3", features = ["actix-web"] }
+deserr = { version = "0.6.4", features = ["actix-web"] }
 dump = { path = "../dump" }
 either = "1.15.0"
 file-store = { path = "../file-store" }
-flate2 = "1.1.2"
+flate2 = "1.1.5"
 fst = "0.4.7"
 futures = "0.3.31"
 futures-util = "0.3.31"
 index-scheduler = { path = "../index-scheduler" }
-indexmap = { version = "2.9.0", features = ["serde"] }
-is-terminal = "0.4.16"
+indexmap = { version = "2.12.0", features = ["serde"] }
+is-terminal = "0.4.17"
 itertools = "0.14.0"
 jsonwebtoken = "9.3.1"
 lazy_static = "1.5.0"
 meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
-memmap2 = "0.9.7"
-mimalloc = { version = "0.1.47", default-features = false }
+memmap2 = "0.9.9"
+mimalloc = { version = "0.1.48", default-features = false }
 mime = "0.3.17"
 num_cpus = "1.17.0"
 obkv = "0.3.0"
 once_cell = "1.21.3"
-ordered-float = "5.0.0"
-parking_lot = "0.12.4"
+ordered-float = "5.1.0"
+parking_lot = "0.12.5"
 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 = "1.10.0"
-regex = "1.11.1"
-reqwest = { version = "0.12.20", features = [
+rayon = "1.11.0"
+regex = "1.12.2"
+reqwest = { version = "0.12.24", features = [
     "rustls-tls",
     "json",
 ], default-features = false }
-rustls = { version = "0.23.28", features = ["ring"], default-features = false }
-rustls-pki-types = { version = "1.12.0", features = ["alloc"] }
+rustls = { version = "0.23.35", features = ["ring"], default-features = false }
+rustls-pki-types = { version = "1.13.0", features = ["alloc"] }
 rustls-pemfile = "2.2.0"
 segment = { version = "0.2.6" }
-serde = { version = "1.0.219", features = ["derive"] }
-serde_json = { version = "1.0.140", features = ["preserve_order"] }
+serde = { version = "1.0.228", features = ["derive"] }
+serde_json = { version = "1.0.145", features = ["preserve_order"] }
 sha2 = "0.10.9"
 siphasher = "1.0.1"
 slice-group-by = "0.3.1"
-static-files = { version = "0.2.5", optional = true }
-sysinfo = "0.35.2"
+static-files = { version = "0.3.1", optional = true }
+sysinfo = "0.37.2"
 tar = "0.4.44"
-tempfile = "3.20.0"
-thiserror = "2.0.12"
-time = { version = "0.3.41", features = [
+tempfile = "3.23.0"
+thiserror = "2.0.17"
+time = { version = "0.3.44", features = [
     "serde-well-known",
     "formatting",
     "parsing",
     "macros",
 ] }
-tokio = { version = "1.45.1", features = ["full"] }
-toml = "0.8.23"
-uuid = { version = "1.18.0", features = ["serde", "v4", "v7"] }
+tokio = { version = "1.48.0", features = ["full"] }
+toml = "0.9.8"
+uuid = { version = "1.18.1", features = ["serde", "v4", "v7"] }
 serde_urlencoded = "0.7.1"
 termcolor = "1.4.1"
-url = { version = "2.5.4", features = ["serde"] }
+url = { version = "2.5.7", 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 = "0.7.18"
+tracing-actix-web = "0.7.19"
 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 = "0.24.1", default-features = false }
+actix-web-lab = { version = "0.24.3", 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 = "2.10.0"
-brotli = "8.0.1"
+actix-rt = "2.11.0"
+brotli = "8.0.2"
 # 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 = "0.6.3"
+wiremock = "0.6.5"
 yaup = "0.3.1"
 
 [build-dependencies]
-anyhow = { version = "1.0.98", optional = true }
-cargo_toml = { version = "0.22.1", optional = true }
+anyhow = { version = "1.0.100", optional = true }
+cargo_toml = { version = "0.22.3", optional = true }
 hex = { version = "0.4.3", optional = true }
-reqwest = { version = "0.12.20", features = [
+reqwest = { version = "0.12.24", features = [
     "blocking",
     "rustls-tls",
 ], default-features = false, optional = true }
 sha-1 = { version = "0.10.1", optional = true }
-static-files = { version = "0.2.5", optional = true }
-tempfile = { version = "3.20.0", optional = true }
-zip = { version = "4.1.0", optional = true }
+static-files = { version = "0.3.1", optional = true }
+tempfile = { version = "3.23.0", optional = true }
+zip = { version = "6.0.0", optional = true }
 
 [features]
 default = ["meilisearch-types/all-tokenizations", "mini-dashboard"]
@@ -160,6 +160,7 @@ 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: u64,
+    experimental_limit_batched_tasks_total_size: Option<u64>,
     experimental_network: bool,
     experimental_multimodal: bool,
     experimental_chat_completions: bool,
@@ -208,6 +208,7 @@ struct Infos {
     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,
@@ -217,6 +218,7 @@ 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,
@@ -285,6 +287,8 @@ impl Infos {
             indexer_options,
             config_file_path,
             no_analytics: _,
+            experimental_personalization_api_key,
+            s3_snapshot_options,
         } = options;
 
         let schedule_snapshot = match schedule_snapshot {
@@ -348,13 +352,14 @@ 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.into(),
+                experimental_limit_batched_tasks_total_size.map(|size| size.as_u64()),
             task_queue_webhook: task_webhook_url.is_some(),
             task_webhook_authorization_header: task_webhook_authorization_header.is_some(),
             log_level: log_level.to_string(),
@@ -371,6 +376,7 @@ impl Infos {
             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

@@ -38,6 +38,8 @@ 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,
@@ -137,6 +139,9 @@ impl ErrorCode for MeilisearchHttpError {
             MeilisearchHttpError::InconsistentFacetOrder { .. } => {
                 Code::InvalidMultiSearchFacetOrder
             }
+            MeilisearchHttpError::PersonalizationInFederatedQuery(_) => {
+                Code::InvalidMultiSearchQueryPersonalization
+            }
             MeilisearchHttpError::InconsistentOriginHeaders { .. } => {
                 Code::InconsistentDocumentChangeHeaders
             }

crates/meilisearch/src/lib.rs

@@ -11,6 +11,7 @@ pub mod middleware;
 pub mod option;
 #[cfg(test)]
 mod option_test;
+pub mod personalization;
 pub mod routes;
 pub mod search;
 pub mod search_queue;
@@ -58,6 +59,7 @@ use tracing::{error, info_span};
 use tracing_subscriber::filter::Targets;
 
 use crate::error::MeilisearchHttpError;
+use crate::personalization::PersonalizationService;
 
 /// Default number of simultaneously opened indexes.
 ///
@@ -128,12 +130,8 @@ pub type LogStderrType = tracing_subscriber::filter::Filtered<
 >;
 
 pub fn create_app(
-    index_scheduler: Data<IndexScheduler>,
-    auth_controller: Data<AuthController>,
-    search_queue: Data<SearchQueue>,
+    services: ServicesData,
     opt: Opt,
-    logs: (LogRouteHandle, LogStderrHandle),
-    analytics: Data<Analytics>,
     enable_dashboard: bool,
 ) -> actix_web::App<
     impl ServiceFactory<
@@ -145,17 +143,7 @@ pub fn create_app(
     >,
 > {
     let app = actix_web::App::new()
-        .configure(|s| {
-            configure_data(
-                s,
-                index_scheduler.clone(),
-                auth_controller.clone(),
-                search_queue.clone(),
-                &opt,
-                logs,
-                analytics.clone(),
-            )
-        })
+        .configure(|s| configure_data(s, services, &opt))
         .configure(routes::configure)
         .configure(|s| dashboard(s, enable_dashboard));
 
@@ -216,7 +204,10 @@ enum OnFailure {
     KeepDb,
 }
 
-pub fn setup_meilisearch(opt: &Opt) -> anyhow::Result<(Arc<IndexScheduler>, Arc<AuthController>)> {
+pub fn setup_meilisearch(
+    opt: &Opt,
+    handle: tokio::runtime::Handle,
+) -> anyhow::Result<(Arc<IndexScheduler>, Arc<AuthController>)> {
     let index_scheduler_opt = IndexSchedulerOptions {
         version_file_path: opt.db_path.join(VERSION_FILE_NAME),
         auth_path: opt.db_path.join("auth"),
@@ -230,12 +221,26 @@ pub fn setup_meilisearch(opt: &Opt) -> anyhow::Result<(Arc<IndexScheduler>, Arc<
         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((&opt.indexer_options).try_into()?),
+        indexer_config: Arc::new({
+            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.into(),
+        batched_tasks_size_limit: opt.experimental_limit_batched_tasks_total_size.map_or_else(
+            || {
+                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(),
@@ -256,6 +261,7 @@ pub fn setup_meilisearch(opt: &Opt) -> anyhow::Result<(Arc<IndexScheduler>, Arc<
                     index_scheduler_opt,
                     OnFailure::RemoveDb,
                     binary_version, // the db is empty
+                    handle,
                 )?,
                 Err(e) => {
                     std::fs::remove_dir_all(&opt.db_path)?;
@@ -273,7 +279,7 @@ pub fn setup_meilisearch(opt: &Opt) -> anyhow::Result<(Arc<IndexScheduler>, Arc<
             bail!("snapshot doesn't exist at {}", snapshot_path.display())
         // the snapshot and the db exist, and we can ignore the snapshot because of the ignore_snapshot_if_db_exists flag
         } else {
-            open_or_create_database(opt, index_scheduler_opt, empty_db, binary_version)?
+            open_or_create_database(opt, index_scheduler_opt, empty_db, binary_version, handle)?
         }
     } else if let Some(ref path) = opt.import_dump {
         let src_path_exists = path.exists();
@@ -284,6 +290,7 @@ pub fn setup_meilisearch(opt: &Opt) -> anyhow::Result<(Arc<IndexScheduler>, Arc<
                 index_scheduler_opt,
                 OnFailure::RemoveDb,
                 binary_version, // the db is empty
+                handle,
             )?;
             match import_dump(&opt.db_path, path, &mut index_scheduler, &mut auth_controller) {
                 Ok(()) => (index_scheduler, auth_controller),
@@ -304,10 +311,10 @@ pub fn setup_meilisearch(opt: &Opt) -> anyhow::Result<(Arc<IndexScheduler>, Arc<
         // the dump and the db exist and we can ignore the dump because of the ignore_dump_if_db_exists flag
         // or, the dump is missing but we can ignore that because of the ignore_missing_dump flag
         } else {
-            open_or_create_database(opt, index_scheduler_opt, empty_db, binary_version)?
+            open_or_create_database(opt, index_scheduler_opt, empty_db, binary_version, handle)?
         }
     } else {
-        open_or_create_database(opt, index_scheduler_opt, empty_db, binary_version)?
+        open_or_create_database(opt, index_scheduler_opt, empty_db, binary_version, handle)?
     };
 
     // We create a loop in a thread that registers snapshotCreation tasks
@@ -338,6 +345,7 @@ fn open_or_create_database_unchecked(
     index_scheduler_opt: IndexSchedulerOptions,
     on_failure: OnFailure,
     version: (u32, u32, u32),
+    handle: tokio::runtime::Handle,
 ) -> anyhow::Result<(IndexScheduler, AuthController)> {
     // we don't want to create anything in the data.ms yet, thus we
     // wrap our two builders in a closure that'll be executed later.
@@ -345,7 +353,7 @@ fn open_or_create_database_unchecked(
     let auth_env = open_auth_store_env(&index_scheduler_opt.auth_path).unwrap();
     let auth_controller = AuthController::new(auth_env.clone(), &opt.master_key);
     let index_scheduler_builder = || -> anyhow::Result<_> {
-        Ok(IndexScheduler::new(index_scheduler_opt, auth_env, version)?)
+        Ok(IndexScheduler::new(index_scheduler_opt, auth_env, version, Some(handle))?)
     };
 
     match (
@@ -452,6 +460,7 @@ fn open_or_create_database(
     index_scheduler_opt: IndexSchedulerOptions,
     empty_db: bool,
     binary_version: (u32, u32, u32),
+    handle: tokio::runtime::Handle,
 ) -> anyhow::Result<(IndexScheduler, AuthController)> {
     let version = if !empty_db {
         check_version(opt, &index_scheduler_opt, binary_version)?
@@ -459,7 +468,7 @@ fn open_or_create_database(
         binary_version
     };
 
-    open_or_create_database_unchecked(opt, index_scheduler_opt, OnFailure::KeepDb, version)
+    open_or_create_database_unchecked(opt, index_scheduler_opt, OnFailure::KeepDb, version, handle)
 }
 
 fn import_dump(
@@ -527,7 +536,11 @@ fn import_dump(
     let indexer_config = if base_config.max_threads.is_none() {
         let (thread_pool, _) = default_thread_pool_and_threads();
 
-        let _config = IndexerConfig { thread_pool, ..*base_config };
+        let _config = IndexerConfig {
+            thread_pool,
+            s3_snapshot_options: base_config.s3_snapshot_options.clone(),
+            ..*base_config
+        };
         backup_config = _config;
         &backup_config
     } else {
@@ -675,23 +688,26 @@ fn import_dump(
     Ok(index_scheduler_dump.finish()?)
 }
 
-pub fn configure_data(
-    config: &mut web::ServiceConfig,
-    index_scheduler: Data<IndexScheduler>,
-    auth: Data<AuthController>,
-    search_queue: Data<SearchQueue>,
-    opt: &Opt,
-    (logs_route, logs_stderr): (LogRouteHandle, LogStderrHandle),
-    analytics: Data<Analytics>,
-) {
+pub fn configure_data(config: &mut web::ServiceConfig, services: ServicesData, opt: &Opt) {
+    let ServicesData {
+        index_scheduler,
+        auth,
+        search_queue,
+        personalization_service,
+        logs_route_handle,
+        logs_stderr_handle,
+        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(web::Data::new(logs_route))
-        .app_data(web::Data::new(logs_stderr))
+        .app_data(personalization_service)
+        .app_data(logs_route_handle)
+        .app_data(logs_stderr_handle)
         .app_data(web::Data::new(opt.clone()))
         .app_data(
             web::JsonConfig::default()
@@ -752,3 +768,14 @@ 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

@@ -14,10 +14,11 @@ 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, SubscriberForSecondLayer,
+    LogStderrType, Opt, ServicesData, SubscriberForSecondLayer,
 };
 use meilisearch_auth::{generate_master_key, AuthController, MASTER_KEY_MIN_SIZE};
 use termcolor::{Color, ColorChoice, ColorSpec, StandardStream, WriteColor};
@@ -76,7 +77,10 @@ fn on_panic(info: &std::panic::PanicHookInfo) {
 
 #[actix_web::main]
 async fn main() -> anyhow::Result<()> {
-    try_main().await.inspect_err(|error| {
+    // won't panic inside of tokio::main
+    let runtime = tokio::runtime::Handle::current();
+
+    try_main(runtime).await.inspect_err(|error| {
         tracing::error!(%error);
         let mut current = error.source();
         let mut depth = 0;
@@ -88,7 +92,7 @@ async fn main() -> anyhow::Result<()> {
     })
 }
 
-async fn try_main() -> anyhow::Result<()> {
+async fn try_main(runtime: tokio::runtime::Handle) -> anyhow::Result<()> {
     let (opt, config_read_from) = Opt::try_build()?;
 
     std::panic::set_hook(Box::new(on_panic));
@@ -122,7 +126,7 @@ async fn try_main() -> anyhow::Result<()> {
         _ => (),
     }
 
-    let (index_scheduler, auth_controller) = setup_meilisearch(&opt)?;
+    let (index_scheduler, auth_controller) = setup_meilisearch(&opt, runtime)?;
 
     let analytics =
         analytics::Analytics::new(&opt, index_scheduler.clone(), auth_controller.clone()).await;
@@ -149,8 +153,15 @@ async fn run_http(
     let enable_dashboard = &opt.env == "development";
     let opt_clone = opt.clone();
     let index_scheduler = Data::from(index_scheduler);
-    let auth_controller = Data::from(auth_controller);
+    let auth = 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()
@@ -162,21 +173,25 @@ 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 http_server = HttpServer::new(move || {
-        create_app(
-            index_scheduler.clone(),
-            auth_controller.clone(),
-            search_queue.clone(),
-            opt.clone(),
-            logs.clone(),
-            analytics.clone(),
-            enable_dashboard,
-        )
-    })
-    // Disable signals allows the server to terminate immediately when a user enter CTRL-C
-    .disable_signals()
-    .keep_alive(KeepAlive::Os);
+    let services = ServicesData {
+        index_scheduler,
+        auth,
+        search_queue,
+        personalization_service,
+        logs_route_handle,
+        logs_stderr_handle,
+        analytics,
+    };
+
+    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);
 
     if let Some(config) = opt_clone.get_ssl_config()? {
         http_server.bind_rustls_0_23(opt_clone.http_addr, config)?.run().await?;

crates/meilisearch/src/metrics.rs

@@ -1,7 +1,8 @@
 use lazy_static::lazy_static;
 use prometheus::{
-    opts, register_gauge, register_histogram_vec, register_int_counter_vec, register_int_gauge,
-    register_int_gauge_vec, Gauge, HistogramVec, IntCounterVec, IntGauge, IntGaugeVec,
+    opts, register_gauge, register_gauge_vec, register_histogram_vec, register_int_counter_vec,
+    register_int_gauge, register_int_gauge_vec, Gauge, GaugeVec, HistogramVec, IntCounterVec,
+    IntGauge, IntGaugeVec,
 };
 
 lazy_static! {
@@ -73,6 +74,20 @@ 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");
@@ -114,4 +129,9 @@ 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

@@ -7,12 +7,13 @@ 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;
+use meilisearch_types::milli::update::{IndexerConfig, S3SnapshotOptions};
 use meilisearch_types::milli::ThreadPoolNoAbortBuilder;
 use rustls::server::{ServerSessionMemoryCache, WebPkiClientVerifier};
 use rustls::RootCertStore;
@@ -74,6 +75,22 @@ 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";
@@ -83,6 +100,10 @@ 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";
@@ -452,11 +473,14 @@ pub struct Opt {
     #[serde(default = "default_limit_batched_tasks")]
     pub experimental_max_number_of_batched_tasks: usize,
 
-    /// Experimentally reduces the maximum total size, in bytes, of tasks that will be processed at once,
-    /// see: <https://github.com/orgs/meilisearch/discussions/801>
-    #[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")]
-    pub experimental_limit_batched_tasks_total_size: Byte,
+    /// Experimentally controls the maximum total size, in bytes, of tasks that will be processed
+    /// simultaneously. When unspecified, defaults to half of the maximum indexing memory and
+    /// clamped to 10 GiB.
+    ///
+    /// See: <https://github.com/orgs/meilisearch/discussions/801>
+    #[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.
@@ -475,10 +499,20 @@ 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)]
@@ -580,6 +614,8 @@ 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);
@@ -668,10 +704,12 @@ impl Opt {
             MEILI_EXPERIMENTAL_MAX_NUMBER_OF_BATCHED_TASKS,
             experimental_max_number_of_batched_tasks.to_string(),
         );
-        export_to_env_if_not_present(
-            MEILI_EXPERIMENTAL_LIMIT_BATCHED_TASKS_TOTAL_SIZE,
-            experimental_limit_batched_tasks_total_size.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(),
+            );
+        }
         export_to_env_if_not_present(
             MEILI_EXPERIMENTAL_EMBEDDING_CACHE_ENTRIES,
             experimental_embedding_cache_entries.to_string(),
@@ -680,7 +718,22 @@ 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>> {
@@ -849,6 +902,16 @@ 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()?;
@@ -856,21 +919,163 @@ impl TryFrom<&IndexerOpts> for IndexerConfig {
         Ok(Self {
             thread_pool,
             log_every_n: Some(DEFAULT_LOG_EVERY_N),
-            max_memory: other.max_indexing_memory.map(|b| b.as_u64() as usize),
-            max_threads: *other.max_indexing_threads,
+            max_memory: max_indexing_memory.map(|b| b.as_u64() as usize),
+            max_threads: max_indexing_threads.0,
             max_positions_per_attributes: None,
-            skip_index_budget: other.skip_index_budget,
-            experimental_no_edition_2024_for_settings: other
-                .experimental_no_edition_2024_for_settings,
-            experimental_no_edition_2024_for_dumps: other.experimental_no_edition_2024_for_dumps,
+            skip_index_budget: *skip_index_budget,
+            experimental_no_edition_2024_for_settings: *experimental_no_edition_2024_for_settings,
+            experimental_no_edition_2024_for_dumps: *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: other
-                .experimental_no_edition_2024_for_prefix_post_processing,
-            experimental_no_edition_2024_for_facet_post_processing: other
-                .experimental_no_edition_2024_for_facet_post_processing,
+            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(),
         })
     }
 }
@@ -1073,10 +1278,6 @@ 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
 }
@@ -1089,6 +1290,22 @@ 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

@@ -0,0 +1,366 @@
+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/indexes/community_edition.rs

@@ -0,0 +1,39 @@
+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/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::enterprise_edition::proxy::{proxy, Body};
+use crate::routes::indexes::current_edition::proxy::{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,
@@ -333,10 +333,12 @@ 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();
@@ -359,10 +361,13 @@ 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 || index_scheduler.register(task, uid, dry_run)).await??
+        tokio::task::spawn_blocking(move || {
+            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?;
     }
 
@@ -678,6 +683,19 @@ 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(
@@ -819,6 +837,7 @@ pub async fn replace_documents(
         body,
         IndexDocumentsMethod::ReplaceDocuments,
         uid,
+        params.custom_metadata,
         dry_run,
         allow_index_creation,
         &req,
@@ -921,6 +940,7 @@ pub async fn update_documents(
         body,
         IndexDocumentsMethod::UpdateDocuments,
         uid,
+        params.custom_metadata,
         dry_run,
         allow_index_creation,
         &req,
@@ -940,6 +960,7 @@ 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,
@@ -1065,8 +1086,10 @@ async fn document_addition(
     };
 
     let scheduler = index_scheduler.clone();
-    let task = match tokio::task::spawn_blocking(move || scheduler.register(task, task_id, dry_run))
-        .await?
+    let task = match tokio::task::spawn_blocking(move || {
+        scheduler.register_with_custom_metadata(task, task_id, custom_metadata, dry_run)
+    })
+    .await?
     {
         Ok(task) => task,
         Err(e) => {
@@ -1075,7 +1098,7 @@ async fn document_addition(
         }
     };
 
-    if network.sharding {
+    if network.sharding() {
         if let Some(file) = file {
             proxy(
                 &index_scheduler,
@@ -1130,7 +1153,7 @@ async fn copy_body_to_file(
 /// Delete a set of documents based on an array of document ids.
 #[utoipa::path(
     post,
-    path = "{indexUid}/delete-batch",
+    path = "{indexUid}/documents/delete-batch",
     tag = "Documents",
     security(("Bearer" = ["documents.delete", "documents.*", "*"])),
     params(
@@ -1161,11 +1184,14 @@ 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();
 
@@ -1190,10 +1216,13 @@ 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 || index_scheduler.register(task, uid, dry_run)).await??
+        tokio::task::spawn_blocking(move || {
+            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?;
     }
 
@@ -1244,12 +1273,15 @@ 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();
@@ -1282,10 +1314,13 @@ 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 || index_scheduler.register(task, uid, dry_run)).await??
+        tokio::task::spawn_blocking(move || {
+            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?;
     }
 
@@ -1372,12 +1407,14 @@ 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: AwebJson<DocumentEditionByFunction, DeserrJsonError>,
+    params: AwebQueryParameter<CustomMetadataQuery, DeserrQueryParamError>,
+    body: AwebJson<DocumentEditionByFunction, DeserrJsonError>,
     req: HttpRequest,
     opt: web::Data<Opt>,
     analytics: web::Data<Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
-    debug!(parameters = ?params, "Edit documents by function");
+    debug!(parameters = ?body, "Edit documents by function");
+    let CustomMetadataQuery { custom_metadata } = params.into_inner();
 
     index_scheduler
         .features()
@@ -1387,23 +1424,23 @@ pub async fn edit_documents_by_function(
 
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
     let index_uid = index_uid.into_inner();
-    let params = params.into_inner();
+    let body = body.into_inner();
 
     analytics.publish(
         EditDocumentsByFunctionAggregator {
-            filtered: params.filter.is_some(),
-            with_context: params.context.is_some(),
+            filtered: body.filter.is_some(),
+            with_context: body.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(&params.function) {
+    if let Err(e) = engine.compile(&body.function) {
         return Err(ResponseError::from_msg(e.to_string(), Code::BadRequest));
     }
 
-    if let Some(ref filter) = params.filter {
+    if let Some(ref filter) = body.filter {
         // we ensure the filter is well formed before enqueuing it
         crate::search::parse_filter(
             filter,
@@ -1414,8 +1451,8 @@ pub async fn edit_documents_by_function(
     }
     let task = KindWithContent::DocumentEdition {
         index_uid: index_uid.clone(),
-        filter_expr: params.filter.clone(),
-        context: match params.context.clone() {
+        filter_expr: body.filter.clone(),
+        context: match body.context.clone() {
             Some(Value::Object(m)) => Some(m),
             None => None,
             _ => {
@@ -1425,18 +1462,21 @@ pub async fn edit_documents_by_function(
                 ))
             }
         },
-        function: params.function.clone(),
+        function: body.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 || index_scheduler.register(task, uid, dry_run)).await??
+        tokio::task::spawn_blocking(move || {
+            index_scheduler.register_with_custom_metadata(task, uid, custom_metadata, dry_run)
+        })
+        .await??
     };
 
-    if network.sharding && !dry_run {
-        proxy(&index_scheduler, &index_uid, &req, network, Body::Inline(params), &task).await?;
+    if network.sharding() && !dry_run {
+        proxy(&index_scheduler, &index_uid, &req, network, Body::Inline(body), &task).await?;
     }
 
     let task: SummarizedTaskView = task.into();
@@ -1477,12 +1517,14 @@ 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();
 
     analytics.publish(
         DocumentsDeletionAggregator {
@@ -1501,10 +1543,13 @@ pub async fn clear_all_documents(
     let task = {
         let index_scheduler = index_scheduler.clone();
 
-        tokio::task::spawn_blocking(move || index_scheduler.register(task, uid, dry_run)).await??
+        tokio::task::spawn_blocking(move || {
+            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?;
     }
 

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

@@ -52,7 +52,7 @@ pub async fn proxy<T: serde::Serialize>(
     index_scheduler: &IndexScheduler,
     index_uid: &str,
     req: &HttpRequest,
-    network: meilisearch_types::enterprise_edition::network::Network,
+    network: meilisearch_types::network::Network,
     body: Body<T>,
     task: &meilisearch_types::tasks::Task,
 ) -> Result<(), MeilisearchHttpError> {

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

@@ -343,6 +343,7 @@ impl From<FacetSearchQuery> for SearchQuery {
             hybrid,
             ranking_score_threshold,
             locales,
+            personalize: None,
         }
     }
 }

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

@@ -30,7 +30,16 @@ 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;
@@ -41,7 +50,7 @@ mod settings_analytics;
 pub mod similar;
 mod similar_analytics;
 
-pub use enterprise_edition::proxy::{PROXY_ORIGIN_REMOTE_HEADER, PROXY_ORIGIN_TASK_UID_HEADER};
+pub use current_edition::proxy::{PROXY_ORIGIN_REMOTE_HEADER, PROXY_ORIGIN_TASK_UID_HEADER};
 
 #[derive(OpenApi)]
 #[openapi(

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

@@ -24,9 +24,9 @@ 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, RankingScoreThreshold,
-    RetrieveVectors, SearchKind, SearchParams, SearchQuery, SearchResult, SemanticRatio,
-    DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG,
+    add_search_rules, perform_search, HybridQuery, MatchingStrategy, Personalize,
+    RankingScoreThreshold, RetrieveVectors, SearchKind, SearchParams, SearchQuery, SearchResult,
+    SemanticRatio, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG,
     DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET, DEFAULT_SEMANTIC_RATIO,
 };
 use crate::search_queue::SearchQueue;
@@ -134,6 +134,8 @@ 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)]
@@ -205,6 +207,9 @@ 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`
@@ -234,6 +239,7 @@ 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,
         })
     }
 }
@@ -322,6 +328,7 @@ 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,
@@ -342,9 +349,16 @@ pub async fn search_with_url_query(
 
     let index = index_scheduler.index(&index_uid)?;
 
+    // Extract personalization and query string before moving query
+    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);
 
@@ -365,12 +379,24 @@ pub async fn search_with_url_query(
     .await;
     permit.drop().await;
     let search_result = search_result?;
-    if let Ok(ref search_result) = search_result {
+    if let Ok((search_result, _)) = search_result.as_ref() {
         aggregate.succeed(search_result);
     }
     analytics.publish(aggregate, &req);
 
-    let search_result = search_result?;
+    let (mut search_result, time_budget) = search_result?;
+
+    // Apply personalization if requested
+    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))
@@ -435,6 +461,7 @@ 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,
@@ -455,12 +482,18 @@ pub async fn search_with_post(
 
     let index = index_scheduler.index(&index_uid)?;
 
+    // Extract personalization and query string before moving query
+    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(
@@ -479,7 +512,7 @@ pub async fn search_with_post(
     .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();
@@ -487,7 +520,19 @@ pub async fn search_with_post(
     }
     analytics.publish(aggregate, &req);
 
-    let search_result = search_result?;
+    let (mut search_result, time_budget) = search_result?;
+
+    // Apply personalization if requested
+    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))

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

@@ -7,6 +7,7 @@ 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,
@@ -95,6 +96,9 @@ pub struct SearchAggregator<Method: AggregateMethod> {
     show_ranking_score_details: bool,
     ranking_score_threshold: bool,
 
+    // personalization
+    total_personalized: usize,
+
     marker: std::marker::PhantomData<Method>,
 }
 
@@ -129,6 +133,7 @@ impl<Method: AggregateMethod> SearchAggregator<Method> {
             hybrid,
             ranking_score_threshold,
             locales,
+            personalize,
         } = query;
 
         let mut ret = Self::default();
@@ -204,6 +209,12 @@ 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();
@@ -296,6 +307,7 @@ impl<Method: AggregateMethod> Aggregate for SearchAggregator<Method> {
             total_used_negative_operator,
             ranking_score_threshold,
             mut locales,
+            total_personalized,
             marker: _,
         } = *new;
 
@@ -381,6 +393,9 @@ 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
     }
 
@@ -426,6 +441,7 @@ impl<Method: AggregateMethod> Aggregate for SearchAggregator<Method> {
             total_used_negative_operator,
             ranking_score_threshold,
             locales,
+            total_personalized,
             marker: _,
         } = *self;
 
@@ -499,6 +515,9 @@ 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,
+            },
         })
     }
 }

crates/meilisearch/src/routes/metrics.rs

@@ -4,6 +4,7 @@ use index_scheduler::{IndexScheduler, Query};
 use meilisearch_auth::AuthController;
 use meilisearch_types::error::ResponseError;
 use meilisearch_types::keys::actions;
+use meilisearch_types::milli::progress::ProgressStepView;
 use meilisearch_types::tasks::Status;
 use prometheus::{Encoder, TextEncoder};
 use time::OffsetDateTime;
@@ -38,6 +39,12 @@ pub fn configure(config: &mut web::ServiceConfig) {
 # HELP meilisearch_db_size_bytes Meilisearch DB Size In Bytes
 # TYPE meilisearch_db_size_bytes gauge
 meilisearch_db_size_bytes 1130496
+# HELP meilisearch_batch_running_progress_trace The currently running progress trace
+# TYPE meilisearch_batch_running_progress_trace gauge
+meilisearch_batch_running_progress_trace{batch_uid="0",step_name="document"} 0.710618582519409
+meilisearch_batch_running_progress_trace{batch_uid="0",step_name="extracting word proximity"} 0.2222222222222222
+meilisearch_batch_running_progress_trace{batch_uid="0",step_name="indexing"} 0.6666666666666666
+meilisearch_batch_running_progress_trace{batch_uid="0",step_name="processing tasks"} 0
 # HELP meilisearch_http_requests_total Meilisearch HTTP requests total
 # TYPE meilisearch_http_requests_total counter
 meilisearch_http_requests_total{method="GET",path="/metrics",status="400"} 1
@@ -61,6 +68,13 @@ meilisearch_http_response_time_seconds_bucket{method="GET",path="/metrics",le="1
 meilisearch_http_response_time_seconds_bucket{method="GET",path="/metrics",le="+Inf"} 0
 meilisearch_http_response_time_seconds_sum{method="GET",path="/metrics"} 0
 meilisearch_http_response_time_seconds_count{method="GET",path="/metrics"} 0
+# HELP meilisearch_last_finished_batches_progress_trace_ms The last few batches progress trace in milliseconds
+# TYPE meilisearch_last_finished_batches_progress_trace_ms gauge
+meilisearch_last_finished_batches_progress_trace_ms{batch_uid="0",step_name="processing tasks"} 19360
+meilisearch_last_finished_batches_progress_trace_ms{batch_uid="0",step_name="processing tasks > computing document changes"} 368
+meilisearch_last_finished_batches_progress_trace_ms{batch_uid="0",step_name="processing tasks > computing document changes > preparing payloads"} 367
+meilisearch_last_finished_batches_progress_trace_ms{batch_uid="0",step_name="processing tasks > computing document changes > preparing payloads > payload"} 367
+meilisearch_last_finished_batches_progress_trace_ms{batch_uid="0",step_name="processing tasks > indexing"} 18970
 # HELP meilisearch_index_count Meilisearch Index Count
 # TYPE meilisearch_index_count gauge
 meilisearch_index_count 1
@@ -148,6 +162,46 @@ pub async fn get_metrics(
         }
     }
 
+    // Fetch and expose the current progressing step
+    crate::metrics::MEILISEARCH_BATCH_RUNNING_PROGRESS_TRACE.reset();
+    let (batches, _total) = index_scheduler.get_batches_from_authorized_indexes(
+        &Query { statuses: Some(vec![Status::Processing]), ..Query::default() },
+        auth_filters,
+    )?;
+    if let Some(batch) = batches.into_iter().next() {
+        let batch_uid = batch.uid.to_string();
+        if let Some(progress) = batch.progress {
+            for ProgressStepView { current_step, finished, total } in progress.steps {
+                crate::metrics::MEILISEARCH_BATCH_RUNNING_PROGRESS_TRACE
+                    .with_label_values(&[batch_uid.as_str(), current_step.as_ref()])
+                    // We return the completion ratio of the current step
+                    .set(finished as f64 / total as f64);
+            }
+        }
+    }
+
+    crate::metrics::MEILISEARCH_LAST_FINISHED_BATCHES_PROGRESS_TRACE_MS.reset();
+    let (batches, _total) = index_scheduler.get_batches_from_authorized_indexes(
+        // Fetch the finished batches...
+        &Query { statuses: Some(vec![Status::Succeeded, Status::Failed]), ..Query::default() },
+        auth_filters,
+    )?;
+    // ...and get the last batch only.
+    if let Some(batch) = batches.into_iter().next() {
+        let batch_uid = batch.uid.to_string();
+        for (step_name, duration_str) in batch.stats.progress_trace {
+            let Some(duration_str) = duration_str.as_str() else { continue };
+            match humantime::parse_duration(duration_str) {
+                Ok(duration) => {
+                    crate::metrics::MEILISEARCH_LAST_FINISHED_BATCHES_PROGRESS_TRACE_MS
+                        .with_label_values(&[&batch_uid, &step_name])
+                        .set(duration.as_millis() as i64);
+                }
+                Err(e) => tracing::error!("Failed to parse duration: {e}"),
+            }
+        }
+    }
+
     if let Some(last_update) = response.last_update {
         crate::metrics::MEILISEARCH_LAST_UPDATE.set(last_update.unix_timestamp());
     }

crates/meilisearch/src/routes/mod.rs

@@ -41,7 +41,9 @@ use crate::routes::indexes::IndexView;
 use crate::routes::multi_search::SearchResults;
 use crate::routes::network::{Network, Remote};
 use crate::routes::swap_indexes::SwapIndexesPayload;
-use crate::routes::webhooks::{WebhookResults, WebhookSettings, WebhookWithMetadata};
+use crate::routes::webhooks::{
+    WebhookResults, WebhookSettings, WebhookWithMetadataRedactedAuthorization,
+};
 use crate::search::{
     FederatedSearch, FederatedSearchResult, Federation, FederationOptions, MergeFacets,
     SearchQueryWithIndex, SearchResultWithIndex, SimilarQuery, SimilarResult,
@@ -103,7 +105,7 @@ mod webhooks;
         url = "/",
         description = "Local server",
     )),
-    components(schemas(PaginationView<KeyView>, PaginationView<IndexView>, IndexView, DocumentDeletionByFilter, AllBatches, BatchStats, ProgressStepView, ProgressView, BatchView, RuntimeTogglableFeatures, SwapIndexesPayload, DocumentEditionByFunction, MergeFacets, FederationOptions, SearchQueryWithIndex, Federation, FederatedSearch, FederatedSearchResult, SearchResults, SearchResultWithIndex, SimilarQuery, SimilarResult, PaginationView<serde_json::Value>, BrowseQuery, UpdateIndexRequest, IndexUid, IndexCreateRequest, KeyView, Action, CreateApiKey, UpdateStderrLogs, LogMode, GetLogs, IndexStats, Stats, HealthStatus, HealthResponse, VersionResponse, Code, ErrorType, AllTasks, TaskView, Status, DetailsView, ResponseError, Settings<Unchecked>, Settings<Checked>, TypoSettings, MinWordSizeTyposSetting, FacetingSettings, PaginationSettings, SummarizedTaskView, Kind, Network, Remote, FilterableAttributesRule, FilterableAttributesPatterns, AttributePatterns, FilterableAttributesFeatures, FilterFeatures, Export, WebhookSettings, WebhookResults, WebhookWithMetadata, meilisearch_types::milli::vector::VectorStoreBackend))
+    components(schemas(PaginationView<KeyView>, PaginationView<IndexView>, IndexView, DocumentDeletionByFilter, AllBatches, BatchStats, ProgressStepView, ProgressView, BatchView, RuntimeTogglableFeatures, SwapIndexesPayload, DocumentEditionByFunction, MergeFacets, FederationOptions, SearchQueryWithIndex, Federation, FederatedSearch, FederatedSearchResult, SearchResults, SearchResultWithIndex, SimilarQuery, SimilarResult, PaginationView<serde_json::Value>, BrowseQuery, UpdateIndexRequest, IndexUid, IndexCreateRequest, KeyView, Action, CreateApiKey, UpdateStderrLogs, LogMode, GetLogs, IndexStats, Stats, HealthStatus, HealthResponse, VersionResponse, Code, ErrorType, AllTasks, TaskView, Status, DetailsView, ResponseError, Settings<Unchecked>, Settings<Checked>, TypoSettings, MinWordSizeTyposSetting, FacetingSettings, PaginationSettings, SummarizedTaskView, Kind, Network, Remote, FilterableAttributesRule, FilterableAttributesPatterns, AttributePatterns, FilterableAttributesFeatures, FilterFeatures, Export, WebhookSettings, WebhookResults, WebhookWithMetadataRedactedAuthorization, meilisearch_types::milli::vector::VectorStoreBackend))
 )]
 pub struct MeilisearchApi;
 
@@ -216,6 +218,8 @@ pub struct SummarizedTaskView {
         deserialize_with = "time::serde::rfc3339::deserialize"
     )]
     enqueued_at: OffsetDateTime,
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    custom_metadata: Option<String>,
 }
 
 impl From<Task> for SummarizedTaskView {
@@ -226,6 +230,7 @@ impl From<Task> for SummarizedTaskView {
             status: task.status,
             kind: task.kind.as_kind(),
             enqueued_at: task.enqueued_at,
+            custom_metadata: task.custom_metadata,
         }
     }
 }

crates/meilisearch/src/routes/multi_search.rs

@@ -146,6 +146,7 @@ pub struct SearchResults {
 pub async fn multi_search_with_post(
     index_scheduler: GuardedData<ActionPolicy<{ actions::SEARCH }>, Data<IndexScheduler>>,
     search_queue: Data<SearchQueue>,
+    personalization_service: web::Data<crate::personalization::PersonalizationService>,
     params: AwebJson<FederatedSearch, DeserrJsonError>,
     req: HttpRequest,
     analytics: web::Data<Analytics>,
@@ -236,7 +237,7 @@ pub async fn multi_search_with_post(
             // changes.
             let search_results: Result<_, (ResponseError, usize)> = async {
                 let mut search_results = Vec::with_capacity(queries.len());
-                for (query_index, (index_uid, query, federation_options)) in queries
+                for (query_index, (index_uid, mut query, federation_options)) in queries
                     .into_iter()
                     .map(SearchQueryWithIndex::into_index_query_federation)
                     .enumerate()
@@ -269,6 +270,13 @@ pub async fn multi_search_with_post(
                         })
                         .with_index(query_index)?;
 
+                    // Extract personalization and query string before moving query
+                    let personalize = query.personalize.take();
+
+                    // Save the query string for personalization if requested
+                    let personalize_query =
+                        personalize.is_some().then(|| query.q.clone()).flatten();
+
                     let index_uid_str = index_uid.to_string();
 
                     let search_kind = search_kind(
@@ -280,7 +288,7 @@ pub async fn multi_search_with_post(
                     .with_index(query_index)?;
                     let retrieve_vector = RetrieveVectors::new(query.retrieve_vectors);
 
-                    let search_result = tokio::task::spawn_blocking(move || {
+                    let (mut search_result, time_budget) = tokio::task::spawn_blocking(move || {
                         perform_search(
                             SearchParams {
                                 index_uid: index_uid_str.clone(),
@@ -295,11 +303,25 @@ pub async fn multi_search_with_post(
                         )
                     })
                     .await
+                    .with_index(query_index)?
                     .with_index(query_index)?;
 
+                    // Apply personalization if requested
+                    if let Some(personalize) = personalize.as_ref() {
+                        search_result = personalization_service
+                            .rerank_search_results(
+                                search_result,
+                                personalize,
+                                personalize_query.as_deref(),
+                                time_budget,
+                            )
+                            .await
+                            .with_index(query_index)?;
+                    }
+
                     search_results.push(SearchResultWithIndex {
                         index_uid: index_uid.into_inner(),
-                        result: search_result.with_index(query_index)?,
+                        result: search_result,
                     });
                 }
                 Ok(search_results)

crates/meilisearch/src/routes/multi_search_analytics.rs

@@ -67,6 +67,7 @@ impl MultiSearchAggregator {
             hybrid: _,
             ranking_score_threshold: _,
             locales: _,
+            personalize: _,
         } in &federated_search.queries
         {
             if let Some(federation_options) = federation_options {

crates/meilisearch/src/routes/network.rs

@@ -7,7 +7,6 @@ use deserr::Deserr;
 use index_scheduler::IndexScheduler;
 use itertools::{EitherOrBoth, Itertools};
 use meilisearch_types::deserr::DeserrJsonError;
-use meilisearch_types::enterprise_edition::network::{Network as DbNetwork, Remote as DbRemote};
 use meilisearch_types::error::deserr_codes::{
     InvalidNetworkRemotes, InvalidNetworkSearchApiKey, InvalidNetworkSelf, InvalidNetworkSharding,
     InvalidNetworkUrl, InvalidNetworkWriteApiKey,
@@ -15,6 +14,7 @@ use meilisearch_types::error::deserr_codes::{
 use meilisearch_types::error::ResponseError;
 use meilisearch_types::keys::actions;
 use meilisearch_types::milli::update::Setting;
+use meilisearch_types::network::{Network as DbNetwork, Remote as DbRemote};
 use serde::Serialize;
 use tracing::debug;
 use utoipa::{OpenApi, ToSchema};
@@ -211,6 +211,16 @@ async fn patch_network(
     let old_network = index_scheduler.network();
     debug!(parameters = ?new_network, "Patch network");
 
+    #[cfg(not(feature = "enterprise"))]
+    if new_network.sharding.set().is_some() {
+        use meilisearch_types::error::Code;
+
+        return Err(ResponseError::from_msg(
+            "Meilisearch Enterprise Edition is required to set `network.sharding`".into(),
+            Code::RequiresEnterpriseEdition,
+        ));
+    }
+
     let merged_self = match new_network.local {
         Setting::Set(new_self) => Some(new_self),
         Setting::Reset => None,
@@ -312,6 +322,7 @@ async fn patch_network(
 
     let merged_network =
         DbNetwork { local: merged_self, remotes: merged_remotes, sharding: merged_sharding };
+
     index_scheduler.put_network(merged_network.clone())?;
     debug!(returns = ?merged_network, "Patch network");
     Ok(HttpResponse::Ok().json(merged_network))

crates/meilisearch/src/routes/webhooks.rs

@@ -90,7 +90,7 @@ fn deny_immutable_fields_webhook(
 #[derive(Debug, Serialize, ToSchema)]
 #[serde(rename_all = "camelCase")]
 #[schema(rename_all = "camelCase")]
-pub(super) struct WebhookWithMetadata {
+pub(super) struct WebhookWithMetadataRedactedAuthorization {
     uuid: Uuid,
     is_editable: bool,
     #[schema(value_type = WebhookSettings)]
@@ -98,8 +98,9 @@ pub(super) struct WebhookWithMetadata {
     webhook: Webhook,
 }
 
-impl WebhookWithMetadata {
-    pub fn from(uuid: Uuid, webhook: Webhook) -> Self {
+impl WebhookWithMetadataRedactedAuthorization {
+    pub fn from(uuid: Uuid, mut webhook: Webhook) -> Self {
+        webhook.redact_authorization_header();
         Self { uuid, is_editable: uuid != Uuid::nil(), webhook }
     }
 }
@@ -107,7 +108,7 @@ impl WebhookWithMetadata {
 #[derive(Debug, Serialize, ToSchema)]
 #[serde(rename_all = "camelCase")]
 pub(super) struct WebhookResults {
-    results: Vec<WebhookWithMetadata>,
+    results: Vec<WebhookWithMetadataRedactedAuthorization>,
 }
 
 #[utoipa::path(
@@ -150,7 +151,7 @@ async fn get_webhooks(
     let results = webhooks
         .webhooks
         .into_iter()
-        .map(|(uuid, webhook)| WebhookWithMetadata::from(uuid, webhook))
+        .map(|(uuid, webhook)| WebhookWithMetadataRedactedAuthorization::from(uuid, webhook))
         .collect::<Vec<_>>();
     let results = WebhookResults { results };
 
@@ -301,7 +302,7 @@ fn check_changed(uuid: Uuid, webhook: &Webhook) -> Result<(), WebhooksError> {
     tag = "Webhooks",
     security(("Bearer" = ["webhooks.get", "webhooks.*", "*.get", "*"])),
     responses(
-        (status = 200, description = "Webhook found", body = WebhookWithMetadata, content_type = "application/json", example = json!({
+        (status = 200, description = "Webhook found", body = WebhookWithMetadataRedactedAuthorization, content_type = "application/json", example = json!({
             "uuid": "550e8400-e29b-41d4-a716-446655440000",
             "url": "https://your.site/on-tasks-completed",
             "headers": {
@@ -324,7 +325,7 @@ async fn get_webhook(
     let mut webhooks = index_scheduler.webhooks_view();
 
     let webhook = webhooks.webhooks.remove(&uuid).ok_or(WebhookNotFound(uuid))?;
-    let webhook = WebhookWithMetadata::from(uuid, webhook);
+    let webhook = WebhookWithMetadataRedactedAuthorization::from(uuid, webhook);
 
     debug!(returns = ?webhook, "Get webhook");
     Ok(HttpResponse::Ok().json(webhook))
@@ -337,7 +338,7 @@ async fn get_webhook(
     request_body = WebhookSettings,
     security(("Bearer" = ["webhooks.create", "webhooks.*", "*"])),
     responses(
-        (status = 201, description = "Webhook created successfully", body = WebhookWithMetadata, content_type = "application/json", example = json!({
+        (status = 201, description = "Webhook created successfully", body = WebhookWithMetadataRedactedAuthorization, content_type = "application/json", example = json!({
             "uuid": "550e8400-e29b-41d4-a716-446655440000",
             "url": "https://your.site/on-tasks-completed",
             "headers": {
@@ -383,7 +384,7 @@ async fn post_webhook(
 
     analytics.publish(PostWebhooksAnalytics, &req);
 
-    let response = WebhookWithMetadata::from(uuid, webhook);
+    let response = WebhookWithMetadataRedactedAuthorization::from(uuid, webhook);
     debug!(returns = ?response, "Post webhook");
     Ok(HttpResponse::Created().json(response))
 }
@@ -395,7 +396,7 @@ async fn post_webhook(
     request_body = WebhookSettings,
     security(("Bearer" = ["webhooks.update", "webhooks.*", "*"])),
     responses(
-        (status = 200, description = "Webhook updated successfully", body = WebhookWithMetadata, content_type = "application/json", example = json!({
+        (status = 200, description = "Webhook updated successfully", body = WebhookWithMetadataRedactedAuthorization, content_type = "application/json", example = json!({
             "uuid": "550e8400-e29b-41d4-a716-446655440000",
             "url": "https://your.site/on-tasks-completed",
             "headers": {
@@ -435,7 +436,7 @@ async fn patch_webhook(
 
     analytics.publish(PatchWebhooksAnalytics, &req);
 
-    let response = WebhookWithMetadata::from(uuid, webhook);
+    let response = WebhookWithMetadataRedactedAuthorization::from(uuid, webhook);
     debug!(returns = ?response, "Patch webhook");
     Ok(HttpResponse::Ok().json(response))
 }

crates/meilisearch/src/search/federated/perform.rs

@@ -9,12 +9,12 @@ use std::vec::{IntoIter, Vec};
 use actix_http::StatusCode;
 use index_scheduler::{IndexScheduler, RoFeatures};
 use itertools::Itertools;
-use meilisearch_types::enterprise_edition::network::{Network, Remote};
 use meilisearch_types::error::ResponseError;
 use meilisearch_types::milli::order_by_map::OrderByMap;
 use meilisearch_types::milli::score_details::{ScoreDetails, WeightedScoreValue};
 use meilisearch_types::milli::vector::Embedding;
 use meilisearch_types::milli::{self, DocumentId, OrderBy, TimeBudget, DEFAULT_VALUES_PER_FACET};
+use meilisearch_types::network::{Network, Remote};
 use roaring::RoaringBitmap;
 use tokio::task::JoinHandle;
 use uuid::Uuid;
@@ -601,6 +601,10 @@ impl PartitionedQueries {
             .into());
         }
 
+        if federated_query.has_personalize() {
+            return Err(MeilisearchHttpError::PersonalizationInFederatedQuery(query_index).into());
+        }
+
         let (index_uid, query, federation_options) = federated_query.into_index_query_federation();
 
         let federation_options = federation_options.unwrap_or_default();

crates/meilisearch/src/search/federated/proxy.rs

@@ -1,6 +1,6 @@
 pub use error::ProxySearchError;
 use error::ReqwestErrorWithoutUrl;
-use meilisearch_types::enterprise_edition::network::Remote;
+use meilisearch_types::network::Remote;
 use rand::Rng as _;
 use reqwest::{Client, Response, StatusCode};
 use serde::de::DeserializeOwned;

crates/meilisearch/src/search/federated/types.rs

@@ -18,10 +18,9 @@ use serde::{Deserialize, Serialize};
 use utoipa::ToSchema;
 use uuid::Uuid;
 
-use crate::search::SearchMetadata;
-
 use super::super::{ComputedFacets, FacetStats, HitsInfo, SearchHit, SearchQueryWithIndex};
 use crate::milli::vector::Embedding;
+use crate::search::SearchMetadata;
 
 pub const DEFAULT_FEDERATED_WEIGHT: f64 = 1.0;
 

crates/meilisearch/src/search/mod.rs

@@ -59,6 +59,13 @@ pub const DEFAULT_HIGHLIGHT_POST_TAG: fn() -> String = || "</em>".to_string();
 pub const DEFAULT_SEMANTIC_RATIO: fn() -> SemanticRatio = || SemanticRatio(0.5);
 pub const INCLUDE_METADATA_HEADER: &str = "Meili-Include-Metadata";
 
+#[derive(Clone, Default, PartialEq, Deserr, ToSchema, Debug)]
+#[deserr(error = DeserrJsonError<InvalidSearchPersonalize>, rename_all = camelCase, deny_unknown_fields)]
+pub struct Personalize {
+    #[deserr(error = DeserrJsonError<InvalidSearchPersonalizeUserContext>)]
+    pub user_context: String,
+}
+
 #[derive(Clone, Default, PartialEq, Deserr, ToSchema)]
 #[deserr(error = DeserrJsonError, rename_all = camelCase, deny_unknown_fields)]
 pub struct SearchQuery {
@@ -122,6 +129,8 @@ pub struct SearchQuery {
     pub ranking_score_threshold: Option<RankingScoreThreshold>,
     #[deserr(default, error = DeserrJsonError<InvalidSearchLocales>)]
     pub locales: Option<Vec<Locale>>,
+    #[deserr(default, error = DeserrJsonError<InvalidSearchPersonalize>, default)]
+    pub personalize: Option<Personalize>,
 }
 
 impl From<SearchParameters> for SearchQuery {
@@ -169,6 +178,7 @@ impl From<SearchParameters> for SearchQuery {
             highlight_post_tag: DEFAULT_HIGHLIGHT_POST_TAG(),
             crop_marker: DEFAULT_CROP_MARKER(),
             locales: None,
+            personalize: None,
         }
     }
 }
@@ -250,6 +260,7 @@ impl fmt::Debug for SearchQuery {
             attributes_to_search_on,
             ranking_score_threshold,
             locales,
+            personalize,
         } = self;
 
         let mut debug = f.debug_struct("SearchQuery");
@@ -338,6 +349,10 @@ impl fmt::Debug for SearchQuery {
             debug.field("locales", &locales);
         }
 
+        if let Some(personalize) = personalize {
+            debug.field("personalize", &personalize);
+        }
+
         debug.finish()
     }
 }
@@ -543,6 +558,9 @@ pub struct SearchQueryWithIndex {
     pub ranking_score_threshold: Option<RankingScoreThreshold>,
     #[deserr(default, error = DeserrJsonError<InvalidSearchLocales>, default)]
     pub locales: Option<Vec<Locale>>,
+    #[deserr(default, error = DeserrJsonError<InvalidSearchPersonalize>, default)]
+    #[serde(skip)]
+    pub personalize: Option<Personalize>,
 
     #[deserr(default)]
     pub federation_options: Option<FederationOptions>,
@@ -567,6 +585,10 @@ impl SearchQueryWithIndex {
         self.facets.as_deref().filter(|v| !v.is_empty())
     }
 
+    pub fn has_personalize(&self) -> bool {
+        self.personalize.is_some()
+    }
+
     pub fn from_index_query_federation(
         index_uid: IndexUid,
         query: SearchQuery,
@@ -600,6 +622,7 @@ impl SearchQueryWithIndex {
             attributes_to_search_on,
             ranking_score_threshold,
             locales,
+            personalize,
         } = query;
 
         SearchQueryWithIndex {
@@ -631,6 +654,7 @@ impl SearchQueryWithIndex {
             attributes_to_search_on,
             ranking_score_threshold,
             locales,
+            personalize,
             federation_options,
         }
     }
@@ -666,6 +690,7 @@ impl SearchQueryWithIndex {
             hybrid,
             ranking_score_threshold,
             locales,
+            personalize,
         } = self;
         (
             index_uid,
@@ -697,6 +722,7 @@ impl SearchQueryWithIndex {
                 hybrid,
                 ranking_score_threshold,
                 locales,
+                personalize,
                 // do not use ..Default::default() here,
                 // rather add any missing field from `SearchQuery` to `SearchQueryWithIndex`
             },
@@ -1149,7 +1175,10 @@ pub struct SearchParams {
     pub include_metadata: bool,
 }
 
-pub fn perform_search(params: SearchParams, index: &Index) -> Result<SearchResult, ResponseError> {
+pub fn perform_search(
+    params: SearchParams,
+    index: &Index,
+) -> Result<(SearchResult, TimeBudget), ResponseError> {
     let SearchParams {
         index_uid,
         query,
@@ -1168,7 +1197,7 @@ pub fn perform_search(params: SearchParams, index: &Index) -> Result<SearchResul
     };
 
     let (search, is_finite_pagination, max_total_hits, offset) =
-        prepare_search(index, &rtxn, &query, &search_kind, time_budget, features)?;
+        prepare_search(index, &rtxn, &query, &search_kind, time_budget.clone(), features)?;
 
     let (
         milli::SearchResult {
@@ -1226,6 +1255,7 @@ pub fn perform_search(params: SearchParams, index: &Index) -> Result<SearchResul
         attributes_to_search_on: _,
         filter: _,
         distinct: _,
+        personalize: _,
     } = query;
 
     let format = AttributesFormat {
@@ -1291,7 +1321,7 @@ pub fn perform_search(params: SearchParams, index: &Index) -> Result<SearchResul
         request_uid: Some(request_uid),
         metadata,
     };
-    Ok(result)
+    Ok((result, time_budget))
 }
 
 #[derive(Debug, Clone, Default, Serialize, Deserialize, ToSchema)]

crates/meilisearch/tests/common/index.rs

@@ -91,7 +91,16 @@ impl<'a> Index<'a, Owned> {
         documents: Value,
         primary_key: Option<&str>,
     ) -> (Value, StatusCode) {
-        self._add_documents(documents, primary_key).await
+        self._add_documents(documents, primary_key, None).await
+    }
+
+    pub async fn add_documents_with_custom_metadata(
+        &self,
+        documents: Value,
+        primary_key: Option<&str>,
+        custom_metadata: Option<&str>,
+    ) -> (Value, StatusCode) {
+        self._add_documents(documents, primary_key, custom_metadata).await
     }
 
     pub async fn raw_add_documents(
@@ -352,12 +361,25 @@ impl<State> Index<'_, State> {
         &self,
         documents: Value,
         primary_key: Option<&str>,
+        custom_metadata: Option<&str>,
     ) -> (Value, StatusCode) {
-        let url = match primary_key {
-            Some(key) => {
-                format!("/indexes/{}/documents?primaryKey={}", urlencode(self.uid.as_ref()), key)
+        let url = match (primary_key, custom_metadata) {
+            (Some(key), Some(meta)) => {
+                format!(
+                    "/indexes/{}/documents?primaryKey={key}&customMetadata={meta}",
+                    urlencode(self.uid.as_ref()),
+                )
             }
-            None => format!("/indexes/{}/documents", urlencode(self.uid.as_ref())),
+            (None, Some(meta)) => {
+                format!(
+                    "/indexes/{}/documents?&customMetadata={meta}",
+                    urlencode(self.uid.as_ref()),
+                )
+            }
+            (Some(key), None) => {
+                format!("/indexes/{}/documents?&primaryKey={key}", urlencode(self.uid.as_ref()),)
+            }
+            (None, None) => format!("/indexes/{}/documents", urlencode(self.uid.as_ref())),
         };
         self.service.post_encoded(url, documents, self.encoder).await
     }

crates/meilisearch/tests/common/mod.rs

@@ -241,7 +241,7 @@ pub async fn shared_index_with_documents() -> &'static Index<'static, Shared> {
         let server = Server::new_shared();
         let index = server._index("SHARED_DOCUMENTS").to_shared();
         let documents = DOCUMENTS.clone();
-        let (response, _code) = index._add_documents(documents, None).await;
+        let (response, _code) = index._add_documents(documents, None, None).await;
         server.wait_task(response.uid()).await.succeeded();
         let (response, _code) = index
             ._update_settings(
@@ -284,7 +284,7 @@ pub async fn shared_index_with_score_documents() -> &'static Index<'static, Shar
         let server = Server::new_shared();
         let index = server._index("SHARED_SCORE_DOCUMENTS").to_shared();
         let documents = SCORE_DOCUMENTS.clone();
-        let (response, _code) = index._add_documents(documents, None).await;
+        let (response, _code) = index._add_documents(documents, None, None).await;
         server.wait_task(response.uid()).await.succeeded();
         let (response, _code) = index
             ._update_settings(
@@ -361,7 +361,7 @@ pub async fn shared_index_with_nested_documents() -> &'static Index<'static, Sha
         let server = Server::new_shared();
         let index = server._index("SHARED_NESTED_DOCUMENTS").to_shared();
         let documents = NESTED_DOCUMENTS.clone();
-        let (response, _code) = index._add_documents(documents, None).await;
+        let (response, _code) = index._add_documents(documents, None, None).await;
         server.wait_task(response.uid()).await.succeeded();
         let (response, _code) = index
             ._update_settings(
@@ -508,7 +508,7 @@ pub async fn shared_index_with_geo_documents() -> &'static Index<'static, Shared
         .get_or_init(|| async {
             let server = Server::new_shared();
             let index = server._index("SHARED_GEO_DOCUMENTS").to_shared();
-            let (response, _code) = index._add_documents(GEO_DOCUMENTS.clone(), None).await;
+            let (response, _code) = index._add_documents(GEO_DOCUMENTS.clone(), None, None).await;
             server.wait_task(response.uid()).await.succeeded();
 
             let (response, _code) = index
@@ -531,7 +531,7 @@ pub async fn shared_index_geojson_documents() -> &'static Index<'static, Shared>
             let index = server._index("SHARED_GEOJSON_DOCUMENTS").to_shared();
             let countries = include_str!("../documents/geojson/assets/countries.json");
             let lille = serde_json::from_str::<serde_json::Value>(countries).unwrap();
-            let (response, _code) = index._add_documents(Value(lille), Some("name")).await;
+            let (response, _code) = index._add_documents(Value(lille), Some("name"), None).await;
             server.wait_task(response.uid()).await.succeeded();
 
             let (response, _code) =

crates/meilisearch/tests/common/server.rs

@@ -49,8 +49,8 @@ impl Server<Owned> {
         }
 
         let options = default_settings(dir.path());
-
-        let (index_scheduler, auth) = setup_meilisearch(&options).unwrap();
+        let handle = tokio::runtime::Handle::current();
+        let (index_scheduler, auth) = setup_meilisearch(&options, handle).unwrap();
         let service = Service { index_scheduler, auth, options, api_key: None };
 
         Server { service, _dir: Some(dir), _marker: PhantomData }
@@ -65,7 +65,9 @@ impl Server<Owned> {
 
         options.master_key = Some("MASTER_KEY".to_string());
 
-        let (index_scheduler, auth) = setup_meilisearch(&options).unwrap();
+        let handle = tokio::runtime::Handle::current();
+
+        let (index_scheduler, auth) = setup_meilisearch(&options, handle).unwrap();
         let service = Service { index_scheduler, auth, options, api_key: None };
 
         Server { service, _dir: Some(dir), _marker: PhantomData }
@@ -78,7 +80,9 @@ impl Server<Owned> {
     }
 
     pub async fn new_with_options(options: Opt) -> Result<Self, anyhow::Error> {
-        let (index_scheduler, auth) = setup_meilisearch(&options)?;
+        let handle = tokio::runtime::Handle::current();
+
+        let (index_scheduler, auth) = setup_meilisearch(&options, handle)?;
         let service = Service { index_scheduler, auth, options, api_key: None };
 
         Ok(Server { service, _dir: None, _marker: PhantomData })
@@ -217,8 +221,9 @@ impl Server<Shared> {
         }
 
         let options = default_settings(dir.path());
+        let handle = tokio::runtime::Handle::current();
 
-        let (index_scheduler, auth) = setup_meilisearch(&options).unwrap();
+        let (index_scheduler, auth) = setup_meilisearch(&options, handle).unwrap();
         let service = Service { index_scheduler, auth, api_key: None, options };
 
         Server { service, _dir: Some(dir), _marker: PhantomData }

crates/meilisearch/tests/common/service.rs

@@ -10,8 +10,9 @@ use actix_web::test::TestRequest;
 use actix_web::web::Data;
 use index_scheduler::IndexScheduler;
 use meilisearch::analytics::Analytics;
+use meilisearch::personalization::PersonalizationService;
 use meilisearch::search_queue::SearchQueue;
-use meilisearch::{create_app, Opt, SubscriberForSecondLayer};
+use meilisearch::{create_app, Opt, ServicesData, SubscriberForSecondLayer};
 use meilisearch_auth::AuthController;
 use tracing::level_filters::LevelFilter;
 use tracing_subscriber::Layer;
@@ -135,14 +136,24 @@ impl Service {
             self.options.experimental_search_queue_size,
             NonZeroUsize::new(1).unwrap(),
         );
+        let personalization_service = self
+            .options
+            .experimental_personalization_api_key
+            .clone()
+            .map(PersonalizationService::cohere)
+            .unwrap_or_else(PersonalizationService::disabled);
 
         actix_web::test::init_service(create_app(
-            self.index_scheduler.clone().into(),
-            self.auth.clone().into(),
-            Data::new(search_queue),
+            ServicesData {
+                index_scheduler: self.index_scheduler.clone().into(),
+                auth: self.auth.clone().into(),
+                search_queue: Data::new(search_queue),
+                personalization_service: Data::new(personalization_service),
+                logs_route_handle: Data::new(route_layer_handle),
+                logs_stderr_handle: Data::new(stderr_layer_handle),
+                analytics: Data::new(Analytics::no_analytics()),
+            },
             self.options.clone(),
-            (route_layer_handle, stderr_layer_handle),
-            Data::new(Analytics::no_analytics()),
             true,
         ))
         .await

crates/meilisearch/tests/documents/get_documents.rs

@@ -1339,3 +1339,117 @@ async fn get_document_with_vectors() {
     }
     "###);
 }
+
+#[actix_rt::test]
+async fn test_fetch_documents_pagination_with_sorting() {
+    let server = Server::new_shared();
+    let index = server.unique_index();
+    let (task, _code) = index.create(None).await;
+    server.wait_task(task.uid()).await.succeeded();
+
+    // Set name as sortable attribute
+    let (task, code) = index.update_settings_sortable_attributes(json!(["name"])).await;
+    assert_eq!(code, 202);
+    server.wait_task(task.uid()).await.succeeded();
+
+    let documents = json!((0..50)
+        .map(|i| json!({"id": i, "name": format!("doc_{:05}", std::cmp::min(i, 5))}))
+        .collect::<Vec<_>>());
+
+    // Add documents as described in the bug report
+    let (task, code) = index.add_documents(documents, None).await;
+    assert_eq!(code, 202);
+    server.wait_task(task.uid()).await.succeeded();
+
+    // Request 1 (first page): offset 0, limit 2
+    let (response, code) = index
+        .fetch_documents(json!({
+            "offset": 0,
+            "limit": 2,
+            "sort": ["name:asc"]
+        }))
+        .await;
+    assert_eq!(code, 200);
+    let results = response["results"].as_array().unwrap();
+    snapshot!(json_string!(results), @r###"
+    [
+      {
+        "id": 0,
+        "name": "doc_00000"
+      },
+      {
+        "id": 1,
+        "name": "doc_00001"
+      }
+    ]
+    "###);
+
+    // Request 2 (second page): offset 2, limit 2
+    let (response, code) = index
+        .fetch_documents(json!({
+            "offset": 2,
+            "limit": 2,
+            "sort": ["name:asc"]
+        }))
+        .await;
+    assert_eq!(code, 200);
+    let results = response["results"].as_array().unwrap();
+    snapshot!(json_string!(results), @r###"
+    [
+      {
+        "id": 2,
+        "name": "doc_00002"
+      },
+      {
+        "id": 3,
+        "name": "doc_00003"
+      }
+    ]
+    "###);
+
+    // Request 3 (third page): offset 4, limit 2
+    let (response, code) = index
+        .fetch_documents(json!({
+            "offset": 4,
+            "limit": 2,
+            "sort": ["name:asc"]
+        }))
+        .await;
+    assert_eq!(code, 200);
+    let results = response["results"].as_array().unwrap();
+    snapshot!(json_string!(results), @r###"
+    [
+      {
+        "id": 4,
+        "name": "doc_00004"
+      },
+      {
+        "id": 5,
+        "name": "doc_00005"
+      }
+    ]
+    "###);
+
+    // Request 4 (fourth page): offset 6, limit 2
+    let (response, code) = index
+        .fetch_documents(json!({
+            "offset": 6,
+            "limit": 2,
+            "sort": ["name:asc"]
+        }))
+        .await;
+    assert_eq!(code, 200);
+    let results = response["results"].as_array().unwrap();
+    snapshot!(json_string!(results), @r###"
+    [
+      {
+        "id": 6,
+        "name": "doc_00005"
+      },
+      {
+        "id": 7,
+        "name": "doc_00005"
+      }
+    ]
+    "###);
+}

crates/meilisearch/tests/features/mod.rs

@@ -207,3 +207,118 @@ async fn errors() {
     }
     "###);
 }
+
+#[actix_rt::test]
+async fn search_with_personalization_without_enabling_the_feature() {
+    let server = Server::new().await;
+    let index = server.unique_index();
+
+    // Create the index and add some documents
+    let (task, _code) = index.create(None).await;
+    server.wait_task(task.uid()).await.succeeded();
+
+    let (task, _code) = index
+        .add_documents(
+            json!([
+                {"id": 1, "title": "The Dark Knight", "genre": "Action"},
+                {"id": 2, "title": "Inception", "genre": "Sci-Fi"},
+                {"id": 3, "title": "The Matrix", "genre": "Sci-Fi"}
+            ]),
+            None,
+        )
+        .await;
+    server.wait_task(task.uid()).await.succeeded();
+
+    // Try to search with personalization - should return feature_not_enabled error
+    let (response, code) = index
+        .search_post(json!({
+            "q": "movie",
+            "personalize": {
+                "userContext": "I love science fiction movies"
+            }
+        }))
+        .await;
+
+    meili_snap::snapshot!(code, @"400 Bad Request");
+    meili_snap::snapshot!(meili_snap::json_string!(response), @r###"
+    {
+      "message": "reranking search results requires enabling the `personalization` experimental feature. See https://github.com/orgs/meilisearch/discussions/866",
+      "code": "feature_not_enabled",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#feature_not_enabled"
+    }
+    "###);
+}
+
+#[actix_rt::test]
+async fn multi_search_with_personalization_without_enabling_the_feature() {
+    let server = Server::new().await;
+    let index = server.unique_index();
+
+    // Create the index and add some documents
+    let (task, _code) = index.create(None).await;
+    server.wait_task(task.uid()).await.succeeded();
+
+    let (task, _code) = index
+        .add_documents(
+            json!([
+                {"id": 1, "title": "The Dark Knight", "genre": "Action"},
+                {"id": 2, "title": "Inception", "genre": "Sci-Fi"},
+                {"id": 3, "title": "The Matrix", "genre": "Sci-Fi"}
+            ]),
+            None,
+        )
+        .await;
+    server.wait_task(task.uid()).await.succeeded();
+
+    // Try to multi-search with personalization - should return feature_not_enabled error
+    let (response, code) = server
+        .multi_search(json!({
+            "queries": [
+                {
+                    "indexUid": index.uid,
+                    "q": "movie",
+                    "personalize": {
+                        "userContext": "I love science fiction movies"
+                    }
+                }
+            ]
+        }))
+        .await;
+
+    meili_snap::snapshot!(code, @"400 Bad Request");
+    meili_snap::snapshot!(meili_snap::json_string!(response), @r###"
+    {
+      "message": "Inside `.queries[0]`: reranking search results requires enabling the `personalization` experimental feature. See https://github.com/orgs/meilisearch/discussions/866",
+      "code": "feature_not_enabled",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#feature_not_enabled"
+    }
+    "###);
+
+    // Try to federated search with personalization - should return feature_not_enabled error
+    let (response, code) = server
+        .multi_search(json!({
+          "federation": {},
+            "queries": [
+                {
+                    "indexUid": index.uid,
+                    "q": "movie",
+                    "personalize": {
+                        "userContext": "I love science fiction movies"
+                    }
+                }
+            ]
+        }))
+        .await;
+
+    meili_snap::snapshot!(code, @"400 Bad Request");
+    meili_snap::snapshot!(meili_snap::json_string!(response), @r###"
+    {
+      "message": "Inside `.queries[0]`: Using `.personalize` is not allowed in federated queries.\n - Hint: remove `personalize` from query #0 or remove `federation` from the request",
+      "code": "invalid_multi_search_query_personalization",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#invalid_multi_search_query_personalization"
+    }
+    "###);
+}

crates/meilisearch/tests/logs/mod.rs

@@ -8,8 +8,9 @@ use actix_web::http::header::ContentType;
 use actix_web::web::Data;
 use meili_snap::snapshot;
 use meilisearch::analytics::Analytics;
+use meilisearch::personalization::PersonalizationService;
 use meilisearch::search_queue::SearchQueue;
-use meilisearch::{create_app, Opt, SubscriberForSecondLayer};
+use meilisearch::{create_app, Opt, ServicesData, SubscriberForSecondLayer};
 use tracing::level_filters::LevelFilter;
 use tracing_subscriber::layer::SubscriberExt;
 use tracing_subscriber::Layer;
@@ -50,12 +51,16 @@ async fn basic_test_log_stream_route() {
     );
 
     let app = actix_web::test::init_service(create_app(
-        server.service.index_scheduler.clone().into(),
-        server.service.auth.clone().into(),
-        Data::new(search_queue),
+        ServicesData {
+            index_scheduler: server.service.index_scheduler.clone().into(),
+            auth: server.service.auth.clone().into(),
+            search_queue: Data::new(search_queue),
+            personalization_service: Data::new(PersonalizationService::disabled()),
+            logs_route_handle: Data::new(route_layer_handle),
+            logs_stderr_handle: Data::new(stderr_layer_handle),
+            analytics: Data::new(Analytics::no_analytics()),
+        },
         server.service.options.clone(),
-        (route_layer_handle, stderr_layer_handle),
-        Data::new(Analytics::no_analytics()),
         true,
     ))
     .await;

crates/meilisearch/tests/search/errors.rs

@@ -1,7 +1,11 @@
 use meili_snap::*;
+use meilisearch::Opt;
+use tempfile::TempDir;
 
 use super::test_settings_documents_indexing_swapping_and_search;
-use crate::common::{shared_does_not_exists_index, Server, DOCUMENTS, NESTED_DOCUMENTS};
+use crate::common::{
+    default_settings, shared_does_not_exists_index, Server, DOCUMENTS, NESTED_DOCUMENTS,
+};
 use crate::json;
 
 #[actix_rt::test]
@@ -1320,3 +1324,98 @@ async fn search_with_contains_without_enabling_the_feature() {
     }
     "#);
 }
+
+#[actix_rt::test]
+#[ignore]
+async fn search_with_personalization_invalid_api_key() {
+    // Create a server with a fake personalization API key
+    let dir = TempDir::new().unwrap();
+    let options = Opt {
+        experimental_personalization_api_key: Some("fake-api-key-12345".to_string()),
+        ..default_settings(dir.path())
+    };
+    let server = Server::new_with_options(options).await.unwrap();
+    let index = server.unique_index();
+
+    // Create the index and add some documents
+    let (task, _code) = index.create(None).await;
+    server.wait_task(task.uid()).await.succeeded();
+
+    let (task, _code) = index
+        .add_documents(
+            json!([
+                {"id": 1, "title": "The Dark Knight", "genre": "Action"},
+                {"id": 2, "title": "Inception", "genre": "Sci-Fi"},
+                {"id": 3, "title": "The Matrix", "genre": "Sci-Fi"}
+            ]),
+            None,
+        )
+        .await;
+    server.wait_task(task.uid()).await.succeeded();
+
+    // Try to search with personalization - should return remote_invalid_api_key error
+    let (response, code) = index
+        .search_post(json!({
+            "q": "the",
+            "personalize": {
+                "userContext": "I love science fiction movies"
+            }
+        }))
+        .await;
+
+    snapshot!(code, @"403 Forbidden");
+    snapshot!(json_string!(response), @r#"
+    {
+      "message": "Personalization service: Unauthorized: invalid API key",
+      "code": "remote_invalid_api_key",
+      "type": "auth",
+      "link": "https://docs.meilisearch.com/errors#remote_invalid_api_key"
+    }
+    "#);
+}
+
+#[actix_rt::test]
+async fn search_with_personalization_no_user_context() {
+    // Create a server with a fake personalization API key
+    let dir = TempDir::new().unwrap();
+    let options = Opt {
+        experimental_personalization_api_key: Some("fake-api-key-12345".to_string()),
+        ..default_settings(dir.path())
+    };
+    let server = Server::new_with_options(options).await.unwrap();
+    let index = server.unique_index();
+
+    // Create the index and add some documents
+    let (task, _code) = index.create(None).await;
+    server.wait_task(task.uid()).await.succeeded();
+
+    let (task, _code) = index
+        .add_documents(
+            json!([
+                {"id": 1, "title": "The Dark Knight", "genre": "Action"},
+                {"id": 2, "title": "Inception", "genre": "Sci-Fi"},
+                {"id": 3, "title": "The Matrix", "genre": "Sci-Fi"}
+            ]),
+            None,
+        )
+        .await;
+    server.wait_task(task.uid()).await.succeeded();
+
+    // Try to search with personalization - should return remote_invalid_api_key error
+    let (response, code) = index
+        .search_post(json!({
+            "q": "the",
+            "personalize": {}
+        }))
+        .await;
+
+    snapshot!(code, @"400 Bad Request");
+    snapshot!(json_string!(response), @r###"
+    {
+      "message": "Missing field `userContext` inside `.personalize`",
+      "code": "invalid_search_personalize",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#invalid_search_personalize"
+    }
+    "###);
+}

crates/meilisearch/tests/search/hybrid.rs

@@ -137,6 +137,60 @@ static SIMPLE_SEARCH_DOCUMENTS: Lazy<Value> = Lazy::new(|| {
     }])
 });
 
+static MANY_DOCS: Lazy<Value> = Lazy::new(|| {
+    json!([
+    {
+        "title": "Shazam!",
+        "desc": "a Captain Marvel ersatz",
+        "id": "1",
+    },
+    {
+        "title": "Captain Planet",
+        "desc": "He's not part of the Marvel Cinematic Universe",
+        "id": "2",
+    },
+    {
+        "title": "Captain Marvel",
+        "desc": "a Shazam ersatz",
+        "id": "3",
+    },
+        {
+        "title": "Captain Marvel",
+        "desc": "a Shazam ersatz",
+        "id": "4",
+    },
+        {
+        "title": "Captain Marvel",
+        "desc": "a Shazam ersatz",
+        "id": "5",
+    },
+        {
+        "title": "Captain Marvel",
+        "desc": "a Shazam ersatz",
+        "id": "6",
+    },
+        {
+        "title": "Captain Marvel",
+        "desc": "a Shazam ersatz",
+        "id": "7",
+    },
+        {
+        "title": "Captain Marvel",
+        "desc": "a Shazam ersatz",
+        "id": "8",
+    },
+        {
+        "title": "Captain Marvel",
+        "desc": "a Shazam ersatz",
+        "id": "9",
+    },
+        {
+        "title": "Captain Marvel",
+        "desc": "a Shazam ersatz",
+        "id": "10",
+    }])
+});
+
 #[actix_rt::test]
 async fn simple_search() {
     let server = Server::new_shared();
@@ -449,6 +503,38 @@ async fn simple_search_hf() {
     snapshot!(response["semanticHitCount"], @"3");
 }
 
+#[actix_rt::test]
+async fn issue_5976_missing_docs_hf() {
+    let server = Server::new_shared();
+    let index = index_with_documents_hf(server, &MANY_DOCS).await;
+    let (response, code) = index
+        .search_post(
+            json!({"q": "Wonder replacement", "hybrid": {"embedder": "default", "semanticRatio": 1.0}, "retrieveVectors": true}),
+        )
+        .await;
+    snapshot!(code, @"200 OK");
+    let are_empty: Vec<_> = response["hits"]
+        .as_array()
+        .unwrap()
+        .iter()
+        .map(|hit| hit["_vectors"]["default"]["embeddings"].as_array().unwrap().is_empty())
+        .collect();
+    snapshot!(json!(are_empty), @r###"
+    [
+      false,
+      false,
+      false,
+      false,
+      false,
+      false,
+      false,
+      false,
+      false,
+      false
+    ]
+    "###);
+}
+
 #[actix_rt::test]
 async fn distribution_shift() {
     let server = Server::new_shared();

crates/meilisearch/tests/search/multi/proxy.rs

@@ -3141,3 +3141,537 @@ fn fail(override_response_body: Option<&str>) -> ResponseTemplate {
         response.set_body_json(json!({"error": "provoked error", "code": "test_error", "link": "https://docs.meilisearch.com/errors#test_error"}))
     }
 }
+
+#[cfg(feature = "enterprise")]
+#[actix_rt::test]
+async fn remote_auto_sharding() {
+    let ms0 = Server::new().await;
+    let ms1 = Server::new().await;
+    let ms2 = Server::new().await;
+
+    // enable feature
+
+    let (response, code) = ms0.set_features(json!({"network": true})).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(response["network"]), @"true");
+    let (response, code) = ms1.set_features(json!({"network": true})).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(response["network"]), @"true");
+    let (response, code) = ms2.set_features(json!({"network": true})).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(response["network"]), @"true");
+
+    // set self & sharding
+    let (response, code) = ms0.set_network(json!({"self": "ms0", "sharding": true})).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(response), @r###"
+    {
+      "self": "ms0",
+      "remotes": {},
+      "sharding": true
+    }
+    "###);
+    let (response, code) = ms1.set_network(json!({"self": "ms1", "sharding": true})).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(response), @r###"
+    {
+      "self": "ms1",
+      "remotes": {},
+      "sharding": true
+    }
+    "###);
+    let (response, code) = ms2.set_network(json!({"self": "ms2", "sharding": true})).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(response), @r###"
+    {
+      "self": "ms2",
+      "remotes": {},
+      "sharding": true
+    }
+    "###);
+
+    // wrap servers
+    let ms0 = Arc::new(ms0);
+    let ms1 = Arc::new(ms1);
+    let ms2 = Arc::new(ms2);
+
+    let rms0 = LocalMeili::new(ms0.clone()).await;
+    let rms1 = LocalMeili::new(ms1.clone()).await;
+    let rms2 = LocalMeili::new(ms2.clone()).await;
+
+    // set network
+    let network = json!({"remotes": {
+        "ms0": {
+            "url": rms0.url()
+        },
+        "ms1": {
+            "url": rms1.url()
+        },
+        "ms2": {
+            "url": rms2.url()
+        }
+    }});
+
+    println!("{}", serde_json::to_string_pretty(&network).unwrap());
+
+    let (_response, status_code) = ms0.set_network(network.clone()).await;
+    snapshot!(status_code, @"200 OK");
+    let (_response, status_code) = ms1.set_network(network.clone()).await;
+    snapshot!(status_code, @"200 OK");
+    let (_response, status_code) = ms2.set_network(network.clone()).await;
+    snapshot!(status_code, @"200 OK");
+
+    // add documents
+    let documents = SCORE_DOCUMENTS.clone();
+    let documents = documents.as_array().unwrap();
+    let index0 = ms0.index("test");
+    let _index1 = ms1.index("test");
+    let _index2 = ms2.index("test");
+
+    let (task, _status_code) = index0.add_documents(json!(documents), None).await;
+
+    let t0 = task.uid();
+    let (t, _) = ms0.get_task(task.uid()).await;
+    let t1 = t["network"]["remote_tasks"]["ms1"]["taskUid"].as_u64().unwrap();
+    let t2 = t["network"]["remote_tasks"]["ms2"]["taskUid"].as_u64().unwrap();
+
+    ms0.wait_task(t0).await.succeeded();
+    ms1.wait_task(t1).await.succeeded();
+    ms2.wait_task(t2).await.succeeded();
+
+    // perform multi-search
+    let query = "badman returns";
+    let request = json!({
+        "federation": {},
+        "queries": [
+            {
+                "q": query,
+                "indexUid": "test",
+                "federationOptions": {
+                    "remote": "ms0"
+                }
+            },
+            {
+                "q": query,
+                "indexUid": "test",
+                "federationOptions": {
+                    "remote": "ms1"
+                }
+            },
+            {
+                "q": query,
+                "indexUid": "test",
+                "federationOptions": {
+                    "remote": "ms2"
+                }
+            },
+        ]
+    });
+
+    let (response, _status_code) = ms0.multi_search(request.clone()).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(response, { ".processingTimeMs" => "[time]", ".requestUid" => "[uuid]" }), @r###"
+    {
+      "hits": [
+        {
+          "title": "Batman Returns",
+          "id": "C",
+          "_federation": {
+            "indexUid": "test",
+            "queriesPosition": 2,
+            "weightedRankingScore": 0.8317901234567902,
+            "remote": "ms2"
+          }
+        },
+        {
+          "title": "Batman the dark knight returns: Part 1",
+          "id": "A",
+          "_federation": {
+            "indexUid": "test",
+            "queriesPosition": 1,
+            "weightedRankingScore": 0.7028218694885362,
+            "remote": "ms1"
+          }
+        },
+        {
+          "title": "Batman the dark knight returns: Part 2",
+          "id": "B",
+          "_federation": {
+            "indexUid": "test",
+            "queriesPosition": 1,
+            "weightedRankingScore": 0.7028218694885362,
+            "remote": "ms1"
+          }
+        },
+        {
+          "title": "Badman",
+          "id": "E",
+          "_federation": {
+            "indexUid": "test",
+            "queriesPosition": 2,
+            "weightedRankingScore": 0.5,
+            "remote": "ms2"
+          }
+        },
+        {
+          "title": "Batman",
+          "id": "D",
+          "_federation": {
+            "indexUid": "test",
+            "queriesPosition": 0,
+            "weightedRankingScore": 0.23106060606060605,
+            "remote": "ms0"
+          }
+        }
+      ],
+      "processingTimeMs": "[time]",
+      "limit": 20,
+      "offset": 0,
+      "estimatedTotalHits": 5,
+      "requestUid": "[uuid]",
+      "remoteErrors": {}
+    }
+    "###);
+    let (response, _status_code) = ms1.multi_search(request.clone()).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(response, { ".processingTimeMs" => "[time]", ".requestUid" => "[uuid]" }), @r###"
+    {
+      "hits": [
+        {
+          "title": "Batman Returns",
+          "id": "C",
+          "_federation": {
+            "indexUid": "test",
+            "queriesPosition": 2,
+            "weightedRankingScore": 0.8317901234567902,
+            "remote": "ms2"
+          }
+        },
+        {
+          "title": "Batman the dark knight returns: Part 1",
+          "id": "A",
+          "_federation": {
+            "indexUid": "test",
+            "queriesPosition": 1,
+            "weightedRankingScore": 0.7028218694885362,
+            "remote": "ms1"
+          }
+        },
+        {
+          "title": "Batman the dark knight returns: Part 2",
+          "id": "B",
+          "_federation": {
+            "indexUid": "test",
+            "queriesPosition": 1,
+            "weightedRankingScore": 0.7028218694885362,
+            "remote": "ms1"
+          }
+        },
+        {
+          "title": "Badman",
+          "id": "E",
+          "_federation": {
+            "indexUid": "test",
+            "queriesPosition": 2,
+            "weightedRankingScore": 0.5,
+            "remote": "ms2"
+          }
+        },
+        {
+          "title": "Batman",
+          "id": "D",
+          "_federation": {
+            "indexUid": "test",
+            "queriesPosition": 0,
+            "weightedRankingScore": 0.23106060606060605,
+            "remote": "ms0"
+          }
+        }
+      ],
+      "processingTimeMs": "[time]",
+      "limit": 20,
+      "offset": 0,
+      "estimatedTotalHits": 5,
+      "requestUid": "[uuid]",
+      "remoteErrors": {}
+    }
+    "###);
+    let (response, _status_code) = ms2.multi_search(request.clone()).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(response, { ".processingTimeMs" => "[time]", ".requestUid" => "[uuid]" }), @r###"
+    {
+      "hits": [
+        {
+          "title": "Batman Returns",
+          "id": "C",
+          "_federation": {
+            "indexUid": "test",
+            "queriesPosition": 2,
+            "weightedRankingScore": 0.8317901234567902,
+            "remote": "ms2"
+          }
+        },
+        {
+          "title": "Batman the dark knight returns: Part 1",
+          "id": "A",
+          "_federation": {
+            "indexUid": "test",
+            "queriesPosition": 1,
+            "weightedRankingScore": 0.7028218694885362,
+            "remote": "ms1"
+          }
+        },
+        {
+          "title": "Batman the dark knight returns: Part 2",
+          "id": "B",
+          "_federation": {
+            "indexUid": "test",
+            "queriesPosition": 1,
+            "weightedRankingScore": 0.7028218694885362,
+            "remote": "ms1"
+          }
+        },
+        {
+          "title": "Badman",
+          "id": "E",
+          "_federation": {
+            "indexUid": "test",
+            "queriesPosition": 2,
+            "weightedRankingScore": 0.5,
+            "remote": "ms2"
+          }
+        },
+        {
+          "title": "Batman",
+          "id": "D",
+          "_federation": {
+            "indexUid": "test",
+            "queriesPosition": 0,
+            "weightedRankingScore": 0.23106060606060605,
+            "remote": "ms0"
+          }
+        }
+      ],
+      "processingTimeMs": "[time]",
+      "limit": 20,
+      "offset": 0,
+      "estimatedTotalHits": 5,
+      "requestUid": "[uuid]",
+      "remoteErrors": {}
+    }
+    "###);
+}
+
+#[cfg(not(feature = "enterprise"))]
+#[actix_rt::test]
+async fn sharding_not_enterprise() {
+    let ms0 = Server::new().await;
+
+    // enable feature
+
+    let (response, code) = ms0.set_features(json!({"network": true})).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(response["network"]), @"true");
+
+    let (response, code) = ms0.set_network(json!({"self": "ms0", "sharding": true})).await;
+    snapshot!(code, @"451 Unavailable For Legal Reasons");
+    snapshot!(json_string!(response), @r###"
+    {
+      "message": "Meilisearch Enterprise Edition is required to set `network.sharding`",
+      "code": "requires_enterprise_edition",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#requires_enterprise_edition"
+    }
+    "###);
+}
+
+#[cfg(feature = "enterprise")]
+#[actix_rt::test]
+async fn remote_auto_sharding_with_custom_metadata() {
+    let ms0 = Server::new().await;
+    let ms1 = Server::new().await;
+    let ms2 = Server::new().await;
+
+    // enable feature
+
+    let (response, code) = ms0.set_features(json!({"network": true})).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(response["network"]), @"true");
+    let (response, code) = ms1.set_features(json!({"network": true})).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(response["network"]), @"true");
+    let (response, code) = ms2.set_features(json!({"network": true})).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(response["network"]), @"true");
+
+    // set self & sharding
+
+    let (response, code) = ms0.set_network(json!({"self": "ms0", "sharding": true})).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(response), @r###"
+    {
+      "self": "ms0",
+      "remotes": {},
+      "sharding": true
+    }
+    "###);
+    let (response, code) = ms1.set_network(json!({"self": "ms1", "sharding": true})).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(response), @r###"
+    {
+      "self": "ms1",
+      "remotes": {},
+      "sharding": true
+    }
+    "###);
+    let (response, code) = ms2.set_network(json!({"self": "ms2", "sharding": true})).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(response), @r###"
+    {
+      "self": "ms2",
+      "remotes": {},
+      "sharding": true
+    }
+    "###);
+
+    // wrap servers
+    let ms0 = Arc::new(ms0);
+    let ms1 = Arc::new(ms1);
+    let ms2 = Arc::new(ms2);
+
+    let rms0 = LocalMeili::new(ms0.clone()).await;
+    let rms1 = LocalMeili::new(ms1.clone()).await;
+    let rms2 = LocalMeili::new(ms2.clone()).await;
+
+    // set network
+    let network = json!({"remotes": {
+        "ms0": {
+            "url": rms0.url()
+        },
+        "ms1": {
+            "url": rms1.url()
+        },
+        "ms2": {
+            "url": rms2.url()
+        }
+    }});
+
+    println!("{}", serde_json::to_string_pretty(&network).unwrap());
+
+    let (_response, status_code) = ms0.set_network(network.clone()).await;
+    snapshot!(status_code, @"200 OK");
+    let (_response, status_code) = ms1.set_network(network.clone()).await;
+    snapshot!(status_code, @"200 OK");
+    let (_response, status_code) = ms2.set_network(network.clone()).await;
+    snapshot!(status_code, @"200 OK");
+
+    // add documents
+    let documents = SCORE_DOCUMENTS.clone();
+    let documents = documents.as_array().unwrap();
+    let index0 = ms0.index("test");
+    let _index1 = ms1.index("test");
+    let _index2 = ms2.index("test");
+
+    let (task, _status_code) = index0
+        .add_documents_with_custom_metadata(
+            json!(documents),
+            None,
+            Some("remote_auto_sharding_with_custom_metadata"),
+        )
+        .await;
+
+    let t0 = task.uid();
+    let (t, _) = ms0.get_task(task.uid()).await;
+    let t1 = t["network"]["remote_tasks"]["ms1"]["taskUid"].as_u64().unwrap();
+    let t2 = t["network"]["remote_tasks"]["ms2"]["taskUid"].as_u64().unwrap();
+
+    let t = ms0.wait_task(t0).await.succeeded();
+    snapshot!(t, @r###"
+    {
+      "uid": "[uid]",
+      "batchUid": "[batch_uid]",
+      "indexUid": "test",
+      "status": "succeeded",
+      "type": "documentAdditionOrUpdate",
+      "canceledBy": null,
+      "details": {
+        "receivedDocuments": 5,
+        "indexedDocuments": 1
+      },
+      "error": null,
+      "duration": "[duration]",
+      "enqueuedAt": "[date]",
+      "startedAt": "[date]",
+      "finishedAt": "[date]",
+      "network": {
+        "remote_tasks": {
+          "ms1": {
+            "taskUid": 0,
+            "error": null
+          },
+          "ms2": {
+            "taskUid": 0,
+            "error": null
+          }
+        }
+      },
+      "customMetadata": "remote_auto_sharding_with_custom_metadata"
+    }
+    "###);
+
+    let t = ms1.wait_task(t1).await.succeeded();
+    snapshot!(t, @r###"
+    {
+      "uid": "[uid]",
+      "batchUid": "[batch_uid]",
+      "indexUid": "test",
+      "status": "succeeded",
+      "type": "documentAdditionOrUpdate",
+      "canceledBy": null,
+      "details": {
+        "receivedDocuments": 5,
+        "indexedDocuments": 2
+      },
+      "error": null,
+      "duration": "[duration]",
+      "enqueuedAt": "[date]",
+      "startedAt": "[date]",
+      "finishedAt": "[date]",
+      "network": {
+        "origin": {
+          "remoteName": "ms0",
+          "taskUid": 0
+        }
+      },
+      "customMetadata": "remote_auto_sharding_with_custom_metadata"
+    }
+    "###);
+
+    let t = ms2.wait_task(t2).await.succeeded();
+    snapshot!(t, @r###"
+    {
+      "uid": "[uid]",
+      "batchUid": "[batch_uid]",
+      "indexUid": "test",
+      "status": "succeeded",
+      "type": "documentAdditionOrUpdate",
+      "canceledBy": null,
+      "details": {
+        "receivedDocuments": 5,
+        "indexedDocuments": 2
+      },
+      "error": null,
+      "duration": "[duration]",
+      "enqueuedAt": "[date]",
+      "startedAt": "[date]",
+      "finishedAt": "[date]",
+      "network": {
+        "origin": {
+          "remoteName": "ms0",
+          "taskUid": 0
+        }
+      },
+      "customMetadata": "remote_auto_sharding_with_custom_metadata"
+    }
+    "###);
+}

crates/meilisearch/tests/tasks/webhook.rs

@@ -82,7 +82,7 @@ async fn cli_only() {
 
     let (webhooks, code) = server.get_webhooks().await;
     snapshot!(code, @"200 OK");
-    snapshot!(webhooks, @r#"
+    snapshot!(webhooks, @r###"
     {
       "results": [
         {
@@ -90,12 +90,12 @@ async fn cli_only() {
           "isEditable": false,
           "url": "https://example-cli.com/",
           "headers": {
-            "Authorization": "Bearer a-secret-token"
+            "Authorization": "Bearer a-XXXX..."
           }
         }
       ]
     }
-    "#);
+    "###);
 }
 
 #[actix_web::test]
@@ -233,7 +233,7 @@ async fn cli_with_dumps() {
 
     let (webhooks, code) = server.get_webhooks().await;
     snapshot!(code, @"200 OK");
-    snapshot!(webhooks, @r#"
+    snapshot!(webhooks, @r###"
     {
       "results": [
         {
@@ -241,7 +241,7 @@ async fn cli_with_dumps() {
           "isEditable": false,
           "url": "http://defined-in-test-cli.com/",
           "headers": {
-            "Authorization": "Bearer a-secret-token-defined-in-test-cli"
+            "Authorization": "Bearer a-secXXXXXX..."
           }
         },
         {
@@ -255,7 +255,7 @@ async fn cli_with_dumps() {
           "isEditable": true,
           "url": "https://example.com/hook",
           "headers": {
-            "authorization": "TOKEN"
+            "authorization": "XXX..."
           }
         },
         {
@@ -266,7 +266,7 @@ async fn cli_with_dumps() {
         }
       ]
     }
-    "#);
+    "###);
 }
 
 #[actix_web::test]
@@ -367,30 +367,30 @@ async fn post_get_delete() {
         }))
         .await;
     snapshot!(code, @"201 Created");
-    snapshot!(json_string!(value, { ".uuid" => "[uuid]" }), @r#"
+    snapshot!(json_string!(value, { ".uuid" => "[uuid]" }), @r###"
     {
       "uuid": "[uuid]",
       "isEditable": true,
       "url": "https://example.com/hook",
       "headers": {
-        "authorization": "TOKEN"
+        "authorization": "XXX..."
       }
     }
-    "#);
+    "###);
 
     let uuid = value.get("uuid").unwrap().as_str().unwrap();
     let (value, code) = server.get_webhook(uuid).await;
     snapshot!(code, @"200 OK");
-    snapshot!(json_string!(value, { ".uuid" => "[uuid]" }), @r#"
+    snapshot!(json_string!(value, { ".uuid" => "[uuid]" }), @r###"
     {
       "uuid": "[uuid]",
       "isEditable": true,
       "url": "https://example.com/hook",
       "headers": {
-        "authorization": "TOKEN"
+        "authorization": "XXX..."
       }
     }
-    "#);
+    "###);
 
     let (_value, code) = server.delete_webhook(uuid).await;
     snapshot!(code, @"204 No Content");
@@ -430,31 +430,31 @@ async fn create_and_patch() {
     let (value, code) =
         server.patch_webhook(&uuid, json!({ "headers": { "authorization": "TOKEN" } })).await;
     snapshot!(code, @"200 OK");
-    snapshot!(json_string!(value, { ".uuid" => "[uuid]" }), @r#"
+    snapshot!(json_string!(value, { ".uuid" => "[uuid]" }), @r###"
     {
       "uuid": "[uuid]",
       "isEditable": true,
       "url": "https://example.com/hook",
       "headers": {
-        "authorization": "TOKEN"
+        "authorization": "XXX..."
       }
     }
-    "#);
+    "###);
 
     let (value, code) =
         server.patch_webhook(&uuid, json!({ "headers": { "authorization2": "TOKEN" } })).await;
     snapshot!(code, @"200 OK");
-    snapshot!(json_string!(value, { ".uuid" => "[uuid]" }), @r#"
+    snapshot!(json_string!(value, { ".uuid" => "[uuid]" }), @r###"
     {
       "uuid": "[uuid]",
       "isEditable": true,
       "url": "https://example.com/hook",
       "headers": {
-        "authorization": "TOKEN",
+        "authorization": "XXX...",
         "authorization2": "TOKEN"
       }
     }
-    "#);
+    "###);
 
     let (value, code) =
         server.patch_webhook(&uuid, json!({ "headers": { "authorization": null } })).await;
@@ -656,3 +656,119 @@ async fn forbidden_fields() {
     }
     "#);
 }
+
+#[actix_web::test]
+async fn receive_custom_metadata() {
+    let WebhookHandle { server_handle: handle1, url: url1, receiver: mut receiver1 } =
+        create_webhook_server().await;
+    let WebhookHandle { server_handle: handle2, url: url2, receiver: mut receiver2 } =
+        create_webhook_server().await;
+    let WebhookHandle { server_handle: handle3, url: url3, receiver: mut receiver3 } =
+        create_webhook_server().await;
+
+    let db_path = tempfile::tempdir().unwrap();
+    let server = Server::new_with_options(Opt {
+        task_webhook_url: Some(Url::parse(&url3).unwrap()),
+        ..default_settings(db_path.path())
+    })
+    .await
+    .unwrap();
+
+    for url in [url1, url2] {
+        let (value, code) = server.create_webhook(json!({ "url": url })).await;
+        snapshot!(code, @"201 Created");
+        snapshot!(json_string!(value, { ".uuid" => "[uuid]", ".url" => "[ignored]" }), @r#"
+        {
+          "uuid": "[uuid]",
+          "isEditable": true,
+          "url": "[ignored]",
+          "headers": {}
+        }
+        "#);
+    }
+    let index = server.index("tamo");
+    let (response, code) = index
+        .add_documents_with_custom_metadata(
+            json!({ "id": 1, "doggo": "bone" }),
+            None,
+            Some("test_meta"),
+        )
+        .await;
+
+    snapshot!(response, @r###"
+    {
+      "taskUid": 0,
+      "indexUid": "tamo",
+      "status": "enqueued",
+      "type": "documentAdditionOrUpdate",
+      "enqueuedAt": "[date]",
+      "customMetadata": "test_meta"
+    }
+    "###);
+    snapshot!(code, @"202 Accepted");
+
+    let mut count1 = 0;
+    let mut count2 = 0;
+    let mut count3 = 0;
+    while count1 == 0 || count2 == 0 || count3 == 0 {
+        tokio::select! {
+            msg = receiver1.recv() => {
+              if let Some(msg) = msg {
+                count1 += 1;
+                check_metadata(msg);
+              }
+           },
+            msg = receiver2.recv() => {
+              if let Some(msg) = msg {
+                count2 += 1;
+                check_metadata(msg);
+              }
+             },
+            msg = receiver3.recv() => {
+              if let Some(msg) = msg {
+                count3 += 1;
+                check_metadata(msg);
+              }
+            },
+        }
+    }
+
+    assert_eq!(count1, 1);
+    assert_eq!(count2, 1);
+    assert_eq!(count3, 1);
+
+    handle1.abort();
+    handle2.abort();
+    handle3.abort();
+}
+
+fn check_metadata(msg: Vec<u8>) {
+    let msg = String::from_utf8(msg).unwrap();
+    let tasks = msg.split('\n');
+    for task in tasks {
+        if task.is_empty() {
+            continue;
+        }
+        let task: serde_json::Value = serde_json::from_str(task).unwrap();
+        snapshot!(common::Value(task), @r###"
+        {
+          "uid": "[uid]",
+          "batchUid": "[batch_uid]",
+          "indexUid": "tamo",
+          "status": "succeeded",
+          "type": "documentAdditionOrUpdate",
+          "canceledBy": null,
+          "details": {
+            "receivedDocuments": 1,
+            "indexedDocuments": 1
+          },
+          "error": null,
+          "duration": "[duration]",
+          "enqueuedAt": "[date]",
+          "startedAt": "[date]",
+          "finishedAt": "[date]",
+          "customMetadata": "test_meta"
+        }
+        "###);
+    }
+}

crates/meilisearch/tests/upgrade/mod.rs

@@ -43,7 +43,7 @@ async fn version_too_old() {
     std::fs::write(db_path.join("VERSION"), "1.11.9999").unwrap();
     let options = Opt { experimental_dumpless_upgrade: true, ..default_settings };
     let err = Server::new_with_options(options).await.map(|_| ()).unwrap_err();
-    snapshot!(err, @"Database version 1.11.9999 is too old for the experimental dumpless upgrade feature. Please generate a dump using the v1.11.9999 and import it in the v1.24.0");
+    snapshot!(err, @"Database version 1.11.9999 is too old for the experimental dumpless upgrade feature. Please generate a dump using the v1.11.9999 and import it in the v1.27.0");
 }
 
 #[actix_rt::test]
@@ -58,7 +58,7 @@ async fn version_requires_downgrade() {
     std::fs::write(db_path.join("VERSION"), format!("{major}.{minor}.{patch}")).unwrap();
     let options = Opt { experimental_dumpless_upgrade: true, ..default_settings };
     let err = Server::new_with_options(options).await.map(|_| ()).unwrap_err();
-    snapshot!(err, @"Database version 1.24.1 is higher than the Meilisearch version 1.24.0. Downgrade is not supported");
+    snapshot!(err, @"Database version 1.27.1 is higher than the Meilisearch version 1.27.0. Downgrade is not supported");
 }
 
 #[actix_rt::test]

crates/meilisearch/tests/upgrade/v1_12/snapshots/v1_12_0.rs/check_the_index_scheduler/batches_filter_afterEnqueuedAt_equal_2025-01-16T16_47_41.snap

@@ -8,7 +8,7 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
       "progress": null,
       "details": {
         "upgradeFrom": "v1.12.0",
-        "upgradeTo": "v1.24.0"
+        "upgradeTo": "v1.27.0"
       },
       "stats": {
         "totalNbTasks": 1,

crates/meilisearch/tests/upgrade/v1_12/snapshots/v1_12_0.rs/check_the_index_scheduler/batches_filter_afterFinishedAt_equal_2025-01-16T16_47_41.snap

@@ -8,7 +8,7 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
       "progress": null,
       "details": {
         "upgradeFrom": "v1.12.0",
-        "upgradeTo": "v1.24.0"
+        "upgradeTo": "v1.27.0"
       },
       "stats": {
         "totalNbTasks": 1,

crates/meilisearch/tests/upgrade/v1_12/snapshots/v1_12_0.rs/check_the_index_scheduler/batches_filter_afterStartedAt_equal_2025-01-16T16_47_41.snap

@@ -8,7 +8,7 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
       "progress": null,
       "details": {
         "upgradeFrom": "v1.12.0",
-        "upgradeTo": "v1.24.0"
+        "upgradeTo": "v1.27.0"
       },
       "stats": {
         "totalNbTasks": 1,

crates/meilisearch/tests/upgrade/v1_12/snapshots/v1_12_0.rs/check_the_index_scheduler/tasks_filter_afterEnqueuedAt_equal_2025-01-16T16_47_41.snap

@@ -12,7 +12,7 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
       "canceledBy": null,
       "details": {
         "upgradeFrom": "v1.12.0",
-        "upgradeTo": "v1.24.0"
+        "upgradeTo": "v1.27.0"
       },
       "error": null,
       "duration": "[duration]",

crates/meilisearch/tests/upgrade/v1_12/snapshots/v1_12_0.rs/check_the_index_scheduler/tasks_filter_afterFinishedAt_equal_2025-01-16T16_47_41.snap

@@ -12,7 +12,7 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
       "canceledBy": null,
       "details": {
         "upgradeFrom": "v1.12.0",
-        "upgradeTo": "v1.24.0"
+        "upgradeTo": "v1.27.0"
       },
       "error": null,
       "duration": "[duration]",

crates/meilisearch/tests/upgrade/v1_12/snapshots/v1_12_0.rs/check_the_index_scheduler/tasks_filter_afterStartedAt_equal_2025-01-16T16_47_41.snap

@@ -12,7 +12,7 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
       "canceledBy": null,
       "details": {
         "upgradeFrom": "v1.12.0",
-        "upgradeTo": "v1.24.0"
+        "upgradeTo": "v1.27.0"
       },
       "error": null,
       "duration": "[duration]",

crates/meilisearch/tests/upgrade/v1_12/snapshots/v1_12_0.rs/check_the_index_scheduler/the_whole_batch_queue_once_everything_has_been_processed.snap

@@ -8,7 +8,7 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
       "progress": null,
       "details": {
         "upgradeFrom": "v1.12.0",
-        "upgradeTo": "v1.24.0"
+        "upgradeTo": "v1.27.0"
       },
       "stats": {
         "totalNbTasks": 1,

crates/meilisearch/tests/upgrade/v1_12/snapshots/v1_12_0.rs/check_the_index_scheduler/the_whole_task_queue_once_everything_has_been_processed.snap

@@ -12,7 +12,7 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
       "canceledBy": null,
       "details": {
         "upgradeFrom": "v1.12.0",
-        "upgradeTo": "v1.24.0"
+        "upgradeTo": "v1.27.0"
       },
       "error": null,
       "duration": "[duration]",

crates/meilitool/Cargo.toml

@@ -9,15 +9,15 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-anyhow = "1.0.98"
-clap = { version = "4.5.40", features = ["derive"] }
+anyhow = "1.0.100"
+clap = { version = "4.5.52", features = ["derive"] }
 dump = { path = "../dump" }
 file-store = { path = "../file-store" }
-indexmap = { version = "2.9.0", features = ["serde"] }
+indexmap = { version = "2.12.0", features = ["serde"] }
 meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
-serde = { version = "1.0.219", features = ["derive"] }
-serde_json = { version = "1.0.140", features = ["preserve_order"] }
-tempfile = "3.20.0"
-time = { version = "0.3.41", features = ["formatting", "parsing", "alloc"] }
-uuid = { version = "1.17.0", features = ["v4"], default-features = false }
+serde = { version = "1.0.228", features = ["derive"] }
+serde_json = { version = "1.0.145", features = ["preserve_order"] }
+tempfile = "3.23.0"
+time = { version = "0.3.44", features = ["formatting", "parsing", "alloc"] }
+uuid = { version = "1.18.1", features = ["v4"], default-features = false }

crates/meilitool/src/upgrade/v1_12.rs

@@ -68,7 +68,7 @@ fn convert_update_files(db_path: &Path) -> anyhow::Result<()> {
 
     for uuid in file_store.all_uuids().context("while retrieving uuids from file store")? {
         let uuid = uuid.context("while retrieving uuid from file store")?;
-        let update_file_path = file_store.get_update_path(uuid);
+        let update_file_path = file_store.update_path(uuid);
         let update_file = file_store
             .get_update(uuid)
             .with_context(|| format!("while getting update file for uuid {uuid:?}"))?;

crates/milli/Cargo.toml

@@ -15,15 +15,15 @@ license.workspace = true
 big_s = "1.0.2"
 bimap = { version = "0.6.3", features = ["serde"] }
 bincode = "1.3.3"
-bstr = "1.12.0"
-bytemuck = { version = "1.23.1", features = ["extern_crate_alloc"] }
+bstr = "1.12.1"
+bytemuck = { version = "1.24.0", features = ["extern_crate_alloc"] }
 byteorder = "1.5.0"
-charabia = { version = "0.9.7", default-features = false }
+charabia = { version = "0.9.9", default-features = false }
 cellulite = "0.3.1-nested-rtxns-2"
 concat-arrays = "0.1.2"
-convert_case = "0.8.0"
+convert_case = "0.9.0"
 crossbeam-channel = "0.5.15"
-deserr = "0.6.3"
+deserr = "0.6.4"
 either = { version = "1.15.0", features = ["serde"] }
 flatten-serde-json = { path = "../flatten-serde-json" }
 fst = "0.4.7"
@@ -34,55 +34,56 @@ grenad = { version = "0.5.0", default-features = false, features = [
     "rayon",
     "tempfile",
 ] }
-heed = { version = "0.22.1-nested-rtxns", default-features = false, features = [
+heed = { version = "0.22.1-nested-rtxns-6", default-features = false, features = [
     "serde-json",
     "serde-bincode",
 ] }
-indexmap = { version = "2.9.0", features = ["serde"] }
+indexmap = { version = "2.12.0", features = ["serde"] }
 json-depth-checker = { path = "../json-depth-checker" }
 levenshtein_automata = { version = "0.2.1", features = ["fst_automaton"] }
-memchr = "2.7.5"
-memmap2 = "0.9.7"
+memchr = "2.7.6"
+memmap2 = "0.9.9"
 obkv = "0.3.0"
 once_cell = "1.21.3"
-ordered-float = "5.0.0"
-rayon = "1.10.0"
+ordered-float = "5.1.0"
+rayon = "1.11.0"
 roaring = { version = "0.10.12", features = ["serde"] }
 rstar = { version = "0.12.2", features = ["serde"] }
-serde = { version = "1.0.219", features = ["derive"] }
-serde_json = { version = "1.0.140", features = ["preserve_order", "raw_value"] }
+serde = { version = "1.0.228", features = ["derive"] }
+serde_json = { version = "1.0.145", features = ["preserve_order", "raw_value"] }
 slice-group-by = "0.3.1"
-smallstr = { version = "0.3.0", features = ["serde"] }
+smallstr = { version = "0.3.1", features = ["serde"] }
 smallvec = "1.15.1"
 smartstring = "1.0.1"
-tempfile = "3.20.0"
-thiserror = "2.0.12"
-time = { version = "0.3.41", features = [
+tempfile = "3.23.0"
+thiserror = "2.0.17"
+time = { version = "0.3.44", features = [
     "serde-well-known",
     "formatting",
     "parsing",
     "macros",
 ] }
-uuid = { version = "1.17.0", features = ["v4"] }
+uuid = { version = "1.18.1", features = ["v4"] }
 
 filter-parser = { path = "../filter-parser" }
 
 # documents words self-join
 itertools = "0.14.0"
 
-csv = "1.3.1"
+csv = "1.4.0"
 candle-core = { version = "0.9.1" }
 candle-transformers = { version = "0.9.1" }
 candle-nn = { version = "0.9.1" }
-tokenizers = { git = "https://github.com/huggingface/tokenizers.git", tag = "v0.15.2", version = "0.15.2", default-features = false, features = [
+tokenizers = { version = "0.22.1", default-features = false, features = [
     "onig",
 ] }
 hf-hub = { git = "https://github.com/dureuill/hf-hub.git", branch = "rust_tls", default-features = false, features = [
     "online",
 ] }
-tiktoken-rs = "0.7.0"
+safetensors = "0.6.2"
+tiktoken-rs = "0.9.1"
 liquid = "0.26.11"
-rhai = { version = "1.22.2", features = [
+rhai = { version = "1.23.6", features = [
     "serde",
     "no_module",
     "no_custom_syntax",
@@ -94,15 +95,14 @@ hannoy = { version = "0.0.9-nested-rtxns-2", features = ["arroy"] }
 rand = "0.8.5"
 tracing = "0.1.41"
 ureq = { version = "2.12.1", features = ["json"] }
-url = "2.5.4"
-hashbrown = "0.15.4"
-bumpalo = "3.18.1"
+url = "2.5.7"
+hashbrown = "0.15.5"
+bumpalo = "3.19.0"
 bumparaw-collections = "0.1.4"
 steppe = { version = "0.4", default-features = false }
 thread_local = "1.1.9"
-allocator-api2 = "0.3.0"
 rustc-hash = "2.1.1"
-enum-iterator = "2.1.0"
+enum-iterator = "2.3.0"
 bbqueue = { git = "https://github.com/meilisearch/bbqueue" }
 flume = { version = "0.11.1", default-features = false }
 utoipa = { version = "5.4.0", features = [
@@ -112,22 +112,24 @@ utoipa = { version = "5.4.0", features = [
     "time",
     "openapi_extensions",
 ] }
-lru = "0.14.0"
-twox-hash = { version = "2.1.1", default-features = false, features = [
+lru = "0.16.2"
+twox-hash = { version = "2.1.2", default-features = false, features = [
     "std",
     "xxhash3_64",
     "xxhash64",
 ] }
-geo-types = "0.7.16"
+geo-types = "0.7.17"
 zerometry = "0.3.0"
+bitpacking = "0.9.2"
 
 [dev-dependencies]
-mimalloc = { version = "0.1.47", default-features = false }
 # fixed version due to format breakages in v1.40
 insta = "=1.39.0"
+mimalloc = { version = "0.1.48", default-features = false }
 maplit = "1.0.2"
-md5 = "0.7.0"
+md5 = "0.8.0"
 meili-snap = { path = "../meili-snap" }
+quickcheck = "1.0.3"
 rand = { version = "0.8.5", features = ["small_rng"] }
 
 [features]
@@ -141,6 +143,8 @@ lmdb-posix-sem = ["heed/posix-sem"]
 chinese = ["charabia/chinese"]
 chinese-pinyin = ["chinese", "charabia/chinese-normalization-pinyin"]
 
+enterprise = []
+
 # allow hebrew specialized tokenization
 hebrew = ["charabia/hebrew"]
 

crates/milli/src/documents/sort.rs

@@ -87,7 +87,7 @@ impl Iterator for SortedDocumentsIterator<'_> {
         };
 
         // Otherwise don't directly iterate over children, skip them if we know we will go further
-        let mut to_skip = n - 1;
+        let mut to_skip = n;
         while to_skip > 0 {
             if let Err(e) = SortedDocumentsIterator::update_current(
                 current_child,
@@ -108,7 +108,7 @@ impl Iterator for SortedDocumentsIterator<'_> {
                 continue;
             } else {
                 // The current iterator is large enough, so we can forward the call to it.
-                return inner.nth(to_skip + 1);
+                return inner.nth(to_skip);
             }
         }