reduce the number of computed prefix

More Precise Post Processing

.github/workflows/check-valid-milestone.yml

@@ -0,0 +1,100 @@
+name: PR Milestone Check
+
+on:
+  pull_request:
+    types: [opened, reopened, edited, synchronize, milestoned, demilestoned]
+    branches:
+      - "main"
+      - "release-v*.*.*"
+
+jobs:
+  check-milestone:
+    name: Check PR Milestone
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v3
+
+      - name: Validate PR milestone
+        uses: actions/github-script@v6
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            // Get PR number directly from the event payload
+            const prNumber = context.payload.pull_request.number;
+
+            // Get PR details
+            const { data: prData } = await github.rest.pulls.get({
+              owner: 'meilisearch',
+              repo: 'meilisearch',
+              pull_number: prNumber
+            });
+
+            // Get base branch name
+            const baseBranch = prData.base.ref;
+            console.log(`Base branch: ${baseBranch}`);
+
+            // Get PR milestone
+            const prMilestone = prData.milestone;
+            if (!prMilestone) {
+              core.setFailed('PR must have a milestone assigned');
+              return;
+            }
+            console.log(`PR milestone: ${prMilestone.title}`);
+
+            // Validate milestone format: vx.y.z
+            const milestoneRegex = /^v\d+\.\d+\.\d+$/;
+            if (!milestoneRegex.test(prMilestone.title)) {
+              core.setFailed(`Milestone "${prMilestone.title}" does not follow the required format vx.y.z`);
+              return;
+            }
+
+            // For main branch PRs, check if the milestone is the highest one
+            if (baseBranch === 'main') {
+              // Get all milestones
+              const { data: milestones } = await github.rest.issues.listMilestones({
+                owner: 'meilisearch',
+                repo: 'meilisearch',
+                state: 'open',
+                sort: 'due_on',
+                direction: 'desc'
+              });
+
+              // Sort milestones by version number (vx.y.z)
+              const sortedMilestones = milestones
+                .filter(m => milestoneRegex.test(m.title))
+                .sort((a, b) => {
+                  const versionA = a.title.substring(1).split('.').map(Number);
+                  const versionB = b.title.substring(1).split('.').map(Number);
+
+                  // Compare major version
+                  if (versionA[0] !== versionB[0]) return versionB[0] - versionA[0];
+                  // Compare minor version
+                  if (versionA[1] !== versionB[1]) return versionB[1] - versionA[1];
+                  // Compare patch version
+                  return versionB[2] - versionA[2];
+                });
+
+              if (sortedMilestones.length === 0) {
+                core.setFailed('No valid milestones found in the repository. Please create at least one milestone with the format vx.y.z');
+                return;
+              }
+
+              const highestMilestone = sortedMilestones[0];
+              console.log(`Highest milestone: ${highestMilestone.title}`);
+
+              if (prMilestone.title !== highestMilestone.title) {
+                core.setFailed(`PRs targeting the main branch must use the highest milestone (${highestMilestone.title}), but this PR uses ${prMilestone.title}`);
+                return;
+              }
+            } else {
+              // For release branches, the milestone should match the branch version
+              const branchVersion = baseBranch.substring(8); // remove 'release-'
+              if (prMilestone.title !== branchVersion) {
+                core.setFailed(`PRs targeting release branch "${baseBranch}" must use the matching milestone "${branchVersion}", but this PR uses "${prMilestone.title}"`);
+                return;
+              }
+            }
+
+            console.log('PR milestone validation passed!');

.github/workflows/flaky-tests.yml

@@ -9,22 +9,22 @@ jobs:
   flaky:
     runs-on: ubuntu-latest
     container:
-      # Use ubuntu-20.04 to compile with glibc 2.28
+      # Use ubuntu-22.04 to compile with glibc 2.35
-      image: ubuntu:20.04
+      image: ubuntu:22.04
     steps:
-    - uses: actions/checkout@v3
+      - uses: actions/checkout@v3
-    - name: Install needed dependencies
+      - name: Install needed dependencies
-      run: |
+        run: |
-        apt-get update && apt-get install -y curl
+          apt-get update && apt-get install -y curl
-        apt-get install build-essential -y
+          apt-get install build-essential -y
-    - uses: dtolnay/rust-toolchain@1.81
+      - uses: dtolnay/rust-toolchain@1.81
-    - name: Install cargo-flaky
+      - name: Install cargo-flaky
-      run: cargo install cargo-flaky
+        run: cargo install cargo-flaky
-    - name: Run cargo flaky in the dumps
+      - name: Run cargo flaky in the dumps
-      run: cd crates/dump; cargo flaky -i 100 --release
+        run: cd crates/dump; cargo flaky -i 100 --release
-    - name: Run cargo flaky in the index-scheduler
+      - name: Run cargo flaky in the index-scheduler
-      run: cd crates/index-scheduler; cargo flaky -i 100 --release
+        run: cd crates/index-scheduler; cargo flaky -i 100 --release
-    - name: Run cargo flaky in the auth
+      - name: Run cargo flaky in the auth
-      run: cd crates/meilisearch-auth; cargo flaky -i 100 --release
+        run: cd crates/meilisearch-auth; cargo flaky -i 100 --release
-    - name: Run cargo flaky in meilisearch
+      - name: Run cargo flaky in meilisearch
-      run: cd crates/meilisearch; cargo flaky -i 100 --release
+        run: cd crates/meilisearch; cargo flaky -i 100 --release

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

@@ -18,28 +18,28 @@ jobs:
     runs-on: ubuntu-latest
     needs: check-version
     container:
-      # Use ubuntu-20.04 to compile with glibc 2.28
+      # Use ubuntu-22.04 to compile with glibc 2.35
-      image: ubuntu:20.04
+      image: ubuntu:22.04
     steps:
-    - name: Install needed dependencies
+      - name: Install needed dependencies
-      run: |
+        run: |
-        apt-get update && apt-get install -y curl
+          apt-get update && apt-get install -y curl
-        apt-get install build-essential -y
+          apt-get install build-essential -y
-    - uses: dtolnay/rust-toolchain@1.81
+      - uses: dtolnay/rust-toolchain@1.81
-    - name: Install cargo-deb
+      - name: Install cargo-deb
-      run: cargo install cargo-deb
+        run: cargo install cargo-deb
-    - uses: actions/checkout@v3
+      - uses: actions/checkout@v3
-    - name: Build deb package
+      - name: Build deb package
-      run: cargo deb -p meilisearch -o target/debian/meilisearch.deb
+        run: cargo deb -p meilisearch -o target/debian/meilisearch.deb
-    - name: Upload debian pkg to release
+      - name: Upload debian pkg to release
-      uses: svenstaro/upload-release-action@2.7.0
+        uses: svenstaro/upload-release-action@2.7.0
-      with:
+        with:
-        repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
+          repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
-        file: target/debian/meilisearch.deb
+          file: target/debian/meilisearch.deb
-        asset_name: meilisearch.deb
+          asset_name: meilisearch.deb
-        tag: ${{ github.ref }}
+          tag: ${{ github.ref }}
-    - name: Upload debian pkg to apt repository
+      - name: Upload debian pkg to apt repository
-      run: curl -F package=@target/debian/meilisearch.deb https://${{ secrets.GEMFURY_PUSH_TOKEN }}@push.fury.io/meilisearch/
+        run: curl -F package=@target/debian/meilisearch.deb https://${{ secrets.GEMFURY_PUSH_TOKEN }}@push.fury.io/meilisearch/
 
   homebrew:
     name: Bump Homebrew formula

.github/workflows/publish-binaries.yml

@@ -3,7 +3,7 @@ name: Publish binaries to GitHub release
 on:
   workflow_dispatch:
   schedule:
-    - cron: '0 2 * * *' # Every day at 2:00am
+    - cron: "0 2 * * *" # Every day at 2:00am
   release:
     types: [published]
 
@@ -37,26 +37,26 @@ jobs:
     runs-on: ubuntu-latest
     needs: check-version
     container:
-      # Use ubuntu-20.04 to compile with glibc 2.28
+      # Use ubuntu-22.04 to compile with glibc 2.35
-      image: ubuntu:20.04
+      image: ubuntu:22.04
     steps:
-    - uses: actions/checkout@v3
+      - uses: actions/checkout@v3
-    - name: Install needed dependencies
+      - name: Install needed dependencies
-      run: |
+        run: |
-        apt-get update && apt-get install -y curl
+          apt-get update && apt-get install -y curl
-        apt-get install build-essential -y
+          apt-get install build-essential -y
-    - uses: dtolnay/rust-toolchain@1.81
+      - uses: dtolnay/rust-toolchain@1.81
-    - name: Build
+      - name: Build
-      run: cargo build --release --locked
+        run: cargo build --release --locked
-    # No need to upload binaries for dry run (cron)
+      # No need to upload binaries for dry run (cron)
-    - name: Upload binaries to release
+      - name: Upload binaries to release
-      if: github.event_name == 'release'
+        if: github.event_name == 'release'
-      uses: svenstaro/upload-release-action@2.7.0
+        uses: svenstaro/upload-release-action@2.7.0
-      with:
+        with:
-        repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
+          repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
-        file: target/release/meilisearch
+          file: target/release/meilisearch
-        asset_name: meilisearch-linux-amd64
+          asset_name: meilisearch-linux-amd64
-        tag: ${{ github.ref }}
+          tag: ${{ github.ref }}
 
   publish-macos-windows:
     name: Publish binary for ${{ matrix.os }}
@@ -74,19 +74,19 @@ jobs:
             artifact_name: meilisearch.exe
             asset_name: meilisearch-windows-amd64.exe
     steps:
-    - uses: actions/checkout@v3
+      - uses: actions/checkout@v3
-    - uses: dtolnay/rust-toolchain@1.81
+      - uses: dtolnay/rust-toolchain@1.81
-    - name: Build
+      - name: Build
-      run: cargo build --release --locked
+        run: cargo build --release --locked
-    # No need to upload binaries for dry run (cron)
+      # No need to upload binaries for dry run (cron)
-    - name: Upload binaries to release
+      - name: Upload binaries to release
-      if: github.event_name == 'release'
+        if: github.event_name == 'release'
-      uses: svenstaro/upload-release-action@2.7.0
+        uses: svenstaro/upload-release-action@2.7.0
-      with:
+        with:
-        repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
+          repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
-        file: target/release/${{ matrix.artifact_name }}
+          file: target/release/${{ matrix.artifact_name }}
-        asset_name: ${{ matrix.asset_name }}
+          asset_name: ${{ matrix.asset_name }}
-        tag: ${{ github.ref }}
+          tag: ${{ github.ref }}
 
   publish-macos-apple-silicon:
     name: Publish binary for macOS silicon
@@ -127,8 +127,8 @@ jobs:
     env:
       DEBIAN_FRONTEND: noninteractive
     container:
-      # Use ubuntu-20.04 to compile with glibc 2.28
+      # Use ubuntu-22.04 to compile with glibc 2.35
-      image: ubuntu:20.04
+      image: ubuntu:22.04
     strategy:
       matrix:
         include:

.github/workflows/sdks-tests.yml

@@ -52,7 +52,7 @@ jobs:
       - name: Setup .NET Core
         uses: actions/setup-dotnet@v4
         with:
-          dotnet-version: "6.0.x"
+          dotnet-version: "8.0.x"
       - name: Install dependencies
         run: dotnet restore
       - name: Build

.github/workflows/test-suite.yml

@@ -6,11 +6,7 @@ on:
     # Everyday at 5:00am
     - cron: "0 5 * * *"
   pull_request:
-  push:
+  merge_group:
-    # trying and staging branches are for Bors config
-    branches:
-      - trying
-      - staging
 
 env:
   CARGO_TERM_COLOR: always
@@ -19,13 +15,13 @@ env:
 
 jobs:
   test-linux:
-    name: Tests on ubuntu-20.04
+    name: Tests on ubuntu-22.04
     runs-on: ubuntu-latest
     container:
-      # Use ubuntu-20.04 to compile with glibc 2.28
+      # Use ubuntu-22.04 to compile with glibc 2.35
-      image: ubuntu:20.04
+      image: ubuntu:22.04
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - name: Install needed dependencies
         run: |
           apt-get update && apt-get install -y curl
@@ -72,8 +68,8 @@ jobs:
     name: Tests almost all features
     runs-on: ubuntu-latest
     container:
-      # Use ubuntu-20.04 to compile with glibc 2.28
+      # Use ubuntu-22.04 to compile with glibc 2.35
-      image: ubuntu:20.04
+      image: ubuntu:22.04
     if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
     steps:
       - uses: actions/checkout@v3
@@ -125,7 +121,7 @@ jobs:
     name: Test disabled tokenization
     runs-on: ubuntu-latest
     container:
-      image: ubuntu:20.04
+      image: ubuntu:22.04
     if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
     steps:
       - uses: actions/checkout@v3
@@ -149,8 +145,8 @@ jobs:
     name: Run tests in debug
     runs-on: ubuntu-latest
     container:
-      # Use ubuntu-20.04 to compile with glibc 2.28
+      # Use ubuntu-22.04 to compile with glibc 2.35
-      image: ubuntu:20.04
+      image: ubuntu:22.04
     steps:
       - uses: actions/checkout@v3
       - name: Install needed dependencies

CONTRIBUTING.md

@@ -95,6 +95,11 @@ Meilisearch follows the [cargo xtask](https://github.com/matklad/cargo-xtask) wo
 
 Run `cargo xtask --help` from the root of the repository to find out what is available.
 
+#### Update the openAPI file if the API changed
+
+To update the openAPI file in the code, see [sprint_issue.md](https://github.com/meilisearch/meilisearch/blob/main/.github/ISSUE_TEMPLATE/sprint_issue.md#reminders-when-modifying-the-api).
+If you want to update the openAPI file on the [open-api repository](https://github.com/meilisearch/open-api), see [update-openapi-issue.md](https://github.com/meilisearch/engine-team/blob/main/issue-templates/update-openapi-issue.md).
+
 ### Logging
 
 Meilisearch uses [`tracing`](https://lib.rs/crates/tracing) for logging purposes. Tracing logs are structured and can be displayed as JSON to the end user, so prefer passing arguments as fields rather than interpolating them in the message.
@@ -145,7 +150,7 @@ Some notes on GitHub PRs:
 - The PR title should be accurate and descriptive of the changes.
 - [Convert your PR as a draft](https://help.github.com/en/github/collaborating-with-issues-and-pull-requests/changing-the-stage-of-a-pull-request) if your changes are a work in progress: no one will review it until you pass your PR as ready for review.<br>
   The draft PRs are recommended when you want to show that you are working on something and make your work visible.
-- The branch related to the PR must be **up-to-date with `main`** before merging. Fortunately, this project uses [Bors](https://github.com/bors-ng/bors-ng) to automatically enforce this requirement without the PR author having to rebase manually.
+- The branch related to the PR must be **up-to-date with `main`** before merging. Fortunately, this project uses [GitHub Merge Queues](https://github.blog/news-insights/product-news/github-merge-queue-is-generally-available/) to automatically enforce this requirement without the PR author having to rebase manually.
 
 ## Release Process (for internal team only)
 
@@ -153,8 +158,7 @@ Meilisearch tools follow the [Semantic Versioning Convention](https://semver.org
 
 ### Automation to rebase and Merge the PRs
 
-This project integrates a bot that helps us manage pull requests merging.<br>
+This project uses GitHub Merge Queues that helps us manage pull requests merging.
-_[Read more about this](https://github.com/meilisearch/integration-guides/blob/main/resources/bors.md)._
 
 ### How to Publish a new Release
 

Cargo.lock

@@ -47,7 +47,7 @@ dependencies = [
  "actix-utils",
  "ahash 0.8.11",
  "base64 0.22.1",
- "bitflags 2.6.0",
+ "bitflags 2.9.0",
  "brotli",
  "bytes",
  "bytestring",
@@ -258,7 +258,7 @@ version = "0.7.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "891477e0c6a8957309ee5c45a6368af3ae14bb510732d2684ffa19af310920f9"
 dependencies = [
- "getrandom",
+ "getrandom 0.2.15",
  "once_cell",
  "version_check",
 ]
@@ -271,7 +271,7 @@ checksum = "e89da841a80418a9b391ebaea17f5c112ffaaa96f621d2c285b5174da76b9011"
 dependencies = [
  "cfg-if",
  "const-random",
- "getrandom",
+ "getrandom 0.2.15",
  "once_cell",
  "version_check",
  "zerocopy",
@@ -393,41 +393,24 @@ checksum = "96d30a06541fbafbc7f82ed10c06164cfbd2c401138f6addd8404629c4b16711"
 
 [[package]]
 name = "arroy"
-version = "0.5.0"
+version = "0.6.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "dfc5f272f38fa063bbff0a7ab5219404e221493de005e2b4078c62d626ef567e"
+checksum = "08e6111f351d004bd13e95ab540721272136fd3218b39d3ec95a2ea1c4e6a0a6"
 dependencies = [
  "bytemuck",
  "byteorder",
+ "enum-iterator",
  "heed",
- "log",
  "memmap2",
  "nohash",
  "ordered-float",
+ "page_size",
  "rand",
  "rayon",
  "roaring",
  "tempfile",
- "thiserror 1.0.69",
+ "thiserror 2.0.9",
-]
+ "tracing",
-
-[[package]]
-name = "arroy"
-version = "0.5.0"
-source = "git+https://github.com/meilisearch/arroy/?tag=DO-NOT-DELETE-upgrade-v04-to-v05#053807bf38dc079f25b003f19fc30fbf3613f6e7"
-dependencies = [
- "bytemuck",
- "byteorder",
- "heed",
- "log",
- "memmap2",
- "nohash",
- "ordered-float",
- "rand",
- "rayon",
- "roaring",
- "tempfile",
- "thiserror 1.0.69",
 ]
 
 [[package]]
@@ -503,7 +486,7 @@ source = "git+https://github.com/meilisearch/bbqueue#cbb87cc707b5af415ef203bdaf2
 
 [[package]]
 name = "benchmarks"
-version = "1.13.0"
+version = "1.14.0"
 dependencies = [
  "anyhow",
  "bumpalo",
@@ -553,7 +536,7 @@ version = "0.70.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f49d8fed880d473ea71efb9bf597651e77201bdd4893efe54c9e5d65ae04ce6f"
 dependencies = [
- "bitflags 2.6.0",
+ "bitflags 2.9.0",
  "cexpr",
  "clang-sys",
  "itertools 0.13.0",
@@ -599,9 +582,9 @@ checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a"
 
 [[package]]
 name = "bitflags"
-version = "2.6.0"
+version = "2.9.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b048fb63fd8b5923fc5aa7b340d8e156aec7ec02f0c78fa8a6ddc2613f6f71de"
+checksum = "5c8214115b7bf84099f1309324e63141d4c5d7cc26862f97a0a857dbefe165bd"
 dependencies = [
  "serde",
 ]
@@ -694,7 +677,7 @@ dependencies = [
 
 [[package]]
 name = "build-info"
-version = "1.13.0"
+version = "1.14.0"
 dependencies = [
  "anyhow",
  "time",
@@ -807,22 +790,20 @@ dependencies = [
 
 [[package]]
 name = "bzip2"
-version = "0.4.4"
+version = "0.5.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bdb116a6ef3f6c3698828873ad02c3014b3c85cadb88496095628e3ef1e347f8"
+checksum = "49ecfb22d906f800d4fe833b6282cf4dc1c298f5057ca0b5445e5c209735ca47"
 dependencies = [
  "bzip2-sys",
- "libc",
 ]
 
 [[package]]
 name = "bzip2-sys"
-version = "0.1.11+1.0.8"
+version = "0.1.13+1.0.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "736a955f3fa7875102d57c82b8cac37ec45224a07fd32d58f9f7a186b6cd4cdc"
+checksum = "225bff33b2141874fe80d71e07d6eec4f85c5c216453dd96388240f96e1acc14"
 dependencies = [
  "cc",
- "libc",
  "pkg-config",
 ]
 
@@ -944,13 +925,13 @@ checksum = "37b2a672a2cb129a2e41c10b1224bb368f9f37a2b16b612598138befd7b37eb5"
 
 [[package]]
 name = "cc"
-version = "1.0.104"
+version = "1.2.16"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "74b6a57f98764a267ff415d50a25e6e166f3831a5071af4995296ea97d210490"
+checksum = "be714c154be609ec7f5dad223a33bf1482fff90472de28f7362806e6d4832b8c"
 dependencies = [
  "jobserver",
  "libc",
- "once_cell",
+ "shlex",
 ]
 
 [[package]]
@@ -995,9 +976,9 @@ dependencies = [
 
 [[package]]
 name = "charabia"
-version = "0.9.2"
+version = "0.9.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cf8921fe4d53ab8f9e8f9b72ce6f91726cfc40fffab1243d27db406b5e2e9cc2"
+checksum = "650d52f87a36472ea1c803dee49d6bfd23d426efa9363e2f4c4a0e6a236d3407"
 dependencies = [
  "aho-corasick",
  "csv",
@@ -1160,7 +1141,7 @@ version = "0.1.16"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f9d839f2a20b0aee515dc581a6172f2321f96cab76c1a38a4c584a194955390e"
 dependencies = [
- "getrandom",
+ "getrandom 0.2.15",
  "once_cell",
  "tiny-keccak",
 ]
@@ -1671,7 +1652,7 @@ dependencies = [
 
 [[package]]
 name = "dump"
-version = "1.13.0"
+version = "1.14.0"
 dependencies = [
  "anyhow",
  "big_s",
@@ -1873,7 +1854,7 @@ checksum = "37909eebbb50d72f9059c3b6d82c0463f2ff062c9e95845c43a6c9c0355411be"
 
 [[package]]
 name = "file-store"
-version = "1.13.0"
+version = "1.14.0"
 dependencies = [
  "tempfile",
  "thiserror 2.0.9",
@@ -1895,7 +1876,7 @@ dependencies = [
 
 [[package]]
 name = "filter-parser"
-version = "1.13.0"
+version = "1.14.0"
 dependencies = [
  "insta",
  "nom",
@@ -1915,7 +1896,7 @@ dependencies = [
 
 [[package]]
 name = "flatten-serde-json"
-version = "1.13.0"
+version = "1.14.0"
 dependencies = [
  "criterion",
  "serde_json",
@@ -2054,7 +2035,7 @@ dependencies = [
 
 [[package]]
 name = "fuzzers"
-version = "1.13.0"
+version = "1.14.0"
 dependencies = [
  "arbitrary",
  "bumpalo",
@@ -2082,7 +2063,7 @@ version = "0.7.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ce20bbb48248608ba4908b45fe36e17e40f56f8c6bb385ecf5d3c4a1e8b05a22"
 dependencies = [
- "bitflags 2.6.0",
+ "bitflags 2.9.0",
  "debugid",
  "fxhash",
  "serde",
@@ -2233,10 +2214,24 @@ dependencies = [
  "cfg-if",
  "js-sys",
  "libc",
- "wasi",
+ "wasi 0.11.0+wasi-snapshot-preview1",
  "wasm-bindgen",
 ]
 
+[[package]]
+name = "getrandom"
+version = "0.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "43a49c392881ce6d5c3b8cb70f98717b7c07aabbdff06687b9030dbfbe2725f8"
+dependencies = [
+ "cfg-if",
+ "js-sys",
+ "libc",
+ "wasi 0.13.3+wasi-0.2.2",
+ "wasm-bindgen",
+ "windows-targets 0.52.6",
+]
+
 [[package]]
 name = "gimli"
 version = "0.27.3"
@@ -2249,7 +2244,7 @@ version = "0.19.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b903b73e45dc0c6c596f2d37eccece7c1c8bb6e4407b001096387c63d0d93724"
 dependencies = [
- "bitflags 2.6.0",
+ "bitflags 2.9.0",
  "libc",
  "libgit2-sys",
  "log",
@@ -2397,11 +2392,11 @@ checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea"
 
 [[package]]
 name = "heed"
-version = "0.20.5"
+version = "0.22.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7d4f449bab7320c56003d37732a917e18798e2f1709d80263face2b4f9436ddb"
+checksum = "6a56c94661ddfb51aa9cdfbf102cfcc340aa69267f95ebccc4af08d7c530d393"
 dependencies = [
- "bitflags 2.6.0",
+ "bitflags 2.9.0",
  "byteorder",
  "heed-traits",
  "heed-types",
@@ -2421,9 +2416,9 @@ checksum = "eb3130048d404c57ce5a1ac61a903696e8fcde7e8c2991e9fcfc1f27c3ef74ff"
 
 [[package]]
 name = "heed-types"
-version = "0.20.1"
+version = "0.21.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9d3f528b053a6d700b2734eabcd0fd49cb8230647aa72958467527b0b7917114"
+checksum = "13c255bdf46e07fb840d120a36dcc81f385140d7191c76a7391672675c01a55d"
 dependencies = [
  "bincode",
  "byteorder",
@@ -2743,14 +2738,14 @@ checksum = "206ca75c9c03ba3d4ace2460e57b189f39f43de612c2f85836e65c929701bb2d"
 
 [[package]]
 name = "index-scheduler"
-version = "1.13.0"
+version = "1.14.0"
 dependencies = [
  "anyhow",
- "arroy 0.5.0 (registry+https://github.com/rust-lang/crates.io-index)",
  "big_s",
  "bincode",
  "bumpalo",
  "bumparaw-collections",
+ "byte-unit",
  "convert_case 0.6.0",
  "crossbeam-channel",
  "csv",
@@ -2759,6 +2754,7 @@ dependencies = [
  "enum-iterator",
  "file-store",
  "flate2",
+ "indexmap",
  "insta",
  "maplit",
  "meili-snap",
@@ -2941,16 +2937,17 @@ dependencies = [
 
 [[package]]
 name = "js-sys"
-version = "0.3.69"
+version = "0.3.77"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "29c15563dc2726973df627357ce0c9ddddbea194836909d655df6a75d2cf296d"
+checksum = "1cfaf33c695fc6e08064efbc1f72ec937429614f25eef83af942d0e227c3a28f"
 dependencies = [
+ "once_cell",
  "wasm-bindgen",
 ]
 
 [[package]]
 name = "json-depth-checker"
-version = "1.13.0"
+version = "1.14.0"
 dependencies = [
  "criterion",
  "serde_json",
@@ -3013,9 +3010,9 @@ dependencies = [
 
 [[package]]
 name = "libc"
-version = "0.2.169"
+version = "0.2.171"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b5aba8db14291edd000dfcc4d620c7ebfb122c613afb886ca8803fa4e128a20a"
+checksum = "c19937216e9d3aa9956d9bb8dfc0b0c8beb6058fc4f7a4dc4d850edf86a237d6"
 
 [[package]]
 name = "libgit2-sys"
@@ -3080,9 +3077,9 @@ dependencies = [
 
 [[package]]
 name = "lindera"
-version = "0.32.2"
+version = "0.32.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c6cbc1aad631a7da0a7e9bc4b8669fa92ac9ca8eeb7b35a807376dd3034443ff"
+checksum = "832c220475557e3b44a46cad1862b57f010f0c6e93d771d0e628e08689c068b1"
 dependencies = [
  "lindera-analyzer",
  "lindera-core",
@@ -3093,9 +3090,9 @@ dependencies = [
 
 [[package]]
 name = "lindera-analyzer"
-version = "0.32.2"
+version = "0.32.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "74508ffbb24e36905d1718b261460e378a748029b07bcd7e06f0d18500b8194c"
+checksum = "a8e26651714abf5167e6b6a80f5cdaa0cad41c5fcb84d8ba96bebafcb9029339"
 dependencies = [
  "anyhow",
  "bincode",
@@ -3123,9 +3120,9 @@ dependencies = [
 
 [[package]]
 name = "lindera-assets"
-version = "0.32.2"
+version = "0.32.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6a677c371ecb3bd02b751be306ea09876cd47cf426303ad5f10a3fd6f9a4ded6"
+checksum = "ebb01f1ca53c1e642234c6c7fdb9ac664ad0c1ab9502f33e4200201bac7e6ce7"
 dependencies = [
  "encoding",
  "flate2",
@@ -3136,9 +3133,9 @@ dependencies = [
 
 [[package]]
 name = "lindera-cc-cedict"
-version = "0.32.2"
+version = "0.32.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c35944000d05a177e981f037b5f0805f283b32f05a0c35713003bef136ca8cb4"
+checksum = "5f7618d9aa947fdd7c38eae2b79f0fd237ecb5067608f1363610ba20d20ab5a8"
 dependencies = [
  "bincode",
  "byteorder",
@@ -3150,9 +3147,9 @@ dependencies = [
 
 [[package]]
 name = "lindera-cc-cedict-builder"
-version = "0.32.2"
+version = "0.32.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "85b8f642bc9c9130682569975772a17336c6aab26d11fc0f823f3e663167ace6"
+checksum = "efdbcb809d81428935d601a78c94bfb39500749213f7320705f427a7a1d31aec"
 dependencies = [
  "anyhow",
  "lindera-core",
@@ -3162,9 +3159,9 @@ dependencies = [
 
 [[package]]
 name = "lindera-compress"
-version = "0.32.2"
+version = "0.32.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a7825d8d63592aa5727d67bd209170ac82df56c369533efbf0ddbac277bb68ec"
+checksum = "eac178afa2456dac469d3b1a2d7fbaf3e1ea796a1f52321e8ac29545a53c239c"
 dependencies = [
  "anyhow",
  "flate2",
@@ -3173,9 +3170,9 @@ dependencies = [
 
 [[package]]
 name = "lindera-core"
-version = "0.32.2"
+version = "0.32.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0c28191456debc98af6aa5f7db77872471983e9fa2a737b1c232b6ef543aed62"
+checksum = "649777465f48147ce593ab6db347e235e3af8f693a23f4437be94a1cdbdf5fdf"
 dependencies = [
  "anyhow",
  "bincode",
@@ -3190,9 +3187,9 @@ dependencies = [
 
 [[package]]
 name = "lindera-decompress"
-version = "0.32.2"
+version = "0.32.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4788a1ead2f63f3fc2888109272921dedd86a87b7d0bf05e9daab46600daac51"
+checksum = "9e3faaceb85e43ac250021866c6db3cdc9997b44b3d3ea498594d04edc91fc45"
 dependencies = [
  "anyhow",
  "flate2",
@@ -3201,9 +3198,9 @@ dependencies = [
 
 [[package]]
 name = "lindera-dictionary"
-version = "0.32.2"
+version = "0.32.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bdf5f91725e32b9a21b1656baa7030766c9bafc4de4b4ddeb8ffdde7224dd2f6"
+checksum = "31e15b2d2d8a4ad45f2e373a084931cf3dfbde15f124044e2436bb920af3366c"
 dependencies = [
  "anyhow",
  "bincode",
@@ -3226,9 +3223,9 @@ dependencies = [
 
 [[package]]
 name = "lindera-dictionary-builder"
-version = "0.32.2"
+version = "0.32.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e41f00ba7ac541b0ffd8c30e7a73f2dd197546cc5780462ec4f2e4782945a780"
+checksum = "59802949110545b59b663917ed3fd55dc3b3a8cde6bd20137d7fe24372cfb9aa"
 dependencies = [
  "anyhow",
  "bincode",
@@ -3248,9 +3245,9 @@ dependencies = [
 
 [[package]]
 name = "lindera-filter"
-version = "0.32.2"
+version = "0.32.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "273d27e01e1377e2647314a4a5b9bdca4b52a867b319069ebae8c10191146eca"
+checksum = "1320f118c3fc9e897f4ebfc16864e5ef8c0b06ba769c0a50e53f193f9d682bf8"
 dependencies = [
  "anyhow",
  "csv",
@@ -3273,9 +3270,9 @@ dependencies = [
 
 [[package]]
 name = "lindera-ipadic"
-version = "0.32.2"
+version = "0.32.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b97a52ff0af5acb700093badaf7078051ab9ffd9071859724445a60193995f1f"
+checksum = "5b4731bf3730f1f38266d7ee9bca7d460cd336645c9dfd4e6a1082e58ab1e993"
 dependencies = [
  "bincode",
  "byteorder",
@@ -3287,9 +3284,9 @@ dependencies = [
 
 [[package]]
 name = "lindera-ipadic-builder"
-version = "0.32.2"
+version = "0.32.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bf5031c52686128db13f774b2c5a8abfd52b4cc1f904041d8411aa19d630ce4d"
+checksum = "309966c12e682f67205c3cd3c8dc55bbdcd1eb3b5c7c5cb41fb8acd18906d340"
 dependencies = [
  "anyhow",
  "lindera-core",
@@ -3299,9 +3296,9 @@ dependencies = [
 
 [[package]]
 name = "lindera-ipadic-neologd"
-version = "0.32.2"
+version = "0.32.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d6b36764b27b169aa11d24888141f206a6c246a5b195c1e67127485bac512fb6"
+checksum = "e90e919b4cfb9962d24ee1e1d50a7c163bbf356376495ad66d1996e20b9f9e44"
 dependencies = [
  "bincode",
  "byteorder",
@@ -3313,9 +3310,9 @@ dependencies = [
 
 [[package]]
 name = "lindera-ipadic-neologd-builder"
-version = "0.32.2"
+version = "0.32.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "abf36e40ace904741efdd883ed5c4dba6425f65156a0fb5d3f73a386335950dc"
+checksum = "7e517df0d501f9f8bf3126da20fc8cb9a5e37921e0eec1824d7a62f096463e02"
 dependencies = [
  "anyhow",
  "lindera-core",
@@ -3325,9 +3322,9 @@ dependencies = [
 
 [[package]]
 name = "lindera-ko-dic"
-version = "0.32.2"
+version = "0.32.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4c92a1a3564b531953f0238cbcea392f2905f7b27b449978cf9e702a80e1086d"
+checksum = "e9c6da4e68bc8b452a54b96d65361ebdceb4b6f36ecf262425c0e1f77960ae82"
 dependencies = [
  "bincode",
  "byteorder",
@@ -3340,9 +3337,9 @@ dependencies = [
 
 [[package]]
 name = "lindera-ko-dic-builder"
-version = "0.32.2"
+version = "0.32.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9f2c60425abc1548570c2568858f74a1f042105ecd89faa39c651b4315350fd9"
+checksum = "afc95884cc8f6dfb176caf5991043a4acf94c359215bbd039ea765e00454f271"
 dependencies = [
  "anyhow",
  "lindera-core",
@@ -3352,9 +3349,9 @@ dependencies = [
 
 [[package]]
 name = "lindera-tokenizer"
-version = "0.32.2"
+version = "0.32.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "903e558981bcb6f59870aa7d6b4bcb09e8f7db778886a6a70f67fd74c9fa2ca3"
+checksum = "d122042e1232a55c3604692445952a134e523822e9b4b9ab32a53ff890037ad4"
 dependencies = [
  "bincode",
  "lindera-core",
@@ -3366,9 +3363,9 @@ dependencies = [
 
 [[package]]
 name = "lindera-unidic"
-version = "0.32.2"
+version = "0.32.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d227c3ce9cbd905f865c46c65a0470fd04e89b71104d7f92baa71a212ffe1d4b"
+checksum = "cbffae1fb2f2614abdcb50f99b138476dbac19862ffa57bfdc9c7b5d5b22a90c"
 dependencies = [
  "bincode",
  "byteorder",
@@ -3381,9 +3378,9 @@ dependencies = [
 
 [[package]]
 name = "lindera-unidic-builder"
-version = "0.32.2"
+version = "0.32.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "99e2c50015c242e02c451acb6748667ac6fd1d3d667cd7db48cd89e2f2d2377e"
+checksum = "fe50055327712ebd1bcc74b657cf78c728a78b9586e3f99d5dd0b6a0be221c5d"
 dependencies = [
  "anyhow",
  "lindera-core",
@@ -3468,9 +3465,9 @@ checksum = "4ee93343901ab17bd981295f2cf0026d4ad018c7c31ba84549a4ddbb47a45104"
 
 [[package]]
 name = "lmdb-master-sys"
-version = "0.2.4"
+version = "0.2.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "472c3760e2a8d0f61f322fb36788021bb36d573c502b50fa3e2bcaac3ec326c9"
+checksum = "864808e0b19fb6dd3b70ba94ee671b82fce17554cf80aeb0a155c65bb08027df"
 dependencies = [
  "cc",
  "doxygen-rs",
@@ -3513,9 +3510,18 @@ checksum = "9374ef4228402d4b7e403e5838cb880d9ee663314b0a900d5a6aabf0c213552e"
 
 [[package]]
 name = "log"
-version = "0.4.21"
+version = "0.4.26"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "90ed8c1e510134f979dbc4f070f87d4313098b704861a105fe34231c70a3901c"
+checksum = "30bde2b3dc3671ae49d8e2e9f044c7c005836e7a023ee57cffa25ab82764bb9e"
+
+[[package]]
+name = "lru"
+version = "0.13.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "227748d55f2f0ab4735d87fd623798cb6b664512fe979705f829c9f81c934465"
+dependencies = [
+ "hashbrown 0.15.2",
+]
 
 [[package]]
 name = "lzma-rs"
@@ -3527,6 +3533,17 @@ dependencies = [
  "crc",
 ]
 
+[[package]]
+name = "lzma-sys"
+version = "0.1.20"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5fda04ab3764e6cde78b9974eec4f779acaba7c4e84b36eca3cf77c581b85d27"
+dependencies = [
+ "cc",
+ "libc",
+ "pkg-config",
+]
+
 [[package]]
 name = "macro_rules_attribute"
 version = "0.2.0"
@@ -3569,7 +3586,7 @@ checksum = "490cc448043f947bae3cbee9c203358d62dbee0db12107a74be5c30ccfd09771"
 
 [[package]]
 name = "meili-snap"
-version = "1.13.0"
+version = "1.14.0"
 dependencies = [
  "insta",
  "md5",
@@ -3578,7 +3595,7 @@ dependencies = [
 
 [[package]]
 name = "meilisearch"
-version = "1.13.0"
+version = "1.14.0"
 dependencies = [
  "actix-cors",
  "actix-http",
@@ -3665,12 +3682,12 @@ dependencies = [
  "uuid",
  "wiremock",
  "yaup",
- "zip 2.2.2",
+ "zip 2.3.0",
 ]
 
 [[package]]
 name = "meilisearch-auth"
-version = "1.13.0"
+version = "1.14.0"
 dependencies = [
  "base64 0.22.1",
  "enum-iterator",
@@ -3689,7 +3706,7 @@ dependencies = [
 
 [[package]]
 name = "meilisearch-types"
-version = "1.13.0"
+version = "1.14.0"
 dependencies = [
  "actix-web",
  "anyhow",
@@ -3723,10 +3740,9 @@ dependencies = [
 
 [[package]]
 name = "meilitool"
-version = "1.13.0"
+version = "1.14.0"
 dependencies = [
  "anyhow",
- "arroy 0.5.0 (git+https://github.com/meilisearch/arroy/?tag=DO-NOT-DELETE-upgrade-v04-to-v05)",
  "clap",
  "dump",
  "file-store",
@@ -3758,10 +3774,10 @@ dependencies = [
 
 [[package]]
 name = "milli"
-version = "1.13.0"
+version = "1.14.0"
 dependencies = [
  "allocator-api2",
- "arroy 0.5.0 (registry+https://github.com/rust-lang/crates.io-index)",
+ "arroy",
  "bbqueue",
  "big_s",
  "bimap",
@@ -3798,6 +3814,7 @@ dependencies = [
  "json-depth-checker",
  "levenshtein_automata",
  "liquid",
+ "lru",
  "maplit",
  "md5",
  "meili-snap",
@@ -3891,7 +3908,7 @@ checksum = "a4a650543ca06a924e8b371db273b2756685faae30f8487da1b56505a8f78b0c"
 dependencies = [
  "libc",
  "log",
- "wasi",
+ "wasi 0.11.0+wasi-snapshot-preview1",
  "windows-sys 0.48.0",
 ]
 
@@ -3902,7 +3919,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2886843bf800fba2e3377cff24abf6379b4c4d5c6681eaf9ea5b0d15090450bd"
 dependencies = [
  "libc",
- "wasi",
+ "wasi 0.11.0+wasi-snapshot-preview1",
  "windows-sys 0.52.0",
 ]
 
@@ -4129,9 +4146,9 @@ checksum = "ae4512a8f418ac322335255a72361b9ac927e106f4d7fe6ab4d8ac59cb01f7a9"
 
 [[package]]
 name = "once_cell"
-version = "1.20.2"
+version = "1.21.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1261fe7e33c73b354eab43b1273a57c8f967d0391e80353e51f764ac02cf6775"
+checksum = "cde51589ab56b20a6f686b2c68f7a0bd6add753d697abf720d63f8db3ab7b1ad"
 
 [[package]]
 name = "onig"
@@ -4270,7 +4287,7 @@ checksum = "e3148f5046208a5d56bcfc03053e3ca6334e51da8dfb19b6cdc8b306fae3283e"
 
 [[package]]
 name = "permissive-json-pointer"
-version = "1.13.0"
+version = "1.14.0"
 dependencies = [
  "big_s",
  "serde_json",
@@ -4518,7 +4535,7 @@ version = "0.16.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "731e0d9356b0c25f16f33b5be79b1c57b562f141ebfcdb0ad8ac2c13a24293b4"
 dependencies = [
- "bitflags 2.6.0",
+ "bitflags 2.9.0",
  "hex",
  "lazy_static",
  "procfs-core",
@@ -4531,7 +4548,7 @@ version = "0.16.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2d3554923a69f4ce04c4a754260c338f505ce22642d3830e049a399fc2059a29"
 dependencies = [
- "bitflags 2.6.0",
+ "bitflags 2.9.0",
  "hex",
 ]
 
@@ -4679,7 +4696,7 @@ version = "0.6.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ec0be4795e2f6a28069bec0b5ff3e2ac9bafc99e6a9a7dc3547996c5c816922c"
 dependencies = [
- "getrandom",
+ "getrandom 0.2.15",
 ]
 
 [[package]]
@@ -4771,7 +4788,7 @@ version = "0.4.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b033d837a7cf162d7993aded9304e30a83213c648b6e389db233191f891e5c2b"
 dependencies = [
- "getrandom",
+ "getrandom 0.2.15",
  "redox_syscall 0.2.16",
  "thiserror 1.0.69",
 ]
@@ -4872,7 +4889,7 @@ version = "1.20.0"
 source = "git+https://github.com/rhaiscript/rhai?rev=ef3df63121d27aacd838f366f2b83fd65f20a1e4#ef3df63121d27aacd838f366f2b83fd65f20a1e4"
 dependencies = [
  "ahash 0.8.11",
- "bitflags 2.6.0",
+ "bitflags 2.9.0",
  "instant",
  "num-traits",
  "once_cell",
@@ -4895,15 +4912,14 @@ dependencies = [
 
 [[package]]
 name = "ring"
-version = "0.17.8"
+version = "0.17.14"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c17fa4cb658e3583423e915b9f3acc01cceaee1860e33d59ebae66adc3a2dc0d"
+checksum = "a4689e6c2294d81e88dc6261c768b63bc4fcdb852be6d1352498b114f61383b7"
 dependencies = [
  "cc",
  "cfg-if",
- "getrandom",
+ "getrandom 0.2.15",
  "libc",
- "spin",
  "untrusted",
  "windows-sys 0.52.0",
 ]
@@ -5009,7 +5025,7 @@ version = "0.38.41"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d7f649912bc1495e167a6edee79151c84b1bad49748cb4f1f1167f459f6224f6"
 dependencies = [
- "bitflags 2.6.0",
+ "bitflags 2.9.0",
  "errno",
  "libc",
  "linux-raw-sys",
@@ -5131,9 +5147,9 @@ checksum = "a3f0bf26fd526d2a95683cd0f87bf103b8539e2ca1ef48ce002d67aad59aa0b4"
 
 [[package]]
 name = "serde"
-version = "1.0.217"
+version = "1.0.219"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "02fc4265df13d6fa1d00ecff087228cc0a2b5f3c0e87e258d8b94a156e984c70"
+checksum = "5f0e2c6ed6606019b4e29e69dbaba95b11854410e5347d525002456dbbb786b6"
 dependencies = [
  "serde_derive",
 ]
@@ -5149,9 +5165,9 @@ dependencies = [
 
 [[package]]
 name = "serde_derive"
-version = "1.0.217"
+version = "1.0.219"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5a9bf7cf98d04a2b28aead066b7496853d4779c9cc183c440dbac457641e19a0"
+checksum = "5b0276cf7f2c73365f7157c8123c21cd9a50fbbd844757af28ca1f5925fc2a00"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -5160,9 +5176,9 @@ dependencies = [
 
 [[package]]
 name = "serde_json"
-version = "1.0.135"
+version = "1.0.140"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2b0d7ba2887406110130a978386c4e1befb98c674b4fba677954e4db976630d9"
+checksum = "20068b6e96dc6c9bd23e01df8827e6c7e1f2fddd43c21810382803c136b99373"
 dependencies = [
  "indexmap",
  "itoa",
@@ -5530,7 +5546,7 @@ version = "0.5.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ec7dddc5f0fee506baf8b9fdb989e242f17e4b11c61dfbb0635b705217199eea"
 dependencies = [
- "bitflags 2.6.0",
+ "bitflags 2.9.0",
  "byteorder",
  "enum-as-inner",
  "libc",
@@ -5586,7 +5602,7 @@ checksum = "9a8a559c81686f576e8cd0290cd2a24a2a9ad80c98b3478856500fcbd7acd704"
 dependencies = [
  "cfg-if",
  "fastrand",
- "getrandom",
+ "getrandom 0.2.15",
  "once_cell",
  "rustix",
  "windows-sys 0.52.0",
@@ -5761,7 +5777,7 @@ dependencies = [
  "aho-corasick",
  "derive_builder 0.12.0",
  "esaxx-rs",
- "getrandom",
+ "getrandom 0.2.15",
  "itertools 0.12.1",
  "lazy_static",
  "log",
@@ -6104,9 +6120,9 @@ checksum = "3354b9ac3fae1ff6755cb6db53683adb661634f67557942dea4facebec0fee4b"
 
 [[package]]
 name = "unicode-normalization"
-version = "0.1.23"
+version = "0.1.24"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a56d1686db2308d901306f92a263857ef59ea39678a5458e7cb17f01415101f5"
+checksum = "5033c97c4262335cded6d6fc3e5c18ab755e1a3dc96376350f3d8e9f009ad956"
 dependencies = [
  "tinyvec",
 ]
@@ -6248,7 +6264,7 @@ version = "1.11.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f8c5f0a0af699448548ad1a2fbf920fb4bee257eae39953ba95cb84891a0446a"
 dependencies = [
- "getrandom",
+ "getrandom 0.2.15",
  "serde",
 ]
 
@@ -6345,24 +6361,34 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9c8d87e72b64a3b4db28d11ce29237c246188f4f51057d65a7eab63b7987e423"
 
 [[package]]
-name = "wasm-bindgen"
+name = "wasi"
-version = "0.2.92"
+version = "0.13.3+wasi-0.2.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4be2531df63900aeb2bca0daaaddec08491ee64ceecbee5076636a3b026795a8"
+checksum = "26816d2e1a4a36a2940b96c5296ce403917633dff8f3440e9b236ed6f6bacad2"
+dependencies = [
+ "wit-bindgen-rt",
+]
+
+[[package]]
+name = "wasm-bindgen"
+version = "0.2.100"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1edc8929d7499fc4e8f0be2262a241556cfc54a0bea223790e71446f2aab1ef5"
 dependencies = [
  "cfg-if",
+ "once_cell",
+ "rustversion",
  "wasm-bindgen-macro",
 ]
 
 [[package]]
 name = "wasm-bindgen-backend"
-version = "0.2.92"
+version = "0.2.100"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "614d787b966d3989fa7bb98a654e369c762374fd3213d212cfc0251257e747da"
+checksum = "2f0a0651a5c2bc21487bde11ee802ccaf4c51935d0d3d42a6101f98161700bc6"
 dependencies = [
  "bumpalo",
  "log",
- "once_cell",
  "proc-macro2",
  "quote",
  "syn 2.0.87",
@@ -6383,9 +6409,9 @@ dependencies = [
 
 [[package]]
 name = "wasm-bindgen-macro"
-version = "0.2.92"
+version = "0.2.100"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a1f8823de937b71b9460c0c34e25f3da88250760bec0ebac694b49997550d726"
+checksum = "7fe63fc6d09ed3792bd0897b314f53de8e16568c2b3f7982f468c0bf9bd0b407"
 dependencies = [
  "quote",
  "wasm-bindgen-macro-support",
@@ -6393,9 +6419,9 @@ dependencies = [
 
 [[package]]
 name = "wasm-bindgen-macro-support"
-version = "0.2.92"
+version = "0.2.100"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e94f17b526d0a461a191c78ea52bbce64071ed5c04c9ffe424dcb38f74171bb7"
+checksum = "8ae87ea40c9f689fc23f209965b6fb8a99ad69aeeb0231408be24920604395de"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -6406,9 +6432,12 @@ dependencies = [
 
 [[package]]
 name = "wasm-bindgen-shared"
-version = "0.2.92"
+version = "0.2.100"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "af190c94f2773fdb3729c55b007a722abb5384da03bc0986df4c289bf5567e96"
+checksum = "1a05d73b933a847d6cccdda8f838a22ff101ad9bf93e33684f39c1f5f0eece3d"
+dependencies = [
+ "unicode-ident",
+]
 
 [[package]]
 name = "wasm-streams"
@@ -6813,6 +6842,15 @@ dependencies = [
  "url",
 ]
 
+[[package]]
+name = "wit-bindgen-rt"
+version = "0.33.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3268f3d866458b787f390cf61f4bbb563b922d091359f9608842999eaee3943c"
+dependencies = [
+ "bitflags 2.9.0",
+]
+
 [[package]]
 name = "write16"
 version = "1.0.0"
@@ -6847,7 +6885,7 @@ dependencies = [
 
 [[package]]
 name = "xtask"
-version = "1.13.0"
+version = "1.14.0"
 dependencies = [
  "anyhow",
  "build-info",
@@ -6868,6 +6906,15 @@ dependencies = [
  "uuid",
 ]
 
+[[package]]
+name = "xz2"
+version = "0.1.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "388c44dc09d76f1536602ead6d325eb532f5c122f17782bd57fb47baeeb767e2"
+dependencies = [
+ "lzma-sys",
+]
+
 [[package]]
 name = "yada"
 version = "0.5.1"
@@ -7009,9 +7056,9 @@ dependencies = [
 
 [[package]]
 name = "zip"
-version = "2.2.2"
+version = "2.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ae9c1ea7b3a5e1f4b922ff856a129881167511563dc219869afe3787fc0c1a45"
+checksum = "84e9a772a54b54236b9b744aaaf8d7be01b4d6e99725523cb82cb32d1c81b1d7"
 dependencies = [
  "aes",
  "arbitrary",
@@ -7022,15 +7069,16 @@ dependencies = [
  "deflate64",
  "displaydoc",
  "flate2",
+ "getrandom 0.3.1",
  "hmac",
  "indexmap",
  "lzma-rs",
  "memchr",
  "pbkdf2",
- "rand",
  "sha1",
  "thiserror 2.0.9",
  "time",
+ "xz2",
  "zeroize",
  "zopfli",
  "zstd",

Cargo.toml

@@ -22,7 +22,7 @@ members = [
 ]
 
 [workspace.package]
-version = "1.13.0"
+version = "1.14.0"
 authors = [
     "Quentin de Quelen <quentin@dequelen.me>",
     "Clément Renault <clement@meilisearch.com>",
@@ -36,6 +36,12 @@ license = "MIT"
 [profile.release]
 codegen-units = 1
 
+# We now compile heed without the NDEBUG define for better performance.
+# However, we still enable debug assertions for a better detection of
+# disk corruption on the cloud or in OSS.
+[profile.release.package.heed]
+debug-assertions = true
+
 [profile.dev.package.flate2]
 opt-level = 3
 

README.md

@@ -20,7 +20,7 @@
 <p align="center">
   <a href="https://deps.rs/repo/github/meilisearch/meilisearch"><img src="https://deps.rs/repo/github/meilisearch/meilisearch/status.svg" alt="Dependency status"></a>
   <a href="https://github.com/meilisearch/meilisearch/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-MIT-informational" alt="License"></a>
-  <a href="https://ms-bors.herokuapp.com/repositories/52"><img src="https://bors.tech/images/badge_small.svg" alt="Bors enabled"></a>
+  <a href="https://github.com/meilisearch/meilisearch/queue"><img alt="Merge Queues enabled" src="https://img.shields.io/badge/Merge_Queues-enabled-%2357cf60?logo=github"></a>
 </p>
 
 <p align="center">⚡ A lightning-fast search engine that fits effortlessly into your apps, websites, and workflow 🔍</p>

bors.toml

@@ -1,11 +0,0 @@
-status = [
-    'Tests on ubuntu-20.04',
-    'Tests on macos-13',
-    'Tests on windows-2022',
-    'Run Clippy',
-    'Run Rustfmt',
-    'Run tests in debug',
-]
-pr_status = ['Milestone Check']
-# 3 hours timeout
-timeout-sec = 10800

crates/benchmarks/benches/indexing.rs

@@ -12,7 +12,7 @@ use milli::progress::Progress;
 use milli::update::new::indexer;
 use milli::update::{IndexerConfig, Settings};
 use milli::vector::EmbeddingConfigs;
-use milli::Index;
+use milli::{FilterableAttributesRule, Index};
 use rand::seq::SliceRandom;
 use rand_chacha::rand_core::SeedableRng;
 use roaring::RoaringBitmap;
@@ -35,7 +35,8 @@ fn setup_dir(path: impl AsRef<Path>) {
 fn setup_index() -> Index {
     let path = "benches.mmdb";
     setup_dir(path);
-    let mut options = EnvOpenOptions::new();
+    let options = EnvOpenOptions::new();
+    let mut options = options.read_txn_without_tls();
     options.map_size(100 * 1024 * 1024 * 1024); // 100 GB
     options.max_readers(100);
     Index::new(options, path, true).unwrap()
@@ -57,7 +58,8 @@ fn setup_settings<'t>(
     let searchable_fields = searchable_fields.iter().map(|s| s.to_string()).collect();
     builder.set_searchable_fields(searchable_fields);
 
-    let filterable_fields = filterable_fields.iter().map(|s| s.to_string()).collect();
+    let filterable_fields =
+        filterable_fields.iter().map(|s| FilterableAttributesRule::Field(s.to_string())).collect();
     builder.set_filterable_fields(filterable_fields);
 
     let sortable_fields = sortable_fields.iter().map(|s| s.to_string()).collect();

crates/benchmarks/benches/search_geo.rs

@@ -2,7 +2,7 @@ mod datasets_paths;
 mod utils;
 
 use criterion::{criterion_group, criterion_main};
-use milli::update::Settings;
+use milli::{update::Settings, FilterableAttributesRule};
 use utils::Conf;
 
 #[cfg(not(windows))]
@@ -21,8 +21,10 @@ fn base_conf(builder: &mut Settings) {
         ["name", "alternatenames", "elevation"].iter().map(|s| s.to_string()).collect();
     builder.set_searchable_fields(searchable_fields);
 
-    let filterable_fields =
+    let filterable_fields = ["_geo", "population", "elevation"]
-        ["_geo", "population", "elevation"].iter().map(|s| s.to_string()).collect();
+        .iter()
+        .map(|s| FilterableAttributesRule::Field(s.to_string()))
+        .collect();
     builder.set_filterable_fields(filterable_fields);
 
     let sortable_fields =

crates/benchmarks/benches/search_songs.rs

@@ -2,7 +2,7 @@ mod datasets_paths;
 mod utils;
 
 use criterion::{criterion_group, criterion_main};
-use milli::update::Settings;
+use milli::{update::Settings, FilterableAttributesRule};
 use utils::Conf;
 
 #[cfg(not(windows))]
@@ -22,7 +22,7 @@ fn base_conf(builder: &mut Settings) {
 
     let faceted_fields = ["released-timestamp", "duration-float", "genre", "country", "artist"]
         .iter()
-        .map(|s| s.to_string())
+        .map(|s| FilterableAttributesRule::Field(s.to_string()))
         .collect();
     builder.set_filterable_fields(faceted_fields);
 }

crates/benchmarks/benches/utils.rs

@@ -65,7 +65,8 @@ pub fn base_setup(conf: &Conf) -> Index {
     }
     create_dir_all(conf.database_name).unwrap();
 
-    let mut options = EnvOpenOptions::new();
+    let options = EnvOpenOptions::new();
+    let mut options = options.read_txn_without_tls();
     options.map_size(100 * 1024 * 1024 * 1024); // 100 GB
     options.max_readers(100);
     let index = Index::new(options, conf.database_name, true).unwrap();

crates/dump/README.md

@@ -10,8 +10,10 @@ dump
 ├── instance-uid.uuid
 ├── keys.jsonl
 ├── metadata.json
-└── tasks
+├── tasks
-    ├── update_files
+│   ├── update_files
-    │   └── [task_id].jsonl
+│   │   └── [task_id].jsonl
+│   └── queue.jsonl
+└── batches
     └── queue.jsonl
-```
+```

crates/dump/src/lib.rs

@@ -228,14 +228,16 @@ pub(crate) mod test {
 
     use big_s::S;
     use maplit::{btreemap, btreeset};
+    use meilisearch_types::batches::{Batch, BatchEnqueuedAt, BatchStats};
     use meilisearch_types::facet_values_sort::FacetValuesSort;
-    use meilisearch_types::features::RuntimeTogglableFeatures;
+    use meilisearch_types::features::{Network, Remote, RuntimeTogglableFeatures};
     use meilisearch_types::index_uid_pattern::IndexUidPattern;
     use meilisearch_types::keys::{Action, Key};
-    use meilisearch_types::milli;
     use meilisearch_types::milli::update::Setting;
+    use meilisearch_types::milli::{self, FilterableAttributesRule};
     use meilisearch_types::settings::{Checked, FacetingSettings, Settings};
-    use meilisearch_types::tasks::{Details, Status};
+    use meilisearch_types::task_view::DetailsView;
+    use meilisearch_types::tasks::{Details, Kind, Status};
     use serde_json::{json, Map, Value};
     use time::macros::datetime;
     use uuid::Uuid;
@@ -277,7 +279,10 @@ pub(crate) mod test {
         let settings = Settings {
             displayed_attributes: Setting::Set(vec![S("race"), S("name")]).into(),
             searchable_attributes: Setting::Set(vec![S("name"), S("race")]).into(),
-            filterable_attributes: Setting::Set(btreeset! { S("race"), S("age") }),
+            filterable_attributes: Setting::Set(vec![
+                FilterableAttributesRule::Field(S("race")),
+                FilterableAttributesRule::Field(S("age")),
+            ]),
             sortable_attributes: Setting::Set(btreeset! { S("age") }),
             ranking_rules: Setting::NotSet,
             stop_words: Setting::NotSet,
@@ -305,6 +310,33 @@ pub(crate) mod test {
         settings.check()
     }
 
+    pub fn create_test_batches() -> Vec<Batch> {
+        vec![Batch {
+            uid: 0,
+            details: DetailsView {
+                received_documents: Some(12),
+                indexed_documents: Some(Some(10)),
+                ..DetailsView::default()
+            },
+            progress: None,
+            stats: BatchStats {
+                total_nb_tasks: 1,
+                status: maplit::btreemap! { Status::Succeeded => 1 },
+                types: maplit::btreemap! { Kind::DocumentAdditionOrUpdate => 1 },
+                index_uids: maplit::btreemap! { "doggo".to_string() => 1 },
+                progress_trace: Default::default(),
+                write_channel_congestion: None,
+                internal_database_sizes: Default::default(),
+            },
+            enqueued_at: Some(BatchEnqueuedAt {
+                earliest: datetime!(2022-11-11 0:00 UTC),
+                oldest: datetime!(2022-11-11 0:00 UTC),
+            }),
+            started_at: datetime!(2022-11-20 0:00 UTC),
+            finished_at: Some(datetime!(2022-11-21 0:00 UTC)),
+        }]
+    }
+
     pub fn create_test_tasks() -> Vec<(TaskDump, Option<Vec<Document>>)> {
         vec![
             (
@@ -427,6 +459,15 @@ pub(crate) mod test {
         index.flush().unwrap();
         index.settings(&settings).unwrap();
 
+        // ========== pushing the batch queue
+        let batches = create_test_batches();
+
+        let mut batch_queue = dump.create_batches_queue().unwrap();
+        for batch in &batches {
+            batch_queue.push_batch(batch).unwrap();
+        }
+        batch_queue.flush().unwrap();
+
         // ========== pushing the task queue
         let tasks = create_test_tasks();
 
@@ -455,6 +496,10 @@ pub(crate) mod test {
 
         dump.create_experimental_features(features).unwrap();
 
+        // ========== network
+        let network = create_test_network();
+        dump.create_network(network).unwrap();
+
         // create the dump
         let mut file = tempfile::tempfile().unwrap();
         dump.persist_to(&mut file).unwrap();
@@ -467,6 +512,13 @@ pub(crate) mod test {
         RuntimeTogglableFeatures::default()
     }
 
+    fn create_test_network() -> Network {
+        Network {
+            local: Some("myself".to_string()),
+            remotes: maplit::btreemap! {"other".to_string() => Remote { url: "http://test".to_string(), search_api_key: Some("apiKey".to_string()) }},
+        }
+    }
+
     #[test]
     fn test_creating_and_read_dump() {
         let mut file = create_test_dump();
@@ -515,5 +567,9 @@ pub(crate) mod test {
         // ==== checking the features
         let expected = create_test_features();
         assert_eq!(dump.features().unwrap().unwrap(), expected);
+
+        // ==== checking the network
+        let expected = create_test_network();
+        assert_eq!(&expected, dump.network().unwrap().unwrap());
     }
 }

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

@@ -196,6 +196,10 @@ impl CompatV5ToV6 {
     pub fn features(&self) -> Result<Option<v6::RuntimeTogglableFeatures>> {
         Ok(None)
     }
+
+    pub fn network(&self) -> Result<Option<&v6::Network>> {
+        Ok(None)
+    }
 }
 
 pub enum CompatIndexV5ToV6 {
@@ -318,7 +322,16 @@ impl<T> From<v5::Settings<T>> for v6::Settings<v6::Unchecked> {
         v6::Settings {
             displayed_attributes: v6::Setting::from(settings.displayed_attributes).into(),
             searchable_attributes: v6::Setting::from(settings.searchable_attributes).into(),
-            filterable_attributes: settings.filterable_attributes.into(),
+            filterable_attributes: match settings.filterable_attributes {
+                v5::settings::Setting::Set(filterable_attributes) => v6::Setting::Set(
+                    filterable_attributes
+                        .into_iter()
+                        .map(v6::FilterableAttributesRule::Field)
+                        .collect(),
+                ),
+                v5::settings::Setting::Reset => v6::Setting::Reset,
+                v5::settings::Setting::NotSet => v6::Setting::NotSet,
+            },
             sortable_attributes: settings.sortable_attributes.into(),
             ranking_rules: {
                 match settings.ranking_rules {

crates/dump/src/reader/mod.rs

@@ -23,6 +23,7 @@ mod v6;
 pub type Document = serde_json::Map<String, serde_json::Value>;
 pub type UpdateFile = dyn Iterator<Item = Result<Document>>;
 
+#[allow(clippy::large_enum_variant)]
 pub enum DumpReader {
     Current(V6Reader),
     Compat(CompatV5ToV6),
@@ -101,6 +102,13 @@ impl DumpReader {
         }
     }
 
+    pub fn batches(&mut self) -> Result<Box<dyn Iterator<Item = Result<v6::Batch>> + '_>> {
+        match self {
+            DumpReader::Current(current) => Ok(current.batches()),
+            DumpReader::Compat(_compat) => Ok(Box::new(std::iter::empty())),
+        }
+    }
+
     pub fn keys(&mut self) -> Result<Box<dyn Iterator<Item = Result<v6::Key>> + '_>> {
         match self {
             DumpReader::Current(current) => Ok(current.keys()),
@@ -114,6 +122,13 @@ impl DumpReader {
             DumpReader::Compat(compat) => compat.features(),
         }
     }
+
+    pub fn network(&self) -> Result<Option<&v6::Network>> {
+        match self {
+            DumpReader::Current(current) => Ok(current.network()),
+            DumpReader::Compat(compat) => compat.network(),
+        }
+    }
 }
 
 impl From<V6Reader> for DumpReader {
@@ -219,6 +234,10 @@ pub(crate) mod test {
         insta::assert_snapshot!(dump.date().unwrap(), @"2024-05-16 15:51:34.151044 +00:00:00");
         insta::assert_debug_snapshot!(dump.instance_uid().unwrap(), @"None");
 
+        // batches didn't exists at the time
+        let batches = dump.batches().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        meili_snap::snapshot!(meili_snap::json_string!(batches), @"[]");
+
         // tasks
         let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
         let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
@@ -328,6 +347,7 @@ pub(crate) mod test {
         }
 
         assert_eq!(dump.features().unwrap().unwrap(), RuntimeTogglableFeatures::default());
+        assert_eq!(dump.network().unwrap(), None);
     }
 
     #[test]
@@ -339,6 +359,10 @@ pub(crate) mod test {
         insta::assert_snapshot!(dump.date().unwrap(), @"2023-07-06 7:10:27.21958 +00:00:00");
         insta::assert_debug_snapshot!(dump.instance_uid().unwrap(), @"None");
 
+        // batches didn't exists at the time
+        let batches = dump.batches().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        meili_snap::snapshot!(meili_snap::json_string!(batches), @"[]");
+
         // tasks
         let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
         let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
@@ -373,6 +397,27 @@ pub(crate) mod test {
         assert_eq!(dump.features().unwrap().unwrap(), RuntimeTogglableFeatures::default());
     }
 
+    #[test]
+    fn import_dump_v6_network() {
+        let dump = File::open("tests/assets/v6-with-network.dump").unwrap();
+        let dump = DumpReader::open(dump).unwrap();
+
+        // top level infos
+        insta::assert_snapshot!(dump.date().unwrap(), @"2025-01-29 15:45:32.738676 +00:00:00");
+        insta::assert_debug_snapshot!(dump.instance_uid().unwrap(), @"None");
+
+        // network
+
+        let network = dump.network().unwrap().unwrap();
+        insta::assert_snapshot!(network.local.as_ref().unwrap(), @"ms-0");
+        insta::assert_snapshot!(network.remotes.get("ms-0").as_ref().unwrap().url, @"http://localhost:7700");
+        insta::assert_snapshot!(network.remotes.get("ms-0").as_ref().unwrap().search_api_key.is_none(), @"true");
+        insta::assert_snapshot!(network.remotes.get("ms-1").as_ref().unwrap().url, @"http://localhost:7701");
+        insta::assert_snapshot!(network.remotes.get("ms-1").as_ref().unwrap().search_api_key.is_none(), @"true");
+        insta::assert_snapshot!(network.remotes.get("ms-2").as_ref().unwrap().url, @"http://ms-5679.example.meilisearch.io");
+        insta::assert_snapshot!(network.remotes.get("ms-2").as_ref().unwrap().search_api_key.as_ref().unwrap(), @"foo");
+    }
+
     #[test]
     fn import_dump_v5() {
         let dump = File::open("tests/assets/v5.dump").unwrap();
@@ -382,6 +427,10 @@ pub(crate) mod test {
         insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-04 15:55:10.344982459 +00:00:00");
         insta::assert_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d");
 
+        // batches didn't exists at the time
+        let batches = dump.batches().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        meili_snap::snapshot!(meili_snap::json_string!(batches), @"[]");
+
         // tasks
         let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
         let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
@@ -462,6 +511,10 @@ pub(crate) mod test {
         insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-06 12:53:49.131989609 +00:00:00");
         insta::assert_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d");
 
+        // batches didn't exists at the time
+        let batches = dump.batches().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        meili_snap::snapshot!(meili_snap::json_string!(batches), @"[]");
+
         // tasks
         let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
         let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
@@ -539,6 +592,10 @@ pub(crate) mod test {
         insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-07 11:39:03.709153554 +00:00:00");
         assert_eq!(dump.instance_uid().unwrap(), None);
 
+        // batches didn't exists at the time
+        let batches = dump.batches().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        meili_snap::snapshot!(meili_snap::json_string!(batches), @"[]");
+
         // tasks
         let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
         let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
@@ -632,6 +689,10 @@ pub(crate) mod test {
         insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-09 20:27:59.904096267 +00:00:00");
         assert_eq!(dump.instance_uid().unwrap(), None);
 
+        // batches didn't exists at the time
+        let batches = dump.batches().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        meili_snap::snapshot!(meili_snap::json_string!(batches), @"[]");
+
         // tasks
         let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
         let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
@@ -725,6 +786,10 @@ pub(crate) mod test {
         insta::assert_snapshot!(dump.date().unwrap(), @"2023-01-30 16:26:09.247261 +00:00:00");
         assert_eq!(dump.instance_uid().unwrap(), None);
 
+        // batches didn't exists at the time
+        let batches = dump.batches().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        meili_snap::snapshot!(meili_snap::json_string!(batches), @"[]");
+
         // tasks
         let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
         let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
@@ -801,6 +866,10 @@ pub(crate) mod test {
         assert_eq!(dump.date(), None);
         assert_eq!(dump.instance_uid().unwrap(), None);
 
+        // batches didn't exists at the time
+        let batches = dump.batches().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        meili_snap::snapshot!(meili_snap::json_string!(batches), @"[]");
+
         // tasks
         let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
         let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();

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

@@ -1,5 +1,5 @@
 ---
-source: dump/src/reader/mod.rs
+source: crates/dump/src/reader/mod.rs
 expression: vector_index.settings().unwrap()
 ---
 {
@@ -49,6 +49,7 @@ expression: vector_index.settings().unwrap()
       "source": "huggingFace",
       "model": "BAAI/bge-base-en-v1.5",
       "revision": "617ca489d9e86b49b8167676d8220688b99db36e",
+      "pooling": "forceMean",
       "documentTemplate": "{% for field in fields %} {{ field.name }}: {{ field.value }}\n{% endfor %}"
     }
   },

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

@@ -3,6 +3,7 @@ use std::io::{BufRead, BufReader, ErrorKind};
 use std::path::Path;
 
 pub use meilisearch_types::milli;
+use meilisearch_types::milli::vector::hf::OverridePooling;
 use tempfile::TempDir;
 use time::OffsetDateTime;
 use tracing::debug;
@@ -18,8 +19,10 @@ pub type Checked = meilisearch_types::settings::Checked;
 pub type Unchecked = meilisearch_types::settings::Unchecked;
 
 pub type Task = crate::TaskDump;
+pub type Batch = meilisearch_types::batches::Batch;
 pub type Key = meilisearch_types::keys::Key;
 pub type RuntimeTogglableFeatures = meilisearch_types::features::RuntimeTogglableFeatures;
+pub type Network = meilisearch_types::features::Network;
 
 // ===== Other types to clarify the code of the compat module
 // everything related to the tasks
@@ -43,13 +46,17 @@ pub type ResponseError = meilisearch_types::error::ResponseError;
 pub type Code = meilisearch_types::error::Code;
 pub type RankingRuleView = meilisearch_types::settings::RankingRuleView;
 
+pub type FilterableAttributesRule = meilisearch_types::milli::FilterableAttributesRule;
+
 pub struct V6Reader {
     dump: TempDir,
     instance_uid: Option<Uuid>,
     metadata: Metadata,
     tasks: BufReader<File>,
+    batches: Option<BufReader<File>>,
     keys: BufReader<File>,
     features: Option<RuntimeTogglableFeatures>,
+    network: Option<Network>,
 }
 
 impl V6Reader {
@@ -77,13 +84,38 @@ impl V6Reader {
         } else {
             None
         };
+        let batches = match File::open(dump.path().join("batches").join("queue.jsonl")) {
+            Ok(file) => Some(BufReader::new(file)),
+            // The batch file was only introduced during the v1.13, anything prior to that won't have batches
+            Err(err) if err.kind() == ErrorKind::NotFound => None,
+            Err(e) => return Err(e.into()),
+        };
+
+        let network_file = match fs::read(dump.path().join("network.json")) {
+            Ok(network_file) => Some(network_file),
+            Err(error) => match error.kind() {
+                // Allows the file to be missing, this will only result in all experimental features disabled.
+                ErrorKind::NotFound => {
+                    debug!("`network.json` not found in dump");
+                    None
+                }
+                _ => return Err(error.into()),
+            },
+        };
+        let network = if let Some(network_file) = network_file {
+            Some(serde_json::from_reader(&*network_file)?)
+        } else {
+            None
+        };
 
         Ok(V6Reader {
             metadata: serde_json::from_reader(&*meta_file)?,
             instance_uid,
             tasks: BufReader::new(File::open(dump.path().join("tasks").join("queue.jsonl"))?),
+            batches,
             keys: BufReader::new(File::open(dump.path().join("keys.jsonl"))?),
             features,
+            network,
             dump,
         })
     }
@@ -124,7 +156,7 @@ impl V6Reader {
         &mut self,
     ) -> Box<dyn Iterator<Item = Result<(Task, Option<Box<super::UpdateFile>>)>> + '_> {
         Box::new((&mut self.tasks).lines().map(|line| -> Result<_> {
-            let task: Task = serde_json::from_str(&line?).unwrap();
+            let task: Task = serde_json::from_str(&line?)?;
 
             let update_file_path = self
                 .dump
@@ -136,8 +168,7 @@ impl V6Reader {
             if update_file_path.exists() {
                 Ok((
                     task,
-                    Some(Box::new(UpdateFile::new(&update_file_path).unwrap())
+                    Some(Box::new(UpdateFile::new(&update_file_path)?) as Box<super::UpdateFile>),
-                        as Box<super::UpdateFile>),
                 ))
             } else {
                 Ok((task, None))
@@ -145,6 +176,16 @@ impl V6Reader {
         }))
     }
 
+    pub fn batches(&mut self) -> Box<dyn Iterator<Item = Result<Batch>> + '_> {
+        match self.batches.as_mut() {
+            Some(batches) => Box::new((batches).lines().map(|line| -> Result<_> {
+                let batch = serde_json::from_str(&line?)?;
+                Ok(batch)
+            })),
+            None => Box::new(std::iter::empty()) as Box<dyn Iterator<Item = Result<Batch>> + '_>,
+        }
+    }
+
     pub fn keys(&mut self) -> Box<dyn Iterator<Item = Result<Key>> + '_> {
         Box::new(
             (&mut self.keys).lines().map(|line| -> Result<_> { Ok(serde_json::from_str(&line?)?) }),
@@ -154,6 +195,10 @@ impl V6Reader {
     pub fn features(&self) -> Option<RuntimeTogglableFeatures> {
         self.features
     }
+
+    pub fn network(&self) -> Option<&Network> {
+        self.network.as_ref()
+    }
 }
 
 pub struct UpdateFile {
@@ -210,7 +255,29 @@ impl V6IndexReader {
     }
 
     pub fn settings(&mut self) -> Result<Settings<Checked>> {
-        let settings: Settings<Unchecked> = serde_json::from_reader(&mut self.settings)?;
+        let mut settings: Settings<Unchecked> = serde_json::from_reader(&mut self.settings)?;
+        patch_embedders(&mut settings);
         Ok(settings.check())
     }
 }
+
+fn patch_embedders(settings: &mut Settings<Unchecked>) {
+    if let Setting::Set(embedders) = &mut settings.embedders {
+        for settings in embedders.values_mut() {
+            let Setting::Set(settings) = &mut settings.inner else {
+                continue;
+            };
+            if settings.source != Setting::Set(milli::vector::settings::EmbedderSource::HuggingFace)
+            {
+                continue;
+            }
+            settings.pooling = match settings.pooling {
+                Setting::Set(pooling) => Setting::Set(pooling),
+                // if the pooling for a hugging face embedder is not set, force it to `forceMean`
+                // for backward compatibility with v1.13
+                // dumps created in v1.14 and up will have the setting set for hugging face embedders
+                Setting::Reset | Setting::NotSet => Setting::Set(OverridePooling::ForceMean),
+            };
+        }
+    }
+}

crates/dump/src/writer.rs

@@ -4,7 +4,8 @@ use std::path::PathBuf;
 
 use flate2::write::GzEncoder;
 use flate2::Compression;
-use meilisearch_types::features::RuntimeTogglableFeatures;
+use meilisearch_types::batches::Batch;
+use meilisearch_types::features::{Network, RuntimeTogglableFeatures};
 use meilisearch_types::keys::Key;
 use meilisearch_types::settings::{Checked, Settings};
 use serde_json::{Map, Value};
@@ -54,6 +55,10 @@ impl DumpWriter {
         TaskWriter::new(self.dir.path().join("tasks"))
     }
 
+    pub fn create_batches_queue(&self) -> Result<BatchWriter> {
+        BatchWriter::new(self.dir.path().join("batches"))
+    }
+
     pub fn create_experimental_features(&self, features: RuntimeTogglableFeatures) -> Result<()> {
         Ok(std::fs::write(
             self.dir.path().join("experimental-features.json"),
@@ -61,6 +66,10 @@ impl DumpWriter {
         )?)
     }
 
+    pub fn create_network(&self, network: Network) -> Result<()> {
+        Ok(std::fs::write(self.dir.path().join("network.json"), serde_json::to_string(&network)?)?)
+    }
+
     pub fn persist_to(self, mut writer: impl Write) -> Result<()> {
         let gz_encoder = GzEncoder::new(&mut writer, Compression::default());
         let mut tar_encoder = tar::Builder::new(gz_encoder);
@@ -84,7 +93,7 @@ impl KeyWriter {
     }
 
     pub fn push_key(&mut self, key: &Key) -> Result<()> {
-        self.keys.write_all(&serde_json::to_vec(key)?)?;
+        serde_json::to_writer(&mut self.keys, &key)?;
         self.keys.write_all(b"\n")?;
         Ok(())
     }
@@ -114,7 +123,7 @@ impl TaskWriter {
     /// Pushes tasks in the dump.
     /// If the tasks has an associated `update_file` it'll use the `task_id` as its name.
     pub fn push_task(&mut self, task: &TaskDump) -> Result<UpdateFile> {
-        self.queue.write_all(&serde_json::to_vec(task)?)?;
+        serde_json::to_writer(&mut self.queue, &task)?;
         self.queue.write_all(b"\n")?;
 
         Ok(UpdateFile::new(self.update_files.join(format!("{}.jsonl", task.uid))))
@@ -126,6 +135,30 @@ impl TaskWriter {
     }
 }
 
+pub struct BatchWriter {
+    queue: BufWriter<File>,
+}
+
+impl BatchWriter {
+    pub(crate) fn new(path: PathBuf) -> Result<Self> {
+        std::fs::create_dir(&path)?;
+        let queue = File::create(path.join("queue.jsonl"))?;
+        Ok(BatchWriter { queue: BufWriter::new(queue) })
+    }
+
+    /// Pushes batches in the dump.
+    pub fn push_batch(&mut self, batch: &Batch) -> Result<()> {
+        serde_json::to_writer(&mut self.queue, &batch)?;
+        self.queue.write_all(b"\n")?;
+        Ok(())
+    }
+
+    pub fn flush(mut self) -> Result<()> {
+        self.queue.flush()?;
+        Ok(())
+    }
+}
+
 pub struct UpdateFile {
     path: PathBuf,
     writer: Option<BufWriter<File>>,
@@ -137,8 +170,8 @@ impl UpdateFile {
     }
 
     pub fn push_document(&mut self, document: &Document) -> Result<()> {
-        if let Some(writer) = self.writer.as_mut() {
+        if let Some(mut writer) = self.writer.as_mut() {
-            writer.write_all(&serde_json::to_vec(document)?)?;
+            serde_json::to_writer(&mut writer, &document)?;
             writer.write_all(b"\n")?;
         } else {
             let file = File::create(&self.path).unwrap();
@@ -205,8 +238,8 @@ pub(crate) mod test {
     use super::*;
     use crate::reader::Document;
     use crate::test::{
-        create_test_api_keys, create_test_documents, create_test_dump, create_test_instance_uid,
+        create_test_api_keys, create_test_batches, create_test_documents, create_test_dump,
-        create_test_settings, create_test_tasks,
+        create_test_instance_uid, create_test_settings, create_test_tasks,
     };
 
     fn create_directory_hierarchy(dir: &Path) -> String {
@@ -281,8 +314,10 @@ pub(crate) mod test {
         let dump_path = dump.path();
 
         // ==== checking global file hierarchy (we want to be sure there isn't too many files or too few)
-        insta::assert_snapshot!(create_directory_hierarchy(dump_path), @r###"
+        insta::assert_snapshot!(create_directory_hierarchy(dump_path), @r"
         .
+        ├---- batches/
+        │    └---- queue.jsonl
         ├---- indexes/
         │    └---- doggos/
         │    │    ├---- documents.jsonl
@@ -295,8 +330,9 @@ pub(crate) mod test {
         ├---- experimental-features.json
         ├---- instance_uid.uuid
         ├---- keys.jsonl
-        └---- metadata.json
+        ├---- metadata.json
-        "###);
+        └---- network.json
+        ");
 
         // ==== checking the top level infos
         let metadata = fs::read_to_string(dump_path.join("metadata.json")).unwrap();
@@ -349,6 +385,16 @@ pub(crate) mod test {
             }
         }
 
+        // ==== checking the batch queue
+        let batches_queue = fs::read_to_string(dump_path.join("batches/queue.jsonl")).unwrap();
+        for (batch, expected) in batches_queue.lines().zip(create_test_batches()) {
+            let mut batch = serde_json::from_str::<Batch>(batch).unwrap();
+            if batch.details.settings == Some(Box::new(Settings::<Unchecked>::default())) {
+                batch.details.settings = None;
+            }
+            assert_eq!(batch, expected, "{batch:#?}{expected:#?}");
+        }
+
         // ==== checking the keys
         let keys = fs::read_to_string(dump_path.join("keys.jsonl")).unwrap();
         for (key, expected) in keys.lines().zip(create_test_api_keys()) {

crates/filter-parser/src/condition.rs

@@ -30,6 +30,25 @@ pub enum Condition<'a> {
     StartsWith { keyword: Token<'a>, word: Token<'a> },
 }
 
+impl Condition<'_> {
+    pub fn operator(&self) -> &str {
+        match self {
+            Condition::GreaterThan(_) => ">",
+            Condition::GreaterThanOrEqual(_) => ">=",
+            Condition::Equal(_) => "=",
+            Condition::NotEqual(_) => "!=",
+            Condition::Null => "IS NULL",
+            Condition::Empty => "IS EMPTY",
+            Condition::Exists => "EXISTS",
+            Condition::LowerThan(_) => "<",
+            Condition::LowerThanOrEqual(_) => "<=",
+            Condition::Between { .. } => "TO",
+            Condition::Contains { .. } => "CONTAINS",
+            Condition::StartsWith { .. } => "STARTS WITH",
+        }
+    }
+}
+
 /// condition      = value ("==" | ">" ...) value
 pub fn parse_condition(input: Span) -> IResult<FilterCondition> {
     let operator = alt((tag("<="), tag(">="), tag("!="), tag("<"), tag(">"), tag("=")));

crates/fuzzers/src/bin/fuzz-indexing.rs

@@ -57,7 +57,8 @@ fn main() {
         let opt = opt.clone();
 
         let handle = std::thread::spawn(move || {
-            let mut options = EnvOpenOptions::new();
+            let options = EnvOpenOptions::new();
+            let mut options = options.read_txn_without_tls();
             options.map_size(1024 * 1024 * 1024 * 1024);
             let tempdir = match opt.path {
                 Some(path) => TempDir::new_in(path).unwrap(),

crates/index-scheduler/Cargo.toml

@@ -13,6 +13,7 @@ license.workspace = true
 [dependencies]
 anyhow = "1.0.95"
 bincode = "1.3.3"
+byte-unit = "5.1.6"
 bumpalo = "3.16.0"
 bumparaw-collections = "0.1.4"
 convert_case = "0.6.0"
@@ -22,6 +23,7 @@ dump = { path = "../dump" }
 enum-iterator = "2.1.0"
 file-store = { path = "../file-store" }
 flate2 = "1.0.35"
+indexmap = "2.7.0"
 meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
 memmap2 = "0.9.5"
@@ -29,7 +31,7 @@ page_size = "0.6.0"
 rayon = "1.10.0"
 roaring = { version = "0.10.10", features = ["serde"] }
 serde = { version = "1.0.217", features = ["derive"] }
-serde_json = { version = "1.0.135", features = ["preserve_order"] }
+serde_json = { version = "1.0.138", features = ["preserve_order"] }
 synchronoise = "1.0.1"
 tempfile = "3.15.0"
 thiserror = "2.0.9"
@@ -44,7 +46,6 @@ ureq = "2.12.1"
 uuid = { version = "1.11.0", features = ["serde", "v4"] }
 
 [dev-dependencies]
-arroy = "0.5.0"
 big_s = "1.0.2"
 crossbeam-channel = "0.5.14"
 # fixed version due to format breakages in v1.40

crates/index-scheduler/src/dump.rs

@@ -2,6 +2,7 @@ use std::collections::HashMap;
 use std::io;
 
 use dump::{KindDump, TaskDump, UpdateFile};
+use meilisearch_types::batches::{Batch, BatchId};
 use meilisearch_types::heed::RwTxn;
 use meilisearch_types::milli;
 use meilisearch_types::tasks::{Kind, KindWithContent, Status, Task};
@@ -14,9 +15,15 @@ pub struct Dump<'a> {
     index_scheduler: &'a IndexScheduler,
     wtxn: RwTxn<'a>,
 
+    batch_to_task_mapping: HashMap<BatchId, RoaringBitmap>,
+
     indexes: HashMap<String, RoaringBitmap>,
     statuses: HashMap<Status, RoaringBitmap>,
     kinds: HashMap<Kind, RoaringBitmap>,
+
+    batch_indexes: HashMap<String, RoaringBitmap>,
+    batch_statuses: HashMap<Status, RoaringBitmap>,
+    batch_kinds: HashMap<Kind, RoaringBitmap>,
 }
 
 impl<'a> Dump<'a> {
@@ -27,12 +34,72 @@ impl<'a> Dump<'a> {
         Ok(Dump {
             index_scheduler,
             wtxn,
+            batch_to_task_mapping: HashMap::new(),
             indexes: HashMap::new(),
             statuses: HashMap::new(),
             kinds: HashMap::new(),
+            batch_indexes: HashMap::new(),
+            batch_statuses: HashMap::new(),
+            batch_kinds: HashMap::new(),
         })
     }
 
+    /// Register a new batch coming from a dump in the scheduler.
+    /// By taking a mutable ref we're pretty sure no one will ever import a dump while actix is running.
+    pub fn register_dumped_batch(&mut self, batch: Batch) -> Result<()> {
+        self.index_scheduler.queue.batches.all_batches.put(&mut self.wtxn, &batch.uid, &batch)?;
+        if let Some(enqueued_at) = batch.enqueued_at {
+            utils::insert_task_datetime(
+                &mut self.wtxn,
+                self.index_scheduler.queue.batches.enqueued_at,
+                enqueued_at.earliest,
+                batch.uid,
+            )?;
+            utils::insert_task_datetime(
+                &mut self.wtxn,
+                self.index_scheduler.queue.batches.enqueued_at,
+                enqueued_at.oldest,
+                batch.uid,
+            )?;
+        }
+        utils::insert_task_datetime(
+            &mut self.wtxn,
+            self.index_scheduler.queue.batches.started_at,
+            batch.started_at,
+            batch.uid,
+        )?;
+        if let Some(finished_at) = batch.finished_at {
+            utils::insert_task_datetime(
+                &mut self.wtxn,
+                self.index_scheduler.queue.batches.finished_at,
+                finished_at,
+                batch.uid,
+            )?;
+        }
+
+        for index in batch.stats.index_uids.keys() {
+            match self.batch_indexes.get_mut(index) {
+                Some(bitmap) => {
+                    bitmap.insert(batch.uid);
+                }
+                None => {
+                    let mut bitmap = RoaringBitmap::new();
+                    bitmap.insert(batch.uid);
+                    self.batch_indexes.insert(index.to_string(), bitmap);
+                }
+            };
+        }
+
+        for status in batch.stats.status.keys() {
+            self.batch_statuses.entry(*status).or_default().insert(batch.uid);
+        }
+        for kind in batch.stats.types.keys() {
+            self.batch_kinds.entry(*kind).or_default().insert(batch.uid);
+        }
+
+        Ok(())
+    }
+
     /// Register a new task coming from a dump in the scheduler.
     /// By taking a mutable ref we're pretty sure no one will ever import a dump while actix is running.
     pub fn register_dumped_task(
@@ -149,6 +216,9 @@ impl<'a> Dump<'a> {
         };
 
         self.index_scheduler.queue.tasks.all_tasks.put(&mut self.wtxn, &task.uid, &task)?;
+        if let Some(batch_id) = task.batch_uid {
+            self.batch_to_task_mapping.entry(batch_id).or_default().insert(task.uid);
+        }
 
         for index in task.indexes() {
             match self.indexes.get_mut(index) {
@@ -198,6 +268,14 @@ impl<'a> Dump<'a> {
 
     /// Commit all the changes and exit the importing dump state
     pub fn finish(mut self) -> Result<()> {
+        for (batch_id, task_ids) in self.batch_to_task_mapping {
+            self.index_scheduler.queue.batch_to_tasks_mapping.put(
+                &mut self.wtxn,
+                &batch_id,
+                &task_ids,
+            )?;
+        }
+
         for (index, bitmap) in self.indexes {
             self.index_scheduler.queue.tasks.index_tasks.put(&mut self.wtxn, &index, &bitmap)?;
         }
@@ -208,6 +286,16 @@ impl<'a> Dump<'a> {
             self.index_scheduler.queue.tasks.put_kind(&mut self.wtxn, kind, &bitmap)?;
         }
 
+        for (index, bitmap) in self.batch_indexes {
+            self.index_scheduler.queue.batches.index_tasks.put(&mut self.wtxn, &index, &bitmap)?;
+        }
+        for (status, bitmap) in self.batch_statuses {
+            self.index_scheduler.queue.batches.put_status(&mut self.wtxn, status, &bitmap)?;
+        }
+        for (kind, bitmap) in self.batch_kinds {
+            self.index_scheduler.queue.batches.put_kind(&mut self.wtxn, kind, &bitmap)?;
+        }
+
         self.wtxn.commit()?;
         self.index_scheduler.scheduler.wake_up.signal();
 

crates/index-scheduler/src/error.rs

@@ -109,6 +109,8 @@ pub enum Error {
     InvalidIndexUid { index_uid: String },
     #[error("Task `{0}` not found.")]
     TaskNotFound(TaskId),
+    #[error("Task `{0}` does not contain any documents. Only `documentAdditionOrUpdate` tasks with the statuses `enqueued` or `processing` contain documents")]
+    TaskFileNotFound(TaskId),
     #[error("Batch `{0}` not found.")]
     BatchNotFound(BatchId),
     #[error("Query parameters to filter the tasks to delete are missing. Available query parameters are: `uids`, `indexUids`, `statuses`, `types`, `canceledBy`, `beforeEnqueuedAt`, `afterEnqueuedAt`, `beforeStartedAt`, `afterStartedAt`, `beforeFinishedAt`, `afterFinishedAt`.")]
@@ -127,8 +129,8 @@ pub enum Error {
         _ => format!("{error}")
     })]
     Milli { error: milli::Error, index_uid: Option<String> },
-    #[error("An unexpected crash occurred when processing the task.")]
+    #[error("An unexpected crash occurred when processing the task: {0}")]
-    ProcessBatchPanicked,
+    ProcessBatchPanicked(String),
     #[error(transparent)]
     FileStore(#[from] file_store::Error),
     #[error(transparent)]
@@ -189,6 +191,7 @@ impl Error {
             | Error::InvalidTaskCanceledBy { .. }
             | Error::InvalidIndexUid { .. }
             | Error::TaskNotFound(_)
+            | Error::TaskFileNotFound(_)
             | Error::BatchNotFound(_)
             | Error::TaskDeletionWithEmptyQuery
             | Error::TaskCancelationWithEmptyQuery
@@ -196,7 +199,7 @@ impl Error {
             | Error::Dump(_)
             | Error::Heed(_)
             | Error::Milli { .. }
-            | Error::ProcessBatchPanicked
+            | Error::ProcessBatchPanicked(_)
             | Error::FileStore(_)
             | Error::IoError(_)
             | Error::Persist(_)
@@ -250,6 +253,7 @@ impl ErrorCode for Error {
             Error::InvalidTaskCanceledBy { .. } => Code::InvalidTaskCanceledBy,
             Error::InvalidIndexUid { .. } => Code::InvalidIndexUid,
             Error::TaskNotFound(_) => Code::TaskNotFound,
+            Error::TaskFileNotFound(_) => Code::TaskFileNotFound,
             Error::BatchNotFound(_) => Code::BatchNotFound,
             Error::TaskDeletionWithEmptyQuery => Code::MissingTaskFilters,
             Error::TaskCancelationWithEmptyQuery => Code::MissingTaskFilters,
@@ -257,7 +261,7 @@ impl ErrorCode for Error {
             Error::NoSpaceLeftInTaskQueue => Code::NoSpaceLeftOnDevice,
             Error::Dump(e) => e.error_code(),
             Error::Milli { error, .. } => error.error_code(),
-            Error::ProcessBatchPanicked => Code::Internal,
+            Error::ProcessBatchPanicked(_) => Code::Internal,
             Error::Heed(e) => e.error_code(),
             Error::HeedTransaction(e) => e.error_code(),
             Error::FileStore(e) => e.error_code(),

crates/index-scheduler/src/features.rs

@@ -1,8 +1,8 @@
 use std::sync::{Arc, RwLock};
 
-use meilisearch_types::features::{InstanceTogglableFeatures, RuntimeTogglableFeatures};
+use meilisearch_types::features::{InstanceTogglableFeatures, Network, RuntimeTogglableFeatures};
 use meilisearch_types::heed::types::{SerdeJson, Str};
-use meilisearch_types::heed::{Database, Env, RwTxn};
+use meilisearch_types::heed::{Database, Env, RwTxn, WithoutTls};
 
 use crate::error::FeatureNotEnabledError;
 use crate::Result;
@@ -14,10 +14,16 @@ mod db_name {
     pub const EXPERIMENTAL_FEATURES: &str = "experimental-features";
 }
 
+mod db_keys {
+    pub const EXPERIMENTAL_FEATURES: &str = "experimental-features";
+    pub const NETWORK: &str = "network";
+}
+
 #[derive(Clone)]
 pub(crate) struct FeatureData {
     persisted: Database<Str, SerdeJson<RuntimeTogglableFeatures>>,
     runtime: Arc<RwLock<RuntimeTogglableFeatures>>,
+    network: Arc<RwLock<Network>>,
 }
 
 #[derive(Debug, Clone, Copy)]
@@ -86,6 +92,45 @@ impl RoFeatures {
             .into())
         }
     }
+
+    pub fn check_network(&self, disabled_action: &'static str) -> Result<()> {
+        if self.runtime.network {
+            Ok(())
+        } else {
+            Err(FeatureNotEnabledError {
+                disabled_action,
+                feature: "network",
+                issue_link: "https://github.com/orgs/meilisearch/discussions/805",
+            }
+            .into())
+        }
+    }
+
+    pub fn check_get_task_documents_route(&self) -> Result<()> {
+        if self.runtime.get_task_documents_route {
+            Ok(())
+        } else {
+            Err(FeatureNotEnabledError {
+                disabled_action: "Getting the documents of an enqueued task",
+                feature: "get task documents route",
+                issue_link: "https://github.com/orgs/meilisearch/discussions/808",
+            }
+            .into())
+        }
+    }
+
+    pub fn check_composite_embedders(&self, disabled_action: &'static str) -> Result<()> {
+        if self.runtime.composite_embedders {
+            Ok(())
+        } else {
+            Err(FeatureNotEnabledError {
+                disabled_action,
+                feature: "composite embedders",
+                issue_link: "https://github.com/orgs/meilisearch/discussions/816",
+            }
+            .into())
+        }
+    }
 }
 
 impl FeatureData {
@@ -94,7 +139,7 @@ impl FeatureData {
     }
 
     pub fn new(
-        env: &Env,
+        env: &Env<WithoutTls>,
         wtxn: &mut RwTxn,
         instance_features: InstanceTogglableFeatures,
     ) -> Result<Self> {
@@ -102,7 +147,7 @@ impl FeatureData {
             env.create_database(wtxn, Some(db_name::EXPERIMENTAL_FEATURES))?;
 
         let persisted_features: RuntimeTogglableFeatures =
-            runtime_features_db.get(wtxn, db_name::EXPERIMENTAL_FEATURES)?.unwrap_or_default();
+            runtime_features_db.get(wtxn, db_keys::EXPERIMENTAL_FEATURES)?.unwrap_or_default();
         let InstanceTogglableFeatures { metrics, logs_route, contains_filter } = instance_features;
         let runtime = Arc::new(RwLock::new(RuntimeTogglableFeatures {
             metrics: metrics || persisted_features.metrics,
@@ -111,7 +156,14 @@ impl FeatureData {
             ..persisted_features
         }));
 
-        Ok(Self { persisted: runtime_features_db, runtime })
+        let network_db = runtime_features_db.remap_data_type::<SerdeJson<Network>>();
+        let network: Network = network_db.get(wtxn, db_keys::NETWORK)?.unwrap_or_default();
+
+        Ok(Self {
+            persisted: runtime_features_db,
+            runtime,
+            network: Arc::new(RwLock::new(network)),
+        })
     }
 
     pub fn put_runtime_features(
@@ -119,7 +171,7 @@ impl FeatureData {
         mut wtxn: RwTxn,
         features: RuntimeTogglableFeatures,
     ) -> Result<()> {
-        self.persisted.put(&mut wtxn, db_name::EXPERIMENTAL_FEATURES, &features)?;
+        self.persisted.put(&mut wtxn, db_keys::EXPERIMENTAL_FEATURES, &features)?;
         wtxn.commit()?;
 
         // safe to unwrap, the lock will only fail if:
@@ -140,4 +192,21 @@ impl FeatureData {
     pub fn features(&self) -> RoFeatures {
         RoFeatures::new(self)
     }
+
+    pub fn put_network(&self, mut wtxn: RwTxn, new_network: Network) -> Result<()> {
+        self.persisted.remap_data_type::<SerdeJson<Network>>().put(
+            &mut wtxn,
+            db_keys::NETWORK,
+            &new_network,
+        )?;
+        wtxn.commit()?;
+
+        let mut network = self.network.write().unwrap();
+        *network = new_network;
+        Ok(())
+    }
+
+    pub fn network(&self) -> Network {
+        Network::clone(&*self.network.read().unwrap())
+    }
 }

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

@@ -1,5 +1,7 @@
 use std::collections::BTreeMap;
+use std::env::VarError;
 use std::path::Path;
+use std::str::FromStr;
 use std::time::Duration;
 
 use meilisearch_types::heed::{EnvClosingEvent, EnvFlags, EnvOpenOptions};
@@ -302,9 +304,21 @@ fn create_or_open_index(
     map_size: usize,
     creation: bool,
 ) -> Result<Index> {
-    let mut options = EnvOpenOptions::new();
+    let options = EnvOpenOptions::new();
+    let mut options = options.read_txn_without_tls();
     options.map_size(clamp_to_page_size(map_size));
-    options.max_readers(1024);
+
+    // You can find more details about this experimental
+    // environment variable on the following GitHub discussion:
+    // <https://github.com/orgs/meilisearch/discussions/806>
+    let max_readers = match std::env::var("MEILI_EXPERIMENTAL_INDEX_MAX_READERS") {
+        Ok(value) => u32::from_str(&value).unwrap(),
+        Err(VarError::NotPresent) => 1024,
+        Err(VarError::NotUnicode(value)) => panic!(
+            "Invalid unicode for the `MEILI_EXPERIMENTAL_INDEX_MAX_READERS` env var: {value:?}"
+        ),
+    };
+    options.max_readers(max_readers);
     if enable_mdb_writemap {
         unsafe { options.flags(EnvFlags::WRITE_MAP) };
     }
@@ -320,7 +334,7 @@ fn create_or_open_index(
 #[cfg(test)]
 mod tests {
 
-    use meilisearch_types::heed::Env;
+    use meilisearch_types::heed::{Env, WithoutTls};
     use meilisearch_types::Index;
     use uuid::Uuid;
 
@@ -330,7 +344,7 @@ mod tests {
     use crate::IndexScheduler;
 
     impl IndexMapper {
-        fn test() -> (Self, Env, IndexSchedulerHandle) {
+        fn test() -> (Self, Env<WithoutTls>, IndexSchedulerHandle) {
             let (index_scheduler, handle) = IndexScheduler::test(true, vec![]);
             (index_scheduler.index_mapper, index_scheduler.env, handle)
         }

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

@@ -4,8 +4,9 @@ use std::time::Duration;
 use std::{fs, thread};
 
 use meilisearch_types::heed::types::{SerdeJson, Str};
-use meilisearch_types::heed::{Database, Env, RoTxn, RwTxn};
+use meilisearch_types::heed::{Database, Env, RoTxn, RwTxn, WithoutTls};
 use meilisearch_types::milli;
+use meilisearch_types::milli::database_stats::DatabaseStats;
 use meilisearch_types::milli::update::IndexerConfig;
 use meilisearch_types::milli::{FieldDistribution, Index};
 use serde::{Deserialize, Serialize};
@@ -98,14 +99,25 @@ pub enum IndexStatus {
 /// The statistics that can be computed from an `Index` object.
 #[derive(Serialize, Deserialize, Debug)]
 pub struct IndexStats {
-    /// Number of documents in the index.
+    /// Stats of the documents database.
-    pub number_of_documents: u64,
+    #[serde(default)]
+    pub documents_database_stats: DatabaseStats,
+
+    #[serde(default, skip_serializing)]
+    pub number_of_documents: Option<u64>,
+
     /// Size taken up by the index' DB, in bytes.
     ///
     /// This includes the size taken by both the used and free pages of the DB, and as the free pages
     /// are not returned to the disk after a deletion, this number is typically larger than
     /// `used_database_size` that only includes the size of the used pages.
     pub database_size: u64,
+    /// Number of embeddings in the index.
+    /// Option: retrocompatible with the stats of the pre-v1.13.0 versions of meilisearch
+    pub number_of_embeddings: Option<u64>,
+    /// Number of embedded documents in the index.
+    /// Option: retrocompatible with the stats of the pre-v1.13.0 versions of meilisearch
+    pub number_of_embedded_documents: Option<u64>,
     /// Size taken by the used pages of the index' DB, in bytes.
     ///
     /// As the DB backend does not return to the disk the pages that are not currently used by the DB,
@@ -130,8 +142,12 @@ impl IndexStats {
     ///
     /// - rtxn: a RO transaction for the index, obtained from `Index::read_txn()`.
     pub fn new(index: &Index, rtxn: &RoTxn) -> milli::Result<Self> {
+        let arroy_stats = index.arroy_stats(rtxn)?;
         Ok(IndexStats {
-            number_of_documents: index.number_of_documents(rtxn)?,
+            number_of_embeddings: Some(arroy_stats.number_of_embeddings),
+            number_of_embedded_documents: Some(arroy_stats.documents.len()),
+            documents_database_stats: index.documents_stats(rtxn)?.unwrap_or_default(),
+            number_of_documents: None,
             database_size: index.on_disk_size()?,
             used_database_size: index.used_size()?,
             primary_key: index.primary_key(rtxn)?.map(|s| s.to_string()),
@@ -148,7 +164,7 @@ impl IndexMapper {
     }
 
     pub fn new(
-        env: &Env,
+        env: &Env<WithoutTls>,
         wtxn: &mut RwTxn,
         options: &IndexSchedulerOptions,
         budget: IndexBudget,

crates/index-scheduler/src/insta_snapshot.rs

@@ -1,7 +1,7 @@
 use std::collections::BTreeSet;
 use std::fmt::Write;
 
-use meilisearch_types::batches::Batch;
+use meilisearch_types::batches::{Batch, BatchEnqueuedAt, BatchStats};
 use meilisearch_types::heed::types::{SerdeBincode, SerdeJson, Str};
 use meilisearch_types::heed::{Database, RoTxn};
 use meilisearch_types::milli::{CboRoaringBitmapCodec, RoaringBitmapCodec, BEU32};
@@ -341,14 +341,24 @@ pub fn snapshot_canceled_by(rtxn: &RoTxn, db: Database<BEU32, RoaringBitmapCodec
 
 pub fn snapshot_batch(batch: &Batch) -> String {
     let mut snap = String::new();
-    let Batch { uid, details, stats, started_at, finished_at, progress: _ } = batch;
+    let Batch { uid, details, stats, started_at, finished_at, progress: _, enqueued_at } = batch;
+    let stats = BatchStats {
+        progress_trace: Default::default(),
+        internal_database_sizes: Default::default(),
+        write_channel_congestion: None,
+        ..stats.clone()
+    };
     if let Some(finished_at) = finished_at {
         assert!(finished_at > started_at);
     }
+    let BatchEnqueuedAt { earliest, oldest } = enqueued_at.unwrap();
+    assert!(*started_at > earliest);
+    assert!(earliest >= oldest);
+
     snap.push('{');
     snap.push_str(&format!("uid: {uid}, "));
     snap.push_str(&format!("details: {}, ", serde_json::to_string(details).unwrap()));
-    snap.push_str(&format!("stats: {}, ", serde_json::to_string(stats).unwrap()));
+    snap.push_str(&format!("stats: {}, ", serde_json::to_string(&stats).unwrap()));
     snap.push('}');
     snap
 }
@@ -361,7 +371,8 @@ pub fn snapshot_index_mapper(rtxn: &RoTxn, mapper: &IndexMapper) -> String {
         let stats = mapper.stats_of(rtxn, &name).unwrap();
         s.push_str(&format!(
             "{name}: {{ number_of_documents: {}, field_distribution: {:?} }}\n",
-            stats.number_of_documents, stats.field_distribution
+            stats.documents_database_stats.number_of_entries(),
+            stats.field_distribution
         ));
     }
 

crates/index-scheduler/src/lib.rs

@@ -33,7 +33,7 @@ mod test_utils;
 pub mod upgrade;
 mod utils;
 pub mod uuid_codec;
-mod versioning;
+pub mod versioning;
 
 pub type Result<T, E = Error> = std::result::Result<T, E>;
 pub type TaskId = u32;
@@ -51,10 +51,10 @@ pub use features::RoFeatures;
 use flate2::bufread::GzEncoder;
 use flate2::Compression;
 use meilisearch_types::batches::Batch;
-use meilisearch_types::features::{InstanceTogglableFeatures, RuntimeTogglableFeatures};
+use meilisearch_types::features::{InstanceTogglableFeatures, Network, RuntimeTogglableFeatures};
 use meilisearch_types::heed::byteorder::BE;
 use meilisearch_types::heed::types::I128;
-use meilisearch_types::heed::{self, Env, RoTxn};
+use meilisearch_types::heed::{self, Env, RoTxn, WithoutTls};
 use meilisearch_types::milli::index::IndexEmbeddingConfig;
 use meilisearch_types::milli::update::IndexerConfig;
 use meilisearch_types::milli::vector::{Embedder, EmbedderOptions, EmbeddingConfigs};
@@ -125,13 +125,17 @@ pub struct IndexSchedulerOptions {
     pub instance_features: InstanceTogglableFeatures,
     /// The experimental features enabled for this instance.
     pub auto_upgrade: bool,
+    /// The maximal number of entries in the search query cache of an embedder.
+    ///
+    /// 0 disables the cache.
+    pub embedding_cache_cap: usize,
 }
 
 /// Structure which holds meilisearch's indexes and schedules the tasks
 /// to be performed on them.
 pub struct IndexScheduler {
     /// The LMDB environment which the DBs are associated with.
-    pub(crate) env: Env,
+    pub(crate) env: Env<WithoutTls>,
 
     /// The list of tasks currently processing
     pub(crate) processing_tasks: Arc<RwLock<ProcessingTasks>>,
@@ -156,6 +160,11 @@ pub struct IndexScheduler {
     /// The Authorization header to send to the webhook URL.
     pub(crate) webhook_authorization_header: Option<String>,
 
+    /// A map to retrieve the runtime representation of an embedder depending on its configuration.
+    ///
+    /// This map may return the same embedder object for two different indexes or embedder settings,
+    /// but it will only do this if the embedder configuration options are the same, leading
+    /// to the same embeddings for the same input text.
     embedders: Arc<RwLock<HashMap<EmbedderOptions, Arc<Embedder>>>>,
 
     // ================= test
@@ -209,6 +218,7 @@ impl IndexScheduler {
     #[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)>,
@@ -240,7 +250,9 @@ impl IndexScheduler {
         };
 
         let env = unsafe {
-            heed::EnvOpenOptions::new()
+            let env_options = heed::EnvOpenOptions::new();
+            let mut env_options = env_options.read_txn_without_tls();
+            env_options
                 .max_dbs(Self::nb_db())
                 .map_size(budget.task_db_size)
                 .open(&options.tasks_path)
@@ -260,7 +272,7 @@ impl IndexScheduler {
             processing_tasks: Arc::new(RwLock::new(ProcessingTasks::new())),
             version,
             queue,
-            scheduler: Scheduler::new(&options),
+            scheduler: Scheduler::new(&options, auth_env),
 
             index_mapper,
             env,
@@ -358,7 +370,7 @@ impl IndexScheduler {
         }
     }
 
-    pub fn read_txn(&self) -> Result<RoTxn> {
+    pub fn read_txn(&self) -> Result<RoTxn<WithoutTls>> {
         self.env.read_txn().map_err(|e| e.into())
     }
 
@@ -427,12 +439,14 @@ impl IndexScheduler {
     /// If you need to fetch information from or perform an action on all indexes,
     /// see the `try_for_each_index` function.
     pub fn index(&self, name: &str) -> Result<Index> {
-        self.index_mapper.index(&self.env.read_txn()?, name)
+        let rtxn = self.env.read_txn()?;
+        self.index_mapper.index(&rtxn, name)
     }
 
     /// Return the boolean referring if index exists.
     pub fn index_exists(&self, name: &str) -> Result<bool> {
-        self.index_mapper.index_exists(&self.env.read_txn()?, name)
+        let rtxn = self.env.read_txn()?;
+        self.index_mapper.index_exists(&rtxn, name)
     }
 
     /// Return the name of all indexes without opening them.
@@ -507,7 +521,8 @@ impl IndexScheduler {
     /// 2. The name of the specific data related to the property can be `enqueued` for the `statuses`, `settingsUpdate` for the `types`, or the name of the index for the `indexes`, for example.
     /// 3. The number of times the properties appeared.
     pub fn get_stats(&self) -> Result<BTreeMap<String, BTreeMap<String, u64>>> {
-        self.queue.get_stats(&self.read_txn()?, &self.processing_tasks.read().unwrap())
+        let rtxn = self.read_txn()?;
+        self.queue.get_stats(&rtxn, &self.processing_tasks.read().unwrap())
     }
 
     // Return true if there is at least one task that is processing.
@@ -770,7 +785,16 @@ impl IndexScheduler {
         Ok(())
     }
 
-    // TODO: consider using a type alias or a struct embedder/template
+    pub fn put_network(&self, network: Network) -> Result<()> {
+        let wtxn = self.env.write_txn().map_err(Error::HeedTransaction)?;
+        self.features.put_network(wtxn, network)?;
+        Ok(())
+    }
+
+    pub fn network(&self) -> Network {
+        self.features.network()
+    }
+
     pub fn embedders(
         &self,
         index_uid: String,
@@ -803,7 +827,7 @@ impl IndexScheduler {
 
                     // add missing embedder
                     let embedder = Arc::new(
-                        Embedder::new(embedder_options.clone())
+                        Embedder::new(embedder_options.clone(), self.scheduler.embedding_cache_cap)
                             .map_err(meilisearch_types::milli::vector::Error::from)
                             .map_err(|err| {
                                 Error::from_milli(err.into(), Some(index_uid.clone()))

crates/index-scheduler/src/processing.rs

@@ -64,6 +64,13 @@ make_enum_progress! {
     }
 }
 
+make_enum_progress! {
+    pub enum FinalizingIndexStep {
+        Committing,
+        ComputingStats,
+    }
+}
+
 make_enum_progress! {
     pub enum TaskCancelationProgress {
         RetrievingTasks,
@@ -96,6 +103,7 @@ make_enum_progress! {
         StartTheDumpCreation,
         DumpTheApiKeys,
         DumpTheTasks,
+        DumpTheBatches,
         DumpTheIndexes,
         DumpTheExperimentalFeatures,
         CompressTheDump,

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

@@ -3,7 +3,7 @@ use std::ops::{Bound, RangeBounds};
 
 use meilisearch_types::batches::{Batch, BatchId};
 use meilisearch_types::heed::types::{DecodeIgnore, SerdeBincode, SerdeJson, Str};
-use meilisearch_types::heed::{Database, Env, RoTxn, RwTxn};
+use meilisearch_types::heed::{Database, Env, RoTxn, RwTxn, WithoutTls};
 use meilisearch_types::milli::{CboRoaringBitmapCodec, RoaringBitmapCodec, BEU32};
 use meilisearch_types::tasks::{Kind, Status};
 use roaring::{MultiOps, RoaringBitmap};
@@ -12,8 +12,8 @@ use time::OffsetDateTime;
 use super::{Query, Queue};
 use crate::processing::ProcessingTasks;
 use crate::utils::{
-    insert_task_datetime, keep_ids_within_datetimes, map_bound, remove_task_datetime,
+    insert_task_datetime, keep_ids_within_datetimes, map_bound,
-    ProcessingBatch,
+    remove_n_tasks_datetime_earlier_than, remove_task_datetime, ProcessingBatch,
 };
 use crate::{Error, Result, BEI128};
 
@@ -66,7 +66,7 @@ impl BatchQueue {
         NUMBER_OF_DATABASES
     }
 
-    pub(super) fn new(env: &Env, wtxn: &mut RwTxn) -> Result<Self> {
+    pub(super) fn new(env: &Env<WithoutTls>, wtxn: &mut RwTxn) -> Result<Self> {
         Ok(Self {
             all_batches: env.create_database(wtxn, Some(db_name::ALL_BATCHES))?,
             status: env.create_database(wtxn, Some(db_name::BATCH_STATUS))?,
@@ -181,6 +181,7 @@ impl BatchQueue {
                 stats: batch.stats,
                 started_at: batch.started_at,
                 finished_at: batch.finished_at,
+                enqueued_at: batch.enqueued_at,
             },
         )?;
 
@@ -234,34 +235,25 @@ impl BatchQueue {
         // What we know, though, is that the task date is from before the enqueued_at, and max two timestamps have been written
         // to the DB per batches.
         if let Some(ref old_batch) = old_batch {
-            let started_at = old_batch.started_at.unix_timestamp_nanos();
+            if let Some(enqueued_at) = old_batch.enqueued_at {
-
+                remove_task_datetime(wtxn, self.enqueued_at, enqueued_at.earliest, old_batch.uid)?;
-            // We have either one or two enqueued at to remove
+                remove_task_datetime(wtxn, self.enqueued_at, enqueued_at.oldest, old_batch.uid)?;
-            let mut exit = old_batch.stats.total_nb_tasks.clamp(0, 2);
+            } else {
-            let mut iterator = self.enqueued_at.rev_iter_mut(wtxn)?;
+                // If we don't have the enqueued at in the batch it means the database comes from the v1.12
-            while let Some(entry) = iterator.next() {
+                // and we still need to find the date by scrolling the database
-                let (key, mut value) = entry?;
+                remove_n_tasks_datetime_earlier_than(
-                if key > started_at {
+                    wtxn,
-                    continue;
+                    self.enqueued_at,
-                }
+                    old_batch.started_at,
-                if value.remove(old_batch.uid) {
+                    old_batch.stats.total_nb_tasks.clamp(1, 2) as usize,
-                    exit = exit.saturating_sub(1);
+                    old_batch.uid,
-                    // Safe because the key and value are owned
+                )?;
-                    unsafe {
-                        iterator.put_current(&key, &value)?;
-                    }
-                    if exit == 0 {
-                        break;
-                    }
-                }
             }
         }
-        if let Some(enqueued_at) = batch.oldest_enqueued_at {
+        // A finished batch MUST contains at least one task and have an enqueued_at
-            insert_task_datetime(wtxn, self.enqueued_at, enqueued_at, batch.uid)?;
+        let enqueued_at = batch.enqueued_at.as_ref().unwrap();
-        }
+        insert_task_datetime(wtxn, self.enqueued_at, enqueued_at.earliest, batch.uid)?;
-        if let Some(enqueued_at) = batch.earliest_enqueued_at {
+        insert_task_datetime(wtxn, self.enqueued_at, enqueued_at.oldest, batch.uid)?;
-            insert_task_datetime(wtxn, self.enqueued_at, enqueued_at, batch.uid)?;
-        }
 
         // Update the started at and finished at
         if let Some(ref old_batch) = old_batch {

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

@@ -102,30 +102,33 @@ fn query_batches_simple() {
         .unwrap();
     assert_eq!(batches.len(), 1);
     batches[0].started_at = OffsetDateTime::UNIX_EPOCH;
+    assert!(batches[0].enqueued_at.is_some());
+    batches[0].enqueued_at = None;
     // Insta cannot snapshot our batches because the batch stats contains an enum as key: https://github.com/mitsuhiko/insta/issues/689
     let batch = serde_json::to_string_pretty(&batches[0]).unwrap();
     snapshot!(batch, @r#"
-        {
+    {
-          "uid": 0,
+      "uid": 0,
-          "details": {
+      "details": {
-            "primaryKey": "mouse"
+        "primaryKey": "mouse"
-          },
+      },
-          "stats": {
+      "stats": {
-            "totalNbTasks": 1,
+        "totalNbTasks": 1,
-            "status": {
+        "status": {
-              "processing": 1
+          "processing": 1
-            },
+        },
-            "types": {
+        "types": {
-              "indexCreation": 1
+          "indexCreation": 1
-            },
+        },
-            "indexUids": {
+        "indexUids": {
-              "catto": 1
+          "catto": 1
-            }
-          },
-          "startedAt": "1970-01-01T00:00:00Z",
-          "finishedAt": null
         }
-        "#);
+      },
+      "startedAt": "1970-01-01T00:00:00Z",
+      "finishedAt": null,
+      "enqueuedAt": null
+    }
+    "#);
 
     let query = Query { statuses: Some(vec![Status::Enqueued]), ..Default::default() };
     let (batches, _) = index_scheduler

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

@@ -8,11 +8,12 @@ mod tasks_test;
 mod test;
 
 use std::collections::BTreeMap;
+use std::fs::File as StdFile;
 use std::time::Duration;
 
 use file_store::FileStore;
 use meilisearch_types::batches::BatchId;
-use meilisearch_types::heed::{Database, Env, RoTxn, RwTxn};
+use meilisearch_types::heed::{Database, Env, RoTxn, RwTxn, WithoutTls};
 use meilisearch_types::milli::{CboRoaringBitmapCodec, BEU32};
 use meilisearch_types::tasks::{Kind, KindWithContent, Status, Task};
 use roaring::RoaringBitmap;
@@ -156,7 +157,7 @@ impl Queue {
 
     /// Create an index scheduler and start its run loop.
     pub(crate) fn new(
-        env: &Env,
+        env: &Env<WithoutTls>,
         wtxn: &mut RwTxn,
         options: &IndexSchedulerOptions,
     ) -> Result<Self> {
@@ -216,6 +217,11 @@ impl Queue {
         }
     }
 
+    /// Open and returns the task's content File.
+    pub fn update_file(&self, uuid: Uuid) -> file_store::Result<StdFile> {
+        self.file_store.get_update(uuid)
+    }
+
     /// Delete a file from the index scheduler.
     ///
     /// Counterpart to the [`create_update_file`](IndexScheduler::create_update_file) method.

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

@@ -1,7 +1,7 @@
 use std::ops::{Bound, RangeBounds};
 
 use meilisearch_types::heed::types::{DecodeIgnore, SerdeBincode, SerdeJson, Str};
-use meilisearch_types::heed::{Database, Env, RoTxn, RwTxn};
+use meilisearch_types::heed::{Database, Env, RoTxn, RwTxn, WithoutTls};
 use meilisearch_types::milli::{CboRoaringBitmapCodec, RoaringBitmapCodec, BEU32};
 use meilisearch_types::tasks::{Kind, Status, Task};
 use roaring::{MultiOps, RoaringBitmap};
@@ -68,7 +68,7 @@ impl TaskQueue {
         NUMBER_OF_DATABASES
     }
 
-    pub(crate) fn new(env: &Env, wtxn: &mut RwTxn) -> Result<Self> {
+    pub(crate) fn new(env: &Env<WithoutTls>, wtxn: &mut RwTxn) -> Result<Self> {
         Ok(Self {
             all_tasks: env.create_database(wtxn, Some(db_name::ALL_TASKS))?,
             status: env.create_database(wtxn, Some(db_name::STATUS))?,

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

@@ -326,7 +326,7 @@ fn test_auto_deletion_of_tasks() {
 fn test_task_queue_is_full() {
     let (index_scheduler, mut handle) = IndexScheduler::test_with_custom_config(vec![], |config| {
         // that's the minimum map size possible
-        config.task_db_size = 1048576;
+        config.task_db_size = 1048576 * 3;
         None
     });
 

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

@@ -20,9 +20,12 @@ use std::path::PathBuf;
 use std::sync::atomic::{AtomicBool, AtomicU32, Ordering};
 use std::sync::Arc;
 
+use convert_case::{Case, Casing as _};
 use meilisearch_types::error::ResponseError;
+use meilisearch_types::heed::{Env, WithoutTls};
 use meilisearch_types::milli;
 use meilisearch_types::tasks::Status;
+use process_batch::ProcessBatchInfo;
 use rayon::current_num_threads;
 use rayon::iter::{IntoParallelIterator, ParallelIterator};
 use roaring::RoaringBitmap;
@@ -71,10 +74,15 @@ pub struct Scheduler {
     pub(crate) snapshots_path: PathBuf,
 
     /// The path to the folder containing the auth LMDB env.
-    pub(crate) auth_path: PathBuf,
+    pub(crate) auth_env: Env<WithoutTls>,
 
     /// The path to the version file of Meilisearch.
     pub(crate) version_file_path: PathBuf,
+
+    /// The maximal number of entries in the search query cache of an embedder.
+    ///
+    /// 0 disables the cache.
+    pub(crate) embedding_cache_cap: usize,
 }
 
 impl Scheduler {
@@ -87,12 +95,13 @@ impl Scheduler {
             batched_tasks_size_limit: self.batched_tasks_size_limit,
             dumps_path: self.dumps_path.clone(),
             snapshots_path: self.snapshots_path.clone(),
-            auth_path: self.auth_path.clone(),
+            auth_env: self.auth_env.clone(),
             version_file_path: self.version_file_path.clone(),
+            embedding_cache_cap: self.embedding_cache_cap,
         }
     }
 
-    pub fn new(options: &IndexSchedulerOptions) -> Scheduler {
+    pub fn new(options: &IndexSchedulerOptions, auth_env: Env<WithoutTls>) -> Scheduler {
         Scheduler {
             must_stop_processing: MustStopProcessing::default(),
             // we want to start the loop right away in case meilisearch was ctrl+Ced while processing things
@@ -102,8 +111,9 @@ impl Scheduler {
             batched_tasks_size_limit: options.batched_tasks_size_limit,
             dumps_path: options.dumps_path.clone(),
             snapshots_path: options.snapshots_path.clone(),
-            auth_path: options.auth_path.clone(),
+            auth_env,
             version_file_path: options.version_file_path.clone(),
+            embedding_cache_cap: options.embedding_cache_cap,
         }
     }
 }
@@ -166,13 +176,41 @@ impl IndexScheduler {
             let processing_batch = &mut processing_batch;
             let progress = progress.clone();
             std::thread::scope(|s| {
+                let p = progress.clone();
                 let handle = std::thread::Builder::new()
                     .name(String::from("batch-operation"))
                     .spawn_scoped(s, move || {
-                        cloned_index_scheduler.process_batch(batch, processing_batch, progress)
+                        cloned_index_scheduler.process_batch(batch, processing_batch, p)
                     })
                     .unwrap();
-                handle.join().unwrap_or(Err(Error::ProcessBatchPanicked))
+
+                match handle.join() {
+                    Ok(ret) => {
+                        if ret.is_err() {
+                            if let Ok(progress_view) =
+                                serde_json::to_string(&progress.as_progress_view())
+                            {
+                                tracing::warn!("Batch failed while doing: {progress_view}")
+                            }
+                        }
+                        ret
+                    }
+                    Err(panic) => {
+                        if let Ok(progress_view) =
+                            serde_json::to_string(&progress.as_progress_view())
+                        {
+                            tracing::warn!("Batch failed while doing: {progress_view}")
+                        }
+                        let msg = match panic.downcast_ref::<&'static str>() {
+                            Some(s) => *s,
+                            None => match panic.downcast_ref::<String>() {
+                                Some(s) => &s[..],
+                                None => "Box<dyn Any>",
+                            },
+                        };
+                        Err(Error::ProcessBatchPanicked(msg.to_string()))
+                    }
+                }
             })
         };
 
@@ -187,14 +225,16 @@ impl IndexScheduler {
         let mut stop_scheduler_forever = false;
         let mut wtxn = self.env.write_txn().map_err(Error::HeedTransaction)?;
         let mut canceled = RoaringBitmap::new();
+        let mut process_batch_info = ProcessBatchInfo::default();
 
         match res {
-            Ok(tasks) => {
+            Ok((tasks, info)) => {
                 #[cfg(test)]
                 self.breakpoint(crate::test_utils::Breakpoint::ProcessBatchSucceeded);
 
                 let (task_progress, task_progress_obj) = AtomicTaskStep::new(tasks.len() as u32);
                 progress.update_progress(task_progress_obj);
+                process_batch_info = info;
                 let mut success = 0;
                 let mut failure = 0;
                 let mut canceled_by = None;
@@ -311,6 +351,58 @@ impl IndexScheduler {
 
         // We must re-add the canceled task so they're part of the same batch.
         ids |= canceled;
+
+        let ProcessBatchInfo { congestion, pre_commit_dabases_sizes, post_commit_dabases_sizes } =
+            process_batch_info;
+
+        processing_batch.stats.progress_trace =
+            progress.accumulated_durations().into_iter().map(|(k, v)| (k, v.into())).collect();
+        processing_batch.stats.write_channel_congestion = congestion.map(|congestion| {
+            let mut congestion_info = serde_json::Map::new();
+            congestion_info.insert("attempts".into(), congestion.attempts.into());
+            congestion_info.insert("blocking_attempts".into(), congestion.blocking_attempts.into());
+            congestion_info.insert("blocking_ratio".into(), congestion.congestion_ratio().into());
+            congestion_info
+        });
+        processing_batch.stats.internal_database_sizes = pre_commit_dabases_sizes
+            .iter()
+            .flat_map(|(dbname, pre_size)| {
+                post_commit_dabases_sizes
+                    .get(dbname)
+                    .map(|post_size| {
+                        use byte_unit::{Byte, UnitType::Binary};
+                        use std::cmp::Ordering::{Equal, Greater, Less};
+
+                        let post = Byte::from_u64(*post_size as u64).get_appropriate_unit(Binary);
+                        let diff_size = post_size.abs_diff(*pre_size) as u64;
+                        let diff = Byte::from_u64(diff_size).get_appropriate_unit(Binary);
+                        let sign = match post_size.cmp(pre_size) {
+                            Equal => return None,
+                            Greater => "+",
+                            Less => "-",
+                        };
+
+                        Some((
+                            dbname.to_case(Case::Camel),
+                            format!("{post:#.2} ({sign}{diff:#.2})").into(),
+                        ))
+                    })
+                    .into_iter()
+                    .flatten()
+            })
+            .collect();
+
+        if let Some(congestion) = congestion {
+            tracing::debug!(
+                "Channel congestion metrics - Attempts: {}, Blocked attempts: {}  ({:.1}% congestion)",
+                congestion.attempts,
+                congestion.blocking_attempts,
+                congestion.congestion_ratio(),
+            );
+        }
+
+        tracing::debug!("call trace: {:?}", progress.accumulated_durations());
+
         self.queue.write_batch(&mut wtxn, processing_batch, &ids)?;
 
         #[cfg(test)]

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

@@ -2,23 +2,36 @@ use std::collections::{BTreeSet, HashMap, HashSet};
 use std::panic::{catch_unwind, AssertUnwindSafe};
 use std::sync::atomic::Ordering;
 
-use meilisearch_types::batches::BatchId;
+use meilisearch_types::batches::{BatchEnqueuedAt, BatchId};
 use meilisearch_types::heed::{RoTxn, RwTxn};
 use meilisearch_types::milli::progress::{Progress, VariableNameStep};
-use meilisearch_types::milli::{self};
+use meilisearch_types::milli::{self, ChannelCongestion};
 use meilisearch_types::tasks::{Details, IndexSwap, KindWithContent, Status, Task};
 use milli::update::Settings as MilliSettings;
 use roaring::RoaringBitmap;
 
 use super::create_batch::Batch;
 use crate::processing::{
-    AtomicBatchStep, AtomicTaskStep, CreateIndexProgress, DeleteIndexProgress,
+    AtomicBatchStep, AtomicTaskStep, CreateIndexProgress, DeleteIndexProgress, FinalizingIndexStep,
     InnerSwappingTwoIndexes, SwappingTheIndexes, TaskCancelationProgress, TaskDeletionProgress,
     UpdateIndexProgress,
 };
-use crate::utils::{self, swap_index_uid_in_task, ProcessingBatch};
+use crate::utils::{
+    self, remove_n_tasks_datetime_earlier_than, remove_task_datetime, swap_index_uid_in_task,
+    ProcessingBatch,
+};
 use crate::{Error, IndexScheduler, Result, TaskId};
 
+#[derive(Debug, Default)]
+pub struct ProcessBatchInfo {
+    /// The write channel congestion. None when unavailable: settings update.
+    pub congestion: Option<ChannelCongestion>,
+    /// The sizes of the different databases before starting the indexation.
+    pub pre_commit_dabases_sizes: indexmap::IndexMap<&'static str, usize>,
+    /// The sizes of the different databases after commiting the indexation.
+    pub post_commit_dabases_sizes: indexmap::IndexMap<&'static str, usize>,
+}
+
 impl IndexScheduler {
     /// Apply the operation associated with the given batch.
     ///
@@ -32,7 +45,7 @@ impl IndexScheduler {
         batch: Batch,
         current_batch: &mut ProcessingBatch,
         progress: Progress,
-    ) -> Result<Vec<Task>> {
+    ) -> Result<(Vec<Task>, ProcessBatchInfo)> {
         #[cfg(test)]
         {
             self.maybe_fail(crate::test_utils::FailureLocation::InsideProcessBatch)?;
@@ -73,7 +86,7 @@ impl IndexScheduler {
 
                 canceled_tasks.push(task);
 
-                Ok(canceled_tasks)
+                Ok((canceled_tasks, ProcessBatchInfo::default()))
             }
             Batch::TaskDeletions(mut tasks) => {
                 // 1. Retrieve the tasks that matched the query at enqueue-time.
@@ -112,10 +125,14 @@ impl IndexScheduler {
                         _ => unreachable!(),
                     }
                 }
-                Ok(tasks)
+                Ok((tasks, ProcessBatchInfo::default()))
             }
-            Batch::SnapshotCreation(tasks) => self.process_snapshot(progress, tasks),
+            Batch::SnapshotCreation(tasks) => self
-            Batch::Dump(task) => self.process_dump_creation(progress, task),
+                .process_snapshot(progress, tasks)
+                .map(|tasks| (tasks, ProcessBatchInfo::default())),
+            Batch::Dump(task) => self
+                .process_dump_creation(progress, task)
+                .map(|tasks| (tasks, ProcessBatchInfo::default())),
             Batch::IndexOperation { op, must_create_index } => {
                 let index_uid = op.index_uid().to_string();
                 let index = if must_create_index {
@@ -132,9 +149,12 @@ impl IndexScheduler {
                     .set_currently_updating_index(Some((index_uid.clone(), index.clone())));
 
                 let mut index_wtxn = index.write_txn()?;
-                let tasks = self.apply_index_operation(&mut index_wtxn, &index, op, progress)?;
+                let pre_commit_dabases_sizes = index.database_sizes(&index_wtxn)?;
+                let (tasks, congestion) =
+                    self.apply_index_operation(&mut index_wtxn, &index, op, &progress)?;
 
                 {
+                    progress.update_progress(FinalizingIndexStep::Committing);
                     let span = tracing::trace_span!(target: "indexing::scheduler", "commit");
                     let _entered = span.enter();
 
@@ -145,12 +165,15 @@ impl IndexScheduler {
                 // stats of the index. Since the tasks have already been processed and
                 // this is a non-critical operation. If it fails, we should not fail
                 // the entire batch.
+                let mut post_commit_dabases_sizes = None;
                 let res = || -> Result<()> {
+                    progress.update_progress(FinalizingIndexStep::ComputingStats);
                     let index_rtxn = index.read_txn()?;
                     let stats = crate::index_mapper::IndexStats::new(&index, &index_rtxn)
                         .map_err(|e| Error::from_milli(e, Some(index_uid.to_string())))?;
                     let mut wtxn = self.env.write_txn()?;
                     self.index_mapper.store_stats_of(&mut wtxn, &index_uid, &stats)?;
+                    post_commit_dabases_sizes = Some(index.database_sizes(&index_rtxn)?);
                     wtxn.commit()?;
                     Ok(())
                 }();
@@ -163,7 +186,16 @@ impl IndexScheduler {
                     ),
                 }
 
-                Ok(tasks)
+                let info = ProcessBatchInfo {
+                    congestion,
+                    // In case we fail to the get post-commit sizes we decide
+                    // that nothing changed and use the pre-commit sizes.
+                    post_commit_dabases_sizes: post_commit_dabases_sizes
+                        .unwrap_or_else(|| pre_commit_dabases_sizes.clone()),
+                    pre_commit_dabases_sizes,
+                };
+
+                Ok((tasks, info))
             }
             Batch::IndexCreation { index_uid, primary_key, task } => {
                 progress.update_progress(CreateIndexProgress::CreatingTheIndex);
@@ -231,7 +263,7 @@ impl IndexScheduler {
                     ),
                 }
 
-                Ok(vec![task])
+                Ok((vec![task], ProcessBatchInfo::default()))
             }
             Batch::IndexDeletion { index_uid, index_has_been_created, mut tasks } => {
                 progress.update_progress(DeleteIndexProgress::DeletingTheIndex);
@@ -265,7 +297,9 @@ impl IndexScheduler {
                     };
                 }
 
-                Ok(tasks)
+                // Here we could also show that all the internal database sizes goes to 0
+                // but it would mean opening the index and that's costly.
+                Ok((tasks, ProcessBatchInfo::default()))
             }
             Batch::IndexSwap { mut task } => {
                 progress.update_progress(SwappingTheIndexes::EnsuringCorrectnessOfTheSwap);
@@ -313,7 +347,7 @@ impl IndexScheduler {
                 }
                 wtxn.commit()?;
                 task.status = Status::Succeeded;
-                Ok(vec![task])
+                Ok((vec![task], ProcessBatchInfo::default()))
             }
             Batch::UpgradeDatabase { mut tasks } => {
                 let KindWithContent::UpgradeDatabase { from } = tasks.last().unwrap().kind else {
@@ -323,8 +357,17 @@ impl IndexScheduler {
                 match ret {
                     Ok(Ok(())) => (),
                     Ok(Err(e)) => return Err(Error::DatabaseUpgrade(Box::new(e))),
-                    Err(_e) => {
+                    Err(e) => {
-                        return Err(Error::DatabaseUpgrade(Box::new(Error::ProcessBatchPanicked)));
+                        let msg = match e.downcast_ref::<&'static str>() {
+                            Some(s) => *s,
+                            None => match e.downcast_ref::<String>() {
+                                Some(s) => &s[..],
+                                None => "Box<dyn Any>",
+                            },
+                        };
+                        return Err(Error::DatabaseUpgrade(Box::new(Error::ProcessBatchPanicked(
+                            msg.to_string(),
+                        ))));
                     }
                 }
 
@@ -334,7 +377,7 @@ impl IndexScheduler {
                     task.error = None;
                 }
 
-                Ok(tasks)
+                Ok((tasks, ProcessBatchInfo::default()))
             }
         }
     }
@@ -418,7 +461,6 @@ impl IndexScheduler {
         to_delete_tasks -= &enqueued_tasks;
 
         // 2. We now have a list of tasks to delete, delete them
-
         let mut affected_indexes = HashSet::new();
         let mut affected_statuses = HashSet::new();
         let mut affected_kinds = HashSet::new();
@@ -515,9 +557,51 @@ impl IndexScheduler {
                 tasks -= &to_delete_tasks;
                 // We must remove the batch entirely
                 if tasks.is_empty() {
-                    self.queue.batches.all_batches.delete(wtxn, &batch_id)?;
+                    if let Some(batch) = self.queue.batches.get_batch(wtxn, batch_id)? {
-                    self.queue.batch_to_tasks_mapping.delete(wtxn, &batch_id)?;
+                        if let Some(BatchEnqueuedAt { earliest, oldest }) = batch.enqueued_at {
+                            remove_task_datetime(
+                                wtxn,
+                                self.queue.batches.enqueued_at,
+                                earliest,
+                                batch_id,
+                            )?;
+                            remove_task_datetime(
+                                wtxn,
+                                self.queue.batches.enqueued_at,
+                                oldest,
+                                batch_id,
+                            )?;
+                        } else {
+                            // If we don't have the enqueued at in the batch it means the database comes from the v1.12
+                            // and we still need to find the date by scrolling the database
+                            remove_n_tasks_datetime_earlier_than(
+                                wtxn,
+                                self.queue.batches.enqueued_at,
+                                batch.started_at,
+                                batch.stats.total_nb_tasks.clamp(1, 2) as usize,
+                                batch_id,
+                            )?;
+                        }
+                        remove_task_datetime(
+                            wtxn,
+                            self.queue.batches.started_at,
+                            batch.started_at,
+                            batch_id,
+                        )?;
+                        if let Some(finished_at) = batch.finished_at {
+                            remove_task_datetime(
+                                wtxn,
+                                self.queue.batches.finished_at,
+                                finished_at,
+                                batch_id,
+                            )?;
+                        }
+
+                        self.queue.batches.all_batches.delete(wtxn, &batch_id)?;
+                        self.queue.batch_to_tasks_mapping.delete(wtxn, &batch_id)?;
+                    }
                 }
+
                 // Anyway, we must remove the batch from all its reverse indexes.
                 // The only way to do that is to check
 

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

@@ -1,3 +1,4 @@
+use std::collections::BTreeMap;
 use std::fs::File;
 use std::io::BufWriter;
 use std::sync::atomic::Ordering;
@@ -11,7 +12,9 @@ use meilisearch_types::tasks::{Details, KindWithContent, Status, Task};
 use time::macros::format_description;
 use time::OffsetDateTime;
 
-use crate::processing::{AtomicDocumentStep, AtomicTaskStep, DumpCreationProgress};
+use crate::processing::{
+    AtomicBatchStep, AtomicDocumentStep, AtomicTaskStep, DumpCreationProgress,
+};
 use crate::{Error, IndexScheduler, Result};
 
 impl IndexScheduler {
@@ -102,7 +105,40 @@ impl IndexScheduler {
         }
         dump_tasks.flush()?;
 
-        // 3. Dump the indexes
+        // 3. dump the batches
+        progress.update_progress(DumpCreationProgress::DumpTheBatches);
+        let mut dump_batches = dump.create_batches_queue()?;
+
+        let (atomic_batch_progress, update_batch_progress) =
+            AtomicBatchStep::new(self.queue.batches.all_batches.len(&rtxn)? as u32);
+        progress.update_progress(update_batch_progress);
+
+        for ret in self.queue.batches.all_batches.iter(&rtxn)? {
+            if self.scheduler.must_stop_processing.get() {
+                return Err(Error::AbortedTask);
+            }
+
+            let (_, mut b) = ret?;
+            // In the case we're dumping ourselves we want to be marked as finished
+            // to not loop over ourselves indefinitely.
+            if b.uid == task.uid {
+                let finished_at = OffsetDateTime::now_utc();
+
+                // We're going to fake the date because we don't know if everything is going to go well.
+                // But we need to dump the task as finished and successful.
+                // If something fail everything will be set appropriately in the end.
+                let mut statuses = BTreeMap::new();
+                statuses.insert(Status::Succeeded, b.stats.total_nb_tasks);
+                b.stats.status = statuses;
+                b.finished_at = Some(finished_at);
+            }
+
+            dump_batches.push_batch(&b)?;
+            atomic_batch_progress.fetch_add(1, Ordering::Relaxed);
+        }
+        dump_batches.flush()?;
+
+        // 4. Dump the indexes
         progress.update_progress(DumpCreationProgress::DumpTheIndexes);
         let nb_indexes = self.index_mapper.index_mapping.len(&rtxn)? as u32;
         let mut count = 0;
@@ -142,7 +178,7 @@ impl IndexScheduler {
             let documents = index
                 .all_documents(&rtxn)
                 .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?;
-            // 3.1. Dump the documents
+            // 4.1. Dump the documents
             for ret in documents {
                 if self.scheduler.must_stop_processing.get() {
                     return Err(Error::AbortedTask);
@@ -204,7 +240,7 @@ impl IndexScheduler {
                 atomic.fetch_add(1, Ordering::Relaxed);
             }
 
-            // 3.2. Dump the settings
+            // 4.2. Dump the settings
             let settings = meilisearch_types::settings::settings(
                 index,
                 &rtxn,
@@ -215,10 +251,12 @@ impl IndexScheduler {
             Ok(())
         })?;
 
-        // 4. Dump experimental feature settings
+        // 5. Dump experimental feature settings
         progress.update_progress(DumpCreationProgress::DumpTheExperimentalFeatures);
         let features = self.features().runtime_features();
         dump.create_experimental_features(features)?;
+        let network = self.network();
+        dump.create_network(network)?;
 
         let dump_uid = started_at.format(format_description!(
                     "[year repr:full][month repr:numerical][day padding:zero]-[hour padding:zero][minute padding:zero][second padding:zero][subsecond digits:3]"

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

@@ -5,7 +5,7 @@ use meilisearch_types::milli::documents::PrimaryKey;
 use meilisearch_types::milli::progress::Progress;
 use meilisearch_types::milli::update::new::indexer::{self, UpdateByFunction};
 use meilisearch_types::milli::update::DocumentAdditionResult;
-use meilisearch_types::milli::{self, Filter, ThreadPoolNoAbortBuilder};
+use meilisearch_types::milli::{self, ChannelCongestion, Filter, ThreadPoolNoAbortBuilder};
 use meilisearch_types::settings::apply_settings_to_builder;
 use meilisearch_types::tasks::{Details, KindWithContent, Status, Task};
 use meilisearch_types::Index;
@@ -32,10 +32,9 @@ impl IndexScheduler {
         index_wtxn: &mut RwTxn<'i>,
         index: &'i Index,
         operation: IndexOperation,
-        progress: Progress,
+        progress: &Progress,
-    ) -> Result<Vec<Task>> {
+    ) -> Result<(Vec<Task>, Option<ChannelCongestion>)> {
         let indexer_alloc = Bump::new();
-
         let started_processing_at = std::time::Instant::now();
         let must_stop_processing = self.scheduler.must_stop_processing.clone();
 
@@ -60,7 +59,7 @@ impl IndexScheduler {
                     };
                 }
 
-                Ok(tasks)
+                Ok((tasks, None))
             }
             IndexOperation::DocumentOperation { index_uid, primary_key, operations, mut tasks } => {
                 progress.update_progress(DocumentOperationProgress::RetrievingConfig);
@@ -173,21 +172,24 @@ impl IndexScheduler {
                 }
 
                 progress.update_progress(DocumentOperationProgress::Indexing);
+                let mut congestion = None;
                 if tasks.iter().any(|res| res.error.is_none()) {
-                    indexer::index(
+                    congestion = Some(
-                        index_wtxn,
+                        indexer::index(
-                        index,
+                            index_wtxn,
-                        pool,
+                            index,
-                        indexer_config.grenad_parameters(),
+                            pool,
-                        &db_fields_ids_map,
+                            indexer_config.grenad_parameters(),
-                        new_fields_ids_map,
+                            &db_fields_ids_map,
-                        primary_key,
+                            new_fields_ids_map,
-                        &document_changes,
+                            primary_key,
-                        embedders,
+                            &document_changes,
-                        &|| must_stop_processing.get(),
+                            embedders,
-                        &progress,
+                            &|| must_stop_processing.get(),
-                    )
+                            progress,
-                    .map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?;
+                        )
+                        .map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?,
+                    );
 
                     let addition = DocumentAdditionResult {
                         indexed_documents: candidates_count,
@@ -199,7 +201,7 @@ impl IndexScheduler {
                     tracing::info!(indexing_result = ?addition, processed_in = ?started_processing_at.elapsed(), "document indexing done");
                 }
 
-                Ok(tasks)
+                Ok((tasks, congestion))
             }
             IndexOperation::DocumentEdition { index_uid, mut task } => {
                 progress.update_progress(DocumentEditionProgress::RetrievingConfig);
@@ -247,7 +249,7 @@ impl IndexScheduler {
                         edited_documents: Some(0),
                     });
 
-                    return Ok(vec![task]);
+                    return Ok((vec![task], None));
                 }
 
                 let rtxn = index.read_txn()?;
@@ -262,6 +264,7 @@ impl IndexScheduler {
 
                 let result_count = Ok((candidates.len(), candidates.len())) as Result<_>;
 
+                let mut congestion = None;
                 if task.error.is_none() {
                     let local_pool;
                     let indexer_config = self.index_mapper.indexer_config();
@@ -292,20 +295,22 @@ impl IndexScheduler {
                     let embedders = self.embedders(index_uid.clone(), embedders)?;
 
                     progress.update_progress(DocumentEditionProgress::Indexing);
-                    indexer::index(
+                    congestion = Some(
-                        index_wtxn,
+                        indexer::index(
-                        index,
+                            index_wtxn,
-                        pool,
+                            index,
-                        indexer_config.grenad_parameters(),
+                            pool,
-                        &db_fields_ids_map,
+                            indexer_config.grenad_parameters(),
-                        new_fields_ids_map,
+                            &db_fields_ids_map,
-                        None, // cannot change primary key in DocumentEdition
+                            new_fields_ids_map,
-                        &document_changes,
+                            None, // cannot change primary key in DocumentEdition
-                        embedders,
+                            &document_changes,
-                        &|| must_stop_processing.get(),
+                            embedders,
-                        &progress,
+                            &|| must_stop_processing.get(),
-                    )
+                            progress,
-                    .map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?;
+                        )
+                        .map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?,
+                    );
 
                     let addition = DocumentAdditionResult {
                         indexed_documents: candidates_count,
@@ -341,7 +346,7 @@ impl IndexScheduler {
                     }
                 }
 
-                Ok(vec![task])
+                Ok((vec![task], congestion))
             }
             IndexOperation::DocumentDeletion { mut tasks, index_uid } => {
                 progress.update_progress(DocumentDeletionProgress::RetrievingConfig);
@@ -408,7 +413,7 @@ impl IndexScheduler {
                 }
 
                 if to_delete.is_empty() {
-                    return Ok(tasks);
+                    return Ok((tasks, None));
                 }
 
                 let rtxn = index.read_txn()?;
@@ -422,6 +427,7 @@ impl IndexScheduler {
                     PrimaryKey::new_or_insert(primary_key, &mut new_fields_ids_map)
                         .map_err(|err| Error::from_milli(err.into(), Some(index_uid.clone())))?;
 
+                let mut congestion = None;
                 if !tasks.iter().all(|res| res.error.is_some()) {
                     let local_pool;
                     let indexer_config = self.index_mapper.indexer_config();
@@ -447,20 +453,22 @@ impl IndexScheduler {
                     let embedders = self.embedders(index_uid.clone(), embedders)?;
 
                     progress.update_progress(DocumentDeletionProgress::Indexing);
-                    indexer::index(
+                    congestion = Some(
-                        index_wtxn,
+                        indexer::index(
-                        index,
+                            index_wtxn,
-                        pool,
+                            index,
-                        indexer_config.grenad_parameters(),
+                            pool,
-                        &db_fields_ids_map,
+                            indexer_config.grenad_parameters(),
-                        new_fields_ids_map,
+                            &db_fields_ids_map,
-                        None, // document deletion never changes primary key
+                            new_fields_ids_map,
-                        &document_changes,
+                            None, // document deletion never changes primary key
-                        embedders,
+                            &document_changes,
-                        &|| must_stop_processing.get(),
+                            embedders,
-                        &progress,
+                            &|| must_stop_processing.get(),
-                    )
+                            progress,
-                    .map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?;
+                        )
+                        .map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?,
+                    );
 
                     let addition = DocumentAdditionResult {
                         indexed_documents: candidates_count,
@@ -472,7 +480,7 @@ impl IndexScheduler {
                     tracing::info!(indexing_result = ?addition, processed_in = ?started_processing_at.elapsed(), "document indexing done");
                 }
 
-                Ok(tasks)
+                Ok((tasks, congestion))
             }
             IndexOperation::Settings { index_uid, settings, mut tasks } => {
                 progress.update_progress(SettingsProgress::RetrievingAndMergingTheSettings);
@@ -497,7 +505,7 @@ impl IndexScheduler {
                     )
                     .map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?;
 
-                Ok(tasks)
+                Ok((tasks, None))
             }
             IndexOperation::DocumentClearAndSetting {
                 index_uid,
@@ -505,17 +513,17 @@ impl IndexScheduler {
                 settings,
                 settings_tasks,
             } => {
-                let mut import_tasks = self.apply_index_operation(
+                let (mut import_tasks, _congestion) = self.apply_index_operation(
                     index_wtxn,
                     index,
                     IndexOperation::DocumentClear {
                         index_uid: index_uid.clone(),
                         tasks: cleared_tasks,
                     },
-                    progress.clone(),
+                    progress,
                 )?;
 
-                let settings_tasks = self.apply_index_operation(
+                let (settings_tasks, _congestion) = self.apply_index_operation(
                     index_wtxn,
                     index,
                     IndexOperation::Settings { index_uid, settings, tasks: settings_tasks },
@@ -524,7 +532,7 @@ impl IndexScheduler {
 
                 let mut tasks = settings_tasks;
                 tasks.append(&mut import_tasks);
-                Ok(tasks)
+                Ok((tasks, None))
             }
         }
     }

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

@@ -4,7 +4,6 @@ use std::sync::atomic::Ordering;
 
 use meilisearch_types::heed::CompactionOption;
 use meilisearch_types::milli::progress::{Progress, VariableNameStep};
-use meilisearch_types::milli::{self};
 use meilisearch_types::tasks::{Status, Task};
 use meilisearch_types::{compression, VERSION_FILE_NAME};
 
@@ -28,7 +27,7 @@ impl IndexScheduler {
 
         // 2. Snapshot the index-scheduler LMDB env
         //
-        // When we call copy_to_file, LMDB opens a read transaction by itself,
+        // When we call copy_to_path, LMDB opens a read transaction by itself,
         // we can't provide our own. It is an issue as we would like to know
         // the update files to copy but new ones can be enqueued between the copy
         // of the env and the new transaction we open to retrieve the enqueued tasks.
@@ -42,7 +41,7 @@ impl IndexScheduler {
         progress.update_progress(SnapshotCreationProgress::SnapshotTheIndexScheduler);
         let dst = temp_snapshot_dir.path().join("tasks");
         fs::create_dir_all(&dst)?;
-        self.env.copy_to_file(dst.join("data.mdb"), CompactionOption::Enabled)?;
+        self.env.copy_to_path(dst.join("data.mdb"), CompactionOption::Enabled)?;
 
         // 2.2 Create a read transaction on the index-scheduler
         let rtxn = self.env.read_txn()?;
@@ -81,7 +80,7 @@ impl IndexScheduler {
             let dst = temp_snapshot_dir.path().join("indexes").join(uuid.to_string());
             fs::create_dir_all(&dst)?;
             index
-                .copy_to_file(dst.join("data.mdb"), CompactionOption::Enabled)
+                .copy_to_path(dst.join("data.mdb"), CompactionOption::Enabled)
                 .map_err(|e| Error::from_milli(e, Some(name.to_string())))?;
         }
 
@@ -91,14 +90,7 @@ impl IndexScheduler {
         progress.update_progress(SnapshotCreationProgress::SnapshotTheApiKeys);
         let dst = temp_snapshot_dir.path().join("auth");
         fs::create_dir_all(&dst)?;
-        // TODO We can't use the open_auth_store_env function here but we should
+        self.scheduler.auth_env.copy_to_path(dst.join("data.mdb"), CompactionOption::Enabled)?;
-        let auth = unsafe {
-            milli::heed::EnvOpenOptions::new()
-                .map_size(1024 * 1024 * 1024) // 1 GiB
-                .max_dbs(2)
-                .open(&self.scheduler.auth_path)
-        }?;
-        auth.copy_to_file(dst.join("data.mdb"), CompactionOption::Enabled)?;
 
         // 5. Copy and tarball the flat snapshot
         progress.update_progress(SnapshotCreationProgress::CreateTheTarball);

crates/index-scheduler/src/scheduler/snapshots/index_scheduler__scheduler__test_embedders__import_vectors-8.snap

@@ -1,12 +1,12 @@
 ---
 source: crates/index-scheduler/src/scheduler/test_embedders.rs
 expression: simple_hf_config.embedder_options
-snapshot_kind: text
 ---
 {
   "HuggingFace": {
     "model": "sentence-transformers/all-MiniLM-L6-v2",
     "revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
-    "distribution": null
+    "distribution": null,
+    "pooling": "useModel"
   }
 }

crates/index-scheduler/src/scheduler/snapshots/test.rs/task_deletion_delete_same_task_twice/task_deletion_processed.snap

@@ -56,16 +56,13 @@ succeeded [1,]
 ### Batches Index Tasks:
 ----------------------------------------------------------------------
 ### Batches Enqueued At:
-[timestamp] [0,]
 [timestamp] [1,]
 [timestamp] [1,]
 ----------------------------------------------------------------------
 ### Batches Started At:
-[timestamp] [0,]
 [timestamp] [1,]
 ----------------------------------------------------------------------
 ### Batches Finished At:
-[timestamp] [0,]
 [timestamp] [1,]
 ----------------------------------------------------------------------
 ### File Store:

crates/index-scheduler/src/scheduler/snapshots/test.rs/task_deletion_deleteable/task_deletion_processed.snap

@@ -54,15 +54,12 @@ succeeded [1,]
 ### Batches Index Tasks:
 ----------------------------------------------------------------------
 ### Batches Enqueued At:
-[timestamp] [0,]
 [timestamp] [1,]
 ----------------------------------------------------------------------
 ### Batches Started At:
-[timestamp] [0,]
 [timestamp] [1,]
 ----------------------------------------------------------------------
 ### Batches Finished At:
-[timestamp] [0,]
 [timestamp] [1,]
 ----------------------------------------------------------------------
 ### File Store:

crates/index-scheduler/src/scheduler/snapshots/test.rs/test_settings_update/after_registering_settings_task.snap

@@ -1,13 +1,12 @@
 ---
 source: crates/index-scheduler/src/scheduler/test.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, status: enqueued, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+0 {uid: 0, status: enqueued, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, pooling: NotSet, api_key: Set("My super secret"), dimensions: Set(4), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, search_embedder: NotSet, indexing_embedder: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, pooling: NotSet, api_key: Set("My super secret"), dimensions: Set(4), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, search_embedder: NotSet, indexing_embedder: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued [0,]

crates/index-scheduler/src/scheduler/snapshots/test.rs/test_settings_update/settings_update_processed.snap

@@ -1,13 +1,12 @@
 ---
 source: crates/index-scheduler/src/scheduler/test.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, batch_uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+0 {uid: 0, batch_uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, pooling: NotSet, api_key: Set("My super secret"), dimensions: Set(4), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, search_embedder: NotSet, indexing_embedder: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, pooling: NotSet, api_key: Set("My super secret"), dimensions: Set(4), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, search_embedder: NotSet, indexing_embedder: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued []

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

@@ -1,13 +1,12 @@
 ---
 source: crates/index-scheduler/src/scheduler/test_embedders.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, batch_uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+0 {uid: 0, batch_uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, pooling: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, search_embedder: NotSet, indexing_embedder: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), pooling: NotSet, api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, search_embedder: NotSet, indexing_embedder: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, pooling: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, search_embedder: NotSet, indexing_embedder: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), pooling: NotSet, api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, search_embedder: NotSet, indexing_embedder: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 1 {uid: 1, batch_uid: 1, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
 2 {uid: 2, batch_uid: 2, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: None, method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
 ----------------------------------------------------------------------

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

@@ -1,13 +1,12 @@
 ---
 source: crates/index-scheduler/src/scheduler/test_embedders.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, batch_uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+0 {uid: 0, batch_uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, pooling: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, search_embedder: NotSet, indexing_embedder: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), pooling: NotSet, api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, search_embedder: NotSet, indexing_embedder: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, pooling: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, search_embedder: NotSet, indexing_embedder: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), pooling: NotSet, api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, search_embedder: NotSet, indexing_embedder: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 1 {uid: 1, batch_uid: 1, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
 2 {uid: 2, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: None, method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
 ----------------------------------------------------------------------

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

@@ -1,13 +1,12 @@
 ---
 source: crates/index-scheduler/src/scheduler/test_embedders.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, batch_uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+0 {uid: 0, batch_uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, pooling: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, search_embedder: NotSet, indexing_embedder: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), pooling: NotSet, api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, search_embedder: NotSet, indexing_embedder: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, pooling: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, search_embedder: NotSet, indexing_embedder: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), pooling: NotSet, api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, search_embedder: NotSet, indexing_embedder: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 1 {uid: 1, batch_uid: 1, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:

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

@@ -1,13 +1,12 @@
 ---
 source: crates/index-scheduler/src/scheduler/test_embedders.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, batch_uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+0 {uid: 0, batch_uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, pooling: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, search_embedder: NotSet, indexing_embedder: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), pooling: NotSet, api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, search_embedder: NotSet, indexing_embedder: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, pooling: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, search_embedder: NotSet, indexing_embedder: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), pooling: NotSet, api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, search_embedder: NotSet, indexing_embedder: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 1 {uid: 1, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:

crates/index-scheduler/src/scheduler/snapshots/test_embedders.rs/import_vectors/after_registering_settings_task_vectors.snap

@@ -1,13 +1,12 @@
 ---
 source: crates/index-scheduler/src/scheduler/test_embedders.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, status: enqueued, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+0 {uid: 0, status: enqueued, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, pooling: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, search_embedder: NotSet, indexing_embedder: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), pooling: NotSet, api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, search_embedder: NotSet, indexing_embedder: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, pooling: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, search_embedder: NotSet, indexing_embedder: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), pooling: NotSet, api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, search_embedder: NotSet, indexing_embedder: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued [0,]

crates/index-scheduler/src/scheduler/snapshots/test_embedders.rs/import_vectors/settings_update_processed_vectors.snap

@@ -1,13 +1,12 @@
 ---
 source: crates/index-scheduler/src/scheduler/test_embedders.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, batch_uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+0 {uid: 0, batch_uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, pooling: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, search_embedder: NotSet, indexing_embedder: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), pooling: NotSet, api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, search_embedder: NotSet, indexing_embedder: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, pooling: NotSet, api_key: Set("My super secret"), dimensions: Set(384), binary_quantized: NotSet, document_template: NotSet, document_template_max_bytes: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, search_embedder: NotSet, indexing_embedder: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), pooling: NotSet, api_key: NotSet, dimensions: NotSet, binary_quantized: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), document_template_max_bytes: NotSet, url: NotSet, request: NotSet, response: NotSet, headers: NotSet, search_embedder: NotSet, indexing_embedder: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued []

crates/index-scheduler/src/scheduler/snapshots/test_failure.rs/fail_in_process_batch_for_document_deletion/after_adding_the_documents.snap

@@ -1,13 +1,12 @@
 ---
 source: crates/index-scheduler/src/scheduler/test_failure.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, batch_uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+0 {uid: 0, batch_uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set([Field("catto")]), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set([Field("catto")]), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 1 {uid: 1, batch_uid: 1, status: succeeded, details: { received_documents: 3, indexed_documents: Some(3) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:

crates/index-scheduler/src/scheduler/snapshots/test_failure.rs/fail_in_process_batch_for_document_deletion/after_adding_the_settings.snap

@@ -1,13 +1,12 @@
 ---
 source: crates/index-scheduler/src/scheduler/test_failure.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, batch_uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+0 {uid: 0, batch_uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set([Field("catto")]), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set([Field("catto")]), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 1 {uid: 1, status: enqueued, details: { received_documents: 3, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:

crates/index-scheduler/src/scheduler/snapshots/test_failure.rs/fail_in_process_batch_for_document_deletion/after_removing_the_documents.snap

@@ -1,17 +1,16 @@
 ---
 source: crates/index-scheduler/src/scheduler/test_failure.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, batch_uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+0 {uid: 0, batch_uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set([Field("catto")]), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set([Field("catto")]), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 1 {uid: 1, batch_uid: 1, status: succeeded, details: { received_documents: 3, indexed_documents: Some(3) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
 2 {uid: 2, batch_uid: 2, status: succeeded, details: { received_document_ids: 1, deleted_documents: Some(1) }, kind: DocumentDeletion { index_uid: "doggos", documents_ids: ["1"] }}
 3 {uid: 3, batch_uid: 2, status: failed, error: ResponseError { code: 200, message: "Index `doggos`: Invalid type for filter subexpression: expected: String, Array, found: true.", error_code: "invalid_document_filter", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#invalid_document_filter" }, details: { original_filter: true, deleted_documents: Some(0) }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: Bool(true) }}
-4 {uid: 4, batch_uid: 2, status: failed, error: ResponseError { code: 200, message: "Index `doggos`: Attribute `id` is not filterable. Available filterable attributes are: `catto`.\n1:3 id = 2", error_code: "invalid_document_filter", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#invalid_document_filter" }, details: { original_filter: "id = 2", deleted_documents: Some(0) }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: String("id = 2") }}
+4 {uid: 4, batch_uid: 2, status: failed, error: ResponseError { code: 200, message: "Index `doggos`: Attribute `id` is not filterable. Available filterable attribute patterns are: `catto`.\n1:3 id = 2", error_code: "invalid_document_filter", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#invalid_document_filter" }, details: { original_filter: "id = 2", deleted_documents: Some(0) }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: String("id = 2") }}
 5 {uid: 5, batch_uid: 2, status: succeeded, details: { original_filter: "catto EXISTS", deleted_documents: Some(1) }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: String("catto EXISTS") }}
 ----------------------------------------------------------------------
 ### Status:

crates/index-scheduler/src/scheduler/snapshots/test_failure.rs/fail_in_process_batch_for_document_deletion/registered_the_document_deletions.snap

@@ -1,13 +1,12 @@
 ---
 source: crates/index-scheduler/src/scheduler/test_failure.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, batch_uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+0 {uid: 0, batch_uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set([Field("catto")]), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set([Field("catto")]), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 1 {uid: 1, batch_uid: 1, status: succeeded, details: { received_documents: 3, indexed_documents: Some(3) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
 2 {uid: 2, status: enqueued, details: { received_document_ids: 1, deleted_documents: None }, kind: DocumentDeletion { index_uid: "doggos", documents_ids: ["1"] }}
 3 {uid: 3, status: enqueued, details: { original_filter: true, deleted_documents: None }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: Bool(true) }}

crates/index-scheduler/src/scheduler/snapshots/test_failure.rs/fail_in_process_batch_for_document_deletion/registered_the_setting_and_document_addition.snap

@@ -1,13 +1,12 @@
 ---
 source: crates/index-scheduler/src/scheduler/test_failure.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, status: enqueued, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+0 {uid: 0, status: enqueued, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set([Field("catto")]), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set([Field("catto")]), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 1 {uid: 1, status: enqueued, details: { received_documents: 3, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:

crates/index-scheduler/src/scheduler/snapshots/test_failure.rs/panic_in_process_batch_for_index_creation/index_creation_failed.snap

@@ -7,7 +7,7 @@ snapshot_kind: text
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, batch_uid: 0, status: failed, error: ResponseError { code: 200, message: "An unexpected crash occurred when processing the task.", error_code: "internal", error_type: "internal", error_link: "https://docs.meilisearch.com/errors#internal" }, details: { primary_key: Some("mouse") }, kind: IndexCreation { index_uid: "catto", primary_key: Some("mouse") }}
+0 {uid: 0, batch_uid: 0, status: failed, error: ResponseError { code: 200, message: "An unexpected crash occurred when processing the task: simulated panic", error_code: "internal", error_type: "internal", error_link: "https://docs.meilisearch.com/errors#internal" }, details: { primary_key: Some("mouse") }, kind: IndexCreation { index_uid: "catto", primary_key: Some("mouse") }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued []

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

@@ -1,13 +1,12 @@
 ---
 source: crates/index-scheduler/src/scheduler/test_failure.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, batch_uid: 0, status: succeeded, details: { from: (1, 12, 0), to: (1, 13, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
+0 {uid: 0, batch_uid: 0, status: succeeded, details: { from: (1, 12, 0), to: (1, 14, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
 1 {uid: 1, batch_uid: 1, status: succeeded, details: { primary_key: Some("mouse") }, kind: IndexCreation { index_uid: "catto", primary_key: Some("mouse") }}
 2 {uid: 2, batch_uid: 2, status: succeeded, details: { primary_key: Some("bone") }, 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") }, kind: IndexCreation { index_uid: "doggo", primary_key: Some("bone") }}
@@ -58,7 +57,7 @@ girafo: { number_of_documents: 0, field_distribution: {} }
 [timestamp] [4,]
 ----------------------------------------------------------------------
 ### All Batches:
-0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.13.0"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"upgradeDatabase":1},"indexUids":{}}, }
+0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.14.0"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"upgradeDatabase":1},"indexUids":{}}, }
 1 {uid: 1, details: {"primaryKey":"mouse"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"catto":1}}, }
 2 {uid: 2, details: {"primaryKey":"bone"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"doggo":1}}, }
 3 {uid: 3, details: {"primaryKey":"bone"}, stats: {"totalNbTasks":1,"status":{"failed":1},"types":{"indexCreation":1},"indexUids":{"doggo":1}}, }

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

@@ -87,7 +87,6 @@ doggo [2,3,]
 girafo [4,]
 ----------------------------------------------------------------------
 ### Batches Enqueued At:
-[timestamp] [0,]
 [timestamp] [1,]
 [timestamp] [2,]
 [timestamp] [3,]
@@ -95,7 +94,6 @@ girafo [4,]
 [timestamp] [5,]
 ----------------------------------------------------------------------
 ### Batches Started At:
-[timestamp] [0,]
 [timestamp] [1,]
 [timestamp] [2,]
 [timestamp] [3,]
@@ -103,7 +101,6 @@ girafo [4,]
 [timestamp] [5,]
 ----------------------------------------------------------------------
 ### Batches Finished At:
-[timestamp] [0,]
 [timestamp] [1,]
 [timestamp] [2,]
 [timestamp] [3,]

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

@@ -1,13 +1,12 @@
 ---
 source: crates/index-scheduler/src/scheduler/test_failure.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, status: enqueued, details: { from: (1, 12, 0), to: (1, 13, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
+0 {uid: 0, status: enqueued, details: { from: (1, 12, 0), to: (1, 14, 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

@@ -1,13 +1,12 @@
 ---
 source: crates/index-scheduler/src/scheduler/test_failure.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, status: enqueued, details: { from: (1, 12, 0), to: (1, 13, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
+0 {uid: 0, status: enqueued, details: { from: (1, 12, 0), to: (1, 14, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
 1 {uid: 1, status: enqueued, details: { primary_key: Some("mouse") }, 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

@@ -1,13 +1,12 @@
 ---
 source: crates/index-scheduler/src/scheduler/test_failure.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
 []
 ----------------------------------------------------------------------
 ### 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, 13, 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, 14, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
 1 {uid: 1, status: enqueued, details: { primary_key: Some("mouse") }, kind: IndexCreation { index_uid: "catto", primary_key: Some("mouse") }}
 ----------------------------------------------------------------------
 ### Status:
@@ -38,7 +37,7 @@ catto [1,]
 [timestamp] [0,]
 ----------------------------------------------------------------------
 ### All Batches:
-0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.13.0"}, stats: {"totalNbTasks":1,"status":{"failed":1},"types":{"upgradeDatabase":1},"indexUids":{}}, }
+0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.14.0"}, stats: {"totalNbTasks":1,"status":{"failed":1},"types":{"upgradeDatabase":1},"indexUids":{}}, }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]

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

@@ -1,13 +1,12 @@
 ---
 source: crates/index-scheduler/src/scheduler/test_failure.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
 []
 ----------------------------------------------------------------------
 ### 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, 13, 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, 14, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
 1 {uid: 1, status: enqueued, details: { primary_key: Some("mouse") }, kind: IndexCreation { index_uid: "catto", primary_key: Some("mouse") }}
 2 {uid: 2, status: enqueued, details: { primary_key: Some("bone") }, kind: IndexCreation { index_uid: "doggo", primary_key: Some("bone") }}
 ----------------------------------------------------------------------
@@ -41,7 +40,7 @@ doggo [2,]
 [timestamp] [0,]
 ----------------------------------------------------------------------
 ### All Batches:
-0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.13.0"}, stats: {"totalNbTasks":1,"status":{"failed":1},"types":{"upgradeDatabase":1},"indexUids":{}}, }
+0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.14.0"}, stats: {"totalNbTasks":1,"status":{"failed":1},"types":{"upgradeDatabase":1},"indexUids":{}}, }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]

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

@@ -1,13 +1,12 @@
 ---
 source: crates/index-scheduler/src/scheduler/test_failure.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, batch_uid: 0, status: succeeded, details: { from: (1, 12, 0), to: (1, 13, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
+0 {uid: 0, batch_uid: 0, status: succeeded, details: { from: (1, 12, 0), to: (1, 14, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
 1 {uid: 1, status: enqueued, details: { primary_key: Some("mouse") }, kind: IndexCreation { index_uid: "catto", primary_key: Some("mouse") }}
 2 {uid: 2, status: enqueued, details: { primary_key: Some("bone") }, kind: IndexCreation { index_uid: "doggo", primary_key: Some("bone") }}
 3 {uid: 3, status: enqueued, details: { primary_key: Some("bone") }, kind: IndexCreation { index_uid: "doggo", primary_key: Some("bone") }}
@@ -44,7 +43,7 @@ doggo [2,3,]
 [timestamp] [0,]
 ----------------------------------------------------------------------
 ### All Batches:
-0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.13.0"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"upgradeDatabase":1},"indexUids":{}}, }
+0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.14.0"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"upgradeDatabase":1},"indexUids":{}}, }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]

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

@@ -903,15 +903,21 @@ fn create_and_list_index() {
 
     index_scheduler.index("kefir").unwrap();
     let list = index_scheduler.get_paginated_indexes_stats(&AuthFilter::default(), 0, 20).unwrap();
-    snapshot!(json_string!(list, { "[1][0][1].created_at" => "[date]", "[1][0][1].updated_at" => "[date]", "[1][0][1].used_database_size" => "[bytes]", "[1][0][1].database_size" => "[bytes]" }), @r#"
+    snapshot!(json_string!(list, { "[1][0][1].created_at" => "[date]", "[1][0][1].updated_at" => "[date]", "[1][0][1].used_database_size" => "[bytes]", "[1][0][1].database_size" => "[bytes]" }), @r###"
     [
       1,
       [
         [
           "kefir",
           {
-            "number_of_documents": 0,
+            "documents_database_stats": {
+              "numberOfEntries": 0,
+              "totalKeySize": 0,
+              "totalValueSize": 0
+            },
             "database_size": "[bytes]",
+            "number_of_embeddings": 0,
+            "number_of_embedded_documents": 0,
             "used_database_size": "[bytes]",
             "primary_key": null,
             "field_distribution": {},
@@ -921,5 +927,5 @@ fn create_and_list_index() {
         ]
       ]
     ]
-    "#);
+    "###);
 }

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

@@ -104,9 +104,9 @@ fn import_vectors() {
 
         let configs = index_scheduler.embedders("doggos".to_string(), configs).unwrap();
         let (hf_embedder, _, _) = configs.get(&simple_hf_name).unwrap();
-        let beagle_embed = hf_embedder.embed_one(S("Intel the beagle best doggo"), None).unwrap();
+        let beagle_embed = hf_embedder.embed_search("Intel the beagle best doggo", None).unwrap();
-        let lab_embed = hf_embedder.embed_one(S("Max the lab best doggo"), None).unwrap();
+        let lab_embed = hf_embedder.embed_search("Max the lab best doggo", None).unwrap();
-        let patou_embed = hf_embedder.embed_one(S("kefir the patou best doggo"), None).unwrap();
+        let patou_embed = hf_embedder.embed_search("kefir the patou best doggo", None).unwrap();
         (fakerest_name, simple_hf_name, beagle_embed, lab_embed, patou_embed)
     };
 
@@ -404,31 +404,32 @@ fn import_vectors_first_and_embedder_later() {
     // even though we specified the vector for the ID 3, it shouldn't be marked
     // as user provided since we explicitely marked it as NOT user provided.
     snapshot!(format!("{conf:#?}"), @r###"
-        [
+    [
-            IndexEmbeddingConfig {
+        IndexEmbeddingConfig {
-                name: "my_doggo_embedder",
+            name: "my_doggo_embedder",
-                config: EmbeddingConfig {
+            config: EmbeddingConfig {
-                    embedder_options: HuggingFace(
+                embedder_options: HuggingFace(
-                        EmbedderOptions {
+                    EmbedderOptions {
-                            model: "sentence-transformers/all-MiniLM-L6-v2",
+                        model: "sentence-transformers/all-MiniLM-L6-v2",
-                            revision: Some(
+                        revision: Some(
-                                "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
+                            "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
-                            ),
-                            distribution: None,
-                        },
-                    ),
-                    prompt: PromptData {
-                        template: "{{doc.doggo}}",
-                        max_bytes: Some(
-                            400,
                         ),
+                        distribution: None,
+                        pooling: UseModel,
                     },
-                    quantized: None,
+                ),
+                prompt: PromptData {
+                    template: "{{doc.doggo}}",
+                    max_bytes: Some(
+                        400,
+                    ),
                 },
-                user_provided: RoaringBitmap<[1, 2]>,
+                quantized: None,
             },
-        ]
+            user_provided: RoaringBitmap<[1, 2]>,
-        "###);
+        },
+    ]
+    "###);
     let docid = index.external_documents_ids.get(&rtxn, "0").unwrap().unwrap();
     let embeddings = index.embeddings(&rtxn, docid).unwrap();
     let embedding = &embeddings["my_doggo_embedder"];

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

@@ -1,13 +1,12 @@
 use std::time::Instant;
 
 use big_s::S;
-use maplit::btreeset;
 use meili_snap::snapshot;
 use meilisearch_types::milli::obkv_to_json;
 use meilisearch_types::milli::update::IndexDocumentsMethod::*;
 use meilisearch_types::milli::update::Setting;
-use meilisearch_types::tasks::Kind;
+use meilisearch_types::milli::FilterableAttributesRule;
-use meilisearch_types::tasks::KindWithContent;
+use meilisearch_types::tasks::{Kind, KindWithContent};
 
 use crate::insta_snapshot::snapshot_index_scheduler;
 use crate::test_utils::Breakpoint::*;
@@ -128,7 +127,8 @@ fn fail_in_process_batch_for_document_deletion() {
 
     use meilisearch_types::settings::{Settings, Unchecked};
     let mut new_settings: Box<Settings<Unchecked>> = Box::default();
-    new_settings.filterable_attributes = Setting::Set(btreeset!(S("catto")));
+    new_settings.filterable_attributes =
+        Setting::Set(vec![FilterableAttributesRule::Field(S("catto"))]);
 
     index_scheduler
         .register(

crates/index-scheduler/src/test_utils.rs

@@ -5,6 +5,7 @@ use std::time::Duration;
 use big_s::S;
 use crossbeam_channel::RecvTimeoutError;
 use file_store::File;
+use meilisearch_auth::open_auth_store_env;
 use meilisearch_types::document_formats::DocumentFormatError;
 use meilisearch_types::milli::update::IndexDocumentsMethod::ReplaceDocuments;
 use meilisearch_types::milli::update::IndexerConfig;
@@ -111,6 +112,7 @@ impl IndexScheduler {
             batched_tasks_size_limit: u64::MAX,
             instance_features: Default::default(),
             auto_upgrade: true, // Don't cost much and will ensure the happy path works
+            embedding_cache_cap: 10,
         };
         let version = configuration(&mut options).unwrap_or_else(|| {
             (
@@ -120,7 +122,10 @@ impl IndexScheduler {
             )
         });
 
-        let index_scheduler = Self::new(options, version, sender, planned_failures).unwrap();
+        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();
 
         // To be 100% consistent between all test we're going to start the scheduler right now
         // and ensure it's in the expected starting state.

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

@@ -1,5 +1,5 @@
 use anyhow::bail;
-use meilisearch_types::heed::{Env, RwTxn};
+use meilisearch_types::heed::{Env, RwTxn, WithoutTls};
 use meilisearch_types::tasks::{Details, KindWithContent, Status, Task};
 use meilisearch_types::versioning::{VERSION_MAJOR, VERSION_MINOR, VERSION_PATCH};
 use time::OffsetDateTime;
@@ -9,13 +9,17 @@ use crate::queue::TaskQueue;
 use crate::versioning::Versioning;
 
 trait UpgradeIndexScheduler {
-    fn upgrade(&self, env: &Env, wtxn: &mut RwTxn, original: (u32, u32, u32))
+    fn upgrade(
-        -> anyhow::Result<()>;
+        &self,
+        env: &Env<WithoutTls>,
+        wtxn: &mut RwTxn,
+        original: (u32, u32, u32),
+    ) -> anyhow::Result<()>;
     fn target_version(&self) -> (u32, u32, u32);
 }
 
 pub fn upgrade_index_scheduler(
-    env: &Env,
+    env: &Env<WithoutTls>,
     versioning: &Versioning,
     from: (u32, u32, u32),
     to: (u32, u32, u32),
@@ -24,10 +28,12 @@ pub fn upgrade_index_scheduler(
     let current_minor = to.1;
     let current_patch = to.2;
 
-    let upgrade_functions: &[&dyn UpgradeIndexScheduler] = &[&V1_12_ToCurrent {}];
+    let upgrade_functions: &[&dyn UpgradeIndexScheduler] = &[&ToCurrentNoOp {}];
 
     let start = match from {
         (1, 12, _) => 0,
+        (1, 13, _) => 0,
+        (1, 14, _) => 0,
         (major, minor, patch) => {
             if major > current_major
                 || (major == current_major && minor > current_minor)
@@ -46,20 +52,19 @@ pub fn upgrade_index_scheduler(
         }
     };
 
-    let mut current_version = from;
-
     info!("Upgrading the task queue");
+    let mut local_from = from;
     for upgrade in upgrade_functions[start..].iter() {
         let target = upgrade.target_version();
         info!(
             "Upgrading from v{}.{}.{} to v{}.{}.{}",
-            from.0, from.1, from.2, current_version.0, current_version.1, current_version.2
+            local_from.0, local_from.1, local_from.2, target.0, target.1, target.2
         );
         let mut wtxn = env.write_txn()?;
-        upgrade.upgrade(env, &mut wtxn, from)?;
+        upgrade.upgrade(env, &mut wtxn, local_from)?;
         versioning.set_version(&mut wtxn, target)?;
         wtxn.commit()?;
-        current_version = target;
+        local_from = target;
     }
 
     let mut wtxn = env.write_txn()?;
@@ -86,12 +91,12 @@ pub fn upgrade_index_scheduler(
 }
 
 #[allow(non_camel_case_types)]
-struct V1_12_ToCurrent {}
+struct ToCurrentNoOp {}
 
-impl UpgradeIndexScheduler for V1_12_ToCurrent {
+impl UpgradeIndexScheduler for ToCurrentNoOp {
     fn upgrade(
         &self,
-        _env: &Env,
+        _env: &Env<WithoutTls>,
         _wtxn: &mut RwTxn,
         _original: (u32, u32, u32),
     ) -> anyhow::Result<()> {

crates/index-scheduler/src/utils.rs

@@ -3,7 +3,7 @@
 use std::collections::{BTreeSet, HashSet};
 use std::ops::Bound;
 
-use meilisearch_types::batches::{Batch, BatchId, BatchStats};
+use meilisearch_types::batches::{Batch, BatchEnqueuedAt, BatchId, BatchStats};
 use meilisearch_types::heed::{Database, RoTxn, RwTxn};
 use meilisearch_types::milli::CboRoaringBitmapCodec;
 use meilisearch_types::task_view::DetailsView;
@@ -30,8 +30,7 @@ pub struct ProcessingBatch {
     pub kinds: HashSet<Kind>,
     pub indexes: HashSet<String>,
     pub canceled_by: HashSet<TaskId>,
-    pub oldest_enqueued_at: Option<OffsetDateTime>,
+    pub enqueued_at: Option<BatchEnqueuedAt>,
-    pub earliest_enqueued_at: Option<OffsetDateTime>,
     pub started_at: OffsetDateTime,
     pub finished_at: Option<OffsetDateTime>,
 }
@@ -51,8 +50,7 @@ impl ProcessingBatch {
             kinds: HashSet::default(),
             indexes: HashSet::default(),
             canceled_by: HashSet::default(),
-            oldest_enqueued_at: None,
+            enqueued_at: None,
-            earliest_enqueued_at: None,
             started_at: OffsetDateTime::now_utc(),
             finished_at: None,
         }
@@ -80,14 +78,18 @@ impl ProcessingBatch {
             if let Some(canceled_by) = task.canceled_by {
                 self.canceled_by.insert(canceled_by);
             }
-            self.oldest_enqueued_at =
+            match self.enqueued_at.as_mut() {
-                Some(self.oldest_enqueued_at.map_or(task.enqueued_at, |oldest_enqueued_at| {
+                Some(BatchEnqueuedAt { earliest, oldest }) => {
-                    task.enqueued_at.min(oldest_enqueued_at)
+                    *oldest = task.enqueued_at.min(*oldest);
-                }));
+                    *earliest = task.enqueued_at.max(*earliest);
-            self.earliest_enqueued_at =
+                }
-                Some(self.earliest_enqueued_at.map_or(task.enqueued_at, |earliest_enqueued_at| {
+                None => {
-                    task.enqueued_at.max(earliest_enqueued_at)
+                    self.enqueued_at = Some(BatchEnqueuedAt {
-                }));
+                        earliest: task.enqueued_at,
+                        oldest: task.enqueued_at,
+                    });
+                }
+            }
         }
     }
 
@@ -138,6 +140,7 @@ impl ProcessingBatch {
             stats: self.stats.clone(),
             started_at: self.started_at,
             finished_at: self.finished_at,
+            enqueued_at: self.enqueued_at,
         }
     }
 }
@@ -174,6 +177,33 @@ pub(crate) fn remove_task_datetime(
     Ok(())
 }
 
+pub(crate) fn remove_n_tasks_datetime_earlier_than(
+    wtxn: &mut RwTxn,
+    database: Database<BEI128, CboRoaringBitmapCodec>,
+    earlier_than: OffsetDateTime,
+    mut count: usize,
+    task_id: TaskId,
+) -> Result<()> {
+    let earlier_than = earlier_than.unix_timestamp_nanos();
+    let mut iter = database.rev_range_mut(wtxn, &(..earlier_than))?;
+    while let Some((current, mut existing)) = iter.next().transpose()? {
+        count -= existing.remove(task_id) as usize;
+
+        if existing.is_empty() {
+            // safety: We don't keep references to the database
+            unsafe { iter.del_current()? };
+        } else {
+            // safety: We don't keep references to the database
+            unsafe { iter.put_current(&current, &existing)? };
+        }
+        if count == 0 {
+            break;
+        }
+    }
+
+    Ok(())
+}
+
 pub(crate) fn keep_ids_within_datetimes(
     rtxn: &RoTxn,
     ids: &mut RoaringBitmap,
@@ -329,14 +359,27 @@ impl crate::IndexScheduler {
                 kind,
             } = task;
             assert_eq!(uid, task.uid);
-            if let Some(ref batch) = batch_uid {
+            if task.status != Status::Enqueued {
+                let batch_uid = batch_uid.expect("All non enqueued tasks must be part of a batch");
                 assert!(self
                     .queue
                     .batch_to_tasks_mapping
-                    .get(&rtxn, batch)
+                    .get(&rtxn, &batch_uid)
                     .unwrap()
                     .unwrap()
                     .contains(uid));
+                let batch = self.queue.batches.get_batch(&rtxn, batch_uid).unwrap().unwrap();
+                assert_eq!(batch.uid, batch_uid);
+                if task.status == Status::Processing {
+                    assert!(batch.progress.is_some());
+                } else {
+                    assert!(batch.progress.is_none());
+                }
+                assert_eq!(batch.started_at, task.started_at.unwrap());
+                assert_eq!(batch.finished_at, task.finished_at);
+                let enqueued_at = batch.enqueued_at.unwrap();
+                assert!(task.enqueued_at >= enqueued_at.oldest);
+                assert!(task.enqueued_at <= enqueued_at.earliest);
             }
             if let Some(task_index_uid) = &task_index_uid {
                 assert!(self

crates/index-scheduler/src/versioning.rs

@@ -1,9 +1,10 @@
-use crate::{upgrade::upgrade_index_scheduler, Result};
+use meilisearch_types::heed::types::Str;
-use meilisearch_types::{
+use meilisearch_types::heed::{self, Database, Env, RoTxn, RwTxn, WithoutTls};
-    heed::{types::Str, Database, Env, RoTxn, RwTxn},
+use meilisearch_types::milli::heed_codec::version::VersionCodec;
-    milli::heed_codec::version::VersionCodec,
+use meilisearch_types::versioning;
-    versioning,
+
-};
+use crate::upgrade::upgrade_index_scheduler;
+use crate::Result;
 
 /// The number of database used by queue itself
 const NUMBER_OF_DATABASES: u32 = 1;
@@ -21,30 +22,38 @@ pub struct Versioning {
 }
 
 impl Versioning {
-    pub(crate) const fn nb_db() -> u32 {
+    pub const fn nb_db() -> u32 {
         NUMBER_OF_DATABASES
     }
 
-    pub fn get_version(&self, rtxn: &RoTxn) -> Result<Option<(u32, u32, u32)>> {
+    pub fn get_version(&self, rtxn: &RoTxn) -> Result<Option<(u32, u32, u32)>, heed::Error> {
-        Ok(self.version.get(rtxn, entry_name::MAIN)?)
+        self.version.get(rtxn, entry_name::MAIN)
     }
 
-    pub fn set_version(&self, wtxn: &mut RwTxn, version: (u32, u32, u32)) -> Result<()> {
+    pub fn set_version(
-        Ok(self.version.put(wtxn, entry_name::MAIN, &version)?)
+        &self,
+        wtxn: &mut RwTxn,
+        version: (u32, u32, u32),
+    ) -> Result<(), heed::Error> {
+        self.version.put(wtxn, entry_name::MAIN, &version)
     }
 
-    pub fn set_current_version(&self, wtxn: &mut RwTxn) -> Result<()> {
+    pub fn set_current_version(&self, wtxn: &mut RwTxn) -> Result<(), heed::Error> {
         let major = versioning::VERSION_MAJOR.parse().unwrap();
         let minor = versioning::VERSION_MINOR.parse().unwrap();
         let patch = versioning::VERSION_PATCH.parse().unwrap();
         self.set_version(wtxn, (major, minor, patch))
     }
 
-    /// Create an index scheduler and start its run loop.
+    /// Return `Self` without checking anything about the version
-    pub(crate) fn new(env: &Env, db_version: (u32, u32, u32)) -> Result<Self> {
+    pub fn raw_new(env: &Env<WithoutTls>, wtxn: &mut RwTxn) -> Result<Self, heed::Error> {
+        let version = env.create_database(wtxn, Some(db_name::VERSION))?;
+        Ok(Self { version })
+    }
+
+    pub(crate) fn new(env: &Env<WithoutTls>, db_version: (u32, u32, u32)) -> Result<Self> {
         let mut wtxn = env.write_txn()?;
-        let version = env.create_database(&mut wtxn, Some(db_name::VERSION))?;
+        let this = Self::raw_new(env, &mut wtxn)?;
-        let this = Self { version };
         let from = match this.get_version(&wtxn)? {
             Some(version) => version,
             // fresh DB: use the db version

crates/meilisearch-auth/src/dump.rs

@@ -2,6 +2,7 @@ use std::fs::File;
 use std::io::{BufReader, Write};
 use std::path::Path;
 
+use meilisearch_types::heed::{Env, WithoutTls};
 use serde_json::Deserializer;
 
 use crate::{AuthController, HeedAuthStore, Result};
@@ -9,11 +10,8 @@ use crate::{AuthController, HeedAuthStore, Result};
 const KEYS_PATH: &str = "keys";
 
 impl AuthController {
-    pub fn dump(src: impl AsRef<Path>, dst: impl AsRef<Path>) -> Result<()> {
+    pub fn dump(auth_env: Env<WithoutTls>, dst: impl AsRef<Path>) -> Result<()> {
-        let mut store = HeedAuthStore::new(&src)?;
+        let store = HeedAuthStore::new(auth_env)?;
-
-        // do not attempt to close the database on drop!
-        store.set_drop_on_close(false);
 
         let keys_file_path = dst.as_ref().join(KEYS_PATH);
 
@@ -27,8 +25,8 @@ impl AuthController {
         Ok(())
     }
 
-    pub fn load_dump(src: impl AsRef<Path>, dst: impl AsRef<Path>) -> Result<()> {
+    pub fn load_dump(src: impl AsRef<Path>, auth_env: Env<WithoutTls>) -> Result<()> {
-        let store = HeedAuthStore::new(&dst)?;
+        let store = HeedAuthStore::new(auth_env)?;
 
         let keys_file_path = src.as_ref().join(KEYS_PATH);
 

crates/meilisearch-auth/src/lib.rs

@@ -3,11 +3,10 @@ pub mod error;
 mod store;
 
 use std::collections::{HashMap, HashSet};
-use std::path::Path;
-use std::sync::Arc;
 
 use error::{AuthControllerError, Result};
 use maplit::hashset;
+use meilisearch_types::heed::{Env, WithoutTls};
 use meilisearch_types::index_uid_pattern::IndexUidPattern;
 use meilisearch_types::keys::{Action, CreateApiKey, Key, PatchApiKey};
 use meilisearch_types::milli::update::Setting;
@@ -19,19 +18,19 @@ use uuid::Uuid;
 
 #[derive(Clone)]
 pub struct AuthController {
-    store: Arc<HeedAuthStore>,
+    store: HeedAuthStore,
     master_key: Option<String>,
 }
 
 impl AuthController {
-    pub fn new(db_path: impl AsRef<Path>, master_key: &Option<String>) -> Result<Self> {
+    pub fn new(auth_env: Env<WithoutTls>, master_key: &Option<String>) -> Result<Self> {
-        let store = HeedAuthStore::new(db_path)?;
+        let store = HeedAuthStore::new(auth_env)?;
 
         if store.is_empty()? {
             generate_default_keys(&store)?;
         }
 
-        Ok(Self { store: Arc::new(store), master_key: master_key.clone() })
+        Ok(Self { store, master_key: master_key.clone() })
     }
 
     /// Return `Ok(())` if the auth controller is able to access one of its database.

crates/meilisearch-auth/src/store.rs

@@ -1,18 +1,16 @@
 use std::borrow::Cow;
 use std::cmp::Reverse;
 use std::collections::HashSet;
-use std::fs::create_dir_all;
 use std::path::Path;
 use std::result::Result as StdResult;
 use std::str;
 use std::str::FromStr;
-use std::sync::Arc;
 
 use hmac::{Hmac, Mac};
-use meilisearch_types::heed::BoxedError;
+use meilisearch_types::heed::{BoxedError, WithoutTls};
 use meilisearch_types::index_uid_pattern::IndexUidPattern;
 use meilisearch_types::keys::KeyId;
-use meilisearch_types::milli;
+use meilisearch_types::milli::heed;
 use meilisearch_types::milli::heed::types::{Bytes, DecodeIgnore, SerdeJson};
 use meilisearch_types::milli::heed::{Database, Env, EnvOpenOptions, RwTxn};
 use sha2::Sha256;
@@ -25,44 +23,32 @@ use super::error::{AuthControllerError, Result};
 use super::{Action, Key};
 
 const AUTH_STORE_SIZE: usize = 1_073_741_824; //1GiB
-const AUTH_DB_PATH: &str = "auth";
 const KEY_DB_NAME: &str = "api-keys";
 const KEY_ID_ACTION_INDEX_EXPIRATION_DB_NAME: &str = "keyid-action-index-expiration";
 
 #[derive(Clone)]
 pub struct HeedAuthStore {
-    env: Arc<Env>,
+    env: Env<WithoutTls>,
     keys: Database<Bytes, SerdeJson<Key>>,
     action_keyid_index_expiration: Database<KeyIdActionCodec, SerdeJson<Option<OffsetDateTime>>>,
-    should_close_on_drop: bool,
 }
 
-impl Drop for HeedAuthStore {
+pub fn open_auth_store_env(path: &Path) -> heed::Result<Env<WithoutTls>> {
-    fn drop(&mut self) {
+    let options = EnvOpenOptions::new();
-        if self.should_close_on_drop && Arc::strong_count(&self.env) == 1 {
+    let mut options = options.read_txn_without_tls();
-            self.env.as_ref().clone().prepare_for_closing();
-        }
-    }
-}
-
-pub fn open_auth_store_env(path: &Path) -> milli::heed::Result<milli::heed::Env> {
-    let mut options = EnvOpenOptions::new();
     options.map_size(AUTH_STORE_SIZE); // 1GB
     options.max_dbs(2);
     unsafe { options.open(path) }
 }
 
 impl HeedAuthStore {
-    pub fn new(path: impl AsRef<Path>) -> Result<Self> {
+    pub fn new(env: Env<WithoutTls>) -> Result<Self> {
-        let path = path.as_ref().join(AUTH_DB_PATH);
-        create_dir_all(&path)?;
-        let env = Arc::new(open_auth_store_env(path.as_ref())?);
         let mut wtxn = env.write_txn()?;
         let keys = env.create_database(&mut wtxn, Some(KEY_DB_NAME))?;
         let action_keyid_index_expiration =
             env.create_database(&mut wtxn, Some(KEY_ID_ACTION_INDEX_EXPIRATION_DB_NAME))?;
         wtxn.commit()?;
-        Ok(Self { env, keys, action_keyid_index_expiration, should_close_on_drop: true })
+        Ok(Self { env, keys, action_keyid_index_expiration })
     }
 
     /// Return `Ok(())` if the auth store is able to access one of its database.
@@ -82,10 +68,6 @@ impl HeedAuthStore {
         Ok(self.env.non_free_pages_size()?)
     }
 
-    pub fn set_drop_on_close(&mut self, v: bool) {
-        self.should_close_on_drop = v;
-    }
-
     pub fn is_empty(&self) -> Result<bool> {
         let rtxn = self.env.read_txn()?;
 
@@ -293,7 +275,7 @@ impl HeedAuthStore {
 /// optionally on a specific index, for a given key.
 pub struct KeyIdActionCodec;
 
-impl<'a> milli::heed::BytesDecode<'a> for KeyIdActionCodec {
+impl<'a> heed::BytesDecode<'a> for KeyIdActionCodec {
     type DItem = (KeyId, Action, Option<&'a [u8]>);
 
     fn bytes_decode(bytes: &'a [u8]) -> StdResult<Self::DItem, BoxedError> {
@@ -310,7 +292,7 @@ impl<'a> milli::heed::BytesDecode<'a> for KeyIdActionCodec {
     }
 }
 
-impl<'a> milli::heed::BytesEncode<'a> for KeyIdActionCodec {
+impl<'a> heed::BytesEncode<'a> for KeyIdActionCodec {
     type EItem = (&'a KeyId, &'a Action, Option<&'a [u8]>);
 
     fn bytes_encode((key_id, action, index): &Self::EItem) -> StdResult<Cow<[u8]>, BoxedError> {

crates/meilisearch-types/Cargo.toml

@@ -14,6 +14,7 @@ license.workspace = true
 actix-web = { version = "4.9.0", default-features = false }
 anyhow = "1.0.95"
 bumpalo = "3.16.0"
+bumparaw-collections = "0.1.4"
 convert_case = "0.6.0"
 csv = "1.3.1"
 deserr = { version = "0.6.3", features = ["actix-web"] }
@@ -24,12 +25,11 @@ flate2 = "1.0.35"
 fst = "0.4.7"
 memmap2 = "0.9.5"
 milli = { path = "../milli" }
-bumparaw-collections = "0.1.4"
 roaring = { version = "0.10.10", features = ["serde"] }
 rustc-hash = "2.1.0"
 serde = { version = "1.0.217", features = ["derive"] }
 serde-cs = "0.2.4"
-serde_json = "1.0.135"
+serde_json = { version = "1.0.135", features = ["preserve_order"] }
 tar = "0.4.43"
 tempfile = "3.15.0"
 thiserror = "2.0.9"

crates/meilisearch-types/src/batches.rs

@@ -24,9 +24,35 @@ pub struct Batch {
     pub started_at: OffsetDateTime,
     #[serde(with = "time::serde::rfc3339::option")]
     pub finished_at: Option<OffsetDateTime>,
+
+    // Enqueued at is never displayed and is only required when removing a batch.
+    // It's always some except when upgrading from a database pre v1.12
+    pub enqueued_at: Option<BatchEnqueuedAt>,
 }
 
-#[derive(Default, Debug, Clone, Serialize, Deserialize, ToSchema)]
+impl PartialEq for Batch {
+    fn eq(&self, other: &Self) -> bool {
+        let Self { uid, progress, details, stats, started_at, finished_at, enqueued_at } = self;
+
+        *uid == other.uid
+            && progress.is_none() == other.progress.is_none()
+            && details == &other.details
+            && stats == &other.stats
+            && started_at == &other.started_at
+            && finished_at == &other.finished_at
+            && enqueued_at == &other.enqueued_at
+    }
+}
+
+#[derive(Clone, Copy, Debug, PartialEq, Eq, Serialize, Deserialize)]
+pub struct BatchEnqueuedAt {
+    #[serde(with = "time::serde::rfc3339")]
+    pub earliest: OffsetDateTime,
+    #[serde(with = "time::serde::rfc3339")]
+    pub oldest: OffsetDateTime,
+}
+
+#[derive(Default, Debug, Clone, PartialEq, Eq, Serialize, Deserialize, ToSchema)]
 #[serde(rename_all = "camelCase")]
 #[schema(rename_all = "camelCase")]
 pub struct BatchStats {
@@ -34,4 +60,10 @@ pub struct BatchStats {
     pub status: BTreeMap<Status, u32>,
     pub types: BTreeMap<Kind, u32>,
     pub index_uids: BTreeMap<String, u32>,
+    #[serde(default, skip_serializing_if = "serde_json::Map::is_empty")]
+    pub progress_trace: serde_json::Map<String, serde_json::Value>,
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub write_channel_congestion: Option<serde_json::Map<String, serde_json::Value>>,
+    #[serde(default, skip_serializing_if = "serde_json::Map::is_empty")]
+    pub internal_database_sizes: serde_json::Map<String, serde_json::Value>,
 }

crates/meilisearch-types/src/deserr/mod.rs

@@ -193,6 +193,8 @@ merge_with_error_impl_take_error_message!(ParseTaskKindError);
 merge_with_error_impl_take_error_message!(ParseTaskStatusError);
 merge_with_error_impl_take_error_message!(IndexUidFormatError);
 merge_with_error_impl_take_error_message!(InvalidMultiSearchWeight);
+merge_with_error_impl_take_error_message!(InvalidNetworkUrl);
+merge_with_error_impl_take_error_message!(InvalidNetworkSearchApiKey);
 merge_with_error_impl_take_error_message!(InvalidSearchSemanticRatio);
 merge_with_error_impl_take_error_message!(InvalidSearchRankingScoreThreshold);
 merge_with_error_impl_take_error_message!(InvalidSimilarRankingScoreThreshold);

crates/meilisearch-types/src/error.rs

@@ -241,6 +241,7 @@ InvalidDocumentGeoField               , InvalidRequest       , BAD_REQUEST ;
 InvalidVectorDimensions               , InvalidRequest       , BAD_REQUEST ;
 InvalidVectorsType                    , InvalidRequest       , BAD_REQUEST ;
 InvalidDocumentId                     , InvalidRequest       , BAD_REQUEST ;
+InvalidDocumentIds                    , InvalidRequest       , BAD_REQUEST ;
 InvalidDocumentLimit                  , InvalidRequest       , BAD_REQUEST ;
 InvalidDocumentOffset                 , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchEmbedder                 , InvalidRequest       , BAD_REQUEST ;
@@ -260,7 +261,13 @@ InvalidMultiSearchMergeFacets         , InvalidRequest       , BAD_REQUEST ;
 InvalidMultiSearchQueryFacets         , InvalidRequest       , BAD_REQUEST ;
 InvalidMultiSearchQueryPagination     , InvalidRequest       , BAD_REQUEST ;
 InvalidMultiSearchQueryRankingRules   , InvalidRequest       , BAD_REQUEST ;
+InvalidMultiSearchQueryPosition       , InvalidRequest       , BAD_REQUEST ;
+InvalidMultiSearchRemote              , InvalidRequest       , BAD_REQUEST ;
 InvalidMultiSearchWeight              , InvalidRequest       , BAD_REQUEST ;
+InvalidNetworkRemotes                 , InvalidRequest       , BAD_REQUEST ;
+InvalidNetworkSelf                    , InvalidRequest       , BAD_REQUEST ;
+InvalidNetworkSearchApiKey            , InvalidRequest       , BAD_REQUEST ;
+InvalidNetworkUrl                     , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchAttributesToSearchOn     , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchAttributesToCrop         , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchAttributesToHighlight    , InvalidRequest       , BAD_REQUEST ;
@@ -275,6 +282,7 @@ InvalidSearchCropMarker               , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchFacets                   , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchSemanticRatio            , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchLocales                  , InvalidRequest       , BAD_REQUEST ;
+InvalidFacetSearchExhaustiveFacetCount, InvalidRequest       , BAD_REQUEST ;
 InvalidFacetSearchFacetName           , InvalidRequest       , BAD_REQUEST ;
 InvalidSimilarId                      , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchFilter                   , InvalidRequest       , BAD_REQUEST ;
@@ -351,14 +359,22 @@ MissingDocumentId                     , InvalidRequest       , BAD_REQUEST ;
 MissingFacetSearchFacetName           , InvalidRequest       , BAD_REQUEST ;
 MissingIndexUid                       , InvalidRequest       , BAD_REQUEST ;
 MissingMasterKey                      , Auth                 , UNAUTHORIZED ;
+MissingNetworkUrl                     , InvalidRequest       , BAD_REQUEST ;
 MissingPayload                        , InvalidRequest       , BAD_REQUEST ;
 MissingSearchHybrid                   , InvalidRequest       , BAD_REQUEST ;
 MissingSwapIndexes                    , InvalidRequest       , BAD_REQUEST ;
 MissingTaskFilters                    , InvalidRequest       , BAD_REQUEST ;
 NoSpaceLeftOnDevice                   , System               , UNPROCESSABLE_ENTITY;
 PayloadTooLarge                       , InvalidRequest       , PAYLOAD_TOO_LARGE ;
+RemoteBadResponse                     , System               , BAD_GATEWAY ;
+RemoteBadRequest                      , InvalidRequest       , BAD_REQUEST ;
+RemoteCouldNotSendRequest             , System               , BAD_GATEWAY ;
+RemoteInvalidApiKey                   , Auth                 , FORBIDDEN ;
+RemoteRemoteError                     , System               , BAD_GATEWAY ;
+RemoteTimeout                         , System               , BAD_GATEWAY ;
 TooManySearchRequests                 , System               , SERVICE_UNAVAILABLE ;
 TaskNotFound                          , InvalidRequest       , NOT_FOUND ;
+TaskFileNotFound                      , InvalidRequest       , NOT_FOUND ;
 BatchNotFound                         , InvalidRequest       , NOT_FOUND ;
 TooManyOpenFiles                      , System               , UNPROCESSABLE_ENTITY ;
 TooManyVectors                        , InvalidRequest       , BAD_REQUEST ;
@@ -391,7 +407,7 @@ impl ErrorCode for milli::Error {
                 match error {
                     // TODO: wait for spec for new error codes.
                     UserError::SerdeJson(_)
-                    | UserError::InvalidLmdbOpenOptions
+                    | UserError::EnvAlreadyOpened
                     | UserError::DocumentLimitReached
                     | UserError::UnknownInternalDocumentId { .. } => Code::Internal,
                     UserError::InvalidStoreFile => Code::InvalidStoreFile,
@@ -400,6 +416,7 @@ impl ErrorCode for milli::Error {
                     UserError::AttributeLimitReached => Code::MaxFieldsLimitExceeded,
                     UserError::InvalidFilter(_) => Code::InvalidSearchFilter,
                     UserError::InvalidFilterExpression(..) => Code::InvalidSearchFilter,
+                    UserError::FilterOperatorNotAllowed { .. } => Code::InvalidSearchFilter,
                     UserError::MissingDocumentId { .. } => Code::MissingDocumentId,
                     UserError::InvalidDocumentId { .. } | UserError::TooManyDocumentIds { .. } => {
                         Code::InvalidDocumentId
@@ -414,9 +431,10 @@ impl ErrorCode for milli::Error {
                     | UserError::InvalidUrl { .. }
                     | UserError::InvalidSettingsDocumentTemplateMaxBytes { .. }
                     | UserError::InvalidPrompt(_)
-                    | UserError::InvalidDisableBinaryQuantization { .. } => {
+                    | UserError::InvalidDisableBinaryQuantization { .. }
-                        Code::InvalidSettingsEmbedders
+                    | UserError::InvalidSourceForNested { .. }
-                    }
+                    | UserError::MissingSourceForNested { .. }
+                    | UserError::InvalidSettingsEmbedder { .. } => Code::InvalidSettingsEmbedders,
                     UserError::TooManyEmbedders(_) => Code::InvalidSettingsEmbedders,
                     UserError::InvalidPromptForEmbeddings(..) => Code::InvalidSettingsEmbedders,
                     UserError::NoPrimaryKeyCandidateFound => Code::IndexPrimaryKeyNoCandidateFound,
@@ -486,8 +504,7 @@ impl ErrorCode for HeedError {
             HeedError::Mdb(_)
             | HeedError::Encoding(_)
             | HeedError::Decoding(_)
-            | HeedError::DatabaseClosing
+            | HeedError::EnvAlreadyOpened => Code::Internal,
-            | HeedError::BadOpenOptions { .. } => Code::Internal,
         }
     }
 }
@@ -583,6 +600,18 @@ impl fmt::Display for deserr_codes::InvalidSimilarRankingScoreThreshold {
     }
 }
 
+impl fmt::Display for deserr_codes::InvalidNetworkUrl {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        write!(f, "the value of `url` is invalid, expected a string.")
+    }
+}
+
+impl fmt::Display for deserr_codes::InvalidNetworkSearchApiKey {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        write!(f, "the value of `searchApiKey` is invalid, expected a string.")
+    }
+}
+
 #[macro_export]
 macro_rules! internal_error {
     ($target:ty : $($other:path), *) => {

crates/meilisearch-types/src/features.rs

@@ -1,3 +1,5 @@
+use std::collections::BTreeMap;
+
 use serde::{Deserialize, Serialize};
 
 #[derive(Serialize, Deserialize, Debug, Clone, Copy, Default, PartialEq, Eq)]
@@ -7,6 +9,9 @@ pub struct RuntimeTogglableFeatures {
     pub logs_route: bool,
     pub edit_documents_by_function: bool,
     pub contains_filter: bool,
+    pub network: bool,
+    pub get_task_documents_route: bool,
+    pub composite_embedders: bool,
 }
 
 #[derive(Default, Debug, Clone, Copy)]
@@ -15,3 +20,20 @@ pub struct InstanceTogglableFeatures {
     pub logs_route: bool,
     pub contains_filter: 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>,
+}
+
+#[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>,
+}

crates/meilisearch-types/src/index_uid.rs

@@ -4,13 +4,14 @@ use std::fmt;
 use std::str::FromStr;
 
 use deserr::Deserr;
+use serde::Serialize;
 use utoipa::ToSchema;
 
 use crate::error::{Code, ErrorCode};
 
 /// An index uid is composed of only ascii alphanumeric characters, - and _, between 1 and 400
 /// bytes long
-#[derive(Debug, Clone, PartialEq, Eq, Deserr, PartialOrd, Ord, ToSchema)]
+#[derive(Debug, Clone, PartialEq, Eq, Deserr, PartialOrd, Ord, Serialize, ToSchema)]
 #[deserr(try_from(String) = IndexUid::try_from -> IndexUidFormatError)]
 #[schema(value_type = String, example = "movies")]
 pub struct IndexUid(String);

crates/meilisearch-types/src/keys.rs

@@ -302,6 +302,12 @@ pub enum Action {
     #[serde(rename = "experimental.update")]
     #[deserr(rename = "experimental.update")]
     ExperimentalFeaturesUpdate,
+    #[serde(rename = "network.get")]
+    #[deserr(rename = "network.get")]
+    NetworkGet,
+    #[serde(rename = "network.update")]
+    #[deserr(rename = "network.update")]
+    NetworkUpdate,
 }
 
 impl Action {
@@ -341,6 +347,8 @@ impl Action {
             KEYS_DELETE => Some(Self::KeysDelete),
             EXPERIMENTAL_FEATURES_GET => Some(Self::ExperimentalFeaturesGet),
             EXPERIMENTAL_FEATURES_UPDATE => Some(Self::ExperimentalFeaturesUpdate),
+            NETWORK_GET => Some(Self::NetworkGet),
+            NETWORK_UPDATE => Some(Self::NetworkUpdate),
             _otherwise => None,
         }
     }
@@ -386,4 +394,7 @@ pub mod actions {
     pub const KEYS_DELETE: u8 = KeysDelete.repr();
     pub const EXPERIMENTAL_FEATURES_GET: u8 = ExperimentalFeaturesGet.repr();
     pub const EXPERIMENTAL_FEATURES_UPDATE: u8 = ExperimentalFeaturesUpdate.repr();
+
+    pub const NETWORK_GET: u8 = NetworkGet.repr();
+    pub const NETWORK_UPDATE: u8 = NetworkUpdate.repr();
 }

crates/meilisearch-types/src/locales.rs

@@ -1,5 +1,5 @@
 use deserr::Deserr;
-use milli::LocalizedAttributesRule;
+use milli::{AttributePatterns, LocalizedAttributesRule};
 use serde::{Deserialize, Serialize};
 use utoipa::ToSchema;
 
@@ -7,7 +7,7 @@ use utoipa::ToSchema;
 #[deserr(rename_all = camelCase)]
 #[serde(rename_all = "camelCase")]
 pub struct LocalizedAttributesRuleView {
-    pub attribute_patterns: Vec<String>,
+    pub attribute_patterns: AttributePatterns,
     pub locales: Vec<Locale>,
 }
 

crates/meilisearch-types/src/settings.rs

@@ -11,7 +11,7 @@ use fst::IntoStreamer;
 use milli::index::{IndexEmbeddingConfig, PrefixSearch};
 use milli::proximity::ProximityPrecision;
 use milli::update::Setting;
-use milli::{Criterion, CriterionError, Index, DEFAULT_VALUES_PER_FACET};
+use milli::{Criterion, CriterionError, FilterableAttributesRule, Index, DEFAULT_VALUES_PER_FACET};
 use serde::{Deserialize, Serialize, Serializer};
 use utoipa::ToSchema;
 
@@ -202,8 +202,8 @@ pub struct Settings<T> {
     /// Attributes to use for faceting and filtering. See [Filtering and Faceted Search](https://www.meilisearch.com/docs/learn/filtering_and_sorting/search_with_facet_filters).
     #[serde(default, skip_serializing_if = "Setting::is_not_set")]
     #[deserr(default, error = DeserrJsonError<InvalidSettingsFilterableAttributes>)]
-    #[schema(value_type = Option<Vec<String>>, example = json!(["release_date", "genre"]))]
+    #[schema(value_type = Option<Vec<FilterableAttributesRule>>, example = json!(["release_date", "genre"]))]
-    pub filterable_attributes: Setting<BTreeSet<String>>,
+    pub filterable_attributes: Setting<Vec<FilterableAttributesRule>>,
     /// Attributes to use when sorting search results.
     #[serde(default, skip_serializing_if = "Setting::is_not_set")]
     #[deserr(default, error = DeserrJsonError<InvalidSettingsSortableAttributes>)]
@@ -791,7 +791,7 @@ pub fn settings(
         .user_defined_searchable_fields(rtxn)?
         .map(|fields| fields.into_iter().map(String::from).collect());
 
-    let filterable_attributes = index.filterable_fields(rtxn)?.into_iter().collect();
+    let filterable_attributes = index.filterable_attributes_rules(rtxn)?.into_iter().collect();
 
     let sortable_attributes = index.sortable_fields(rtxn)?.into_iter().collect();
 

crates/meilisearch-types/src/versioning.rs

@@ -1,7 +1,10 @@
 use std::fs;
-use std::io::{self, ErrorKind};
+use std::io::{ErrorKind, Write};
 use std::path::Path;
 
+use milli::heed;
+use tempfile::NamedTempFile;
+
 /// The name of the file that contains the version of the database.
 pub const VERSION_FILE_NAME: &str = "VERSION";
 
@@ -10,37 +13,7 @@ pub static VERSION_MINOR: &str = env!("CARGO_PKG_VERSION_MINOR");
 pub static VERSION_PATCH: &str = env!("CARGO_PKG_VERSION_PATCH");
 
 /// Persists the version of the current Meilisearch binary to a VERSION file
-pub fn update_version_file_for_dumpless_upgrade(
+pub fn create_current_version_file(db_path: &Path) -> anyhow::Result<()> {
-    db_path: &Path,
-    from: (u32, u32, u32),
-    to: (u32, u32, u32),
-) -> Result<(), VersionFileError> {
-    let (from_major, from_minor, from_patch) = from;
-    let (to_major, to_minor, to_patch) = to;
-
-    if from_major > to_major
-        || (from_major == to_major && from_minor > to_minor)
-        || (from_major == to_major && from_minor == to_minor && from_patch > to_patch)
-    {
-        Err(VersionFileError::DowngradeNotSupported {
-            major: from_major,
-            minor: from_minor,
-            patch: from_patch,
-        })
-    } else if from_major < 1 || (from_major == to_major && from_minor < 12) {
-        Err(VersionFileError::TooOldForAutomaticUpgrade {
-            major: from_major,
-            minor: from_minor,
-            patch: from_patch,
-        })
-    } else {
-        create_current_version_file(db_path)?;
-        Ok(())
-    }
-}
-
-/// Persists the version of the current Meilisearch binary to a VERSION file
-pub fn create_current_version_file(db_path: &Path) -> io::Result<()> {
     create_version_file(db_path, VERSION_MAJOR, VERSION_MINOR, VERSION_PATCH)
 }
 
@@ -49,9 +22,14 @@ pub fn create_version_file(
     major: &str,
     minor: &str,
     patch: &str,
-) -> io::Result<()> {
+) -> anyhow::Result<()> {
     let version_path = db_path.join(VERSION_FILE_NAME);
-    fs::write(version_path, format!("{}.{}.{}", major, minor, patch))
+    // In order to persist the file later we must create it in the `data.ms` and not in `/tmp`
+    let mut file = NamedTempFile::new_in(db_path)?;
+    file.write_all(format!("{}.{}.{}", major, minor, patch).as_bytes())?;
+    file.flush()?;
+    file.persist(version_path)?;
+    Ok(())
 }
 
 pub fn get_version(db_path: &Path) -> Result<(u32, u32, u32), VersionFileError> {
@@ -61,7 +39,7 @@ pub fn get_version(db_path: &Path) -> Result<(u32, u32, u32), VersionFileError>
         Ok(version) => parse_version(&version),
         Err(error) => match error.kind() {
             ErrorKind::NotFound => Err(VersionFileError::MissingVersionFile),
-            _ => Err(error.into()),
+            _ => Err(anyhow::Error::from(error).into()),
         },
     }
 }
@@ -112,7 +90,9 @@ pub enum VersionFileError {
     DowngradeNotSupported { major: u32, minor: u32, patch: u32 },
     #[error("Database version {major}.{minor}.{patch} is too old for the experimental dumpless upgrade feature. Please generate a dump using the v{major}.{minor}.{patch} and import it in the v{VERSION_MAJOR}.{VERSION_MINOR}.{VERSION_PATCH}")]
     TooOldForAutomaticUpgrade { major: u32, minor: u32, patch: u32 },
+    #[error("Error while modifying the database: {0}")]
+    ErrorWhileModifyingTheDatabase(#[from] heed::Error),
 
     #[error(transparent)]
-    IoError(#[from] std::io::Error),
+    AnyhowError(#[from] anyhow::Error),
 }

crates/meilisearch/Cargo.toml

@@ -30,11 +30,7 @@ actix-web = { version = "4.9.0", default-features = false, features = [
 anyhow = { version = "1.0.95", features = ["backtrace"] }
 async-trait = "0.1.85"
 bstr = "1.11.3"
-byte-unit = { version = "5.1.6", default-features = false, features = [
+byte-unit = { version = "5.1.6", features = ["serde"] }
-    "std",
-    "byte",
-    "serde",
-] }
 bytes = "1.9.0"
 clap = { version = "4.5.24", features = ["derive", "env"] }
 crossbeam-channel = "0.5.14"
@@ -140,7 +136,7 @@ reqwest = { version = "0.12.12", features = [
 sha-1 = { version = "0.10.1", optional = true }
 static-files = { version = "0.2.4", optional = true }
 tempfile = { version = "3.15.0", optional = true }
-zip = { version = "2.2.2", optional = true }
+zip = { version = "2.3.0", optional = true }
 
 [features]
 default = ["meilisearch-types/all-tokenizations", "mini-dashboard"]
@@ -170,5 +166,5 @@ german = ["meilisearch-types/german"]
 turkish = ["meilisearch-types/turkish"]
 
 [package.metadata.mini-dashboard]
-assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.2.16/build.zip"
+assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.2.19/build.zip"
-sha1 = "68f83438a114aabbe76bc9fe480071e741996662"
+sha1 = "7974430d5277c97f67cf6e95eec6faaac2788834"

crates/meilisearch/src/analytics/segment_analytics.rs

@@ -31,6 +31,7 @@ use crate::routes::{create_all_stats, Stats};
 use crate::Opt;
 
 const ANALYTICS_HEADER: &str = "X-Meilisearch-Client";
+const MEILI_SERVER_PROVIDER: &str = "MEILI_SERVER_PROVIDER";
 
 /// Write the instance-uid in the `data.ms` and in `~/.config/MeiliSearch/path-to-db-instance-uid`. Ignore the errors.
 fn write_user_id(db_path: &Path, user_id: &InstanceUid) {
@@ -195,6 +196,10 @@ struct Infos {
     experimental_reduce_indexing_memory_usage: bool,
     experimental_max_number_of_batched_tasks: usize,
     experimental_limit_batched_tasks_total_size: u64,
+    experimental_network: bool,
+    experimental_get_task_documents_route: bool,
+    experimental_composite_embedders: bool,
+    experimental_embedding_cache_entries: usize,
     gpu_enabled: bool,
     db_path: bool,
     import_dump: bool,
@@ -242,6 +247,7 @@ impl Infos {
             experimental_reduce_indexing_memory_usage,
             experimental_max_number_of_batched_tasks,
             experimental_limit_batched_tasks_total_size,
+            experimental_embedding_cache_entries,
             http_addr,
             master_key: _,
             env,
@@ -285,6 +291,9 @@ impl Infos {
             logs_route,
             edit_documents_by_function,
             contains_filter,
+            network,
+            get_task_documents_route,
+            composite_embedders,
         } = features;
 
         // We're going to override every sensible information.
@@ -302,6 +311,10 @@ impl Infos {
             experimental_replication_parameters,
             experimental_enable_logs_route: experimental_enable_logs_route | logs_route,
             experimental_reduce_indexing_memory_usage,
+            experimental_network: network,
+            experimental_get_task_documents_route: get_task_documents_route,
+            experimental_composite_embedders: composite_embedders,
+            experimental_embedding_cache_entries,
             gpu_enabled: meilisearch_types::milli::vector::is_cuda_enabled(),
             db_path: db_path != PathBuf::from("./data.ms"),
             import_dump: import_dump.is_some(),
@@ -316,7 +329,8 @@ impl Infos {
             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:
+                experimental_limit_batched_tasks_total_size.into(),
             task_queue_webhook: task_webhook_url.is_some(),
             task_webhook_authorization_header: task_webhook_authorization_header.is_some(),
             log_level: log_level.to_string(),
@@ -357,7 +371,7 @@ impl Segment {
                     "cores": sys.cpus().len(),
                     "ram_size": sys.total_memory(),
                     "disk_size": disks.iter().map(|disk| disk.total_space()).max(),
-                    "server_provider": std::env::var("MEILI_SERVER_PROVIDER").ok(),
+                    "server_provider": std::env::var(MEILI_SERVER_PROVIDER).ok(),
             })
         });
         let number_of_documents =
@@ -380,10 +394,18 @@ impl Segment {
         index_scheduler: Arc<IndexScheduler>,
         auth_controller: Arc<AuthController>,
     ) {
-        const INTERVAL: Duration = Duration::from_secs(60 * 60); // one hour
+        let interval: Duration = match std::env::var(MEILI_SERVER_PROVIDER) {
-                                                                 // The first batch must be sent after one hour.
+            Ok(provider) if provider.starts_with("meili_cloud:") => {
+                Duration::from_secs(60 * 60) // one hour
+            }
+            _ => {
+                // We're an open source instance
+                Duration::from_secs(60 * 60 * 24) // one day
+            }
+        };
+
         let mut interval =
-            tokio::time::interval_at(tokio::time::Instant::now() + INTERVAL, INTERVAL);
+            tokio::time::interval_at(tokio::time::Instant::now() + interval, interval);
 
         loop {
             select! {

crates/meilisearch/src/lib.rs

@@ -32,18 +32,18 @@ use analytics::Analytics;
 use anyhow::bail;
 use error::PayloadError;
 use extractors::payload::PayloadConfig;
+use index_scheduler::versioning::Versioning;
 use index_scheduler::{IndexScheduler, IndexSchedulerOptions};
-use meilisearch_auth::AuthController;
+use meilisearch_auth::{open_auth_store_env, AuthController};
 use meilisearch_types::milli::constants::VERSION_MAJOR;
 use meilisearch_types::milli::documents::{DocumentsBatchBuilder, DocumentsBatchReader};
 use meilisearch_types::milli::update::{IndexDocumentsConfig, IndexDocumentsMethod};
 use meilisearch_types::settings::apply_settings_to_builder;
 use meilisearch_types::tasks::KindWithContent;
 use meilisearch_types::versioning::{
-    create_current_version_file, get_version, update_version_file_for_dumpless_upgrade,
+    create_current_version_file, get_version, VersionFileError, VERSION_MINOR, VERSION_PATCH,
-    VersionFileError, VERSION_MINOR, VERSION_PATCH,
 };
-use meilisearch_types::{compression, milli, VERSION_FILE_NAME};
+use meilisearch_types::{compression, heed, milli, VERSION_FILE_NAME};
 pub use option::Opt;
 use option::ScheduleSnapshot;
 use search_queue::SearchQueue;
@@ -228,11 +228,12 @@ pub fn setup_meilisearch(opt: &Opt) -> anyhow::Result<(Arc<IndexScheduler>, Arc<
         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,
+        batched_tasks_size_limit: opt.experimental_limit_batched_tasks_total_size.into(),
         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(),
         auto_upgrade: opt.experimental_dumpless_upgrade,
+        embedding_cache_cap: opt.experimental_embedding_cache_entries,
     };
     let bin_major: u32 = VERSION_MAJOR.parse().unwrap();
     let bin_minor: u32 = VERSION_MINOR.parse().unwrap();
@@ -335,9 +336,12 @@ fn open_or_create_database_unchecked(
 ) -> 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.
-    let auth_controller = AuthController::new(&opt.db_path, &opt.master_key);
+    std::fs::create_dir_all(&index_scheduler_opt.auth_path)?;
-    let index_scheduler_builder =
+    let auth_env = open_auth_store_env(&index_scheduler_opt.auth_path).unwrap();
-        || -> anyhow::Result<_> { Ok(IndexScheduler::new(index_scheduler_opt, version)?) };
+    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)?)
+    };
 
     match (
         index_scheduler_builder(),
@@ -356,14 +360,19 @@ fn open_or_create_database_unchecked(
 
 /// Ensures Meilisearch version is compatible with the database, returns an error in case of version mismatch.
 /// Returns the version that was contained in the version file
-fn check_version(opt: &Opt, binary_version: (u32, u32, u32)) -> anyhow::Result<(u32, u32, u32)> {
+fn check_version(
+    opt: &Opt,
+    index_scheduler_opt: &IndexSchedulerOptions,
+    binary_version: (u32, u32, u32),
+) -> anyhow::Result<(u32, u32, u32)> {
     let (bin_major, bin_minor, bin_patch) = binary_version;
     let (db_major, db_minor, db_patch) = get_version(&opt.db_path)?;
 
-    if db_major != bin_major || db_minor != bin_minor || db_patch > bin_patch {
+    if db_major != bin_major || db_minor != bin_minor || db_patch != bin_patch {
         if opt.experimental_dumpless_upgrade {
             update_version_file_for_dumpless_upgrade(
-                &opt.db_path,
+                opt,
+                index_scheduler_opt,
                 (db_major, db_minor, db_patch),
                 (bin_major, bin_minor, bin_patch),
             )?;
@@ -380,6 +389,58 @@ fn check_version(opt: &Opt, binary_version: (u32, u32, u32)) -> anyhow::Result<(
     Ok((db_major, db_minor, db_patch))
 }
 
+/// Persists the version of the current Meilisearch binary to a VERSION file
+pub fn update_version_file_for_dumpless_upgrade(
+    opt: &Opt,
+    index_scheduler_opt: &IndexSchedulerOptions,
+    from: (u32, u32, u32),
+    to: (u32, u32, u32),
+) -> Result<(), VersionFileError> {
+    let (from_major, from_minor, from_patch) = from;
+    let (to_major, to_minor, to_patch) = to;
+
+    // Early exit in case of error
+    if from_major > to_major
+        || (from_major == to_major && from_minor > to_minor)
+        || (from_major == to_major && from_minor == to_minor && from_patch > to_patch)
+    {
+        return Err(VersionFileError::DowngradeNotSupported {
+            major: from_major,
+            minor: from_minor,
+            patch: from_patch,
+        });
+    } else if from_major < 1 || (from_major == to_major && from_minor < 12) {
+        return Err(VersionFileError::TooOldForAutomaticUpgrade {
+            major: from_major,
+            minor: from_minor,
+            patch: from_patch,
+        });
+    }
+
+    // In the case of v1.12, the index-scheduler didn't store its internal version at the time.
+    // => We must write it immediately **in the index-scheduler** otherwise we'll update the version file
+    //    there is a risk of DB corruption if a restart happens after writing the version file but before
+    //    writing the version in the index-scheduler. See <https://github.com/meilisearch/meilisearch/issues/5280>
+    if from_major == 1 && from_minor == 12 {
+        let env = unsafe {
+            heed::EnvOpenOptions::new()
+                .read_txn_without_tls()
+                .max_dbs(Versioning::nb_db())
+                .map_size(index_scheduler_opt.task_db_size)
+                .open(&index_scheduler_opt.tasks_path)
+        }?;
+        let mut wtxn = env.write_txn()?;
+        let versioning = Versioning::raw_new(&env, &mut wtxn)?;
+        versioning.set_version(&mut wtxn, (from_major, from_minor, from_patch))?;
+        wtxn.commit()?;
+        // Should be instant since we're the only one using the env
+        env.prepare_for_closing().wait();
+    }
+
+    create_current_version_file(&opt.db_path)?;
+    Ok(())
+}
+
 /// Ensure you're in a valid state and open the IndexScheduler + AuthController for you.
 fn open_or_create_database(
     opt: &Opt,
@@ -387,7 +448,11 @@ fn open_or_create_database(
     empty_db: bool,
     binary_version: (u32, u32, u32),
 ) -> anyhow::Result<(IndexScheduler, AuthController)> {
-    let version = if !empty_db { check_version(opt, binary_version)? } else { binary_version };
+    let version = if !empty_db {
+        check_version(opt, &index_scheduler_opt, binary_version)?
+    } else {
+        binary_version
+    };
 
     open_or_create_database_unchecked(opt, index_scheduler_opt, OnFailure::KeepDb, version)
 }
@@ -431,10 +496,13 @@ fn import_dump(
         keys.push(key);
     }
 
-    // 3. Import the runtime features.
+    // 3. Import the runtime features and network
     let features = dump_reader.features()?.unwrap_or_default();
     index_scheduler.put_runtime_features(features)?;
 
+    let network = dump_reader.network()?.cloned().unwrap_or_default();
+    index_scheduler.put_network(network)?;
+
     let indexer_config = index_scheduler.indexer_config();
 
     // /!\ The tasks must be imported AFTER importing the indexes or else the scheduler might
@@ -508,9 +576,15 @@ fn import_dump(
         index_scheduler.refresh_index_stats(&uid)?;
     }
 
+    // 5. Import the queue
     let mut index_scheduler_dump = index_scheduler.register_dumped_task()?;
+    // 5.1. Import the batches
+    for ret in dump_reader.batches()? {
+        let batch = ret?;
+        index_scheduler_dump.register_dumped_batch(batch)?;
+    }
 
-    // 5. Import the tasks.
+    // 5.2. Import the tasks
     for ret in dump_reader.tasks()? {
         let (task, file) = ret?;
         index_scheduler_dump.register_dumped_task(task, file)?;

crates/meilisearch/src/option.rs

@@ -63,7 +63,8 @@ const MEILI_EXPERIMENTAL_MAX_NUMBER_OF_BATCHED_TASKS: &str =
     "MEILI_EXPERIMENTAL_MAX_NUMBER_OF_BATCHED_TASKS";
 const MEILI_EXPERIMENTAL_LIMIT_BATCHED_TASKS_TOTAL_SIZE: &str =
     "MEILI_EXPERIMENTAL_LIMIT_BATCHED_TASKS_SIZE";
-
+const MEILI_EXPERIMENTAL_EMBEDDING_CACHE_ENTRIES: &str =
+    "MEILI_EXPERIMENTAL_EMBEDDING_CACHE_ENTRIES";
 const DEFAULT_CONFIG_FILE_PATH: &str = "./config.toml";
 const DEFAULT_DB_PATH: &str = "./data.ms";
 const DEFAULT_HTTP_ADDR: &str = "localhost:7700";
@@ -444,7 +445,15 @@ pub struct Opt {
     /// 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: u64,
+    pub experimental_limit_batched_tasks_total_size: Byte,
+
+    /// Enables experimental caching of search query embeddings. The value represents the maximal number of entries in the cache of each
+    /// distinct embedder.
+    ///
+    /// For more information, see <https://github.com/orgs/meilisearch/discussions/818>.
+    #[clap(long, env = MEILI_EXPERIMENTAL_EMBEDDING_CACHE_ENTRIES, default_value_t = default_embedding_cache_entries())]
+    #[serde(default = "default_embedding_cache_entries")]
+    pub experimental_embedding_cache_entries: usize,
 
     #[serde(flatten)]
     #[clap(flatten)]
@@ -549,6 +558,7 @@ impl Opt {
             experimental_reduce_indexing_memory_usage,
             experimental_max_number_of_batched_tasks,
             experimental_limit_batched_tasks_total_size,
+            experimental_embedding_cache_entries,
         } = self;
         export_to_env_if_not_present(MEILI_DB_PATH, db_path);
         export_to_env_if_not_present(MEILI_HTTP_ADDR, http_addr);
@@ -641,6 +651,10 @@ impl Opt {
             MEILI_EXPERIMENTAL_LIMIT_BATCHED_TASKS_TOTAL_SIZE,
             experimental_limit_batched_tasks_total_size.to_string(),
         );
+        export_to_env_if_not_present(
+            MEILI_EXPERIMENTAL_EMBEDDING_CACHE_ENTRIES,
+            experimental_embedding_cache_entries.to_string(),
+        );
         indexer_options.export_to_env();
     }
 
@@ -944,8 +958,12 @@ fn default_limit_batched_tasks() -> usize {
     usize::MAX
 }
 
-fn default_limit_batched_tasks_total_size() -> u64 {
+fn default_limit_batched_tasks_total_size() -> Byte {
-    u64::MAX
+    Byte::from_u64(u64::MAX)
+}
+
+fn default_embedding_cache_entries() -> usize {
+    0
 }
 
 fn default_snapshot_dir() -> PathBuf {

crates/meilisearch/src/routes/features.rs

@@ -50,6 +50,9 @@ pub fn configure(cfg: &mut web::ServiceConfig) {
             logs_route: Some(false),
             edit_documents_by_function: Some(false),
             contains_filter: Some(false),
+            network: Some(false),
+            get_task_documents_route: Some(false),
+            composite_embedders: Some(false),
         })),
         (status = 401, description = "The authorization header is missing", body = ResponseError, content_type = "application/json", example = json!(
             {
@@ -88,6 +91,12 @@ pub struct RuntimeTogglableFeatures {
     pub edit_documents_by_function: Option<bool>,
     #[deserr(default)]
     pub contains_filter: Option<bool>,
+    #[deserr(default)]
+    pub network: Option<bool>,
+    #[deserr(default)]
+    pub get_task_documents_route: Option<bool>,
+    #[deserr(default)]
+    pub composite_embedders: Option<bool>,
 }
 
 impl From<meilisearch_types::features::RuntimeTogglableFeatures> for RuntimeTogglableFeatures {
@@ -97,6 +106,9 @@ impl From<meilisearch_types::features::RuntimeTogglableFeatures> for RuntimeTogg
             logs_route,
             edit_documents_by_function,
             contains_filter,
+            network,
+            get_task_documents_route,
+            composite_embedders,
         } = value;
 
         Self {
@@ -104,6 +116,9 @@ impl From<meilisearch_types::features::RuntimeTogglableFeatures> for RuntimeTogg
             logs_route: Some(logs_route),
             edit_documents_by_function: Some(edit_documents_by_function),
             contains_filter: Some(contains_filter),
+            network: Some(network),
+            get_task_documents_route: Some(get_task_documents_route),
+            composite_embedders: Some(composite_embedders),
         }
     }
 }
@@ -114,6 +129,9 @@ pub struct PatchExperimentalFeatureAnalytics {
     logs_route: bool,
     edit_documents_by_function: bool,
     contains_filter: bool,
+    network: bool,
+    get_task_documents_route: bool,
+    composite_embedders: bool,
 }
 
 impl Aggregate for PatchExperimentalFeatureAnalytics {
@@ -127,6 +145,9 @@ impl Aggregate for PatchExperimentalFeatureAnalytics {
             logs_route: new.logs_route,
             edit_documents_by_function: new.edit_documents_by_function,
             contains_filter: new.contains_filter,
+            network: new.network,
+            get_task_documents_route: new.get_task_documents_route,
+            composite_embedders: new.composite_embedders,
         })
     }
 
@@ -149,6 +170,9 @@ impl Aggregate for PatchExperimentalFeatureAnalytics {
             logs_route: Some(false),
             edit_documents_by_function: Some(false),
             contains_filter: Some(false),
+            network: Some(false),
+            get_task_documents_route: Some(false),
+            composite_embedders: Some(false),
          })),
         (status = 401, description = "The authorization header is missing", body = ResponseError, content_type = "application/json", example = json!(
             {
@@ -181,16 +205,28 @@ async fn patch_features(
             .edit_documents_by_function
             .unwrap_or(old_features.edit_documents_by_function),
         contains_filter: new_features.0.contains_filter.unwrap_or(old_features.contains_filter),
+        network: new_features.0.network.unwrap_or(old_features.network),
+        get_task_documents_route: new_features
+            .0
+            .get_task_documents_route
+            .unwrap_or(old_features.get_task_documents_route),
+        composite_embedders: new_features
+            .0
+            .composite_embedders
+            .unwrap_or(old_features.composite_embedders),
     };
 
     // explicitly destructure for analytics rather than using the `Serialize` implementation, because
-    // the it renames to camelCase, which we don't want for analytics.
+    // it renames to camelCase, which we don't want for analytics.
     // **Do not** ignore fields with `..` or `_` here, because we want to add them in the future.
     let meilisearch_types::features::RuntimeTogglableFeatures {
         metrics,
         logs_route,
         edit_documents_by_function,
         contains_filter,
+        network,
+        get_task_documents_route,
+        composite_embedders,
     } = new_features;
 
     analytics.publish(
@@ -199,6 +235,9 @@ async fn patch_features(
             logs_route,
             edit_documents_by_function,
             contains_filter,
+            network,
+            get_task_documents_route,
+            composite_embedders,
         },
         &req,
     );

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

@@ -20,11 +20,13 @@ use meilisearch_types::index_uid::IndexUid;
 use meilisearch_types::milli::update::IndexDocumentsMethod;
 use meilisearch_types::milli::vector::parsed_vectors::ExplicitVectors;
 use meilisearch_types::milli::DocumentId;
+use meilisearch_types::serde_cs::vec::CS;
 use meilisearch_types::star_or::OptionStarOrList;
 use meilisearch_types::tasks::KindWithContent;
 use meilisearch_types::{milli, Document, Index};
 use mime::Mime;
 use once_cell::sync::Lazy;
+use roaring::RoaringBitmap;
 use serde::{Deserialize, Serialize};
 use serde_json::Value;
 use tempfile::tempfile;
@@ -43,7 +45,7 @@ use crate::extractors::sequential_extractor::SeqHandler;
 use crate::routes::{
     get_task_id, is_dry_run, PaginationView, SummarizedTaskView, PAGINATION_DEFAULT_LIMIT,
 };
-use crate::search::{parse_filter, RetrieveVectors};
+use crate::search::{parse_filter, ExternalDocumentId, RetrieveVectors};
 use crate::{aggregate_methods, Opt};
 
 static ACCEPTED_CONTENT_TYPE: Lazy<Vec<String>> = Lazy::new(|| {
@@ -137,6 +139,9 @@ pub struct DocumentsFetchAggregator<Method: AggregateMethod> {
     #[serde(rename = "vector.retrieve_vectors")]
     retrieve_vectors: bool,
 
+    // maximum size of `ids` array. 0 if always empty or `null`
+    max_document_ids: usize,
+
     // pagination
     #[serde(rename = "pagination.max_limit")]
     max_limit: usize,
@@ -149,7 +154,7 @@ pub struct DocumentsFetchAggregator<Method: AggregateMethod> {
 #[derive(Copy, Clone, Debug, PartialEq, Eq)]
 pub enum DocumentFetchKind {
     PerDocumentId { retrieve_vectors: bool },
-    Normal { with_filter: bool, limit: usize, offset: usize, retrieve_vectors: bool },
+    Normal { with_filter: bool, limit: usize, offset: usize, retrieve_vectors: bool, ids: usize },
 }
 
 impl<Method: AggregateMethod> DocumentsFetchAggregator<Method> {
@@ -161,12 +166,18 @@ impl<Method: AggregateMethod> DocumentsFetchAggregator<Method> {
             }
         };
 
+        let ids = match query {
+            DocumentFetchKind::Normal { ids, .. } => *ids,
+            DocumentFetchKind::PerDocumentId { .. } => 0,
+        };
+
         Self {
             per_document_id: matches!(query, DocumentFetchKind::PerDocumentId { .. }),
             per_filter: matches!(query, DocumentFetchKind::Normal { with_filter, .. } if *with_filter),
             max_limit: limit,
             max_offset: offset,
             retrieve_vectors,
+            max_document_ids: ids,
 
             marker: PhantomData,
         }
@@ -185,6 +196,7 @@ impl<Method: AggregateMethod> Aggregate for DocumentsFetchAggregator<Method> {
             retrieve_vectors: self.retrieve_vectors | new.retrieve_vectors,
             max_limit: self.max_limit.max(new.max_limit),
             max_offset: self.max_offset.max(new.max_offset),
+            max_document_ids: self.max_document_ids.max(new.max_document_ids),
             marker: PhantomData,
         })
     }
@@ -266,6 +278,7 @@ pub async fn get_document(
             per_filter: false,
             max_limit: 0,
             max_offset: 0,
+            max_document_ids: 0,
             marker: PhantomData,
         },
         &req,
@@ -387,6 +400,9 @@ pub struct BrowseQueryGet {
     #[param(default, value_type = Option<bool>)]
     #[deserr(default, error = DeserrQueryParamError<InvalidDocumentRetrieveVectors>)]
     retrieve_vectors: Param<bool>,
+    #[param(default, value_type = Option<Vec<String>>)]
+    #[deserr(default, error = DeserrQueryParamError<InvalidDocumentIds>)]
+    ids: Option<CS<String>>,
     #[param(default, value_type = Option<String>, example = "popularity > 1000")]
     #[deserr(default, error = DeserrQueryParamError<InvalidDocumentFilter>)]
     filter: Option<String>,
@@ -408,6 +424,9 @@ pub struct BrowseQuery {
     #[schema(default, example = true)]
     #[deserr(default, error = DeserrJsonError<InvalidDocumentRetrieveVectors>)]
     retrieve_vectors: bool,
+    #[schema(value_type = Option<Vec<String>>, example = json!(["cody", "finn", "brandy", "gambit"]))]
+    #[deserr(default, error = DeserrJsonError<InvalidDocumentIds>)]
+    ids: Option<Vec<serde_json::Value>>,
     #[schema(default, value_type = Option<Value>, example = "popularity > 1000")]
     #[deserr(default, error = DeserrJsonError<InvalidDocumentFilter>)]
     filter: Option<Value>,
@@ -479,6 +498,7 @@ pub async fn documents_by_query_post(
             retrieve_vectors: body.retrieve_vectors,
             max_limit: body.limit,
             max_offset: body.offset,
+            max_document_ids: body.ids.as_ref().map(Vec::len).unwrap_or_default(),
             per_document_id: false,
             marker: PhantomData,
         },
@@ -551,7 +571,8 @@ pub async fn get_documents(
 ) -> Result<HttpResponse, ResponseError> {
     debug!(parameters = ?params, "Get documents GET");
 
-    let BrowseQueryGet { limit, offset, fields, retrieve_vectors, filter } = params.into_inner();
+    let BrowseQueryGet { limit, offset, fields, retrieve_vectors, filter, ids } =
+        params.into_inner();
 
     let filter = match filter {
         Some(f) => match serde_json::from_str(&f) {
@@ -561,12 +582,15 @@ pub async fn get_documents(
         None => None,
     };
 
+    let ids = ids.map(|ids| ids.into_iter().map(Into::into).collect());
+
     let query = BrowseQuery {
         offset: offset.0,
         limit: limit.0,
         fields: fields.merge_star_and_none(),
         retrieve_vectors: retrieve_vectors.0,
         filter,
+        ids,
     };
 
     analytics.publish(
@@ -575,6 +599,7 @@ pub async fn get_documents(
             retrieve_vectors: query.retrieve_vectors,
             max_limit: query.limit,
             max_offset: query.offset,
+            max_document_ids: query.ids.as_ref().map(Vec::len).unwrap_or_default(),
             per_document_id: false,
             marker: PhantomData,
         },
@@ -590,15 +615,30 @@ fn documents_by_query(
     query: BrowseQuery,
 ) -> Result<HttpResponse, ResponseError> {
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
-    let BrowseQuery { offset, limit, fields, retrieve_vectors, filter } = query;
+    let BrowseQuery { offset, limit, fields, retrieve_vectors, filter, ids } = query;
 
     let retrieve_vectors = RetrieveVectors::new(retrieve_vectors);
 
+    let ids = if let Some(ids) = ids {
+        let mut parsed_ids = Vec::with_capacity(ids.len());
+        for (index, id) in ids.into_iter().enumerate() {
+            let id = id.try_into().map_err(|error| {
+                let msg = format!("In `.ids[{index}]`: {error}");
+                ResponseError::from_msg(msg, Code::InvalidDocumentIds)
+            })?;
+            parsed_ids.push(id)
+        }
+        Some(parsed_ids)
+    } else {
+        None
+    };
+
     let index = index_scheduler.index(&index_uid)?;
     let (total, documents) = retrieve_documents(
         &index,
         offset,
         limit,
+        ids,
         filter,
         fields,
         retrieve_vectors,
@@ -1451,10 +1491,12 @@ fn some_documents<'a, 't: 'a>(
     }))
 }
 
+#[allow(clippy::too_many_arguments)]
 fn retrieve_documents<S: AsRef<str>>(
     index: &Index,
     offset: usize,
     limit: usize,
+    ids: Option<Vec<ExternalDocumentId>>,
     filter: Option<Value>,
     attributes_to_retrieve: Option<Vec<S>>,
     retrieve_vectors: RetrieveVectors,
@@ -1468,16 +1510,28 @@ fn retrieve_documents<S: AsRef<str>>(
         None
     };
 
-    let candidates = if let Some(filter) = filter {
+    let mut candidates = if let Some(ids) = ids {
-        filter.evaluate(&rtxn, index).map_err(|err| match err {
+        let external_document_ids = index.external_documents_ids();
+        let mut candidates = RoaringBitmap::new();
+        for id in ids.iter() {
+            let Some(docid) = external_document_ids.get(&rtxn, id)? else {
+                continue;
+            };
+            candidates.insert(docid);
+        }
+        candidates
+    } else {
+        index.documents_ids(&rtxn)?
+    };
+
+    if let Some(filter) = filter {
+        candidates &= filter.evaluate(&rtxn, index).map_err(|err| match err {
             milli::Error::UserError(milli::UserError::InvalidFilter(_)) => {
                 ResponseError::from_msg(err.to_string(), Code::InvalidDocumentFilter)
             }
             e => e.into(),
         })?
-    } else {
+    }
-        index.documents_ids(&rtxn)?
-    };
 
     let (it, number_of_documents) = {
         let number_of_documents = candidates.len();

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

@@ -68,6 +68,8 @@ pub struct FacetSearchQuery {
     pub ranking_score_threshold: Option<RankingScoreThreshold>,
     #[deserr(default, error = DeserrJsonError<InvalidSearchLocales>, default)]
     pub locales: Option<Vec<Locale>>,
+    #[deserr(default, error = DeserrJsonError<InvalidFacetSearchExhaustiveFacetCount>, default)]
+    pub exhaustive_facet_count: Option<bool>,
 }
 
 #[derive(Default)]
@@ -98,6 +100,7 @@ impl FacetSearchAggregator {
             hybrid,
             ranking_score_threshold,
             locales,
+            exhaustive_facet_count,
         } = query;
 
         Self {
@@ -110,7 +113,8 @@ impl FacetSearchAggregator {
                 || attributes_to_search_on.is_some()
                 || hybrid.is_some()
                 || ranking_score_threshold.is_some()
-                || locales.is_some(),
+                || locales.is_some()
+                || exhaustive_facet_count.is_some(),
             ..Default::default()
         }
     }
@@ -293,13 +297,24 @@ impl From<FacetSearchQuery> for SearchQuery {
             hybrid,
             ranking_score_threshold,
             locales,
+            exhaustive_facet_count,
         } = value;
 
+        // If exhaustive_facet_count is true, we need to set the page to 0
+        // because the facet search is not exhaustive by default.
+        let page = if exhaustive_facet_count.map_or(false, |exhaustive| exhaustive) {
+            // setting the page to 0 will force the search to be exhaustive when computing the number of hits,
+            // but it will skip the bucket sort saving time.
+            Some(0)
+        } else {
+            None
+        };
+
         SearchQuery {
             q,
             offset: DEFAULT_SEARCH_OFFSET(),
             limit: DEFAULT_SEARCH_LIMIT(),
-            page: None,
+            page,
             hits_per_page: None,
             attributes_to_retrieve: None,
             retrieve_vectors: false,

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

@@ -494,8 +494,18 @@ pub async fn delete_index(
 pub struct IndexStats {
     /// Number of documents in the index
     pub number_of_documents: u64,
+    /// Size of the documents database, in bytes.
+    pub raw_document_db_size: u64,
+    /// Average size of a document in the documents database.
+    pub avg_document_size: u64,
     /// Whether or not the index is currently ingesting document
     pub is_indexing: bool,
+    /// Number of embeddings in the index
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub number_of_embeddings: Option<u64>,
+    /// Number of embedded documents in the index
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub number_of_embedded_documents: Option<u64>,
     /// Association of every field name with the number of times it occurs in the documents.
     #[schema(value_type = HashMap<String, u64>)]
     pub field_distribution: FieldDistribution,
@@ -504,8 +514,15 @@ pub struct IndexStats {
 impl From<index_scheduler::IndexStats> for IndexStats {
     fn from(stats: index_scheduler::IndexStats) -> Self {
         IndexStats {
-            number_of_documents: stats.inner_stats.number_of_documents,
+            number_of_documents: stats
+                .inner_stats
+                .number_of_documents
+                .unwrap_or(stats.inner_stats.documents_database_stats.number_of_entries()),
+            raw_document_db_size: stats.inner_stats.documents_database_stats.total_size(),
+            avg_document_size: stats.inner_stats.documents_database_stats.average_value_size(),
             is_indexing: stats.is_indexing,
+            number_of_embeddings: stats.inner_stats.number_of_embeddings,
+            number_of_embedded_documents: stats.inner_stats.number_of_embedded_documents,
             field_distribution: stats.inner_stats.field_distribution,
         }
     }
@@ -524,6 +541,10 @@ impl From<index_scheduler::IndexStats> for IndexStats {
         (status = OK, description = "The stats of the index", body = IndexStats, content_type = "application/json", example = json!(
             {
                 "numberOfDocuments": 10,
+                "rawDocumentDbSize": 10,
+                "avgDocumentSize": 10,
+                "numberOfEmbeddings": 10,
+                "numberOfEmbeddedDocuments": 10,
                 "isIndexing": true,
                 "fieldDistribution": {
                     "genre": 10,

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

@@ -291,7 +291,7 @@ make_setting_routes!(
     {
         route: "/filterable-attributes",
         update_verb: put,
-        value_type: std::collections::BTreeSet<String>,
+        value_type: Vec<meilisearch_types::milli::FilterableAttributesRule>,
         err_type: meilisearch_types::deserr::DeserrJsonError<
             meilisearch_types::error::deserr_codes::InvalidSettingsFilterableAttributes,
         >,
@@ -716,7 +716,30 @@ pub async fn delete_all(
 
 fn validate_settings(
     settings: Settings<Unchecked>,
-    _index_scheduler: &IndexScheduler,
+    index_scheduler: &IndexScheduler,
 ) -> Result<Settings<Unchecked>, ResponseError> {
+    use meilisearch_types::milli::update::Setting;
+    use meilisearch_types::milli::vector::settings::EmbedderSource;
+
+    let features = index_scheduler.features();
+    if let Setting::Set(embedders) = &settings.embedders {
+        for SettingEmbeddingSettings { inner: embedder } in embedders.values() {
+            let Setting::Set(embedder) = embedder else {
+                continue;
+            };
+            if matches!(embedder.source, Setting::Set(EmbedderSource::Composite)) {
+                features.check_composite_embedders("using `\"composite\"` as source")?;
+            }
+
+            if matches!(embedder.search_embedder, Setting::Set(_)) {
+                features.check_composite_embedders("setting `searchEmbedder`")?;
+            }
+
+            if matches!(embedder.indexing_embedder, Setting::Set(_)) {
+                features.check_composite_embedders("setting `indexingEmbedder`")?;
+            }
+        }
+    }
+
     Ok(settings.validate()?)
 }

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

@@ -8,6 +8,7 @@ use std::collections::{BTreeMap, BTreeSet, HashSet};
 use meilisearch_types::facet_values_sort::FacetValuesSort;
 use meilisearch_types::locales::{Locale, LocalizedAttributesRuleView};
 use meilisearch_types::milli::update::Setting;
+use meilisearch_types::milli::FilterableAttributesRule;
 use meilisearch_types::settings::{
     FacetingSettings, PaginationSettings, PrefixSearchSettings, ProximityPrecisionView,
     RankingRuleView, SettingEmbeddingSettings, TypoSettings,
@@ -89,6 +90,10 @@ impl Aggregate for SettingsAnalytics {
             filterable_attributes: FilterableAttributesAnalytics {
                 total: new.filterable_attributes.total.or(self.filterable_attributes.total),
                 has_geo: new.filterable_attributes.has_geo.or(self.filterable_attributes.has_geo),
+                has_patterns: new
+                    .filterable_attributes
+                    .has_patterns
+                    .or(self.filterable_attributes.has_patterns),
             },
             distinct_attribute: DistinctAttributeAnalytics {
                 set: self.distinct_attribute.set | new.distinct_attribute.set,
@@ -328,13 +333,19 @@ impl SortableAttributesAnalytics {
 pub struct FilterableAttributesAnalytics {
     pub total: Option<usize>,
     pub has_geo: Option<bool>,
+    pub has_patterns: Option<bool>,
 }
 
 impl FilterableAttributesAnalytics {
-    pub fn new(setting: Option<&BTreeSet<String>>) -> Self {
+    pub fn new(setting: Option<&Vec<FilterableAttributesRule>>) -> Self {
         Self {
             total: setting.as_ref().map(|filter| filter.len()),
-            has_geo: setting.as_ref().map(|filter| filter.contains("_geo")),
+            has_geo: setting
+                .as_ref()
+                .map(|filter| filter.iter().any(FilterableAttributesRule::has_geo)),
+            has_patterns: setting.as_ref().map(|filter| {
+                filter.iter().any(|rule| matches!(rule, FilterableAttributesRule::Pattern(_)))
+            }),
         }
     }
 
@@ -512,6 +523,7 @@ impl EmbeddersAnalytics {
                     EmbedderSource::UserProvided => sources.insert("userProvided".to_string()),
                     EmbedderSource::Ollama => sources.insert("ollama".to_string()),
                     EmbedderSource::Rest => sources.insert("rest".to_string()),
+                    EmbedderSource::Composite => sources.insert("composite".to_string()),
                 };
             }
         };

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

@@ -5,7 +5,7 @@ use index_scheduler::IndexScheduler;
 use meilisearch_types::deserr::query_params::Param;
 use meilisearch_types::deserr::{DeserrJsonError, DeserrQueryParamError};
 use meilisearch_types::error::deserr_codes::*;
-use meilisearch_types::error::{ErrorCode as _, ResponseError};
+use meilisearch_types::error::ResponseError;
 use meilisearch_types::index_uid::IndexUid;
 use meilisearch_types::keys::actions;
 use meilisearch_types::serde_cs::vec::CS;
@@ -111,7 +111,7 @@ pub async fn similar_get(
 ) -> Result<HttpResponse, ResponseError> {
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
 
-    let query = params.0.try_into()?;
+    let query = params.0.into();
 
     let mut aggregate = SimilarAggregator::<SimilarGET>::from_query(&query);
 
@@ -295,10 +295,8 @@ impl std::convert::TryFrom<String> for RankingScoreThresholdGet {
     }
 }
 
-impl TryFrom<SimilarQueryGet> for SimilarQuery {
+impl From<SimilarQueryGet> for SimilarQuery {
-    type Error = ResponseError;
+    fn from(
-
-    fn try_from(
         SimilarQueryGet {
             id,
             offset,
@@ -311,7 +309,7 @@ impl TryFrom<SimilarQueryGet> for SimilarQuery {
             embedder,
             ranking_score_threshold,
         }: SimilarQueryGet,
-    ) -> Result<Self, Self::Error> {
+    ) -> Self {
         let filter = match filter {
             Some(f) => match serde_json::from_str(&f) {
                 Ok(v) => Some(v),
@@ -320,10 +318,8 @@ impl TryFrom<SimilarQueryGet> for SimilarQuery {
             None => None,
         };
 
-        Ok(SimilarQuery {
+        SimilarQuery {
-            id: id.0.try_into().map_err(|code: InvalidSimilarId| {
+            id: serde_json::Value::String(id.0),
-                ResponseError::from_msg(code.to_string(), code.error_code())
-            })?,
             offset: offset.0,
             limit: limit.0,
             filter,
@@ -333,6 +329,6 @@ impl TryFrom<SimilarQueryGet> for SimilarQuery {
             show_ranking_score: show_ranking_score.0,
             show_ranking_score_details: show_ranking_score_details.0,
             ranking_score_threshold: ranking_score_threshold.map(|x| x.0),
-        })
+        }
     }
 }

crates/meilisearch/src/routes/mod.rs

@@ -9,6 +9,10 @@ use meilisearch_types::batches::BatchStats;
 use meilisearch_types::error::{Code, ErrorType, ResponseError};
 use meilisearch_types::index_uid::IndexUid;
 use meilisearch_types::keys::CreateApiKey;
+use meilisearch_types::milli::{
+    AttributePatterns, FilterFeatures, FilterableAttributesFeatures, FilterableAttributesPatterns,
+    FilterableAttributesRule,
+};
 use meilisearch_types::settings::{
     Checked, FacetingSettings, MinWordSizeTyposSetting, PaginationSettings, Settings, TypoSettings,
     Unchecked,
@@ -34,6 +38,7 @@ use crate::routes::features::RuntimeTogglableFeatures;
 use crate::routes::indexes::documents::{DocumentDeletionByFilter, DocumentEditionByFunction};
 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::search::{
     FederatedSearch, FederatedSearchResult, Federation, FederationOptions, MergeFacets,
@@ -54,6 +59,7 @@ mod logs;
 mod metrics;
 mod multi_search;
 mod multi_search_analytics;
+pub mod network;
 mod open_api_utils;
 mod snapshot;
 mod swap_indexes;
@@ -75,6 +81,7 @@ pub mod tasks;
         (path = "/multi-search", api = multi_search::MultiSearchApi),
         (path = "/swap-indexes", api = swap_indexes::SwapIndexesApi),
         (path = "/experimental-features", api = features::ExperimentalFeaturesApi),
+        (path = "/network", api = network::NetworkApi),
     ),
     paths(get_health, get_version, get_stats),
     tags(
@@ -85,7 +92,7 @@ pub mod tasks;
         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))
+    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))
 )]
 pub struct MeilisearchApi;
 
@@ -103,7 +110,8 @@ pub fn configure(cfg: &mut web::ServiceConfig) {
         .service(web::scope("/multi-search").configure(multi_search::configure))
         .service(web::scope("/swap-indexes").configure(swap_indexes::configure))
         .service(web::scope("/metrics").configure(metrics::configure))
-        .service(web::scope("/experimental-features").configure(features::configure));
+        .service(web::scope("/experimental-features").configure(features::configure))
+        .service(web::scope("/network").configure(network::configure));
 
     #[cfg(feature = "swagger")]
     {
@@ -359,9 +367,9 @@ pub async fn running() -> HttpResponse {
 #[derive(Serialize, Debug, ToSchema)]
 #[serde(rename_all = "camelCase")]
 pub struct Stats {
-    /// The size of the database, in bytes.
+    /// The disk space used by the database, in bytes.
     pub database_size: u64,
-    #[serde(skip)]
+    /// The size of the database, in bytes.
     pub used_database_size: u64,
     /// The date of the last update in the RFC 3339 formats. Can be `null` if no update has ever been processed.
     #[serde(serialize_with = "time::serde::rfc3339::option::serialize")]
@@ -383,10 +391,14 @@ pub struct Stats {
         (status = 200, description = "The stats of the instance", body = Stats, content_type = "application/json", example = json!(
             {
                 "databaseSize": 567,
+                "usedDatabaseSize": 456,
                 "lastUpdate": "2019-11-20T09:40:33.711324Z",
                 "indexes": {
                     "movies": {
                         "numberOfDocuments": 10,
+                        "rawDocumentDbSize": 100,
+                        "maxDocumentSize": 16,
+                        "avgDocumentSize": 10,
                         "isIndexing": true,
                         "fieldDistribution": {
                             "genre": 10,