Add recommendation route

4548: v1.8 hybrid search changes r=dureuill a=dureuill

Implements the search changes from the [usage page](https://meilisearch.notion.site/v1-8-AI-search-API-usage-135552d6e85a4a52bc7109be82aeca42#40f24df3da694428a39cc8043c9cfc64)

### ⚠️ Breaking changes in an experimental feature:

- Removed the `_semanticScore`. Use the `_rankingScore` instead.
- Removed `vector` in the response of the search (output was too big).
- Removed all the vectors from the `vectorSort` ranking score details
  - target vector appearing in the name of the rule
  - matched vector appearing in the details of the rule

### Other user-facing changes

- Added `semanticHitCount`, indicating how many hits were returned from the semantic search. This is especially useful in the hybrid search.
- Embed lazily: Meilisearch no longer generates an embedding when the keyword results are "good enough".
- Graceful embedding failure in hybrid search: when doing hybrid search (`semanticRatio in ]0.0, 1.0[`), an embedding failure no longer causes the search request to fail. Instead, only the keyword search is performed. When doing a full vector search (`semanticRatio==1.0`), a failure to embed will still result in failing that search.

Co-authored-by: Louis Dureuil <louis@meilisearch.com>

.cargo/config.toml

@@ -0,0 +1,2 @@
+[alias]
+xtask = "run --release --package xtask --"

.github/ISSUE_TEMPLATE/sprint_issue.md

@@ -2,14 +2,13 @@
 name: New sprint issue
 about: ⚠️ Should only be used by the engine team ⚠️
 title: ''
-labels: ''
+labels: 'missing usage in PRD, impacts docs'
 assignees: ''
 
 ---
 
 Related product team resources: [PRD]() (_internal only_)
 Related product discussion:
-Related spec: WIP
 
 ## Motivation
 
@@ -21,12 +20,25 @@ Related spec: WIP
 
 ## TODO
 
-<!---Feel free to adapt this list with more technical/product steps-->
+<!---If necessary, create a list with technical/product steps-->
 
-- [ ] Release a prototype
-- [ ] If prototype validated, merge changes into `main`
-- [ ] Update the spec
+### Reminders when modifying the Setting API
+
+<!--- Special steps to remind when adding a new index setting -->
+
+- [ ] Ensure the new setting route is at least tested by the [`test_setting_routes` macro](https://github.com/meilisearch/meilisearch/blob/5204c0b60b384cbc79621b6b2176fca086069e8e/meilisearch/tests/settings/get_settings.rs#L276)
+- [ ] Ensure Analytics are fully implemented
+  - [ ] `/settings/my-new-setting` configurated in the [`make_setting_routes` macro](https://github.com/meilisearch/meilisearch/blob/5204c0b60b384cbc79621b6b2176fca086069e8e/meilisearch/src/routes/indexes/settings.rs#L141-L165)
+  - [ ] global `/settings` route configurated in the [`update_all` function](https://github.com/meilisearch/meilisearch/blob/5204c0b60b384cbc79621b6b2176fca086069e8e/meilisearch/src/routes/indexes/settings.rs#L655-L751)
+- [ ] Ensure the dump serializing is consistent with the `/settings` route serializing, e.g., enums case can be different (`camelCase` in route and `PascalCase` in the dump)
+
+#### Special cases when adding a setting for an experimental feature
+
+- [ ] ⚠️ API stability: The setting does not appear on the main settings route when the feature has never been enabled (e.g. mark it `Unset` when returned from the index in this situation. See [an example](https://github.com/meilisearch/meilisearch/blob/7a89abd2a025606a42f8b219e539117eb2eb029f/meilisearch-types/src/settings.rs#L608))
+- [ ] The setting cannot be set when the feature is disabled, either by the main settings route or the subroute (see [`validate_settings` function](https://github.com/meilisearch/meilisearch/blob/7a89abd2a025606a42f8b219e539117eb2eb029f/meilisearch/src/routes/indexes/settings.rs#L811))
+- [ ] If possible, the setting is reset when the feature is disabled (hard if it requires reindexing)
 
 ## Impacted teams
 
 <!---Ping the related teams. Ask for the engine manager if any hesitation-->
+<!---@meilisearch/docs-team when there is any API change, e.g. settings addition-->

.github/workflows/bench-manual.yml

@@ -0,0 +1,30 @@
+name: Bench (manual)
+
+on:
+    workflow_dispatch:
+        inputs:
+            workload:
+                description: 'The path to the workloads to execute (workloads/...)'
+                required: true
+                default: 'workloads/movies.json'
+
+env:
+    WORKLOAD_NAME: ${{ github.event.inputs.workload }}
+
+jobs:
+    benchmarks:
+        name: Run and upload benchmarks
+        runs-on: benchmarks
+        timeout-minutes: 180 # 3h
+        steps:
+            - uses: actions/checkout@v3
+            - uses: actions-rs/toolchain@v1
+              with:
+                profile: minimal
+                toolchain: stable
+                override: true
+
+            - name: Run benchmarks - workload ${WORKLOAD_NAME} - branch ${{ github.ref }} - commit ${{ github.sha }}
+              run: |
+               cargo xtask bench --api-key "${{ secrets.BENCHMARK_API_KEY }}" --dashboard-url "${{ vars.BENCHMARK_DASHBOARD_URL }}" --reason "Manual [Run #${{ github.run_id }}](https://github.com/meilisearch/meilisearch/actions/runs/${{ github.run_id }})" -- ${WORKLOAD_NAME}
+

.github/workflows/bench-pr.yml

@@ -0,0 +1,46 @@
+name: Bench (PR)
+on:
+    issue_comment:
+        types: [created]
+
+permissions:
+    issues: write
+
+env:
+    GH_TOKEN: ${{ secrets.MEILI_BOT_GH_PAT }}
+
+jobs:
+    run-benchmarks-on-comment:
+      if: startsWith(github.event.comment.body, '/bench')
+      name: Run and upload benchmarks
+      runs-on: benchmarks
+      timeout-minutes: 180 # 3h
+      steps:
+        - name: Check for Command
+          id: command
+          uses: xt0rted/slash-command-action@v2
+          with:
+              command: bench
+              reaction-type: "rocket"
+              repo-token: ${{ env.GH_TOKEN }}
+
+        - uses: xt0rted/pull-request-comment-branch@v2
+          id: comment-branch
+          with:
+            repo_token: ${{ env.GH_TOKEN }}
+
+        - uses: actions/checkout@v3
+          if: success()
+          with:
+            fetch-depth: 0 # fetch full history to be able to get main commit sha
+            ref: ${{ steps.comment-branch.outputs.head_ref }}
+
+        - uses: actions-rs/toolchain@v1
+          with:
+            profile: minimal
+            toolchain: stable
+            override: true
+
+        - name: Run benchmarks on PR ${{ github.event.issue.id }}
+          run: |
+            cargo xtask bench --api-key "${{ secrets.BENCHMARK_API_KEY }}" --dashboard-url "${{ vars.BENCHMARK_DASHBOARD_URL }}" --reason "[Comment](${{ github.event.comment.html_url }}) on [#${{ github.event.issue.number }}](${{ github.event.issue.html_url }})" -- ${{ steps.command.outputs.command-arguments }}

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

@@ -0,0 +1,25 @@
+name: Indexing bench (push)
+
+on:
+    push:
+        branches:
+            - main
+
+jobs:
+    benchmarks:
+        name: Run and upload benchmarks
+        runs-on: benchmarks
+        timeout-minutes: 180 # 3h
+        steps:
+          - uses: actions/checkout@v3
+          - uses: actions-rs/toolchain@v1
+            with:
+              profile: minimal
+              toolchain: stable
+              override: true
+
+          # Run benchmarks
+          - name: Run benchmarks - Dataset ${BENCH_NAME} - Branch main - Commit ${{ github.sha }}
+            run: |
+              cargo xtask bench --api-key "${{ secrets.BENCHMARK_API_KEY }}" --dashboard-url "${{ vars.BENCHMARK_DASHBOARD_URL }}" --reason "Push on `main` [Run #${{ github.run_id }}](https://github.com/meilisearch/meilisearch/actions/runs/${{ github.run_id }})" -- workloads/*.json
+

.github/workflows/benchmarks-pr.yml

@@ -90,7 +90,8 @@ jobs:
           set -x
           export base_ref=$(git merge-base origin/main ${{ steps.comment-branch.outputs.head_ref }} | head -c8)
           export base_filename=$(echo ${{ steps.command.outputs.command-arguments }}_main_${base_ref}.json)
-          echo 'Here are your benchmarks diff 👊' >> body.txt
+          export bench_name=$(echo ${{ steps.command.outputs.command-arguments }})
+          echo "Here are your $bench_name benchmarks diff 👊" >> body.txt
           echo '```' >> body.txt
           ./benchmarks/scripts/compare.sh $base_filename ${{ steps.file.outputs.basename }}.json >> body.txt
           echo '```' >> body.txt

.github/workflows/milestone-workflow.yml

@@ -110,6 +110,44 @@ jobs:
             --milestone $MILESTONE_VERSION \
             --assignee curquiza
 
+  create-update-version-issue:
+    needs: get-release-version
+    # Create the update-version issue even if the release is a patch release
+    if: github.event.action == 'created'
+    runs-on: ubuntu-latest
+    env:
+      ISSUE_TEMPLATE: issue-template.md
+    steps:
+      - uses: actions/checkout@v3
+      - name: Download the issue template
+        run: curl -s https://raw.githubusercontent.com/meilisearch/engine-team/main/issue-templates/update-version-issue.md > $ISSUE_TEMPLATE
+      - name: Create the issue
+        run: |
+          gh issue create \
+            --title "Update version in Cargo.toml for $MILESTONE_VERSION" \
+            --label 'maintenance' \
+            --body-file $ISSUE_TEMPLATE \
+            --milestone $MILESTONE_VERSION
+
+  create-update-openapi-issue:
+    needs: get-release-version
+    # Create the openAPI issue if the release is not only a patch release
+    if: github.event.action == 'created' && needs.get-release-version.outputs.is-patch == 'false'
+    runs-on: ubuntu-latest
+    env:
+      ISSUE_TEMPLATE: issue-template.md
+    steps:
+      - uses: actions/checkout@v3
+      - name: Download the issue template
+        run: curl -s https://raw.githubusercontent.com/meilisearch/engine-team/main/issue-templates/update-openapi-issue.md > $ISSUE_TEMPLATE
+      - name: Create the issue
+        run: |
+          gh issue create \
+            --title "Update Open API file for $MILESTONE_VERSION" \
+            --label 'maintenance' \
+            --body-file $ISSUE_TEMPLATE \
+            --milestone $MILESTONE_VERSION
+
 # ----------------
 # MILESTONE CLOSED
 # ----------------

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

@@ -97,7 +97,7 @@ jobs:
       - name: Send CI information to Cloud team
         # Do not send if nightly build (i.e. 'schedule' or 'workflow_dispatch' event)
         if: github.event_name == 'push'
-        uses: peter-evans/repository-dispatch@v2
+        uses: peter-evans/repository-dispatch@v3
         with:
           token: ${{ secrets.MEILI_BOT_GH_PAT }}
           repository: meilisearch/meilisearch-cloud

.github/workflows/sdks-tests.yml

@@ -22,7 +22,7 @@ jobs:
     outputs:
       docker-image: ${{ steps.define-image.outputs.docker-image }}
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - name: Define the Docker image we need to use
         id: define-image
         run: |
@@ -46,11 +46,11 @@ jobs:
       MEILISEARCH_VERSION: ${{ needs.define-docker-image.outputs.docker-image }}
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           repository: meilisearch/meilisearch-dotnet
       - name: Setup .NET Core
-        uses: actions/setup-dotnet@v3
+        uses: actions/setup-dotnet@v4
         with:
           dotnet-version: "6.0.x"
       - name: Install dependencies
@@ -75,12 +75,12 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           repository: meilisearch/meilisearch-dart
       - uses: dart-lang/setup-dart@v1
         with:
-          sdk: 3.1.1
+          sdk: 'latest'
       - name: Install dependencies
         run: dart pub get
       - name: Run integration tests
@@ -100,10 +100,10 @@ jobs:
           - '7700:7700'
     steps:
       - name: Set up Go
-        uses: actions/setup-go@v4
+        uses: actions/setup-go@v5
         with:
           go-version: stable
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           repository: meilisearch/meilisearch-go
       - name: Get dependencies
@@ -129,11 +129,11 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           repository: meilisearch/meilisearch-java
       - name: Set up Java
-        uses: actions/setup-java@v3
+        uses: actions/setup-java@v4
         with:
           java-version: 8
           distribution: 'zulu'
@@ -156,7 +156,7 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           repository: meilisearch/meilisearch-js
       - name: Setup node
@@ -191,7 +191,7 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           repository: meilisearch/meilisearch-php
       - name: Install PHP
@@ -220,11 +220,11 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           repository: meilisearch/meilisearch-python
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
       - name: Install pipenv
         uses: dschep/install-pipenv-action@v1
       - name: Install dependencies
@@ -245,7 +245,7 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           repository: meilisearch/meilisearch-ruby
       - name: Set up Ruby 3
@@ -270,7 +270,7 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           repository: meilisearch/meilisearch-rust
       - name: Build
@@ -291,7 +291,7 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           repository: meilisearch/meilisearch-swift
       - name: Run tests
@@ -314,7 +314,7 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           repository: meilisearch/meilisearch-js-plugins
       - name: Setup node
@@ -345,7 +345,7 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           repository: meilisearch/meilisearch-rails
       - name: Set up Ruby 3
@@ -369,7 +369,7 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           repository: meilisearch/meilisearch-symfony
       - name: Install PHP

.github/workflows/test-suite.yml

@@ -31,17 +31,10 @@ jobs:
           apt-get update && apt-get install -y curl
           apt-get install build-essential -y
       - name: Setup test with Rust stable
-        if: github.event_name != 'schedule'
         uses: actions-rs/toolchain@v1
         with:
           toolchain: stable
           override: true
-      - name: Setup test with Rust nightly
-        if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
-        uses: actions-rs/toolchain@v1
-        with:
-          toolchain: nightly
-          override: true
       - name: Cache dependencies
         uses: Swatinem/rust-cache@v2.7.1
       - name: Run cargo check without any default features
@@ -66,6 +59,10 @@ jobs:
       - uses: actions/checkout@v3
       - name: Cache dependencies
         uses: Swatinem/rust-cache@v2.7.1
+      - uses: actions-rs/toolchain@v1
+        with:
+          toolchain: stable
+          override: true
       - name: Run cargo check without any default features
         uses: actions-rs/cargo@v1
         with:
@@ -78,7 +75,7 @@ jobs:
           args: --locked --release --all
 
   test-all-features:
-    name: Tests all features
+    name: Tests almost all features
     runs-on: ubuntu-latest
     container:
       # Use ubuntu-18.04 to compile with glibc 2.27, which are the production expectations
@@ -94,16 +91,12 @@ jobs:
         with:
           toolchain: stable
           override: true
-      - name: Run cargo build with all features
-        uses: actions-rs/cargo@v1
-        with:
-          command: build
-          args: --workspace --locked --release --all-features
-      - name: Run cargo test with all features
-        uses: actions-rs/cargo@v1
-        with:
-          command: test
-          args: --workspace --locked --release --all-features
+      - name: Run cargo build with almost all features
+        run: |
+          cargo build --workspace --locked --release --features "$(cargo xtask list-features --exclude-feature cuda)"
+      - name: Run cargo test with almost all features
+        run: |
+          cargo test --workspace --locked --release --features "$(cargo xtask list-features --exclude-feature cuda)"
 
   test-disabled-tokenization:
     name: Test disabled tokenization
@@ -164,7 +157,7 @@ jobs:
       - uses: actions-rs/toolchain@v1
         with:
           profile: minimal
-          toolchain: 1.71.1
+          toolchain: 1.75.0
           override: true
           components: clippy
       - name: Cache dependencies

.gitignore

@@ -9,6 +9,8 @@
 /data.ms
 /snapshots
 /dumps
+/bench
+/_xtask_benchmark.ms
 
 # Snapshots
 ## ... large

BENCHMARKS.md

@@ -0,0 +1,362 @@
+# Benchmarks
+
+Currently this repository hosts two kinds of benchmarks:
+
+1. The older "milli benchmarks", that use [criterion](https://github.com/bheisler/criterion.rs) and live in the "benchmarks" directory.
+2. The newer "bench" that are workload-based and so split between the [`workloads`](./workloads/) directory and the [`xtask::bench`](./xtask/src/bench/) module.
+
+This document describes the newer "bench" benchmarks. For more details on the "milli benchmarks", see [benchmarks/README.md](./benchmarks/README.md).
+
+## Design philosophy for the benchmarks
+
+The newer "bench" benchmarks are **integration** benchmarks, in the sense that they spawn an actual Meilisearch server and measure its performance end-to-end, including HTTP request overhead.
+
+Since this is prone to fluctuating, the benchmarks regain a bit of precision by measuring the runtime of the individual spans using the [logging machinery](./CONTRIBUTING.md#logging) of Meilisearch.
+
+A span roughly translates to a function call. The benchmark runner collects all the spans by name using the [logs route](https://github.com/orgs/meilisearch/discussions/721) and sums their runtime. The processed results are then sent to the [benchmark dashboard](https://bench.meilisearch.dev), which is in charge of storing and presenting the data.
+
+## Running the benchmarks
+
+Benchmarks can run locally or in CI.
+
+### Locally
+
+#### With a local benchmark dashboard
+
+The benchmarks dashboard lives in its [own repository](https://github.com/meilisearch/benchboard). We provide binaries for Ubuntu/Debian, but you can build from source for other platforms (MacOS should work as it was developed under that platform).
+
+Run the `benchboard` binary to create a fresh database of results. By default it will serve the results and the API to gather results on `http://localhost:9001`.
+
+From the Meilisearch repository, you can then run benchmarks with:
+
+```sh
+cargo xtask bench -- workloads/my_workload_1.json ..
+```
+
+This command will build and run Meilisearch locally on port 7700, so make sure that this port is available.
+To run benchmarks on a different commit, just use the usual git command to get back to the desired commit.
+
+#### Without a local benchmark dashboard
+
+To work with the raw results, you can also skip using a local benchmark dashboard.
+
+Run:
+
+```sh
+cargo xtask bench --no-dashboard -- workloads/my_workload_1.json workloads/my_workload_2.json ..
+```
+
+For processing the results, look at [Looking at benchmark results/Without dashboard](#without-dashboard).
+
+### In CI
+
+We have dedicated runners to run workloads on CI. Currently, there are three ways of running the CI:
+
+1. Automatically, on every push to `main`.
+2. Manually, by clicking the [`Run workflow`](https://github.com/meilisearch/meilisearch/actions/workflows/bench-manual.yml) button and specifying the target reference (tag, commit or branch) as well as one or multiple workloads to run. The workloads must exist in the Meilisearch repository (conventionally, in the [`workloads`](./workloads/) directory) on the target reference. Globbing (e.g., `workloads/*.json`) works.
+3. Manually on a PR, by posting a comment containing a `/bench` command, followed by one or multiple workloads to run. Globbing works. The workloads must exist in the Meilisearch repository in the branch of the PR.
+  ```
+  /bench workloads/movies*.json /hackernews_1M.json
+  ```
+
+## Looking at benchmark results
+
+### On the dashboard
+
+Results are available on the global dashboard used by CI at <https://bench.meilisearch.dev> or on your [local dashboard](#with-a-local-benchmark-dashboard).
+
+The dashboard homepage presents three sections:
+
+1. The latest invocations (a call to `cargo xtask bench`, either local or by CI) with their reason (generally set to some helpful link in CI) and their status.
+2. The latest workloads ran on `main`.
+3. The latest workloads ran on other references.
+
+By default, the workload shows the total runtime delta with the latest applicable commit on `main`. The latest applicable commit is the latest commit for workload invocations that do not originate on `main`, and the latest previous commit for workload invocations that originate on `main`.
+
+You can explicitly request a detailed comparison by span with the `main` branch, the branch or origin, or any previous commit, by clicking the links at the bottom of the workload invocation.
+
+In the detailed comparison view, the spans are sorted by improvements, regressions, stable (no statistically significant change) and unstable (the span runtime is comparable to its standard deviation).
+
+You can click on the name of any span to get a box plot comparing the target commit with multiple commits of the selected branch.
+
+### Without dashboard
+
+After the workloads are done running, the reports will live in the Meilisearch repository, in the `bench/reports` directory (by default).
+
+You can then convert these reports into other formats.
+
+- To [Firefox profiler](https://profiler.firefox.com) format. Run:
+  ```sh
+  cd bench/reports
+  cargo run --release --bin trace-to-firefox -- my_workload_1-0-trace.json
+  ```
+  You can then upload the resulting `firefox-my_workload_1-0-trace.json` file to the online profiler.
+
+
+## Designing benchmark workloads
+
+Benchmark workloads conventionally live in the `workloads` directory of the Meilisearch repository.
+
+They are JSON files with the following structure (comments are not actually supported, to make your own, remove them or copy some existing workload file):
+
+```jsonc
+{
+  // Name of the workload. Must be unique to the workload, as it will be used to group results on the dashboard.
+  "name": "hackernews.ndjson_1M,no-threads",
+  // Number of consecutive runs of the commands that should be performed.
+  // Each run uses a fresh instance of Meilisearch and a fresh database.
+  // Each run produces its own report file.
+  "run_count": 3,
+  // List of arguments to add to the Meilisearch command line.
+  "extra_cli_args": ["--max-indexing-threads=1"],
+  // List of named assets that can be used in the commands.
+  "assets": {
+    // name of the asset.
+    // Must be unique at the workload level.
+    // For better results, the same asset (same sha256) should have the same name accross workloads.
+    // Having multiple assets with the same name and distinct hashes is supported accross workloads,
+    // but will lead to superfluous downloads.
+    //
+    // Assets are stored in the `bench/assets/` directory by default.
+    "hackernews-100_000.ndjson": {
+      // If the assets exists in the local filesystem (Meilisearch repository or for your local workloads)
+      // Its file path can be specified here.
+      // `null` if the asset should be downloaded from a remote location.
+      "local_location": null,
+      // URL of the remote location where the asset can be downloaded.
+      // Use the `--assets-key` of the runner to pass an API key in the `Authorization: Bearer` header of the download requests.
+      // `null` if the asset should be imported from a local location.
+      // if both local and remote locations are specified, then the local one is tried first, then the remote one
+      // if the file is locally missing or its hash differs.
+      "remote_location": "https://milli-benchmarks.fra1.digitaloceanspaces.com/bench/datasets/hackernews/hackernews-100_000.ndjson",
+      // SHA256 of the asset.
+      // Optional, the `sha256` of the asset will be displayed during a run of the workload if it is missing.
+      // If present, the hash of the asset in the `bench/assets/` directory will be compared against this hash before
+      // running the workload. If the hashes differ, the asset will be downloaded anew.
+      "sha256": "60ecd23485d560edbd90d9ca31f0e6dba1455422f2a44e402600fbb5f7f1b213",
+      // Optional, one of "Auto", "Json", "NdJson" or "Raw".
+      // If missing, assumed to be "Auto".
+      // If "Auto", the format will be determined from the extension in the asset name.
+      "format": "NdJson"
+    },
+    "hackernews-200_000.ndjson": {
+      "local_location": null,
+      "remote_location": "https://milli-benchmarks.fra1.digitaloceanspaces.com/bench/datasets/hackernews/hackernews-200_000.ndjson",
+      "sha256": "785b0271fdb47cba574fab617d5d332276b835c05dd86e4a95251cf7892a1685"
+    },
+    "hackernews-300_000.ndjson": {
+      "local_location": null,
+      "remote_location": "https://milli-benchmarks.fra1.digitaloceanspaces.com/bench/datasets/hackernews/hackernews-300_000.ndjson",
+      "sha256": "de73c7154652eddfaf69cdc3b2f824d5c452f095f40a20a1c97bb1b5c4d80ab2"
+    },
+    "hackernews-400_000.ndjson": {
+      "local_location": null,
+      "remote_location": "https://milli-benchmarks.fra1.digitaloceanspaces.com/bench/datasets/hackernews/hackernews-400_000.ndjson",
+      "sha256": "c1b00a24689110f366447e434c201c086d6f456d54ed1c4995894102794d8fe7"
+    },
+    "hackernews-500_000.ndjson": {
+      "local_location": null,
+      "remote_location": "https://milli-benchmarks.fra1.digitaloceanspaces.com/bench/datasets/hackernews/hackernews-500_000.ndjson",
+      "sha256": "ae98f9dbef8193d750e3e2dbb6a91648941a1edca5f6e82c143e7996f4840083"
+    },
+    "hackernews-600_000.ndjson": {
+      "local_location": null,
+      "remote_location": "https://milli-benchmarks.fra1.digitaloceanspaces.com/bench/datasets/hackernews/hackernews-600_000.ndjson",
+      "sha256": "b495fdc72c4a944801f786400f22076ab99186bee9699f67cbab2f21f5b74dbe"
+    },
+    "hackernews-700_000.ndjson": {
+      "local_location": null,
+      "remote_location": "https://milli-benchmarks.fra1.digitaloceanspaces.com/bench/datasets/hackernews/hackernews-700_000.ndjson",
+      "sha256": "4b2c63974f3dabaa4954e3d4598b48324d03c522321ac05b0d583f36cb78a28b"
+    },
+    "hackernews-800_000.ndjson": {
+      "local_location": null,
+      "remote_location": "https://milli-benchmarks.fra1.digitaloceanspaces.com/bench/datasets/hackernews/hackernews-800_000.ndjson",
+      "sha256": "cb7b6afe0e6caa1be111be256821bc63b0771b2a0e1fad95af7aaeeffd7ba546"
+    },
+    "hackernews-900_000.ndjson": {
+      "local_location": null,
+      "remote_location": "https://milli-benchmarks.fra1.digitaloceanspaces.com/bench/datasets/hackernews/hackernews-900_000.ndjson",
+      "sha256": "e1154ddcd398f1c867758a93db5bcb21a07b9e55530c188a2917fdef332d3ba9"
+    },
+    "hackernews-1_000_000.ndjson": {
+      "local_location": null,
+      "remote_location": "https://milli-benchmarks.fra1.digitaloceanspaces.com/bench/datasets/hackernews/hackernews-1_000_000.ndjson",
+      "sha256": "27e25efd0b68b159b8b21350d9af76938710cb29ce0393fa71b41c4f3c630ffe"
+    }
+  },
+  // Core of the workload.
+  // A list of commands to run sequentially.
+  // A command is a request to the Meilisearch instance that is executed while the profiling runs.
+  "commands": [
+    {
+      // Meilisearch route to call. `http://localhost:7700/` will be prepended.
+      "route": "indexes/movies/settings",
+      // HTTP method to call.
+      "method": "PATCH",
+      // If applicable, body of the request.
+      // Optional, if missing, the body will be empty.
+      "body": {
+        // One of "empty", "inline" or "asset".
+        // If using "empty", you can skip the entire "body" key.
+        "inline": {
+          // when "inline" is used, the body is the JSON object that is the value of the `"inline"` key.
+          "displayedAttributes": [
+            "title",
+            "by",
+            "score",
+            "time"
+          ],
+          "searchableAttributes": [
+            "title"
+          ],
+          "filterableAttributes": [
+            "by"
+          ],
+          "sortableAttributes": [
+            "score",
+            "time"
+          ]
+        }
+      },
+      // Whether to wait before running the next request.
+      // One of:
+      // - DontWait: run the next command without waiting the response to this one.
+      // - WaitForResponse: run the next command as soon as the response from the server is received.
+      // - WaitForTask: run the next command once **all** the Meilisearch tasks created up to now have finished processing.
+      "synchronous": "DontWait"
+    },
+    {
+      "route": "indexes/movies/documents",
+      "method": "POST",
+      "body": {
+        // When using "asset", use the name of an asset as value to use the content of that asset as body.
+        // the content type is derived of the format of the asset:
+        // "NdJson" => "application/x-ndjson"
+        // "Json" => "application/json"
+        // "Raw" => "application/octet-stream"
+        // See [AssetFormat::to_content_type](https://github.com/meilisearch/meilisearch/blob/7b670a4afadb132ac4a01b6403108700501a391d/xtask/src/bench/assets.rs#L30)
+        // for details and up-to-date list.
+        "asset": "hackernews-100_000.ndjson"
+      },
+      "synchronous": "WaitForTask"
+    },
+    {
+      "route": "indexes/movies/documents",
+      "method": "POST",
+      "body": {
+        "asset": "hackernews-200_000.ndjson"
+      },
+      "synchronous": "WaitForResponse"
+    },
+    {
+      "route": "indexes/movies/documents",
+      "method": "POST",
+      "body": {
+        "asset": "hackernews-300_000.ndjson"
+      },
+      "synchronous": "WaitForResponse"
+    },
+    {
+      "route": "indexes/movies/documents",
+      "method": "POST",
+      "body": {
+        "asset": "hackernews-400_000.ndjson"
+      },
+      "synchronous": "WaitForResponse"
+    },
+    {
+      "route": "indexes/movies/documents",
+      "method": "POST",
+      "body": {
+        "asset": "hackernews-500_000.ndjson"
+      },
+      "synchronous": "WaitForResponse"
+    },
+    {
+      "route": "indexes/movies/documents",
+      "method": "POST",
+      "body": {
+        "asset": "hackernews-600_000.ndjson"
+      },
+      "synchronous": "WaitForResponse"
+    },
+    {
+      "route": "indexes/movies/documents",
+      "method": "POST",
+      "body": {
+        "asset": "hackernews-700_000.ndjson"
+      },
+      "synchronous": "WaitForResponse"
+    },
+    {
+      "route": "indexes/movies/documents",
+      "method": "POST",
+      "body": {
+        "asset": "hackernews-800_000.ndjson"
+      },
+      "synchronous": "WaitForResponse"
+    },
+    {
+      "route": "indexes/movies/documents",
+      "method": "POST",
+      "body": {
+        "asset": "hackernews-900_000.ndjson"
+      },
+      "synchronous": "WaitForResponse"
+    },
+    {
+      "route": "indexes/movies/documents",
+      "method": "POST",
+      "body": {
+        "asset": "hackernews-1_000_000.ndjson"
+      },
+      "synchronous": "WaitForTask"
+    }
+  ]
+}
+```
+
+### Adding new assets
+
+Assets reside in our DigitalOcean S3 space. Assuming you have team access to the DigitalOcean S3 space:
+
+1. go to <https://cloud.digitalocean.com/spaces/milli-benchmarks?i=d1c552&path=bench%2Fdatasets%2F>
+2. upload your dataset:
+   1. if your dataset is a single file, upload that single file using the "upload" button,
+   2. otherwise, create a folder using the "create folder" button, then inside that folder upload your individual files.
+
+## Upgrading `https://bench.meilisearch.dev`
+
+The URL of the server is in our password manager (look for "benchboard").
+
+1. Make the needed modifications on the [benchboard repository](https://github.com/meilisearch/benchboard) and merge them to main.
+2. Publish a new release to produce the Ubuntu/Debian binary.
+3. Download the binary locally, send it to the server:
+  ```
+  scp -6 ~/Downloads/benchboard root@\[<ipv6-address>\]:/bench/new-benchboard
+  ```
+  Note that the ipv6 must be between escaped square brackets for SCP.
+4. SSH to the server:
+  ```
+  ssh root@<ipv6-address>
+  ```
+  Note the ipv6 must **NOT** be between escaped square brackets for SSH 🥲
+5. On the server, set the correct permissions for the new binary:
+   ```
+   chown bench:bench /bench/new-benchboard
+   chmod 700 /bench/new-benchboard
+   ```
+6. On the server, move the new binary to the location of the running binary (if unsure, start by making a backup of the running binary):
+  ```
+  mv /bench/{new-,}benchboard
+  ```
+7. Restart the benchboard service.
+  ```
+  systemctl restart benchboard
+  ```
+8. Check that the service runs correctly.
+  ```
+  systemctl status benchboard
+  ```
+9. Check the availability of the service by going to <https://bench.meilisearch.dev> on your browser.

CONTRIBUTING.md

@@ -4,7 +4,7 @@ First, thank you for contributing to Meilisearch! The goal of this document is t
 
 Remember that there are many ways to contribute other than writing code: writing [tutorials or blog posts](https://github.com/meilisearch/awesome-meilisearch), improving [the documentation](https://github.com/meilisearch/documentation), submitting [bug reports](https://github.com/meilisearch/meilisearch/issues/new?assignees=&labels=&template=bug_report.md&title=) and [feature requests](https://github.com/meilisearch/product/discussions/categories/feedback-feature-proposal)...
 
-The code in this repository is only concerned with managing multiple indexes, handling the update store, and exposing an HTTP API. Search and indexation are the domain of our core engine, [`milli`](https://github.com/meilisearch/milli), while tokenization is handled by [our `charabia` library](https://github.com/meilisearch/charabia/).
+Meilisearch can manage multiple indexes, handle the update store, and expose an HTTP API. Search and indexation are the domain of our core engine, [`milli`](https://github.com/meilisearch/meilisearch/tree/main/milli), while tokenization is handled by [our `charabia` library](https://github.com/meilisearch/charabia/).
 
 If Meilisearch does not offer optimized support for your language, please consider contributing to `charabia` by following the [CONTRIBUTING.md file](https://github.com/meilisearch/charabia/blob/main/CONTRIBUTING.md) and integrating your intended normalizer/segmenter.
 
@@ -75,6 +75,36 @@ If you get a "Too many open files" error you might want to increase the open fil
 ulimit -Sn 3000
 ```
 
+#### Build tools
+
+Meilisearch follows the [cargo xtask](https://github.com/matklad/cargo-xtask) workflow to provide some build tools.
+
+Run `cargo xtask --help` from the root of the repository to find out what is available.
+
+### 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.
+
+Refer to the [documentation](https://docs.rs/tracing/0.1.40/tracing/index.html#using-the-macros) for the syntax of the spans and events.
+
+Logging spans are used for 3 distinct purposes:
+
+1. Regular logging
+2. Profiling
+3. Benchmarking
+
+As a result, the spans should follow some rules:
+
+- They should not be put on functions that are called too often. That is because opening and closing a span causes some overhead. For regular logging, avoid putting spans on functions that are taking less than a few hundred nanoseconds. For profiling or benchmarking, avoid putting spans on functions that are taking less than a few microseconds.
+- For profiling and benchmarking, use the `TRACE` level.
+- For profiling and benchmarking, use the following `target` prefixes:
+  - `indexing::` for spans meant when profiling the indexing operations.
+  - `search::` for spans meant when profiling the search operations.
+
+### Benchmarking
+
+See [BENCHMARKS.md](./BENCHMARKS.md)
+
 ## Git Guidelines
 
 ### Git Branches

Cargo.toml

@@ -2,6 +2,7 @@
 resolver = "2"
 members = [
     "meilisearch",
+    "meilitool",
     "meilisearch-types",
     "meilisearch-auth",
     "meili-snap",
@@ -15,11 +16,16 @@ members = [
     "json-depth-checker",
     "benchmarks",
     "fuzzers",
+    "tracing-trace",
+    "xtask", "build-info",
 ]
 
 [workspace.package]
-version = "1.4.1"
-authors = ["Quentin de Quelen <quentin@dequelen.me>", "Clément Renault <clement@meilisearch.com>"]
+version = "1.8.0"
+authors = [
+    "Quentin de Quelen <quentin@dequelen.me>",
+    "Clément Renault <clement@meilisearch.com>",
+]
 description = "Meilisearch HTTP server"
 homepage = "https://meilisearch.com"
 readme = "README.md"

Dockerfile

@@ -1,14 +1,14 @@
 # Compile
-FROM    rust:alpine3.16 AS compiler
+FROM    rust:1.75.0-alpine3.18 AS compiler
 
 RUN     apk add -q --update-cache --no-cache build-base openssl-dev
 
-WORKDIR /meilisearch
+WORKDIR /
 
 ARG     COMMIT_SHA
 ARG     COMMIT_DATE
 ARG     GIT_TAG
-ENV     VERGEN_GIT_SHA=${COMMIT_SHA} VERGEN_GIT_COMMIT_TIMESTAMP=${COMMIT_DATE} VERGEN_GIT_SEMVER_LIGHTWEIGHT=${GIT_TAG}
+ENV     VERGEN_GIT_SHA=${COMMIT_SHA} VERGEN_GIT_COMMIT_TIMESTAMP=${COMMIT_DATE} VERGEN_GIT_DESCRIBE=${GIT_TAG}
 ENV     RUSTFLAGS="-C target-feature=-crt-static"
 
 COPY    . .
@@ -17,7 +17,7 @@ RUN     set -eux; \
         if [ "$apkArch" = "aarch64" ]; then \
             export JEMALLOC_SYS_WITH_LG_PAGE=16; \
         fi && \
-        cargo build --release
+        cargo build --release -p meilisearch -p meilitool
 
 # Run
 FROM    alpine:3.16
@@ -28,9 +28,10 @@ ENV     MEILI_SERVER_PROVIDER docker
 RUN     apk update --quiet \
         && apk add -q --no-cache libgcc tini curl
 
-# add meilisearch to the `/bin` so you can run it from anywhere and it's easy
-# to find.
-COPY    --from=compiler /meilisearch/target/release/meilisearch /bin/meilisearch
+# add meilisearch and meilitool to the `/bin` so you can run it from anywhere
+# and it's easy to find.
+COPY    --from=compiler /target/release/meilisearch /bin/meilisearch
+COPY    --from=compiler /target/release/meilitool /bin/meilitool
 # To stay compatible with the older version of the container (pre v0.27.0) we're
 # going to symlink the meilisearch binary in the path to `/meilisearch`
 RUN     ln -s /bin/meilisearch /meilisearch

LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2019-2022 Meili SAS
+Copyright (c) 2019-2024 Meili SAS
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

README.md

@@ -41,10 +41,10 @@ Meilisearch helps you shape a delightful search experience in a snap, offering f
 ## ✨ Features
 
 - **Search-as-you-type:** find search results in less than 50 milliseconds
-- **[Typo tolerance](https://www.meilisearch.com/docs/learn/getting_started/customizing_relevancy?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features#typo-tolerance):** get relevant matches even when queries contain typos and misspellings
-- **[Filtering](https://www.meilisearch.com/docs/learn/fine_tuning_results/filtering?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features) and [faceted search](https://www.meilisearch.com/docs/learn/fine_tuning_results/faceted_search?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** enhance your user's search experience with custom filters and build a faceted search interface in a few lines of code
+- **[Typo tolerance](https://www.meilisearch.com/docs/learn/configuration/typo_tolerance?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** get relevant matches even when queries contain typos and misspellings
+- **[Filtering](https://www.meilisearch.com/docs/learn/fine_tuning_results/filtering?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features) and [faceted search](https://www.meilisearch.com/docs/learn/fine_tuning_results/faceted_search?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** enhance your users' search experience with custom filters and build a faceted search interface in a few lines of code
 - **[Sorting](https://www.meilisearch.com/docs/learn/fine_tuning_results/sorting?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** sort results based on price, date, or pretty much anything else your users need
-- **[Synonym support](https://www.meilisearch.com/docs/learn/getting_started/customizing_relevancy?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features#synonyms):** configure synonyms to include more relevant content in your search results
+- **[Synonym support](https://www.meilisearch.com/docs/learn/configuration/synonyms?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** configure synonyms to include more relevant content in your search results
 - **[Geosearch](https://www.meilisearch.com/docs/learn/fine_tuning_results/geosearch?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** filter and sort documents based on geographic data
 - **[Extensive language support](https://www.meilisearch.com/docs/learn/what_is_meilisearch/language?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** search datasets in any language, with optimized support for Chinese, Japanese, Hebrew, and languages using the Latin alphabet
 - **[Security management](https://www.meilisearch.com/docs/learn/security/master_api_keys?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** control which users can access what data with API keys that allow fine-grained permissions handling
@@ -61,8 +61,6 @@ You can consult Meilisearch's documentation at [https://www.meilisearch.com/docs
 
 For basic instructions on how to set up Meilisearch, add documents to an index, and search for documents, take a look at our [Quick Start](https://www.meilisearch.com/docs/learn/getting_started/quick_start?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=get-started) guide.
 
-You may also want to check out [Meilisearch 101](https://www.meilisearch.com/docs/learn/getting_started/filtering_and_sorting?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=get-started) for an introduction to some of Meilisearch's most popular features.
-
 ## ⚡ Supercharge your Meilisearch experience
 
 Say goodbye to server deployment and manual updates with [Meilisearch Cloud](https://www.meilisearch.com/cloud?utm_campaign=oss&utm_source=github&utm_medium=meilisearch). No credit card required.
@@ -101,7 +99,7 @@ Meilisearch is a search engine created by [Meili](https://www.welcometothejungle
 
 - For feature requests, please visit our [product repository](https://github.com/meilisearch/product/discussions)
 - Found a bug? Open an [issue](https://github.com/meilisearch/meilisearch/issues)!
-- Want to be part of our Discord community? [Join us!](https://discord.gg/meilisearch)
+- Want to be part of our Discord community? [Join us!](https://discord.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=contact)
 
 Thank you for your support!
 

benchmarks/Cargo.toml

@@ -11,24 +11,24 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-anyhow = "1.0.70"
-csv = "1.2.1"
+anyhow = "1.0.79"
+csv = "1.3.0"
 milli = { path = "../milli" }
-mimalloc = { version = "0.1.37", default-features = false }
-serde_json = { version = "1.0.95", features = ["preserve_order"] }
+mimalloc = { version = "0.1.39", default-features = false }
+serde_json = { version = "1.0.111", features = ["preserve_order"] }
 
 [dev-dependencies]
 criterion = { version = "0.5.1", features = ["html_reports"] }
 rand = "0.8.5"
 rand_chacha = "0.3.1"
-roaring = "0.10.1"
+roaring = "0.10.2"
 
 [build-dependencies]
-anyhow = "1.0.70"
-bytes = "1.4.0"
+anyhow = "1.0.79"
+bytes = "1.5.0"
 convert_case = "0.6.0"
-flate2 = "1.0.25"
-reqwest = { version = "0.11.16", features = ["blocking", "rustls-tls"], default-features = false }
+flate2 = "1.0.28"
+reqwest = { version = "0.11.23", features = ["blocking", "rustls-tls"], default-features = false }
 
 [features]
 default = ["milli/all-tokenizations"]

benchmarks/benches/indexing.rs

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

build-info/Cargo.toml

@@ -0,0 +1,18 @@
+[package]
+name = "build-info"
+version.workspace = true
+authors.workspace = true
+description.workspace = true
+homepage.workspace = true
+readme.workspace = true
+edition.workspace = true
+license.workspace = true
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+
+[dependencies]
+time = { version = "0.3.34", features = ["parsing"] }
+
+[build-dependencies]
+anyhow = "1.0.80"
+vergen-git2 = "1.0.0-beta.2"

build-info/build.rs

@@ -0,0 +1,22 @@
+fn main() {
+    if let Err(err) = emit_git_variables() {
+        println!("cargo:warning=vergen: {}", err);
+    }
+}
+
+fn emit_git_variables() -> anyhow::Result<()> {
+    // Note: any code that needs VERGEN_ environment variables should take care to define them manually in the Dockerfile and pass them
+    // in the corresponding GitHub workflow (publish_docker.yml).
+    // This is due to the Dockerfile building the binary outside of the git directory.
+    let mut builder = vergen_git2::Git2Builder::default();
+
+    builder.branch(true);
+    builder.commit_timestamp(true);
+    builder.commit_message(true);
+    builder.describe(true, true, None);
+    builder.sha(false);
+
+    let git2 = builder.build()?;
+
+    vergen_git2::Emitter::default().fail_on_error().add_instructions(&git2)?.emit()
+}

build-info/src/lib.rs

@@ -0,0 +1,203 @@
+use time::format_description::well_known::Iso8601;
+
+#[derive(Debug, Clone)]
+pub struct BuildInfo {
+    pub branch: Option<&'static str>,
+    pub describe: Option<DescribeResult>,
+    pub commit_sha1: Option<&'static str>,
+    pub commit_msg: Option<&'static str>,
+    pub commit_timestamp: Option<time::OffsetDateTime>,
+}
+
+impl BuildInfo {
+    pub fn from_build() -> Self {
+        let branch: Option<&'static str> = option_env!("VERGEN_GIT_BRANCH");
+        let describe = DescribeResult::from_build();
+        let commit_sha1 = option_env!("VERGEN_GIT_SHA");
+        let commit_msg = option_env!("VERGEN_GIT_COMMIT_MESSAGE");
+        let commit_timestamp = option_env!("VERGEN_GIT_COMMIT_TIMESTAMP");
+
+        let commit_timestamp = commit_timestamp.and_then(|commit_timestamp| {
+            time::OffsetDateTime::parse(commit_timestamp, &Iso8601::DEFAULT).ok()
+        });
+
+        Self { branch, describe, commit_sha1, commit_msg, commit_timestamp }
+    }
+}
+
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash)]
+pub enum DescribeResult {
+    Prototype { name: &'static str },
+    Release { version: &'static str, major: u64, minor: u64, patch: u64 },
+    Prerelease { version: &'static str, major: u64, minor: u64, patch: u64, rc: u64 },
+    NotATag { describe: &'static str },
+}
+
+impl DescribeResult {
+    pub fn new(describe: &'static str) -> Self {
+        if let Some(name) = prototype_name(describe) {
+            Self::Prototype { name }
+        } else if let Some(release) = release_version(describe) {
+            release
+        } else if let Some(prerelease) = prerelease_version(describe) {
+            prerelease
+        } else {
+            Self::NotATag { describe }
+        }
+    }
+
+    pub fn from_build() -> Option<Self> {
+        let describe: &'static str = option_env!("VERGEN_GIT_DESCRIBE")?;
+        Some(Self::new(describe))
+    }
+
+    pub fn as_tag(&self) -> Option<&'static str> {
+        match self {
+            DescribeResult::Prototype { name } => Some(name),
+            DescribeResult::Release { version, .. } => Some(version),
+            DescribeResult::Prerelease { version, .. } => Some(version),
+            DescribeResult::NotATag { describe: _ } => None,
+        }
+    }
+
+    pub fn as_prototype(&self) -> Option<&'static str> {
+        match self {
+            DescribeResult::Prototype { name } => Some(name),
+            DescribeResult::Release { .. }
+            | DescribeResult::Prerelease { .. }
+            | DescribeResult::NotATag { .. } => None,
+        }
+    }
+}
+
+/// Parses the input as a prototype name.
+///
+/// Returns `Some(prototype_name)` if the following conditions are met on this value:
+///
+/// 1. starts with `prototype-`,
+/// 2. ends with `-<some_number>`,
+/// 3. does not end with `<some_number>-<some_number>`.
+///
+/// Otherwise, returns `None`.
+fn prototype_name(describe: &'static str) -> Option<&'static str> {
+    if !describe.starts_with("prototype-") {
+        return None;
+    }
+
+    let mut rsplit_prototype = describe.rsplit('-');
+    // last component MUST be a number
+    rsplit_prototype.next()?.parse::<u64>().ok()?;
+    // before than last component SHALL NOT be a number
+    rsplit_prototype.next()?.parse::<u64>().err()?;
+
+    Some(describe)
+}
+
+fn release_version(describe: &'static str) -> Option<DescribeResult> {
+    if !describe.starts_with('v') {
+        return None;
+    }
+
+    // full release version don't contain a `-`
+    if describe.contains('-') {
+        return None;
+    }
+
+    // full release version parse as vX.Y.Z, with X, Y, Z numbers.
+    let mut dots = describe[1..].split('.');
+    let major: u64 = dots.next()?.parse().ok()?;
+    let minor: u64 = dots.next()?.parse().ok()?;
+    let patch: u64 = dots.next()?.parse().ok()?;
+
+    if dots.next().is_some() {
+        return None;
+    }
+
+    Some(DescribeResult::Release { version: describe, major, minor, patch })
+}
+
+fn prerelease_version(describe: &'static str) -> Option<DescribeResult> {
+    // prerelease version is in the shape vM.N.P-rc.C
+    let mut hyphen = describe.rsplit('-');
+    let prerelease = hyphen.next()?;
+    if !prerelease.starts_with("rc.") {
+        return None;
+    }
+
+    let rc: u64 = prerelease[3..].parse().ok()?;
+
+    let release = hyphen.next()?;
+
+    let DescribeResult::Release { version: _, major, minor, patch } = release_version(release)?
+    else {
+        return None;
+    };
+
+    Some(DescribeResult::Prerelease { version: describe, major, minor, patch, rc })
+}
+
+#[cfg(test)]
+mod test {
+    use super::DescribeResult;
+
+    fn assert_not_a_tag(describe: &'static str) {
+        assert_eq!(DescribeResult::NotATag { describe }, DescribeResult::new(describe))
+    }
+
+    fn assert_proto(describe: &'static str) {
+        assert_eq!(DescribeResult::Prototype { name: describe }, DescribeResult::new(describe))
+    }
+
+    fn assert_release(describe: &'static str, major: u64, minor: u64, patch: u64) {
+        assert_eq!(
+            DescribeResult::Release { version: describe, major, minor, patch },
+            DescribeResult::new(describe)
+        )
+    }
+
+    fn assert_prerelease(describe: &'static str, major: u64, minor: u64, patch: u64, rc: u64) {
+        assert_eq!(
+            DescribeResult::Prerelease { version: describe, major, minor, patch, rc },
+            DescribeResult::new(describe)
+        )
+    }
+
+    #[test]
+    fn not_a_tag() {
+        assert_not_a_tag("whatever-fuzzy");
+        assert_not_a_tag("whatever-fuzzy-5-ggg-dirty");
+        assert_not_a_tag("whatever-fuzzy-120-ggg-dirty");
+
+        // technically a tag, but not a proto nor a version, so not parsed as a tag
+        assert_not_a_tag("whatever");
+
+        // dirty version
+        assert_not_a_tag("v1.7.0-1-ggga-dirty");
+        assert_not_a_tag("v1.7.0-rc.1-1-ggga-dirty");
+
+        // after version
+        assert_not_a_tag("v1.7.0-1-ggga");
+        assert_not_a_tag("v1.7.0-rc.1-1-ggga");
+
+        // after proto
+        assert_not_a_tag("protoype-tag-0-1-ggga");
+        assert_not_a_tag("protoype-tag-0-1-ggga-dirty");
+    }
+
+    #[test]
+    fn prototype() {
+        assert_proto("prototype-tag-0");
+        assert_proto("prototype-tag-10");
+        assert_proto("prototype-long-name-tag-10");
+    }
+
+    #[test]
+    fn release() {
+        assert_release("v1.7.2", 1, 7, 2);
+    }
+
+    #[test]
+    fn prerelease() {
+        assert_prerelease("v1.7.2-rc.3", 1, 7, 2, 3);
+    }
+}

config.toml

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

dump/Cargo.toml

@@ -11,22 +11,22 @@ readme.workspace = true
 license.workspace = true
 
 [dependencies]
-anyhow = "1.0.70"
-flate2 = "1.0.25"
-http = "0.2.9"
-log = "0.4.17"
+anyhow = "1.0.79"
+flate2 = "1.0.28"
+http = "0.2.11"
 meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
-once_cell = "1.17.1"
-regex = "1.7.3"
-roaring = { version = "0.10.1", features = ["serde"] }
-serde = { version = "1.0.160", features = ["derive"] }
-serde_json = { version = "1.0.95", features = ["preserve_order"] }
-tar = "0.4.38"
-tempfile = "3.5.0"
-thiserror = "1.0.40"
-time = { version = "0.3.20", features = ["serde-well-known", "formatting", "parsing", "macros"] }
-uuid = { version = "1.3.1", features = ["serde", "v4"] }
+once_cell = "1.19.0"
+regex = "1.10.2"
+roaring = { version = "0.10.2", features = ["serde"] }
+serde = { version = "1.0.195", features = ["derive"] }
+serde_json = { version = "1.0.111", features = ["preserve_order"] }
+tar = "0.4.40"
+tempfile = "3.9.0"
+thiserror = "1.0.56"
+time = { version = "0.3.31", features = ["serde-well-known", "formatting", "parsing", "macros"] }
+tracing = "0.1.40"
+uuid = { version = "1.6.1", features = ["serde", "v4"] }
 
 [dev-dependencies]
 big_s = "1.0.2"

dump/src/lib.rs

@@ -267,6 +267,7 @@ pub(crate) mod test {
             dictionary: Setting::NotSet,
             synonyms: Setting::NotSet,
             distinct_attribute: Setting::NotSet,
+            proximity_precision: Setting::NotSet,
             typo_tolerance: Setting::NotSet,
             faceting: Setting::Set(FacetingSettings {
                 max_values_per_facet: Setting::Set(111),
@@ -275,6 +276,8 @@ pub(crate) mod test {
                 ),
             }),
             pagination: Setting::NotSet,
+            embedders: Setting::NotSet,
+            search_cutoff_ms: Setting::NotSet,
             _kind: std::marker::PhantomData,
         };
         settings.check()

dump/src/reader/compat/v1_to_v2.rs

@@ -120,7 +120,7 @@ impl From<v1::settings::Settings> for v2::Settings<v2::Unchecked> {
                                 criterion.as_ref().map(ToString::to_string)
                             }
                             Err(()) => {
-                                log::warn!(
+                                tracing::warn!(
                                     "Could not import the following ranking rule: `{}`.",
                                     ranking_rule
                                 );
@@ -152,11 +152,11 @@ impl From<v1::update::UpdateStatus> for Option<v2::updates::UpdateStatus> {
         use v2::updates::UpdateStatus as UpdateStatusV2;
         Some(match source {
             UpdateStatusV1::Enqueued { content } => {
-                log::warn!(
+                tracing::warn!(
                     "Cannot import task {} (importing enqueued tasks from v1 dumps is unsupported)",
                     content.update_id
                 );
-                log::warn!("Task will be skipped in the queue of imported tasks.");
+                tracing::warn!("Task will be skipped in the queue of imported tasks.");
 
                 return None;
             }
@@ -229,7 +229,7 @@ impl From<v1::update::UpdateType> for Option<v2::updates::UpdateMeta> {
         Some(match source {
             v1::update::UpdateType::ClearAll => v2::updates::UpdateMeta::ClearDocuments,
             v1::update::UpdateType::Customs => {
-                log::warn!("Ignoring task with type 'Customs' that is no longer supported");
+                tracing::warn!("Ignoring task with type 'Customs' that is no longer supported");
                 return None;
             }
             v1::update::UpdateType::DocumentsAddition { .. } => {
@@ -296,7 +296,7 @@ impl From<v1::settings::RankingRule> for Option<v2::settings::Criterion> {
             v1::settings::RankingRule::Proximity => Some(v2::settings::Criterion::Proximity),
             v1::settings::RankingRule::Attribute => Some(v2::settings::Criterion::Attribute),
             v1::settings::RankingRule::WordsPosition => {
-                log::warn!("Removing the 'WordsPosition' ranking rule that is no longer supported, please check the resulting ranking rules of your indexes");
+                tracing::warn!("Removing the 'WordsPosition' ranking rule that is no longer supported, please check the resulting ranking rules of your indexes");
                 None
             }
             v1::settings::RankingRule::Exactness => Some(v2::settings::Criterion::Exactness),

dump/src/reader/compat/v2_to_v3.rs

@@ -1,4 +1,3 @@
-use std::convert::TryInto;
 use std::str::FromStr;
 
 use time::OffsetDateTime;
@@ -146,8 +145,8 @@ impl From<v2::updates::UpdateStatus> for v3::updates::UpdateStatus {
                         started_processing_at: processing.started_processing_at,
                     }),
                     Err(e) => {
-                        log::warn!("Error with task {}: {}", processing.from.update_id, e);
-                        log::warn!("Task will be marked as `Failed`.");
+                        tracing::warn!("Error with task {}: {}", processing.from.update_id, e);
+                        tracing::warn!("Task will be marked as `Failed`.");
                         v3::updates::UpdateStatus::Failed(v3::updates::Failed {
                             from: v3::updates::Processing {
                                 from: v3::updates::Enqueued {
@@ -172,8 +171,8 @@ impl From<v2::updates::UpdateStatus> for v3::updates::UpdateStatus {
                         enqueued_at: enqueued.enqueued_at,
                     }),
                     Err(e) => {
-                        log::warn!("Error with task {}: {}", enqueued.update_id, e);
-                        log::warn!("Task will be marked as `Failed`.");
+                        tracing::warn!("Error with task {}: {}", enqueued.update_id, e);
+                        tracing::warn!("Task will be marked as `Failed`.");
                         v3::updates::UpdateStatus::Failed(v3::updates::Failed {
                             from: v3::updates::Processing {
                                 from: v3::updates::Enqueued {
@@ -353,7 +352,7 @@ impl From<String> for v3::Code {
             "malformed_payload" => v3::Code::MalformedPayload,
             "missing_payload" => v3::Code::MissingPayload,
             other => {
-                log::warn!("Unknown error code {}", other);
+                tracing::warn!("Unknown error code {}", other);
                 v3::Code::UnretrievableErrorCode
             }
         }

dump/src/reader/compat/v3_to_v4.rs

@@ -76,20 +76,20 @@ impl CompatV3ToV4 {
                         let index_uid = match index_uid {
                             Some(uid) => uid,
                             None => {
-                                log::warn!(
+                                tracing::warn!(
                                     "Error while importing the update {}.",
                                     task.update.id()
                                 );
-                                log::warn!(
+                                tracing::warn!(
                                     "The index associated to the uuid `{}` could not be retrieved.",
                                     task.uuid.to_string()
                                 );
                                 if task.update.is_finished() {
                                     // we're fucking with his history but not his data, that's ok-ish.
-                                    log::warn!("The index-uuid will be set as `unknown`.");
+                                    tracing::warn!("The index-uuid will be set as `unknown`.");
                                     String::from("unknown")
                                 } else {
-                                    log::warn!("The task will be ignored.");
+                                    tracing::warn!("The task will be ignored.");
                                     return None;
                                 }
                             }

dump/src/reader/compat/v4_to_v5.rs

@@ -305,7 +305,7 @@ impl From<v4::ResponseError> for v5::ResponseError {
             "invalid_api_key_expires_at" => v5::Code::InvalidApiKeyExpiresAt,
             "invalid_api_key_description" => v5::Code::InvalidApiKeyDescription,
             other => {
-                log::warn!("Unknown error code {}", other);
+                tracing::warn!("Unknown error code {}", other);
                 v5::Code::UnretrievableErrorCode
             }
         };

dump/src/reader/compat/v5_to_v6.rs

@@ -304,7 +304,7 @@ impl From<v5::ResponseError> for v6::ResponseError {
             "immutable_field" => v6::Code::BadRequest,
             "api_key_already_exists" => v6::Code::ApiKeyAlreadyExists,
             other => {
-                log::warn!("Unknown error code {}", other);
+                tracing::warn!("Unknown error code {}", other);
                 v6::Code::UnretrievableErrorCode
             }
         };
@@ -329,7 +329,7 @@ impl<T> From<v5::Settings<T>> for v6::Settings<v6::Unchecked> {
                                     new_ranking_rules.push(new_rule);
                                 }
                                 Err(_) => {
-                                    log::warn!("Error while importing settings. The ranking rule `{rule}` does not exist anymore.")
+                                    tracing::warn!("Error while importing settings. The ranking rule `{rule}` does not exist anymore.")
                                 }
                             }
                         }
@@ -345,6 +345,7 @@ impl<T> From<v5::Settings<T>> for v6::Settings<v6::Unchecked> {
             dictionary: v6::Setting::NotSet,
             synonyms: settings.synonyms.into(),
             distinct_attribute: settings.distinct_attribute.into(),
+            proximity_precision: v6::Setting::NotSet,
             typo_tolerance: match settings.typo_tolerance {
                 v5::Setting::Set(typo) => v6::Setting::Set(v6::TypoTolerance {
                     enabled: typo.enabled.into(),
@@ -377,6 +378,8 @@ impl<T> From<v5::Settings<T>> for v6::Settings<v6::Unchecked> {
                 v5::Setting::Reset => v6::Setting::Reset,
                 v5::Setting::NotSet => v6::Setting::NotSet,
             },
+            embedders: v6::Setting::NotSet,
+            search_cutoff_ms: v6::Setting::NotSet,
             _kind: std::marker::PhantomData,
         }
     }

dump/src/reader/mod.rs

@@ -13,12 +13,12 @@ use crate::{Result, Version};
 
 mod compat;
 
-pub(self) mod v1;
-pub(self) mod v2;
-pub(self) mod v3;
-pub(self) mod v4;
-pub(self) mod v5;
-pub(self) mod v6;
+mod v1;
+mod v2;
+mod v3;
+mod v4;
+mod v5;
+mod v6;
 
 pub type Document = serde_json::Map<String, serde_json::Value>;
 pub type UpdateFile = dyn Iterator<Item = Result<Document>>;

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

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

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

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

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

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

dump/src/reader/v1/settings.rs

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

dump/src/reader/v2/updates.rs

@@ -61,7 +61,7 @@ pub enum IndexDocumentsMethod {
 #[cfg_attr(test, derive(serde::Serialize))]
 #[non_exhaustive]
 pub enum UpdateFormat {
-    /// The given update is a real **comma seperated** CSV with headers on the first line.
+    /// The given update is a real **comma separated** CSV with headers on the first line.
     Csv,
     /// The given update is a JSON array with documents inside.
     Json,

dump/src/reader/v3/errors.rs

@@ -1,5 +1,6 @@
 use serde::{Deserialize, Serialize};
 
+#[allow(clippy::enum_variant_names)]
 #[derive(Serialize, Deserialize, Debug, Clone, Copy)]
 pub enum Code {
     // index related error

dump/src/reader/v4/errors.rs

@@ -95,6 +95,7 @@ impl fmt::Display for ErrorType {
     }
 }
 
+#[allow(clippy::enum_variant_names)]
 #[derive(Serialize, Deserialize, Debug, Clone, Copy)]
 pub enum Code {
     // index related error

dump/src/reader/v5/errors.rs

@@ -31,6 +31,7 @@ impl ResponseError {
     }
 }
 
+#[allow(clippy::enum_variant_names)]
 #[derive(Deserialize, Debug, Clone, Copy)]
 #[cfg_attr(test, derive(serde::Serialize))]
 pub enum Code {

dump/src/reader/v6/mod.rs

@@ -2,10 +2,10 @@ use std::fs::{self, File};
 use std::io::{BufRead, BufReader, ErrorKind};
 use std::path::Path;
 
-use log::debug;
 pub use meilisearch_types::milli;
 use tempfile::TempDir;
 use time::OffsetDateTime;
+use tracing::debug;
 use uuid::Uuid;
 
 use super::Document;

dump/src/writer.rs

@@ -219,7 +219,7 @@ pub(crate) mod test {
     fn _create_directory_hierarchy(dir: &Path, depth: usize) -> String {
         let mut ret = String::new();
 
-        // the entries are not guarenteed to be returned in the same order thus we need to sort them.
+        // the entries are not guaranteed to be returned in the same order thus we need to sort them.
         let mut entries =
             fs::read_dir(dir).unwrap().collect::<std::result::Result<Vec<_>, _>>().unwrap();
 

file-store/Cargo.toml

@@ -11,9 +11,10 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-tempfile = "3.5.0"
-thiserror = "1.0.40"
-uuid = { version = "1.3.1", features = ["serde", "v4"] }
+tempfile = "3.9.0"
+thiserror = "1.0.56"
+tracing = "0.1.40"
+uuid = { version = "1.6.1", features = ["serde", "v4"] }
 
 [dev-dependencies]
-faux = "0.1.9"
+faux = "0.1.10"

file-store/src/lib.rs

@@ -1,5 +1,5 @@
 use std::fs::File as StdFile;
-use std::ops::{Deref, DerefMut};
+use std::io::Write;
 use std::path::{Path, PathBuf};
 use std::str::FromStr;
 
@@ -22,20 +22,6 @@ pub enum Error {
 
 pub type Result<T> = std::result::Result<T, Error>;
 
-impl Deref for File {
-    type Target = NamedTempFile;
-
-    fn deref(&self) -> &Self::Target {
-        &self.file
-    }
-}
-
-impl DerefMut for File {
-    fn deref_mut(&mut self) -> &mut Self::Target {
-        &mut self.file
-    }
-}
-
 #[derive(Clone, Debug)]
 pub struct FileStore {
     path: PathBuf,
@@ -56,7 +42,7 @@ impl FileStore {
         let file = NamedTempFile::new_in(&self.path)?;
         let uuid = Uuid::new_v4();
         let path = self.path.join(uuid.to_string());
-        let update_file = File { file, path };
+        let update_file = File { file: Some(file), path };
 
         Ok((uuid, update_file))
     }
@@ -67,7 +53,7 @@ impl FileStore {
         let file = NamedTempFile::new_in(&self.path)?;
         let uuid = Uuid::from_u128(uuid);
         let path = self.path.join(uuid.to_string());
-        let update_file = File { file, path };
+        let update_file = File { file: Some(file), path };
 
         Ok((uuid, update_file))
     }
@@ -75,7 +61,13 @@ impl FileStore {
     /// Returns the file corresponding to the requested uuid.
     pub fn get_update(&self, uuid: Uuid) -> Result<StdFile> {
         let path = self.get_update_path(uuid);
-        let file = StdFile::open(path)?;
+        let file = match StdFile::open(path) {
+            Ok(file) => file,
+            Err(e) => {
+                tracing::error!("Can't access update file {uuid}: {e}");
+                return Err(e.into());
+            }
+        };
         Ok(file)
     }
 
@@ -110,8 +102,12 @@ impl FileStore {
 
     pub fn delete(&self, uuid: Uuid) -> Result<()> {
         let path = self.path.join(uuid.to_string());
-        std::fs::remove_file(path)?;
-        Ok(())
+        if let Err(e) = std::fs::remove_file(path) {
+            tracing::error!("Can't delete file {uuid}: {e}");
+            Err(e.into())
+        } else {
+            Ok(())
+        }
     }
 
     /// List the Uuids of the files in the FileStore
@@ -136,16 +132,40 @@ impl FileStore {
 
 pub struct File {
     path: PathBuf,
-    file: NamedTempFile,
+    file: Option<NamedTempFile>,
 }
 
 impl File {
+    pub fn dry_file() -> Result<Self> {
+        Ok(Self { path: PathBuf::new(), file: None })
+    }
+
     pub fn persist(self) -> Result<()> {
-        self.file.persist(&self.path)?;
+        if let Some(file) = self.file {
+            file.persist(&self.path)?;
+        }
         Ok(())
     }
 }
 
+impl Write for File {
+    fn write(&mut self, buf: &[u8]) -> std::io::Result<usize> {
+        if let Some(file) = self.file.as_mut() {
+            file.write(buf)
+        } else {
+            Ok(buf.len())
+        }
+    }
+
+    fn flush(&mut self) -> std::io::Result<()> {
+        if let Some(file) = self.file.as_mut() {
+            file.flush()
+        } else {
+            Ok(())
+        }
+    }
+}
+
 #[cfg(test)]
 mod test {
     use std::io::Write;

filter-parser/Cargo.toml

@@ -13,8 +13,8 @@ license.workspace = true
 
 [dependencies]
 nom = "7.1.3"
-nom_locate = "4.1.0"
-unescaper = "0.1.2"
+nom_locate = "4.2.0"
+unescaper = "0.1.3"
 
 [dev-dependencies]
-insta = "1.29.0"
+insta = "1.34.0"

filter-parser/src/lib.rs

@@ -564,10 +564,10 @@ pub mod tests {
 
     #[test]
     fn parse_escaped() {
-        insta::assert_display_snapshot!(p(r#"title = 'foo\\'"#), @r#"{title} = {foo\}"#);
-        insta::assert_display_snapshot!(p(r#"title = 'foo\\\\'"#), @r#"{title} = {foo\\}"#);
-        insta::assert_display_snapshot!(p(r#"title = 'foo\\\\\\'"#), @r#"{title} = {foo\\\}"#);
-        insta::assert_display_snapshot!(p(r#"title = 'foo\\\\\\\\'"#), @r#"{title} = {foo\\\\}"#);
+        insta::assert_display_snapshot!(p(r"title = 'foo\\'"), @r#"{title} = {foo\}"#);
+        insta::assert_display_snapshot!(p(r"title = 'foo\\\\'"), @r#"{title} = {foo\\}"#);
+        insta::assert_display_snapshot!(p(r"title = 'foo\\\\\\'"), @r#"{title} = {foo\\\}"#);
+        insta::assert_display_snapshot!(p(r"title = 'foo\\\\\\\\'"), @r#"{title} = {foo\\\\}"#);
         // but it also works with other sequencies
         insta::assert_display_snapshot!(p(r#"title = 'foo\x20\n\t\"\'"'"#), @"{title} = {foo \n\t\"\'\"}");
     }

filter-parser/src/value.rs

@@ -42,7 +42,7 @@ fn quoted_by(quote: char, input: Span) -> IResult<Token> {
                 )));
             }
         }
-        // if it was preceeded by a `\` or if it was anything else we can continue to advance
+        // if it was preceded by a `\` or if it was anything else we can continue to advance
     }
 
     Ok((
@@ -270,8 +270,8 @@ pub mod test {
             ("aaaa", "", rtok("", "aaaa"), "aaaa"),
             (r#"aa"aa"#, r#""aa"#, rtok("", "aa"), "aa"),
             (r#"aa\"aa"#, r#""#, rtok("", r#"aa\"aa"#), r#"aa"aa"#),
-            (r#"aa\\\aa"#, r#""#, rtok("", r#"aa\\\aa"#), r#"aa\\\aa"#),
-            (r#"aa\\"\aa"#, r#""\aa"#, rtok("", r#"aa\\"#), r#"aa\\"#),
+            (r"aa\\\aa", r#""#, rtok("", r"aa\\\aa"), r"aa\\\aa"),
+            (r#"aa\\"\aa"#, r#""\aa"#, rtok("", r"aa\\"), r"aa\\"),
             (r#"aa\\\"\aa"#, r#""#, rtok("", r#"aa\\\"\aa"#), r#"aa\\"\aa"#),
             (r#"\"\""#, r#""#, rtok("", r#"\"\""#), r#""""#),
         ];
@@ -301,12 +301,12 @@ pub mod test {
         );
         // simple quote
         assert_eq!(
-            unescape(Span::new_extra(r#"Hello \'World\'"#, ""), '\''),
+            unescape(Span::new_extra(r"Hello \'World\'", ""), '\''),
             r#"Hello 'World'"#.to_string()
         );
         assert_eq!(
-            unescape(Span::new_extra(r#"Hello \\\'World\\\'"#, ""), '\''),
-            r#"Hello \\'World\\'"#.to_string()
+            unescape(Span::new_extra(r"Hello \\\'World\\\'", ""), '\''),
+            r"Hello \\'World\\'".to_string()
         );
     }
 
@@ -335,19 +335,19 @@ pub mod test {
             ("\"cha'nnel\"", "cha'nnel", false),
             ("I'm tamo", "I", false),
             // escaped thing but not quote
-            (r#""\\""#, r#"\"#, true),
-            (r#""\\\\\\""#, r#"\\\"#, true),
-            (r#""aa\\aa""#, r#"aa\aa"#, true),
+            (r#""\\""#, r"\", true),
+            (r#""\\\\\\""#, r"\\\", true),
+            (r#""aa\\aa""#, r"aa\aa", true),
             // with double quote
             (r#""Hello \"world\"""#, r#"Hello "world""#, true),
             (r#""Hello \\\"world\\\"""#, r#"Hello \"world\""#, true),
             (r#""I'm \"super\" tamo""#, r#"I'm "super" tamo"#, true),
             (r#""\"\"""#, r#""""#, true),
             // with simple quote
-            (r#"'Hello \'world\''"#, r#"Hello 'world'"#, true),
-            (r#"'Hello \\\'world\\\''"#, r#"Hello \'world\'"#, true),
+            (r"'Hello \'world\''", r#"Hello 'world'"#, true),
+            (r"'Hello \\\'world\\\''", r"Hello \'world\'", true),
             (r#"'I\'m "super" tamo'"#, r#"I'm "super" tamo"#, true),
-            (r#"'\'\''"#, r#"''"#, true),
+            (r"'\'\''", r#"''"#, true),
         ];
 
         for (input, expected, escaped) in test_case {

fuzzers/Cargo.toml

@@ -11,10 +11,10 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-arbitrary = { version = "1.3.0", features = ["derive"] }
-clap = { version = "4.3.0", features = ["derive"] }
-fastrand = "2.0.0"
+arbitrary = { version = "1.3.2", features = ["derive"] }
+clap = { version = "4.4.17", features = ["derive"] }
+fastrand = "2.0.1"
 milli = { path = "../milli" }
-serde = { version = "1.0.160", features = ["derive"] }
-serde_json = { version = "1.0.95", features = ["preserve_order"] }
-tempfile = "3.5.0"
+serde = { version = "1.0.195", features = ["derive"] }
+serde_json = { version = "1.0.111", features = ["preserve_order"] }
+tempfile = "3.9.0"

fuzzers/src/bin/fuzz-indexing.rs

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

index-scheduler/Cargo.toml

@@ -11,30 +11,37 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-anyhow = "1.0.70"
+anyhow = "1.0.79"
 bincode = "1.3.3"
-csv = "1.2.1"
+csv = "1.3.0"
 derive_builder = "0.12.0"
 dump = { path = "../dump" }
-enum-iterator = "1.4.0"
+enum-iterator = "1.5.0"
 file-store = { path = "../file-store" }
-log = "0.4.17"
+flate2 = "1.0.28"
 meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
 page_size = "0.5.0"
-puffin = "0.16.0"
-roaring = { version = "0.10.1", features = ["serde"] }
-serde = { version = "1.0.160", features = ["derive"] }
-serde_json = { version = "1.0.95", features = ["preserve_order"] }
+puffin = { version = "0.16.0", features = ["serialization"] }
+rayon = "1.8.1"
+roaring = { version = "0.10.2", features = ["serde"] }
+serde = { version = "1.0.195", features = ["derive"] }
+serde_json = { version = "1.0.111", features = ["preserve_order"] }
 synchronoise = "1.0.1"
-tempfile = "3.5.0"
-thiserror = "1.0.40"
-time = { version = "0.3.20", features = ["serde-well-known", "formatting", "parsing", "macros"] }
-uuid = { version = "1.3.1", features = ["serde", "v4"] }
+tempfile = "3.9.0"
+thiserror = "1.0.56"
+time = { version = "0.3.31", features = [
+    "serde-well-known",
+    "formatting",
+    "parsing",
+    "macros",
+] }
+tracing = "0.1.40"
+ureq = "2.9.1"
+uuid = { version = "1.6.1", features = ["serde", "v4"] }
 
 [dev-dependencies]
 big_s = "1.0.2"
-crossbeam = "0.8.2"
-insta = { version = "1.29.0", features = ["json", "redactions"] }
+crossbeam = "0.8.4"
+insta = { version = "1.34.0", features = ["json", "redactions"] }
 meili-snap = { path = "../meili-snap" }
-nelson = { git = "https://github.com/meilisearch/nelson.git", rev = "675f13885548fb415ead8fbb447e9e6d9314000a"}

index-scheduler/src/autobatcher.rs

@@ -870,7 +870,7 @@ mod tests {
         debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, false, None), settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 2, 1] }, false))");
         debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments,false, None), settings(false), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, false))");
         debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, false, None), settings(false), doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [1, 3, 0, 2] }, false))");
-        // The third and final case is when the first task doesn't create an index but is directly followed by a task creating an index. In this case we can't batch whith what
+        // The third and final case is when the first task doesn't create an index but is directly followed by a task creating an index. In this case we can't batch whit what
         // follows because we first need to process the erronous batch.
         debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments,false, None), settings(true), idx_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
         debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, false, None), settings(true), idx_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");

index-scheduler/src/batch.rs

@@ -24,16 +24,14 @@ use std::fs::{self, File};
 use std::io::BufWriter;
 
 use dump::IndexMetadata;
-use log::{debug, error, info};
 use meilisearch_types::error::Code;
 use meilisearch_types::heed::{RoTxn, RwTxn};
 use meilisearch_types::milli::documents::{obkv_to_object, DocumentsBatchReader};
 use meilisearch_types::milli::heed::CompactionOption;
 use meilisearch_types::milli::update::{
-    DeleteDocuments, DocumentDeletionResult, IndexDocumentsConfig, IndexDocumentsMethod,
-    Settings as MilliSettings,
+    IndexDocumentsConfig, IndexDocumentsMethod, IndexerConfig, Settings as MilliSettings,
 };
-use meilisearch_types::milli::{self, Filter, BEU32};
+use meilisearch_types::milli::{self, Filter};
 use meilisearch_types::settings::{apply_settings_to_builder, Settings, Unchecked};
 use meilisearch_types::tasks::{Details, IndexSwap, Kind, KindWithContent, Status, Task};
 use meilisearch_types::{compression, Index, VERSION_FILE_NAME};
@@ -44,7 +42,7 @@ use uuid::Uuid;
 
 use crate::autobatcher::{self, BatchKind};
 use crate::utils::{self, swap_index_uid_in_task};
-use crate::{Error, IndexScheduler, ProcessingTasks, Result, TaskId};
+use crate::{Error, IndexScheduler, MustStopProcessing, ProcessingTasks, Result, TaskId};
 
 /// Represents a combination of tasks that can all be processed at the same time.
 ///
@@ -61,7 +59,7 @@ pub(crate) enum Batch {
         /// The list of tasks that were processing when this task cancelation appeared.
         previous_processing_tasks: RoaringBitmap,
     },
-    TaskDeletion(Task),
+    TaskDeletions(Vec<Task>),
     SnapshotCreation(Vec<Task>),
     Dump(Task),
     IndexOperation {
@@ -105,12 +103,6 @@ pub(crate) enum IndexOperation {
         operations: Vec<DocumentOperation>,
         tasks: Vec<Task>,
     },
-    DocumentDeletion {
-        index_uid: String,
-        // The vec associated with each document deletion tasks.
-        documents: Vec<Vec<String>>,
-        tasks: Vec<Task>,
-    },
     IndexDocumentDeletionByFilter {
         index_uid: String,
         task: Task,
@@ -150,24 +142,28 @@ pub(crate) enum IndexOperation {
 
 impl Batch {
     /// Return the task ids associated with this batch.
-    pub fn ids(&self) -> Vec<TaskId> {
+    pub fn ids(&self) -> RoaringBitmap {
         match self {
             Batch::TaskCancelation { task, .. }
-            | Batch::TaskDeletion(task)
             | Batch::Dump(task)
             | Batch::IndexCreation { task, .. }
-            | Batch::IndexUpdate { task, .. } => vec![task.uid],
-            Batch::SnapshotCreation(tasks) | Batch::IndexDeletion { tasks, .. } => {
-                tasks.iter().map(|task| task.uid).collect()
+            | Batch::IndexUpdate { task, .. } => {
+                RoaringBitmap::from_sorted_iter(std::iter::once(task.uid)).unwrap()
+            }
+            Batch::SnapshotCreation(tasks)
+            | Batch::TaskDeletions(tasks)
+            | Batch::IndexDeletion { tasks, .. } => {
+                RoaringBitmap::from_iter(tasks.iter().map(|task| task.uid))
             }
             Batch::IndexOperation { op, .. } => match op {
                 IndexOperation::DocumentOperation { tasks, .. }
-                | IndexOperation::DocumentDeletion { tasks, .. }
                 | IndexOperation::Settings { tasks, .. }
                 | IndexOperation::DocumentClear { tasks, .. } => {
-                    tasks.iter().map(|task| task.uid).collect()
+                    RoaringBitmap::from_iter(tasks.iter().map(|task| task.uid))
+                }
+                IndexOperation::IndexDocumentDeletionByFilter { task, .. } => {
+                    RoaringBitmap::from_sorted_iter(std::iter::once(task.uid)).unwrap()
                 }
-                IndexOperation::IndexDocumentDeletionByFilter { task, .. } => vec![task.uid],
                 IndexOperation::SettingsAndDocumentOperation {
                     document_import_tasks: tasks,
                     settings_tasks: other,
@@ -177,9 +173,11 @@ impl Batch {
                     cleared_tasks: tasks,
                     settings_tasks: other,
                     ..
-                } => tasks.iter().chain(other).map(|task| task.uid).collect(),
+                } => RoaringBitmap::from_iter(tasks.iter().chain(other).map(|task| task.uid)),
             },
-            Batch::IndexSwap { task } => vec![task.uid],
+            Batch::IndexSwap { task } => {
+                RoaringBitmap::from_sorted_iter(std::iter::once(task.uid)).unwrap()
+            }
         }
     }
 
@@ -188,7 +186,7 @@ impl Batch {
         use Batch::*;
         match self {
             TaskCancelation { .. }
-            | TaskDeletion(_)
+            | TaskDeletions(_)
             | SnapshotCreation(_)
             | Dump(_)
             | IndexSwap { .. } => None,
@@ -207,7 +205,7 @@ impl fmt::Display for Batch {
         let tasks = self.ids();
         match self {
             Batch::TaskCancelation { .. } => f.write_str("TaskCancelation")?,
-            Batch::TaskDeletion(_) => f.write_str("TaskDeletion")?,
+            Batch::TaskDeletions(_) => f.write_str("TaskDeletion")?,
             Batch::SnapshotCreation(_) => f.write_str("SnapshotCreation")?,
             Batch::Dump(_) => f.write_str("Dump")?,
             Batch::IndexOperation { op, .. } => write!(f, "{op}")?,
@@ -227,7 +225,6 @@ impl IndexOperation {
     pub fn index_uid(&self) -> &str {
         match self {
             IndexOperation::DocumentOperation { index_uid, .. }
-            | IndexOperation::DocumentDeletion { index_uid, .. }
             | IndexOperation::IndexDocumentDeletionByFilter { index_uid, .. }
             | IndexOperation::DocumentClear { index_uid, .. }
             | IndexOperation::Settings { index_uid, .. }
@@ -243,9 +240,6 @@ impl fmt::Display for IndexOperation {
             IndexOperation::DocumentOperation { .. } => {
                 f.write_str("IndexOperation::DocumentOperation")
             }
-            IndexOperation::DocumentDeletion { .. } => {
-                f.write_str("IndexOperation::DocumentDeletion")
-            }
             IndexOperation::IndexDocumentDeletionByFilter { .. } => {
                 f.write_str("IndexOperation::IndexDocumentDeletionByFilter")
             }
@@ -348,18 +342,27 @@ impl IndexScheduler {
             BatchKind::DocumentDeletion { deletion_ids } => {
                 let tasks = self.get_existing_tasks(rtxn, deletion_ids)?;
 
-                let mut documents = Vec::new();
+                let mut operations = Vec::with_capacity(tasks.len());
+                let mut documents_counts = Vec::with_capacity(tasks.len());
                 for task in &tasks {
                     match task.kind {
                         KindWithContent::DocumentDeletion { ref documents_ids, .. } => {
-                            documents.push(documents_ids.clone())
+                            operations.push(DocumentOperation::Delete(documents_ids.clone()));
+                            documents_counts.push(documents_ids.len() as u64);
                         }
                         _ => unreachable!(),
                     }
                 }
 
                 Ok(Some(Batch::IndexOperation {
-                    op: IndexOperation::DocumentDeletion { index_uid, documents, tasks },
+                    op: IndexOperation::DocumentOperation {
+                        index_uid,
+                        primary_key: None,
+                        method: IndexDocumentsMethod::ReplaceDocuments,
+                        documents_counts,
+                        operations,
+                        tasks,
+                    },
                     must_create_index,
                 }))
             }
@@ -518,6 +521,7 @@ impl IndexScheduler {
     /// 3. We get the *next* snapshot to process.
     /// 4. We get the *next* dump to process.
     /// 5. We get the *next* tasks to process for a specific index.
+    #[tracing::instrument(level = "trace", skip(self, rtxn), target = "indexing::scheduler")]
     pub(crate) fn create_next_batch(&self, rtxn: &RoTxn) -> Result<Option<Batch>> {
         #[cfg(test)]
         self.maybe_fail(crate::tests::FailureLocation::InsideCreateBatch)?;
@@ -542,9 +546,9 @@ impl IndexScheduler {
 
         // 2. we get the next task to delete
         let to_delete = self.get_kind(rtxn, Kind::TaskDeletion)? & enqueued;
-        if let Some(task_id) = to_delete.min() {
-            let task = self.get_task(rtxn, task_id)?.ok_or(Error::CorruptedTaskQueue)?;
-            return Ok(Some(Batch::TaskDeletion(task)));
+        if !to_delete.is_empty() {
+            let tasks = self.get_existing_tasks(rtxn, to_delete)?;
+            return Ok(Some(Batch::TaskDeletions(tasks)));
         }
 
         // 3. we batch the snapshot.
@@ -587,7 +591,9 @@ impl IndexScheduler {
         let index_tasks = self.index_tasks(rtxn, index_name)? & enqueued;
 
         // If autobatching is disabled we only take one task at a time.
-        let tasks_limit = if self.autobatching_enabled { usize::MAX } else { 1 };
+        // Otherwise, we take only a maximum of tasks to create batches.
+        let tasks_limit =
+            if self.autobatching_enabled { self.max_number_of_batched_tasks } else { 1 };
 
         let enqueued = index_tasks
             .into_iter()
@@ -621,6 +627,7 @@ impl IndexScheduler {
     /// The list of tasks that were processed. The metadata of each task in the returned
     /// list is updated accordingly, with the exception of the its date fields
     /// [`finished_at`](meilisearch_types::tasks::Task::finished_at) and [`started_at`](meilisearch_types::tasks::Task::started_at).
+    #[tracing::instrument(level = "trace", skip(self, batch), target = "indexing::scheduler", fields(batch=batch.to_string()))]
     pub(crate) fn process_batch(&self, batch: Batch) -> Result<Vec<Task>> {
         #[cfg(test)]
         {
@@ -670,9 +677,10 @@ impl IndexScheduler {
                     Ok(()) => {
                         for content_uuid in canceled_tasks_content_uuids {
                             if let Err(error) = self.delete_update_file(content_uuid) {
-                                error!(
-                                    "We failed deleting the content file indentified as {}: {}",
-                                    content_uuid, error
+                                tracing::error!(
+                                    file_content_uuid = %content_uuid,
+                                    %error,
+                                    "Failed deleting content file"
                                 )
                             }
                         }
@@ -682,31 +690,43 @@ impl IndexScheduler {
 
                 Ok(vec![task])
             }
-            Batch::TaskDeletion(mut task) => {
+            Batch::TaskDeletions(mut tasks) => {
                 // 1. Retrieve the tasks that matched the query at enqueue-time.
-                let matched_tasks =
+                let mut matched_tasks = RoaringBitmap::new();
+
+                for task in tasks.iter() {
                     if let KindWithContent::TaskDeletion { tasks, query: _ } = &task.kind {
-                        tasks
+                        matched_tasks |= tasks;
                     } else {
                         unreachable!()
+                    }
+                }
+
+                let mut wtxn = self.env.write_txn()?;
+                let mut deleted_tasks = self.delete_matched_tasks(&mut wtxn, &matched_tasks)?;
+                wtxn.commit()?;
+
+                for task in tasks.iter_mut() {
+                    task.status = Status::Succeeded;
+                    let KindWithContent::TaskDeletion { tasks, query: _ } = &task.kind else {
+                        unreachable!()
                     };
 
-                let mut wtxn = self.env.write_txn()?;
-                let deleted_tasks_count = self.delete_matched_tasks(&mut wtxn, matched_tasks)?;
+                    let deleted_tasks_count = deleted_tasks.intersection_len(tasks);
+                    deleted_tasks -= tasks;
 
-                task.status = Status::Succeeded;
-                match &mut task.details {
-                    Some(Details::TaskDeletion {
-                        matched_tasks: _,
-                        deleted_tasks,
-                        original_filter: _,
-                    }) => {
-                        *deleted_tasks = Some(deleted_tasks_count);
+                    match &mut task.details {
+                        Some(Details::TaskDeletion {
+                            matched_tasks: _,
+                            deleted_tasks,
+                            original_filter: _,
+                        }) => {
+                            *deleted_tasks = Some(deleted_tasks_count);
+                        }
+                        _ => unreachable!(),
                     }
-                    _ => unreachable!(),
                 }
-                wtxn.commit()?;
-                Ok(vec![task])
+                Ok(tasks)
             }
             Batch::SnapshotCreation(mut tasks) => {
                 fs::create_dir_all(&self.snapshots_path)?;
@@ -718,7 +738,7 @@ impl IndexScheduler {
 
                 // 2. Snapshot the index-scheduler LMDB env
                 //
-                // When we call copy_to_path, LMDB opens a read transaction by itself,
+                // When we call copy_to_file, 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.
@@ -731,7 +751,7 @@ impl IndexScheduler {
                 // 2.1 First copy the LMDB env of the index-scheduler
                 let dst = temp_snapshot_dir.path().join("tasks");
                 fs::create_dir_all(&dst)?;
-                self.env.copy_to_path(dst.join("data.mdb"), CompactionOption::Enabled)?;
+                self.env.copy_to_file(dst.join("data.mdb"), CompactionOption::Enabled)?;
 
                 // 2.2 Create a read transaction on the index-scheduler
                 let rtxn = self.env.read_txn()?;
@@ -756,7 +776,7 @@ impl IndexScheduler {
                     let index = self.index_mapper.index(&rtxn, name)?;
                     let dst = temp_snapshot_dir.path().join("indexes").join(uuid.to_string());
                     fs::create_dir_all(&dst)?;
-                    index.copy_to_path(dst.join("data.mdb"), CompactionOption::Enabled)?;
+                    index.copy_to_file(dst.join("data.mdb"), CompactionOption::Enabled)?;
                 }
 
                 drop(rtxn);
@@ -769,7 +789,7 @@ impl IndexScheduler {
                     .map_size(1024 * 1024 * 1024) // 1 GiB
                     .max_dbs(2)
                     .open(&self.auth_path)?;
-                auth.copy_to_path(dst.join("data.mdb"), CompactionOption::Enabled)?;
+                auth.copy_to_file(dst.join("data.mdb"), CompactionOption::Enabled)?;
 
                 // 5. Copy and tarball the flat snapshot
                 // 5.1 Find the original name of the database
@@ -825,6 +845,10 @@ impl IndexScheduler {
                 // 2. dump the tasks
                 let mut dump_tasks = dump.create_tasks_queue()?;
                 for ret in self.all_tasks.iter(&rtxn)? {
+                    if self.must_stop_processing.get() {
+                        return Err(Error::AbortedTask);
+                    }
+
                     let (_, mut t) = ret?;
                     let status = t.status;
                     let content_file = t.content_uuid();
@@ -845,6 +869,9 @@ impl IndexScheduler {
 
                     // 2.1. Dump the `content_file` associated with the task if there is one and the task is not finished yet.
                     if let Some(content_file) = content_file {
+                        if self.must_stop_processing.get() {
+                            return Err(Error::AbortedTask);
+                        }
                         if status == Status::Enqueued {
                             let content_file = self.file_store.get_update(content_file)?;
 
@@ -884,13 +911,20 @@ impl IndexScheduler {
 
                     // 3.1. Dump the documents
                     for ret in index.all_documents(&rtxn)? {
+                        if self.must_stop_processing.get() {
+                            return Err(Error::AbortedTask);
+                        }
                         let (_id, doc) = ret?;
                         let document = milli::obkv_to_json(&all_fields, &fields_ids_map, doc)?;
                         index_dumper.push_document(&document)?;
                     }
 
                     // 3.2. Dump the settings
-                    let settings = meilisearch_types::settings::settings(index, &rtxn)?;
+                    let settings = meilisearch_types::settings::settings(
+                        index,
+                        &rtxn,
+                        meilisearch_types::settings::SecretPolicy::RevealSecrets,
+                    )?;
                     index_dumper.settings(&settings)?;
                     Ok(())
                 })?;
@@ -903,6 +937,9 @@ impl IndexScheduler {
                     "[year repr:full][month repr:numerical][day padding:zero]-[hour padding:zero][minute padding:zero][second padding:zero][subsecond digits:3]"
                 )).unwrap();
 
+                if self.must_stop_processing.get() {
+                    return Err(Error::AbortedTask);
+                }
                 let path = self.dumps_path.join(format!("{}.dump", dump_uid));
                 let file = File::create(path)?;
                 dump.persist_to(BufWriter::new(file))?;
@@ -923,6 +960,10 @@ impl IndexScheduler {
                     self.index_mapper.index(&rtxn, &index_uid)?
                 };
 
+                // the index operation can take a long time, so save this handle to make it available to the search for the duration of the tick
+                self.index_mapper
+                    .set_currently_updating_index(Some((index_uid.clone(), index.clone())));
+
                 let mut index_wtxn = index.write_txn()?;
                 let tasks = self.apply_index_operation(&mut index_wtxn, &index, op)?;
                 index_wtxn.commit()?;
@@ -942,7 +983,10 @@ impl IndexScheduler {
 
                 match res {
                     Ok(_) => (),
-                    Err(e) => error!("Could not write the stats of the index {}", e),
+                    Err(e) => tracing::error!(
+                        error = &e as &dyn std::error::Error,
+                        "Could not write the stats of the index"
+                    ),
                 }
 
                 Ok(tasks)
@@ -970,7 +1014,7 @@ impl IndexScheduler {
                     builder.set_primary_key(primary_key);
                     let must_stop_processing = self.must_stop_processing.clone();
                     builder.execute(
-                        |indexing_step| debug!("update: {:?}", indexing_step),
+                        |indexing_step| tracing::debug!(update = ?indexing_step),
                         || must_stop_processing.get(),
                     )?;
                     index_wtxn.commit()?;
@@ -997,7 +1041,10 @@ impl IndexScheduler {
 
                 match res {
                     Ok(_) => (),
-                    Err(e) => error!("Could not write the stats of the index {}", e),
+                    Err(e) => tracing::error!(
+                        error = &e as &dyn std::error::Error,
+                        "Could not write the stats of the index"
+                    ),
                 }
 
                 Ok(vec![task])
@@ -1092,7 +1139,7 @@ impl IndexScheduler {
         for task_id in &index_lhs_task_ids | &index_rhs_task_ids {
             let mut task = self.get_task(wtxn, task_id)?.ok_or(Error::CorruptedTaskQueue)?;
             swap_index_uid_in_task(&mut task, (lhs, rhs));
-            self.all_tasks.put(wtxn, &BEU32::new(task_id), &task)?;
+            self.all_tasks.put(wtxn, &task_id, &task)?;
         }
 
         // 4. remove the task from indexuid = before_name
@@ -1116,9 +1163,14 @@ impl IndexScheduler {
     ///
     /// ## Return
     /// The list of processed tasks.
+    #[tracing::instrument(
+        level = "trace",
+        skip(self, index_wtxn, index),
+        target = "indexing::scheduler"
+    )]
     fn apply_index_operation<'i>(
         &self,
-        index_wtxn: &mut RwTxn<'i, '_>,
+        index_wtxn: &mut RwTxn<'i>,
         index: &'i Index,
         operation: IndexOperation,
     ) -> Result<Vec<Task>> {
@@ -1176,7 +1228,7 @@ impl IndexScheduler {
                                 milli::update::Settings::new(index_wtxn, index, indexer_config);
                             builder.set_primary_key(primary_key);
                             builder.execute(
-                                |indexing_step| debug!("update: {:?}", indexing_step),
+                                |indexing_step| tracing::debug!(update = ?indexing_step),
                                 || must_stop_processing.clone().get(),
                             )?;
                             primary_key_has_been_set = true;
@@ -1186,12 +1238,16 @@ impl IndexScheduler {
 
                 let config = IndexDocumentsConfig { update_method: method, ..Default::default() };
 
+                let embedder_configs = index.embedding_configs(index_wtxn)?;
+                // TODO: consider Arc'ing the map too (we only need read access + we'll be cloning it multiple times, so really makes sense)
+                let embedders = self.embedders(embedder_configs)?;
+
                 let mut builder = milli::update::IndexDocuments::new(
                     index_wtxn,
                     index,
                     indexer_config,
                     config,
-                    |indexing_step| debug!("update: {:?}", indexing_step),
+                    |indexing_step| tracing::trace!(?indexing_step, "Update"),
                     || must_stop_processing.get(),
                 )?;
 
@@ -1204,6 +1260,8 @@ impl IndexScheduler {
                             let (new_builder, user_result) = builder.add_documents(reader)?;
                             builder = new_builder;
 
+                            builder = builder.with_embedders(embedders.clone());
+
                             let received_documents =
                                 if let Some(Details::DocumentAdditionOrUpdate {
                                     received_documents,
@@ -1238,7 +1296,8 @@ impl IndexScheduler {
                             let (new_builder, user_result) =
                                 builder.remove_documents(document_ids)?;
                             builder = new_builder;
-
+                            // Uses Invariant: remove documents actually always returns Ok for the inner result
+                            let count = user_result.unwrap();
                             let provided_ids =
                                 if let Some(Details::DocumentDeletion { provided_ids, .. }) =
                                     task.details
@@ -1249,30 +1308,18 @@ impl IndexScheduler {
                                     unreachable!();
                                 };
 
-                            match user_result {
-                                Ok(count) => {
-                                    task.status = Status::Succeeded;
-                                    task.details = Some(Details::DocumentDeletion {
-                                        provided_ids,
-                                        deleted_documents: Some(count),
-                                    });
-                                }
-                                Err(e) => {
-                                    task.status = Status::Failed;
-                                    task.details = Some(Details::DocumentDeletion {
-                                        provided_ids,
-                                        deleted_documents: Some(0),
-                                    });
-                                    task.error = Some(milli::Error::from(e).into());
-                                }
-                            }
+                            task.status = Status::Succeeded;
+                            task.details = Some(Details::DocumentDeletion {
+                                provided_ids,
+                                deleted_documents: Some(count),
+                            });
                         }
                     }
                 }
 
                 if !tasks.iter().all(|res| res.error.is_some()) {
                     let addition = builder.execute()?;
-                    info!("document addition done: {:?}", addition);
+                    tracing::info!(indexing_result = ?addition, "document indexing done");
                 } else if primary_key_has_been_set {
                     // Everything failed but we've set a primary key.
                     // We need to remove it.
@@ -1280,31 +1327,13 @@ impl IndexScheduler {
                         milli::update::Settings::new(index_wtxn, index, indexer_config);
                     builder.reset_primary_key();
                     builder.execute(
-                        |indexing_step| debug!("update: {:?}", indexing_step),
+                        |indexing_step| tracing::trace!(update = ?indexing_step),
                         || must_stop_processing.clone().get(),
                     )?;
                 }
 
                 Ok(tasks)
             }
-            IndexOperation::DocumentDeletion { index_uid: _, documents, mut tasks } => {
-                let mut builder = milli::update::DeleteDocuments::new(index_wtxn, index)?;
-                documents.iter().flatten().for_each(|id| {
-                    builder.delete_external_id(id);
-                });
-
-                let DocumentDeletionResult { deleted_documents, .. } = builder.execute()?;
-
-                for (task, documents) in tasks.iter_mut().zip(documents) {
-                    task.status = Status::Succeeded;
-                    task.details = Some(Details::DocumentDeletion {
-                        provided_ids: documents.len(),
-                        deleted_documents: Some(deleted_documents.min(documents.len() as u64)),
-                    });
-                }
-
-                Ok(tasks)
-            }
             IndexOperation::IndexDocumentDeletionByFilter { mut task, index_uid: _ } => {
                 let filter =
                     if let KindWithContent::DocumentDeletionByFilter { filter_expr, .. } =
@@ -1314,7 +1343,13 @@ impl IndexScheduler {
                     } else {
                         unreachable!()
                     };
-                let deleted_documents = delete_document_by_filter(index_wtxn, filter, index);
+                let deleted_documents = delete_document_by_filter(
+                    index_wtxn,
+                    filter,
+                    self.index_mapper.indexer_config(),
+                    self.must_stop_processing.clone(),
+                    index,
+                );
                 let original_filter = if let Some(Details::DocumentDeletionByFilter {
                     original_filter,
                     deleted_documents: _,
@@ -1362,7 +1397,7 @@ impl IndexScheduler {
 
                 let must_stop_processing = self.must_stop_processing.clone();
                 builder.execute(
-                    |indexing_step| debug!("update: {:?}", indexing_step),
+                    |indexing_step| tracing::debug!(update = ?indexing_step),
                     || must_stop_processing.get(),
                 )?;
 
@@ -1436,7 +1471,11 @@ impl IndexScheduler {
     /// Delete each given task from all the databases (if it is deleteable).
     ///
     /// Return the number of tasks that were actually deleted.
-    fn delete_matched_tasks(&self, wtxn: &mut RwTxn, matched_tasks: &RoaringBitmap) -> Result<u64> {
+    fn delete_matched_tasks(
+        &self,
+        wtxn: &mut RwTxn,
+        matched_tasks: &RoaringBitmap,
+    ) -> Result<RoaringBitmap> {
         // 1. Remove from this list the tasks that we are not allowed to delete
         let enqueued_tasks = self.get_status(wtxn, Status::Enqueued)?;
         let processing_tasks = &self.processing_tasks.read().unwrap().processing.clone();
@@ -1488,10 +1527,9 @@ impl IndexScheduler {
         }
 
         for task in to_delete_tasks.iter() {
-            self.all_tasks.delete(wtxn, &BEU32::new(task))?;
+            self.all_tasks.delete(wtxn, &task)?;
         }
         for canceled_by in affected_canceled_by {
-            let canceled_by = BEU32::new(canceled_by);
             if let Some(mut tasks) = self.canceled_by.get(wtxn, &canceled_by)? {
                 tasks -= &to_delete_tasks;
                 if tasks.is_empty() {
@@ -1502,7 +1540,7 @@ impl IndexScheduler {
             }
         }
 
-        Ok(to_delete_tasks.len())
+        Ok(to_delete_tasks)
     }
 
     /// Cancel each given task from all the databases (if it is cancelable).
@@ -1539,15 +1577,17 @@ impl IndexScheduler {
             task.details = task.details.map(|d| d.to_failed());
             self.update_task(wtxn, &task)?;
         }
-        self.canceled_by.put(wtxn, &BEU32::new(cancel_task_id), &tasks_to_cancel)?;
+        self.canceled_by.put(wtxn, &cancel_task_id, &tasks_to_cancel)?;
 
         Ok(content_files_to_delete)
     }
 }
 
 fn delete_document_by_filter<'a>(
-    wtxn: &mut RwTxn<'a, '_>,
+    wtxn: &mut RwTxn<'a>,
     filter: &serde_json::Value,
+    indexer_config: &IndexerConfig,
+    must_stop_processing: MustStopProcessing,
     index: &'a Index,
 ) -> Result<u64> {
     let filter = Filter::from_json(filter)?;
@@ -1558,9 +1598,26 @@ fn delete_document_by_filter<'a>(
             }
             e => e.into(),
         })?;
-        let mut delete_operation = DeleteDocuments::new(wtxn, index)?;
-        delete_operation.delete_documents(&candidates);
-        delete_operation.execute().map(|result| result.deleted_documents)?
+
+        let config = IndexDocumentsConfig {
+            update_method: IndexDocumentsMethod::ReplaceDocuments,
+            ..Default::default()
+        };
+
+        let mut builder = milli::update::IndexDocuments::new(
+            wtxn,
+            index,
+            indexer_config,
+            config,
+            |indexing_step| tracing::debug!(update = ?indexing_step),
+            || must_stop_processing.get(),
+        )?;
+
+        let (new_builder, count) = builder.remove_documents_from_db_no_batch(&candidates)?;
+        builder = new_builder;
+
+        let _ = builder.execute()?;
+        count
     } else {
         0
     })

index-scheduler/src/error.rs

@@ -48,6 +48,8 @@ impl From<DateField> for Code {
 pub enum Error {
     #[error("{1}")]
     WithCustomErrorCode(Code, Box<Self>),
+    #[error("Received bad task id: {received} should be >= to {expected}.")]
+    BadTaskId { received: TaskId, expected: TaskId },
     #[error("Index `{0}` not found.")]
     IndexNotFound(String),
     #[error("Index `{0}` already exists.")]
@@ -108,6 +110,8 @@ pub enum Error {
     TaskDeletionWithEmptyQuery,
     #[error("Query parameters to filter the tasks to cancel are missing. Available query parameters are: `uids`, `indexUids`, `statuses`, `types`, `canceledBy`, `beforeEnqueuedAt`, `afterEnqueuedAt`, `beforeStartedAt`, `afterStartedAt`, `beforeFinishedAt`, `afterFinishedAt`.")]
     TaskCancelationWithEmptyQuery,
+    #[error("Aborted task")]
+    AbortedTask,
 
     #[error(transparent)]
     Dump(#[from] dump::Error),
@@ -159,6 +163,7 @@ impl Error {
         match self {
             Error::IndexNotFound(_)
             | Error::WithCustomErrorCode(_, _)
+            | Error::BadTaskId { .. }
             | Error::IndexAlreadyExists(_)
             | Error::SwapDuplicateIndexFound(_)
             | Error::SwapDuplicateIndexesFound(_)
@@ -175,6 +180,7 @@ impl Error {
             | Error::TaskNotFound(_)
             | Error::TaskDeletionWithEmptyQuery
             | Error::TaskCancelationWithEmptyQuery
+            | Error::AbortedTask
             | Error::Dump(_)
             | Error::Heed(_)
             | Error::Milli(_)
@@ -202,6 +208,7 @@ impl ErrorCode for Error {
     fn error_code(&self) -> Code {
         match self {
             Error::WithCustomErrorCode(code, _) => *code,
+            Error::BadTaskId { .. } => Code::BadRequest,
             Error::IndexNotFound(_) => Code::IndexNotFound,
             Error::IndexAlreadyExists(_) => Code::IndexAlreadyExists,
             Error::SwapDuplicateIndexesFound(_) => Code::InvalidSwapDuplicateIndexFound,
@@ -236,6 +243,9 @@ impl ErrorCode for Error {
             Error::TaskDatabaseUpdate(_) => Code::Internal,
             Error::CreateBatch(_) => Code::Internal,
 
+            // This one should never be seen by the end user
+            Error::AbortedTask => Code::Internal,
+
             #[cfg(test)]
             Error::PlannedFailure => Code::Internal,
         }

index-scheduler/src/features.rs

@@ -30,19 +30,6 @@ impl RoFeatures {
         self.runtime
     }
 
-    pub fn check_score_details(&self) -> Result<()> {
-        if self.runtime.score_details {
-            Ok(())
-        } else {
-            Err(FeatureNotEnabledError {
-                disabled_action: "Computing score details",
-                feature: "score details",
-                issue_link: "https://github.com/meilisearch/product/discussions/674",
-            }
-            .into())
-        }
-    }
-
     pub fn check_metrics(&self) -> Result<()> {
         if self.runtime.metrics {
             Ok(())
@@ -56,12 +43,25 @@ impl RoFeatures {
         }
     }
 
-    pub fn check_vector(&self) -> Result<()> {
+    pub fn check_logs_route(&self) -> Result<()> {
+        if self.runtime.logs_route {
+            Ok(())
+        } else {
+            Err(FeatureNotEnabledError {
+                disabled_action: "Modifying logs through the `/logs/*` routes",
+                feature: "logs route",
+                issue_link: "https://github.com/orgs/meilisearch/discussions/721",
+            }
+            .into())
+        }
+    }
+
+    pub fn check_vector(&self, disabled_action: &'static str) -> Result<()> {
         if self.runtime.vector_store {
             Ok(())
         } else {
             Err(FeatureNotEnabledError {
-                disabled_action: "Passing `vector` as a query parameter",
+                disabled_action,
                 feature: "vector store",
                 issue_link: "https://github.com/meilisearch/product/discussions/677",
             }
@@ -94,6 +94,7 @@ impl FeatureData {
             runtime_features_db.get(&txn, EXPERIMENTAL_FEATURES)?.unwrap_or_default();
         let runtime = Arc::new(RwLock::new(RuntimeTogglableFeatures {
             metrics: instance_features.metrics || persisted_features.metrics,
+            logs_route: instance_features.logs_route || persisted_features.logs_route,
             ..persisted_features
         }));
 

index-scheduler/src/index_mapper/index_map.rs

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

index-scheduler/src/index_mapper/mod.rs

@@ -3,13 +3,13 @@ use std::sync::{Arc, RwLock};
 use std::time::Duration;
 use std::{fs, thread};
 
-use log::error;
 use meilisearch_types::heed::types::{SerdeJson, Str};
 use meilisearch_types::heed::{Database, Env, RoTxn, RwTxn};
 use meilisearch_types::milli::update::IndexerConfig;
 use meilisearch_types::milli::{FieldDistribution, Index};
 use serde::{Deserialize, Serialize};
 use time::OffsetDateTime;
+use tracing::error;
 use uuid::Uuid;
 
 use self::index_map::IndexMap;
@@ -69,6 +69,10 @@ pub struct IndexMapper {
     /// Whether we open a meilisearch index with the MDB_WRITEMAP option or not.
     enable_mdb_writemap: bool,
     pub indexer_config: Arc<IndexerConfig>,
+
+    /// A few types of long running batches of tasks that act on a single index set this field
+    /// so that a handle to the index is available from other threads (search) in an optimized manner.
+    currently_updating_index: Arc<RwLock<Option<(String, Index)>>>,
 }
 
 /// Whether the index is available for use or is forbidden to be inserted back in the index map
@@ -151,6 +155,7 @@ impl IndexMapper {
             index_growth_amount,
             enable_mdb_writemap,
             indexer_config: Arc::new(indexer_config),
+            currently_updating_index: Default::default(),
         })
     }
 
@@ -303,6 +308,14 @@ impl IndexMapper {
 
     /// Return an index, may open it if it wasn't already opened.
     pub fn index(&self, rtxn: &RoTxn, name: &str) -> Result<Index> {
+        if let Some((current_name, current_index)) =
+            self.currently_updating_index.read().unwrap().as_ref()
+        {
+            if current_name == name {
+                return Ok(current_index.clone());
+            }
+        }
+
         let uuid = self
             .index_mapping
             .get(rtxn, name)?
@@ -474,4 +487,8 @@ impl IndexMapper {
     pub fn indexer_config(&self) -> &IndexerConfig {
         &self.indexer_config
     }
+
+    pub fn set_currently_updating_index(&self, index: Option<(String, Index)>) {
+        *self.currently_updating_index.write().unwrap() = index;
+    }
 }

index-scheduler/src/insta_snapshot.rs

@@ -1,7 +1,7 @@
 use std::collections::BTreeSet;
 use std::fmt::Write;
 
-use meilisearch_types::heed::types::{OwnedType, SerdeBincode, SerdeJson, Str};
+use meilisearch_types::heed::types::{SerdeBincode, SerdeJson, Str};
 use meilisearch_types::heed::{Database, RoTxn};
 use meilisearch_types::milli::{CboRoaringBitmapCodec, RoaringBitmapCodec, BEU32};
 use meilisearch_types::tasks::{Details, Task};
@@ -15,6 +15,7 @@ pub fn snapshot_index_scheduler(scheduler: &IndexScheduler) -> String {
 
     let IndexScheduler {
         autobatching_enabled,
+        cleanup_enabled: _,
         must_stop_processing: _,
         processing_tasks,
         file_store,
@@ -30,15 +31,19 @@ pub fn snapshot_index_scheduler(scheduler: &IndexScheduler) -> String {
         index_mapper,
         features: _,
         max_number_of_tasks: _,
+        max_number_of_batched_tasks: _,
         puffin_frame: _,
         wake_up: _,
         dumps_path: _,
         snapshots_path: _,
         auth_path: _,
         version_file_path: _,
+        webhook_url: _,
+        webhook_authorization_header: _,
         test_breakpoint_sdr: _,
         planned_failures: _,
         run_loop_iteration: _,
+        embedders: _,
     } = scheduler;
 
     let rtxn = env.read_txn().unwrap();
@@ -114,7 +119,7 @@ pub fn snapshot_bitmap(r: &RoaringBitmap) -> String {
     snap
 }
 
-pub fn snapshot_all_tasks(rtxn: &RoTxn, db: Database<OwnedType<BEU32>, SerdeJson<Task>>) -> String {
+pub fn snapshot_all_tasks(rtxn: &RoTxn, db: Database<BEU32, SerdeJson<Task>>) -> String {
     let mut snap = String::new();
     let iter = db.iter(rtxn).unwrap();
     for next in iter {
@@ -124,10 +129,7 @@ pub fn snapshot_all_tasks(rtxn: &RoTxn, db: Database<OwnedType<BEU32>, SerdeJson
     snap
 }
 
-pub fn snapshot_date_db(
-    rtxn: &RoTxn,
-    db: Database<OwnedType<BEI128>, CboRoaringBitmapCodec>,
-) -> String {
+pub fn snapshot_date_db(rtxn: &RoTxn, db: Database<BEI128, CboRoaringBitmapCodec>) -> String {
     let mut snap = String::new();
     let iter = db.iter(rtxn).unwrap();
     for next in iter {
@@ -247,10 +249,7 @@ pub fn snapshot_index_tasks(rtxn: &RoTxn, db: Database<Str, RoaringBitmapCodec>)
     }
     snap
 }
-pub fn snapshot_canceled_by(
-    rtxn: &RoTxn,
-    db: Database<OwnedType<BEU32>, RoaringBitmapCodec>,
-) -> String {
+pub fn snapshot_canceled_by(rtxn: &RoTxn, db: Database<BEU32, RoaringBitmapCodec>) -> String {
     let mut snap = String::new();
     let iter = db.iter(rtxn).unwrap();
     for next in iter {

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

@@ -0,0 +1,13 @@
+---
+source: index-scheduler/src/lib.rs
+expression: task.details
+---
+{
+  "embedders": {
+    "default": {
+      "source": "rest",
+      "apiKey": "MyXXXX...",
+      "url": "http://localhost:7777"
+    }
+  }
+}

index-scheduler/src/snapshots/index_scheduler__tests__settings_update-3.snap

@@ -0,0 +1,23 @@
+---
+source: index-scheduler/src/lib.rs
+expression: embedding_config.embedder_options
+---
+{
+  "Rest": {
+    "api_key": "My super secret",
+    "distribution": null,
+    "dimensions": null,
+    "url": "http://localhost:7777",
+    "query": null,
+    "input_field": [
+      "input"
+    ],
+    "path_to_embeddings": [
+      "data"
+    ],
+    "embedding_object": [
+      "embedding"
+    ],
+    "input_type": "text"
+  }
+}

index-scheduler/src/snapshots/index_scheduler__tests__settings_update.snap

@@ -0,0 +1,13 @@
+---
+source: index-scheduler/src/lib.rs
+expression: task.details
+---
+{
+  "embedders": {
+    "default": {
+      "source": "rest",
+      "apiKey": "MyXXXX...",
+      "url": "http://localhost:7777"
+    }
+  }
+}

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

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

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

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

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

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

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

@@ -34,12 +34,10 @@ catto: { number_of_documents: 1, field_distribution: {"id": 1} }
 [timestamp] [3,]
 ----------------------------------------------------------------------
 ### Started At:
-[timestamp] [2,]
-[timestamp] [3,]
+[timestamp] [2,3,]
 ----------------------------------------------------------------------
 ### Finished At:
-[timestamp] [2,]
-[timestamp] [3,]
+[timestamp] [2,3,]
 ----------------------------------------------------------------------
 ### File Store:
 00000000-0000-0000-0000-000000000001

index-scheduler/src/snapshots/lib.rs/test_disable_auto_deletion_of_tasks/task_deletion_have_not_been_enqueued.snap

@@ -0,0 +1,90 @@
+---
+source: index-scheduler/src/lib.rs
+---
+[
+  {
+    "uid": 0,
+    "enqueuedAt": "[date]",
+    "startedAt": "[date]",
+    "finishedAt": "[date]",
+    "error": null,
+    "canceledBy": null,
+    "details": {
+      "IndexInfo": {
+        "primary_key": null
+      }
+    },
+    "status": "succeeded",
+    "kind": {
+      "indexCreation": {
+        "index_uid": "doggo",
+        "primary_key": null
+      }
+    }
+  },
+  {
+    "uid": 1,
+    "enqueuedAt": "[date]",
+    "startedAt": "[date]",
+    "finishedAt": "[date]",
+    "error": {
+      "message": "Index `doggo` already exists.",
+      "code": "index_already_exists",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#index_already_exists"
+    },
+    "canceledBy": null,
+    "details": {
+      "IndexInfo": {
+        "primary_key": null
+      }
+    },
+    "status": "failed",
+    "kind": {
+      "indexCreation": {
+        "index_uid": "doggo",
+        "primary_key": null
+      }
+    }
+  },
+  {
+    "uid": 2,
+    "enqueuedAt": "[date]",
+    "startedAt": "[date]",
+    "finishedAt": "[date]",
+    "error": null,
+    "canceledBy": null,
+    "details": {
+      "IndexInfo": {
+        "primary_key": null
+      }
+    },
+    "status": "enqueued",
+    "kind": {
+      "indexCreation": {
+        "index_uid": "doggo",
+        "primary_key": null
+      }
+    }
+  },
+  {
+    "uid": 3,
+    "enqueuedAt": "[date]",
+    "startedAt": "[date]",
+    "finishedAt": "[date]",
+    "error": null,
+    "canceledBy": null,
+    "details": {
+      "IndexInfo": {
+        "primary_key": null
+      }
+    },
+    "status": "enqueued",
+    "kind": {
+      "indexCreation": {
+        "index_uid": "doggo",
+        "primary_key": null
+      }
+    }
+  }
+]

index-scheduler/src/snapshots/lib.rs/test_disable_auto_deletion_of_tasks/task_queue_is_full.snap

@@ -0,0 +1,90 @@
+---
+source: index-scheduler/src/lib.rs
+---
+[
+  {
+    "uid": 0,
+    "enqueuedAt": "[date]",
+    "startedAt": "[date]",
+    "finishedAt": "[date]",
+    "error": null,
+    "canceledBy": null,
+    "details": {
+      "IndexInfo": {
+        "primary_key": null
+      }
+    },
+    "status": "succeeded",
+    "kind": {
+      "indexCreation": {
+        "index_uid": "doggo",
+        "primary_key": null
+      }
+    }
+  },
+  {
+    "uid": 1,
+    "enqueuedAt": "[date]",
+    "startedAt": "[date]",
+    "finishedAt": "[date]",
+    "error": {
+      "message": "Index `doggo` already exists.",
+      "code": "index_already_exists",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#index_already_exists"
+    },
+    "canceledBy": null,
+    "details": {
+      "IndexInfo": {
+        "primary_key": null
+      }
+    },
+    "status": "failed",
+    "kind": {
+      "indexCreation": {
+        "index_uid": "doggo",
+        "primary_key": null
+      }
+    }
+  },
+  {
+    "uid": 2,
+    "enqueuedAt": "[date]",
+    "startedAt": "[date]",
+    "finishedAt": "[date]",
+    "error": null,
+    "canceledBy": null,
+    "details": {
+      "IndexInfo": {
+        "primary_key": null
+      }
+    },
+    "status": "enqueued",
+    "kind": {
+      "indexCreation": {
+        "index_uid": "doggo",
+        "primary_key": null
+      }
+    }
+  },
+  {
+    "uid": 3,
+    "enqueuedAt": "[date]",
+    "startedAt": "[date]",
+    "finishedAt": "[date]",
+    "error": null,
+    "canceledBy": null,
+    "details": {
+      "IndexInfo": {
+        "primary_key": null
+      }
+    },
+    "status": "enqueued",
+    "kind": {
+      "indexCreation": {
+        "index_uid": "doggo",
+        "primary_key": null
+      }
+    }
+  }
+]

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

@@ -0,0 +1,36 @@
+---
+source: index-scheduler/src/lib.rs
+---
+### Autobatching Enabled = true
+### Processing Tasks:
+[]
+----------------------------------------------------------------------
+### All Tasks:
+0 {uid: 0, status: enqueued, details: { settings: Settings { displayed_attributes: NotSet, searchable_attributes: 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: NotSet, document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: NotSet, searchable_attributes: 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: NotSet, document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+----------------------------------------------------------------------
+### Status:
+enqueued [0,]
+----------------------------------------------------------------------
+### Kind:
+"settingsUpdate" [0,]
+----------------------------------------------------------------------
+### Index Tasks:
+doggos [0,]
+----------------------------------------------------------------------
+### Index Mapper:
+
+----------------------------------------------------------------------
+### Canceled By:
+
+----------------------------------------------------------------------
+### Enqueued At:
+[timestamp] [0,]
+----------------------------------------------------------------------
+### Started At:
+----------------------------------------------------------------------
+### Finished At:
+----------------------------------------------------------------------
+### File Store:
+
+----------------------------------------------------------------------
+

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

@@ -0,0 +1,40 @@
+---
+source: index-scheduler/src/lib.rs
+---
+### Autobatching Enabled = true
+### Processing Tasks:
+[]
+----------------------------------------------------------------------
+### All Tasks:
+0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: NotSet, searchable_attributes: 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: NotSet, document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: NotSet, searchable_attributes: 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: NotSet, document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+----------------------------------------------------------------------
+### Status:
+enqueued []
+succeeded [0,]
+----------------------------------------------------------------------
+### Kind:
+"settingsUpdate" [0,]
+----------------------------------------------------------------------
+### Index Tasks:
+doggos [0,]
+----------------------------------------------------------------------
+### Index Mapper:
+doggos: { number_of_documents: 0, field_distribution: {} }
+
+----------------------------------------------------------------------
+### Canceled By:
+
+----------------------------------------------------------------------
+### Enqueued At:
+[timestamp] [0,]
+----------------------------------------------------------------------
+### Started At:
+[timestamp] [0,]
+----------------------------------------------------------------------
+### Finished At:
+[timestamp] [0,]
+----------------------------------------------------------------------
+### File Store:
+
+----------------------------------------------------------------------
+

index-scheduler/src/utils.rs

@@ -3,9 +3,9 @@
 use std::collections::{BTreeSet, HashSet};
 use std::ops::Bound;
 
-use meilisearch_types::heed::types::{DecodeIgnore, OwnedType};
+use meilisearch_types::heed::types::DecodeIgnore;
 use meilisearch_types::heed::{Database, RoTxn, RwTxn};
-use meilisearch_types::milli::{CboRoaringBitmapCodec, BEU32};
+use meilisearch_types::milli::CboRoaringBitmapCodec;
 use meilisearch_types::tasks::{Details, IndexSwap, Kind, KindWithContent, Status};
 use roaring::{MultiOps, RoaringBitmap};
 use time::OffsetDateTime;
@@ -18,7 +18,7 @@ impl IndexScheduler {
     }
 
     pub(crate) fn last_task_id(&self, rtxn: &RoTxn) -> Result<Option<TaskId>> {
-        Ok(self.all_tasks.remap_data_type::<DecodeIgnore>().last(rtxn)?.map(|(k, _)| k.get() + 1))
+        Ok(self.all_tasks.remap_data_type::<DecodeIgnore>().last(rtxn)?.map(|(k, _)| k + 1))
     }
 
     pub(crate) fn next_task_id(&self, rtxn: &RoTxn) -> Result<TaskId> {
@@ -26,7 +26,7 @@ impl IndexScheduler {
     }
 
     pub(crate) fn get_task(&self, rtxn: &RoTxn, task_id: TaskId) -> Result<Option<Task>> {
-        Ok(self.all_tasks.get(rtxn, &BEU32::new(task_id))?)
+        Ok(self.all_tasks.get(rtxn, &task_id)?)
     }
 
     /// Convert an iterator to a `Vec` of tasks. The tasks MUST exist or a
@@ -88,7 +88,7 @@ impl IndexScheduler {
             }
         }
 
-        self.all_tasks.put(wtxn, &BEU32::new(task.uid), task)?;
+        self.all_tasks.put(wtxn, &task.uid, task)?;
         Ok(())
     }
 
@@ -169,11 +169,11 @@ impl IndexScheduler {
 
 pub(crate) fn insert_task_datetime(
     wtxn: &mut RwTxn,
-    database: Database<OwnedType<BEI128>, CboRoaringBitmapCodec>,
+    database: Database<BEI128, CboRoaringBitmapCodec>,
     time: OffsetDateTime,
     task_id: TaskId,
 ) -> Result<()> {
-    let timestamp = BEI128::new(time.unix_timestamp_nanos());
+    let timestamp = time.unix_timestamp_nanos();
     let mut task_ids = database.get(wtxn, &timestamp)?.unwrap_or_default();
     task_ids.insert(task_id);
     database.put(wtxn, &timestamp, &RoaringBitmap::from_iter(task_ids))?;
@@ -182,11 +182,11 @@ pub(crate) fn insert_task_datetime(
 
 pub(crate) fn remove_task_datetime(
     wtxn: &mut RwTxn,
-    database: Database<OwnedType<BEI128>, CboRoaringBitmapCodec>,
+    database: Database<BEI128, CboRoaringBitmapCodec>,
     time: OffsetDateTime,
     task_id: TaskId,
 ) -> Result<()> {
-    let timestamp = BEI128::new(time.unix_timestamp_nanos());
+    let timestamp = time.unix_timestamp_nanos();
     if let Some(mut existing) = database.get(wtxn, &timestamp)? {
         existing.remove(task_id);
         if existing.is_empty() {
@@ -202,7 +202,7 @@ pub(crate) fn remove_task_datetime(
 pub(crate) fn keep_tasks_within_datetimes(
     rtxn: &RoTxn,
     tasks: &mut RoaringBitmap,
-    database: Database<OwnedType<BEI128>, CboRoaringBitmapCodec>,
+    database: Database<BEI128, CboRoaringBitmapCodec>,
     after: Option<OffsetDateTime>,
     before: Option<OffsetDateTime>,
 ) -> Result<()> {
@@ -213,8 +213,8 @@ pub(crate) fn keep_tasks_within_datetimes(
         (Some(after), Some(before)) => (Bound::Excluded(*after), Bound::Excluded(*before)),
     };
     let mut collected_task_ids = RoaringBitmap::new();
-    let start = map_bound(start, |b| BEI128::new(b.unix_timestamp_nanos()));
-    let end = map_bound(end, |b| BEI128::new(b.unix_timestamp_nanos()));
+    let start = map_bound(start, |b| b.unix_timestamp_nanos());
+    let end = map_bound(end, |b| b.unix_timestamp_nanos());
     let iter = database.range(rtxn, &(start, end))?;
     for r in iter {
         let (_timestamp, task_ids) = r?;
@@ -337,8 +337,6 @@ impl IndexScheduler {
         let rtxn = self.env.read_txn().unwrap();
         for task in self.all_tasks.iter(&rtxn).unwrap() {
             let (task_id, task) = task.unwrap();
-            let task_id = task_id.get();
-
             let task_index_uid = task.index_uid().map(ToOwned::to_owned);
 
             let Task {
@@ -361,16 +359,13 @@ impl IndexScheduler {
                     .unwrap()
                     .contains(task.uid));
             }
-            let db_enqueued_at = self
-                .enqueued_at
-                .get(&rtxn, &BEI128::new(enqueued_at.unix_timestamp_nanos()))
-                .unwrap()
-                .unwrap();
+            let db_enqueued_at =
+                self.enqueued_at.get(&rtxn, &enqueued_at.unix_timestamp_nanos()).unwrap().unwrap();
             assert!(db_enqueued_at.contains(task_id));
             if let Some(started_at) = started_at {
                 let db_started_at = self
                     .started_at
-                    .get(&rtxn, &BEI128::new(started_at.unix_timestamp_nanos()))
+                    .get(&rtxn, &started_at.unix_timestamp_nanos())
                     .unwrap()
                     .unwrap();
                 assert!(db_started_at.contains(task_id));
@@ -378,7 +373,7 @@ impl IndexScheduler {
             if let Some(finished_at) = finished_at {
                 let db_finished_at = self
                     .finished_at
-                    .get(&rtxn, &BEI128::new(finished_at.unix_timestamp_nanos()))
+                    .get(&rtxn, &finished_at.unix_timestamp_nanos())
                     .unwrap()
                     .unwrap();
                 assert!(db_finished_at.contains(task_id));

index-scheduler/src/uuid_codec.rs

@@ -1,7 +1,6 @@
 use std::borrow::Cow;
-use std::convert::TryInto;
 
-use meilisearch_types::heed::{BytesDecode, BytesEncode};
+use meilisearch_types::heed::{BoxedError, BytesDecode, BytesEncode};
 use uuid::Uuid;
 
 /// A heed codec for value of struct Uuid.
@@ -10,15 +9,15 @@ pub struct UuidCodec;
 impl<'a> BytesDecode<'a> for UuidCodec {
     type DItem = Uuid;
 
-    fn bytes_decode(bytes: &'a [u8]) -> Option<Self::DItem> {
-        bytes.try_into().ok().map(Uuid::from_bytes)
+    fn bytes_decode(bytes: &'a [u8]) -> Result<Self::DItem, BoxedError> {
+        bytes.try_into().map(Uuid::from_bytes).map_err(Into::into)
     }
 }
 
 impl BytesEncode<'_> for UuidCodec {
     type EItem = Uuid;
 
-    fn bytes_encode(item: &Self::EItem) -> Option<Cow<[u8]>> {
-        Some(Cow::Borrowed(item.as_bytes()))
+    fn bytes_encode(item: &Self::EItem) -> Result<Cow<[u8]>, BoxedError> {
+        Ok(Cow::Borrowed(item.as_bytes()))
     }
 }

meili-snap/Cargo.toml

@@ -11,6 +11,6 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-insta = { version = "^1.29.0", features = ["json", "redactions"] }
+insta = { version = "^1.34.0", features = ["json", "redactions"] }
 md5 = "0.7.0"
-once_cell = "1.17"
+once_cell = "1.19"

meilisearch-auth/Cargo.toml

@@ -11,16 +11,16 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-base64 = "0.21.0"
-enum-iterator = "1.4.0"
+base64 = "0.21.7"
+enum-iterator = "1.5.0"
 hmac = "0.12.1"
 maplit = "1.0.2"
 meilisearch-types = { path = "../meilisearch-types" }
 rand = "0.8.5"
-roaring = { version = "0.10.1", features = ["serde"] }
-serde = { version = "1.0.160", features = ["derive"] }
-serde_json = { version = "1.0.95", features = ["preserve_order"] }
-sha2 = "0.10.6"
-thiserror = "1.0.40"
-time = { version = "0.3.20", features = ["serde-well-known", "formatting", "parsing", "macros"] }
-uuid = { version = "1.3.1", features = ["serde", "v4"] }
+roaring = { version = "0.10.2", features = ["serde"] }
+serde = { version = "1.0.195", features = ["derive"] }
+serde_json = { version = "1.0.111", features = ["preserve_order"] }
+sha2 = "0.10.8"
+thiserror = "1.0.56"
+time = { version = "0.3.31", features = ["serde-well-known", "formatting", "parsing", "macros"] }
+uuid = { version = "1.6.1", features = ["serde", "v4"] }

meilisearch-auth/src/store.rs

@@ -1,20 +1,22 @@
 use std::borrow::Cow;
 use std::cmp::Reverse;
 use std::collections::HashSet;
-use std::convert::{TryFrom, TryInto};
 use std::fs::create_dir_all;
 use std::path::Path;
+use std::result::Result as StdResult;
 use std::str;
 use std::str::FromStr;
 use std::sync::Arc;
 
 use hmac::{Hmac, Mac};
+use meilisearch_types::heed::BoxedError;
 use meilisearch_types::index_uid_pattern::IndexUidPattern;
 use meilisearch_types::keys::KeyId;
 use meilisearch_types::milli;
-use meilisearch_types::milli::heed::types::{ByteSlice, DecodeIgnore, SerdeJson};
+use meilisearch_types::milli::heed::types::{Bytes, DecodeIgnore, SerdeJson};
 use meilisearch_types::milli::heed::{Database, Env, EnvOpenOptions, RwTxn};
 use sha2::Sha256;
+use thiserror::Error;
 use time::OffsetDateTime;
 use uuid::fmt::Hyphenated;
 use uuid::Uuid;
@@ -30,7 +32,7 @@ const KEY_ID_ACTION_INDEX_EXPIRATION_DB_NAME: &str = "keyid-action-index-expirat
 #[derive(Clone)]
 pub struct HeedAuthStore {
     env: Arc<Env>,
-    keys: Database<ByteSlice, SerdeJson<Key>>,
+    keys: Database<Bytes, SerdeJson<Key>>,
     action_keyid_index_expiration: Database<KeyIdActionCodec, SerdeJson<Option<OffsetDateTime>>>,
     should_close_on_drop: bool,
 }
@@ -276,7 +278,7 @@ impl HeedAuthStore {
     fn delete_key_from_inverted_db(&self, wtxn: &mut RwTxn, key: &KeyId) -> Result<()> {
         let mut iter = self
             .action_keyid_index_expiration
-            .remap_types::<ByteSlice, DecodeIgnore>()
+            .remap_types::<Bytes, DecodeIgnore>()
             .prefix_iter_mut(wtxn, key.as_bytes())?;
         while iter.next().transpose()?.is_some() {
             // safety: we don't keep references from inside the LMDB database.
@@ -294,23 +296,24 @@ pub struct KeyIdActionCodec;
 impl<'a> milli::heed::BytesDecode<'a> for KeyIdActionCodec {
     type DItem = (KeyId, Action, Option<&'a [u8]>);
 
-    fn bytes_decode(bytes: &'a [u8]) -> Option<Self::DItem> {
-        let (key_id_bytes, action_bytes) = try_split_array_at(bytes)?;
-        let (action_bytes, index) = match try_split_array_at(action_bytes)? {
-            (action, []) => (action, None),
-            (action, index) => (action, Some(index)),
-        };
+    fn bytes_decode(bytes: &'a [u8]) -> StdResult<Self::DItem, BoxedError> {
+        let (key_id_bytes, action_bytes) = try_split_array_at(bytes).ok_or(SliceTooShortError)?;
+        let (&action_byte, index) =
+            match try_split_array_at(action_bytes).ok_or(SliceTooShortError)? {
+                ([action], []) => (action, None),
+                ([action], index) => (action, Some(index)),
+            };
         let key_id = Uuid::from_bytes(*key_id_bytes);
-        let action = Action::from_repr(u8::from_be_bytes(*action_bytes))?;
+        let action = Action::from_repr(action_byte).ok_or(InvalidActionError { action_byte })?;
 
-        Some((key_id, action, index))
+        Ok((key_id, action, index))
     }
 }
 
 impl<'a> milli::heed::BytesEncode<'a> for KeyIdActionCodec {
     type EItem = (&'a KeyId, &'a Action, Option<&'a [u8]>);
 
-    fn bytes_encode((key_id, action, index): &Self::EItem) -> Option<Cow<[u8]>> {
+    fn bytes_encode((key_id, action, index): &Self::EItem) -> StdResult<Cow<[u8]>, BoxedError> {
         let mut bytes = Vec::new();
 
         bytes.extend_from_slice(key_id.as_bytes());
@@ -320,10 +323,20 @@ impl<'a> milli::heed::BytesEncode<'a> for KeyIdActionCodec {
             bytes.extend_from_slice(index);
         }
 
-        Some(Cow::Owned(bytes))
+        Ok(Cow::Owned(bytes))
     }
 }
 
+#[derive(Error, Debug)]
+#[error("the slice is too short")]
+pub struct SliceTooShortError;
+
+#[derive(Error, Debug)]
+#[error("cannot construct a valid Action from {action_byte}")]
+pub struct InvalidActionError {
+    pub action_byte: u8,
+}
+
 pub fn generate_key_as_hexa(uid: Uuid, master_key: &[u8]) -> String {
     // format uid as hyphenated allowing user to generate their own keys.
     let mut uid_buffer = [0; Hyphenated::LENGTH];

meilisearch-types/Cargo.toml

@@ -11,31 +11,31 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-actix-web = { version = "4.3.1", default-features = false }
-anyhow = "1.0.70"
+actix-web = { version = "4.5.1", default-features = false }
+anyhow = "1.0.79"
 convert_case = "0.6.0"
-csv = "1.2.1"
-deserr = { version = "0.6.0", features = ["actix-web"]}
-either = { version = "1.8.1", features = ["serde"] }
-enum-iterator = "1.4.0"
+csv = "1.3.0"
+deserr = { version = "0.6.1", features = ["actix-web"] }
+either = { version = "1.9.0", features = ["serde"] }
+enum-iterator = "1.5.0"
 file-store = { path = "../file-store" }
-flate2 = "1.0.25"
+flate2 = "1.0.28"
 fst = "0.4.7"
 memmap2 = "0.7.1"
 milli = { path = "../milli" }
-roaring = { version = "0.10.1", features = ["serde"] }
-serde = { version = "1.0.160", features = ["derive"] }
+roaring = { version = "0.10.2", features = ["serde"] }
+serde = { version = "1.0.195", features = ["derive"] }
 serde-cs = "0.2.4"
-serde_json = "1.0.95"
-tar = "0.4.38"
-tempfile = "3.5.0"
-thiserror = "1.0.40"
-time = { version = "0.3.20", features = ["serde-well-known", "formatting", "parsing", "macros"] }
-tokio = "1.27"
-uuid = { version = "1.3.1", features = ["serde", "v4"] }
+serde_json = "1.0.111"
+tar = "0.4.40"
+tempfile = "3.9.0"
+thiserror = "1.0.56"
+time = { version = "0.3.31", features = ["serde-well-known", "formatting", "parsing", "macros"] }
+tokio = "1.35"
+uuid = { version = "1.6.1", features = ["serde", "v4"] }
 
 [dev-dependencies]
-insta = "1.29.0"
+insta = "1.34.0"
 meili-snap = { path = "../meili-snap" }
 
 [features]
@@ -50,6 +50,9 @@ hebrew = ["milli/hebrew"]
 japanese = ["milli/japanese"]
 # thai specialized tokenization
 thai = ["milli/thai"]
-
 # allow greek specialized tokenization
 greek = ["milli/greek"]
+# allow khmer specialized tokenization
+khmer = ["milli/khmer"]
+# allow vietnamese specialized tokenization
+vietnamese = ["milli/vietnamese"]

meilisearch-types/src/deserr/mod.rs

@@ -188,3 +188,4 @@ merge_with_error_impl_take_error_message!(ParseOffsetDateTimeError);
 merge_with_error_impl_take_error_message!(ParseTaskKindError);
 merge_with_error_impl_take_error_message!(ParseTaskStatusError);
 merge_with_error_impl_take_error_message!(IndexUidFormatError);
+merge_with_error_impl_take_error_message!(InvalidSearchSemanticRatio);

meilisearch-types/src/document_formats.rs

@@ -1,6 +1,6 @@
 use std::fmt::{self, Debug, Display};
 use std::fs::File;
-use std::io::{self, Seek, Write};
+use std::io::{self, BufWriter, Write};
 use std::marker::PhantomData;
 
 use memmap2::MmapOptions;
@@ -104,8 +104,8 @@ impl ErrorCode for DocumentFormatError {
 }
 
 /// Reads CSV from input and write an obkv batch to writer.
-pub fn read_csv(file: &File, writer: impl Write + Seek, delimiter: u8) -> Result<u64> {
-    let mut builder = DocumentsBatchBuilder::new(writer);
+pub fn read_csv(file: &File, writer: impl Write, delimiter: u8) -> Result<u64> {
+    let mut builder = DocumentsBatchBuilder::new(BufWriter::new(writer));
     let mmap = unsafe { MmapOptions::new().map(file)? };
     let csv = csv::ReaderBuilder::new().delimiter(delimiter).from_reader(mmap.as_ref());
     builder.append_csv(csv).map_err(|e| (PayloadType::Csv { delimiter }, e))?;
@@ -116,9 +116,9 @@ pub fn read_csv(file: &File, writer: impl Write + Seek, delimiter: u8) -> Result
     Ok(count as u64)
 }
 
-/// Reads JSON from temporary file  and write an obkv batch to writer.
-pub fn read_json(file: &File, writer: impl Write + Seek) -> Result<u64> {
-    let mut builder = DocumentsBatchBuilder::new(writer);
+/// Reads JSON from temporary file and write an obkv batch to writer.
+pub fn read_json(file: &File, writer: impl Write) -> Result<u64> {
+    let mut builder = DocumentsBatchBuilder::new(BufWriter::new(writer));
     let mmap = unsafe { MmapOptions::new().map(file)? };
     let mut deserializer = serde_json::Deserializer::from_slice(&mmap);
 
@@ -151,8 +151,8 @@ pub fn read_json(file: &File, writer: impl Write + Seek) -> Result<u64> {
 }
 
 /// Reads JSON from temporary file  and write an obkv batch to writer.
-pub fn read_ndjson(file: &File, writer: impl Write + Seek) -> Result<u64> {
-    let mut builder = DocumentsBatchBuilder::new(writer);
+pub fn read_ndjson(file: &File, writer: impl Write) -> Result<u64> {
+    let mut builder = DocumentsBatchBuilder::new(BufWriter::new(writer));
     let mmap = unsafe { MmapOptions::new().map(file)? };
 
     for result in serde_json::Deserializer::from_slice(&mmap).into_iter() {

meilisearch-types/src/error.rs

@@ -2,6 +2,7 @@ use std::{fmt, io};
 
 use actix_web::http::StatusCode;
 use actix_web::{self as aweb, HttpResponseBuilder};
+use aweb::http::header;
 use aweb::rt::task::JoinError;
 use convert_case::Casing;
 use milli::heed::{Error as HeedError, MdbError};
@@ -56,7 +57,14 @@ where
 impl aweb::error::ResponseError for ResponseError {
     fn error_response(&self) -> aweb::HttpResponse {
         let json = serde_json::to_vec(self).unwrap();
-        HttpResponseBuilder::new(self.status_code()).content_type("application/json").body(json)
+        let mut builder = HttpResponseBuilder::new(self.status_code());
+        builder.content_type("application/json");
+
+        if self.code == StatusCode::SERVICE_UNAVAILABLE {
+            builder.insert_header((header::RETRY_AFTER, "10"));
+        }
+
+        builder.body(json)
     }
 
     fn status_code(&self) -> StatusCode {
@@ -222,6 +230,8 @@ InvalidVectorsType                    , InvalidRequest       , BAD_REQUEST ;
 InvalidDocumentId                     , InvalidRequest       , BAD_REQUEST ;
 InvalidDocumentLimit                  , InvalidRequest       , BAD_REQUEST ;
 InvalidDocumentOffset                 , InvalidRequest       , BAD_REQUEST ;
+InvalidEmbedder                       , InvalidRequest       , BAD_REQUEST ;
+InvalidHybridQuery                    , InvalidRequest       , BAD_REQUEST ;
 InvalidIndexLimit                     , InvalidRequest       , BAD_REQUEST ;
 InvalidIndexOffset                    , InvalidRequest       , BAD_REQUEST ;
 InvalidIndexPrimaryKey                , InvalidRequest       , BAD_REQUEST ;
@@ -233,7 +243,9 @@ InvalidSearchAttributesToRetrieve     , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchCropLength               , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchCropMarker               , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchFacets                   , InvalidRequest       , BAD_REQUEST ;
+InvalidSearchSemanticRatio            , InvalidRequest       , BAD_REQUEST ;
 InvalidFacetSearchFacetName           , InvalidRequest       , BAD_REQUEST ;
+InvalidRecommendId                    , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchFilter                   , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchHighlightPostTag         , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchHighlightPreTag          , InvalidRequest       , BAD_REQUEST ;
@@ -252,9 +264,12 @@ InvalidSearchShowRankingScoreDetails  , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchSort                     , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsDisplayedAttributes    , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsDistinctAttribute      , InvalidRequest       , BAD_REQUEST ;
+InvalidSettingsProximityPrecision     , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsFaceting               , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsFilterableAttributes   , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsPagination             , InvalidRequest       , BAD_REQUEST ;
+InvalidSettingsSearchCutoffMs           , InvalidRequest       , BAD_REQUEST ;
+InvalidSettingsEmbedders              , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsRankingRules           , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsSearchableAttributes   , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsSortableAttributes     , InvalidRequest       , BAD_REQUEST ;
@@ -294,15 +309,21 @@ MissingFacetSearchFacetName           , InvalidRequest       , BAD_REQUEST ;
 MissingIndexUid                       , InvalidRequest       , BAD_REQUEST ;
 MissingMasterKey                      , Auth                 , UNAUTHORIZED ;
 MissingPayload                        , InvalidRequest       , BAD_REQUEST ;
+MissingSearchHybrid                   , InvalidRequest       , BAD_REQUEST ;
 MissingSwapIndexes                    , InvalidRequest       , BAD_REQUEST ;
 MissingTaskFilters                    , InvalidRequest       , BAD_REQUEST ;
 NoSpaceLeftOnDevice                   , System               , UNPROCESSABLE_ENTITY;
 PayloadTooLarge                       , InvalidRequest       , PAYLOAD_TOO_LARGE ;
+TooManySearchRequests                 , System               , SERVICE_UNAVAILABLE ;
 TaskNotFound                          , InvalidRequest       , NOT_FOUND ;
 TooManyOpenFiles                      , System               , UNPROCESSABLE_ENTITY ;
+TooManyVectors                        , InvalidRequest       , BAD_REQUEST ;
 UnretrievableDocument                 , Internal             , BAD_REQUEST ;
 UnretrievableErrorCode                , InvalidRequest       , BAD_REQUEST ;
-UnsupportedMediaType                  , InvalidRequest       , UNSUPPORTED_MEDIA_TYPE
+UnsupportedMediaType                  , InvalidRequest       , UNSUPPORTED_MEDIA_TYPE ;
+
+// Experimental features
+VectorEmbeddingError                  , InvalidRequest       , BAD_REQUEST
 }
 
 impl ErrorCode for JoinError {
@@ -324,7 +345,6 @@ impl ErrorCode for milli::Error {
                     UserError::SerdeJson(_)
                     | UserError::InvalidLmdbOpenOptions
                     | UserError::DocumentLimitReached
-                    | UserError::AccessingSoftDeletedDocument { .. }
                     | UserError::UnknownInternalDocumentId { .. } => Code::Internal,
                     UserError::InvalidStoreFile => Code::InvalidStoreFile,
                     UserError::NoSpaceLeftOnDevice => Code::NoSpaceLeftOnDevice,
@@ -336,6 +356,17 @@ impl ErrorCode for milli::Error {
                     UserError::InvalidDocumentId { .. } | UserError::TooManyDocumentIds { .. } => {
                         Code::InvalidDocumentId
                     }
+                    UserError::MissingDocumentField(_) => Code::InvalidDocumentFields,
+                    UserError::InvalidFieldForSource { .. }
+                    | UserError::MissingFieldForSource { .. }
+                    | UserError::InvalidOpenAiModel { .. }
+                    | UserError::InvalidOpenAiModelDimensions { .. }
+                    | UserError::InvalidOpenAiModelDimensionsMax { .. }
+                    | UserError::InvalidSettingsDimensions { .. }
+                    | UserError::InvalidUrl { .. }
+                    | UserError::InvalidPrompt(_) => Code::InvalidSettingsEmbedders,
+                    UserError::TooManyEmbedders(_) => Code::InvalidSettingsEmbedders,
+                    UserError::InvalidPromptForEmbeddings(..) => Code::InvalidSettingsEmbedders,
                     UserError::NoPrimaryKeyCandidateFound => Code::IndexPrimaryKeyNoCandidateFound,
                     UserError::MultiplePrimaryKeyCandidatesFound { .. } => {
                         Code::IndexPrimaryKeyMultipleCandidatesFound
@@ -353,11 +384,15 @@ impl ErrorCode for milli::Error {
                     UserError::CriterionError(_) => Code::InvalidSettingsRankingRules,
                     UserError::InvalidGeoField { .. } => Code::InvalidDocumentGeoField,
                     UserError::InvalidVectorDimensions { .. } => Code::InvalidVectorDimensions,
+                    UserError::InvalidVectorsMapType { .. } => Code::InvalidVectorsType,
                     UserError::InvalidVectorsType { .. } => Code::InvalidVectorsType,
+                    UserError::TooManyVectors(_, _) => Code::TooManyVectors,
                     UserError::SortError(_) => Code::InvalidSearchSort,
                     UserError::InvalidMinTypoWordLenSetting(_, _) => {
                         Code::InvalidSettingsTypoTolerance
                     }
+                    UserError::InvalidEmbedder(_) => Code::InvalidEmbedder,
+                    UserError::VectorEmbeddingError(_) => Code::VectorEmbeddingError,
                 }
             }
         }
@@ -387,11 +422,11 @@ impl ErrorCode for HeedError {
             HeedError::Mdb(MdbError::Invalid) => Code::InvalidStoreFile,
             HeedError::Io(e) => e.error_code(),
             HeedError::Mdb(_)
-            | HeedError::Encoding
-            | HeedError::Decoding
+            | HeedError::Encoding(_)
+            | HeedError::Decoding(_)
             | HeedError::InvalidDatabaseTyping
             | HeedError::DatabaseClosing
-            | HeedError::BadOpenOptions => Code::Internal,
+            | HeedError::BadOpenOptions { .. } => Code::Internal,
         }
     }
 }
@@ -445,6 +480,15 @@ impl fmt::Display for DeserrParseIntError {
     }
 }
 
+impl fmt::Display for deserr_codes::InvalidSearchSemanticRatio {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        write!(
+            f,
+            "the value of `semanticRatio` is invalid, expected a float between `0.0` and `1.0`."
+        )
+    }
+}
+
 #[macro_export]
 macro_rules! internal_error {
     ($target:ty : $($other:path), *) => {

meilisearch-types/src/features.rs

@@ -3,13 +3,14 @@ use serde::{Deserialize, Serialize};
 #[derive(Serialize, Deserialize, Debug, Clone, Copy, Default, PartialEq, Eq)]
 #[serde(rename_all = "camelCase", default)]
 pub struct RuntimeTogglableFeatures {
-    pub score_details: bool,
     pub vector_store: bool,
     pub metrics: bool,
+    pub logs_route: bool,
     pub export_puffin_reports: bool,
 }
 
 #[derive(Default, Debug, Clone, Copy)]
 pub struct InstanceTogglableFeatures {
     pub metrics: bool,
+    pub logs_route: bool,
 }

meilisearch-types/src/lib.rs

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

meilisearch-types/src/settings.rs

@@ -8,6 +8,7 @@ use std::str::FromStr;
 
 use deserr::{DeserializeError, Deserr, ErrorKind, MergeWithError, ValuePointerRef};
 use fst::IntoStreamer;
+use milli::proximity::ProximityPrecision;
 use milli::update::Setting;
 use milli::{Criterion, CriterionError, Index, DEFAULT_VALUES_PER_FACET};
 use serde::{Deserialize, Serialize, Serializer};
@@ -186,6 +187,9 @@ pub struct Settings<T> {
     #[deserr(default, error = DeserrJsonError<InvalidSettingsDistinctAttribute>)]
     pub distinct_attribute: Setting<String>,
     #[serde(default, skip_serializing_if = "Setting::is_not_set")]
+    #[deserr(default, error = DeserrJsonError<InvalidSettingsProximityPrecision>)]
+    pub proximity_precision: Setting<ProximityPrecisionView>,
+    #[serde(default, skip_serializing_if = "Setting::is_not_set")]
     #[deserr(default, error = DeserrJsonError<InvalidSettingsTypoTolerance>)]
     pub typo_tolerance: Setting<TypoSettings>,
     #[serde(default, skip_serializing_if = "Setting::is_not_set")]
@@ -195,11 +199,55 @@ pub struct Settings<T> {
     #[deserr(default, error = DeserrJsonError<InvalidSettingsPagination>)]
     pub pagination: Setting<PaginationSettings>,
 
+    #[serde(default, skip_serializing_if = "Setting::is_not_set")]
+    #[deserr(default, error = DeserrJsonError<InvalidSettingsEmbedders>)]
+    pub embedders: Setting<BTreeMap<String, Setting<milli::vector::settings::EmbeddingSettings>>>,
+    #[serde(default, skip_serializing_if = "Setting::is_not_set")]
+    #[deserr(default, error = DeserrJsonError<InvalidSettingsSearchCutoffMs>)]
+    pub search_cutoff_ms: Setting<u64>,
+
     #[serde(skip)]
     #[deserr(skip)]
     pub _kind: PhantomData<T>,
 }
 
+impl<T> Settings<T> {
+    pub fn hide_secrets(&mut self) {
+        let Setting::Set(embedders) = &mut self.embedders else {
+            return;
+        };
+
+        for mut embedder in embedders.values_mut() {
+            let Setting::Set(embedder) = &mut embedder else {
+                continue;
+            };
+
+            let Setting::Set(api_key) = &mut embedder.api_key else {
+                continue;
+            };
+
+            Self::hide_secret(api_key);
+        }
+    }
+
+    fn hide_secret(secret: &mut String) {
+        match secret.len() {
+            x if x < 10 => {
+                secret.replace_range(.., "XXX...");
+            }
+            x if x < 20 => {
+                secret.replace_range(2.., "XXXX...");
+            }
+            x if x < 30 => {
+                secret.replace_range(3.., "XXXXX...");
+            }
+            _x => {
+                secret.replace_range(5.., "XXXXXX...");
+            }
+        }
+    }
+}
+
 impl Settings<Checked> {
     pub fn cleared() -> Settings<Checked> {
         Settings {
@@ -214,9 +262,12 @@ impl Settings<Checked> {
             separator_tokens: Setting::Reset,
             dictionary: Setting::Reset,
             distinct_attribute: Setting::Reset,
+            proximity_precision: Setting::Reset,
             typo_tolerance: Setting::Reset,
             faceting: Setting::Reset,
             pagination: Setting::Reset,
+            embedders: Setting::Reset,
+            search_cutoff_ms: Setting::Reset,
             _kind: PhantomData,
         }
     }
@@ -234,9 +285,12 @@ impl Settings<Checked> {
             dictionary,
             synonyms,
             distinct_attribute,
+            proximity_precision,
             typo_tolerance,
             faceting,
             pagination,
+            embedders,
+            search_cutoff_ms,
             ..
         } = self;
 
@@ -252,9 +306,12 @@ impl Settings<Checked> {
             dictionary,
             synonyms,
             distinct_attribute,
+            proximity_precision,
             typo_tolerance,
             faceting,
             pagination,
+            embedders,
+            search_cutoff_ms,
             _kind: PhantomData,
         }
     }
@@ -296,12 +353,30 @@ impl Settings<Unchecked> {
             separator_tokens: self.separator_tokens,
             dictionary: self.dictionary,
             distinct_attribute: self.distinct_attribute,
+            proximity_precision: self.proximity_precision,
             typo_tolerance: self.typo_tolerance,
             faceting: self.faceting,
             pagination: self.pagination,
+            embedders: self.embedders,
+            search_cutoff_ms: self.search_cutoff_ms,
             _kind: PhantomData,
         }
     }
+
+    pub fn validate(self) -> Result<Self, milli::Error> {
+        self.validate_embedding_settings()
+    }
+
+    fn validate_embedding_settings(mut self) -> Result<Self, milli::Error> {
+        let Setting::Set(mut configs) = self.embedders else { return Ok(self) };
+        for (name, config) in configs.iter_mut() {
+            let config_to_check = std::mem::take(config);
+            let checked_config = milli::update::validate_embedding_settings(config_to_check, name)?;
+            *config = checked_config
+        }
+        self.embedders = Setting::Set(configs);
+        Ok(self)
+    }
 }
 
 #[derive(Debug, Clone, Serialize, Deserialize)]
@@ -316,19 +391,40 @@ pub fn apply_settings_to_builder(
     settings: &Settings<Checked>,
     builder: &mut milli::update::Settings,
 ) {
-    match settings.searchable_attributes {
+    let Settings {
+        displayed_attributes,
+        searchable_attributes,
+        filterable_attributes,
+        sortable_attributes,
+        ranking_rules,
+        stop_words,
+        non_separator_tokens,
+        separator_tokens,
+        dictionary,
+        synonyms,
+        distinct_attribute,
+        proximity_precision,
+        typo_tolerance,
+        faceting,
+        pagination,
+        embedders,
+        search_cutoff_ms,
+        _kind,
+    } = settings;
+
+    match searchable_attributes {
         Setting::Set(ref names) => builder.set_searchable_fields(names.clone()),
         Setting::Reset => builder.reset_searchable_fields(),
         Setting::NotSet => (),
     }
 
-    match settings.displayed_attributes {
+    match displayed_attributes {
         Setting::Set(ref names) => builder.set_displayed_fields(names.clone()),
         Setting::Reset => builder.reset_displayed_fields(),
         Setting::NotSet => (),
     }
 
-    match settings.filterable_attributes {
+    match filterable_attributes {
         Setting::Set(ref facets) => {
             builder.set_filterable_fields(facets.clone().into_iter().collect())
         }
@@ -336,13 +432,13 @@ pub fn apply_settings_to_builder(
         Setting::NotSet => (),
     }
 
-    match settings.sortable_attributes {
+    match sortable_attributes {
         Setting::Set(ref fields) => builder.set_sortable_fields(fields.iter().cloned().collect()),
         Setting::Reset => builder.reset_sortable_fields(),
         Setting::NotSet => (),
     }
 
-    match settings.ranking_rules {
+    match ranking_rules {
         Setting::Set(ref criteria) => {
             builder.set_criteria(criteria.iter().map(|c| c.clone().into()).collect())
         }
@@ -350,13 +446,13 @@ pub fn apply_settings_to_builder(
         Setting::NotSet => (),
     }
 
-    match settings.stop_words {
+    match stop_words {
         Setting::Set(ref stop_words) => builder.set_stop_words(stop_words.clone()),
         Setting::Reset => builder.reset_stop_words(),
         Setting::NotSet => (),
     }
 
-    match settings.non_separator_tokens {
+    match non_separator_tokens {
         Setting::Set(ref non_separator_tokens) => {
             builder.set_non_separator_tokens(non_separator_tokens.clone())
         }
@@ -364,7 +460,7 @@ pub fn apply_settings_to_builder(
         Setting::NotSet => (),
     }
 
-    match settings.separator_tokens {
+    match separator_tokens {
         Setting::Set(ref separator_tokens) => {
             builder.set_separator_tokens(separator_tokens.clone())
         }
@@ -372,25 +468,31 @@ pub fn apply_settings_to_builder(
         Setting::NotSet => (),
     }
 
-    match settings.dictionary {
+    match dictionary {
         Setting::Set(ref dictionary) => builder.set_dictionary(dictionary.clone()),
         Setting::Reset => builder.reset_dictionary(),
         Setting::NotSet => (),
     }
 
-    match settings.synonyms {
+    match synonyms {
         Setting::Set(ref synonyms) => builder.set_synonyms(synonyms.clone().into_iter().collect()),
         Setting::Reset => builder.reset_synonyms(),
         Setting::NotSet => (),
     }
 
-    match settings.distinct_attribute {
+    match distinct_attribute {
         Setting::Set(ref attr) => builder.set_distinct_field(attr.clone()),
         Setting::Reset => builder.reset_distinct_field(),
         Setting::NotSet => (),
     }
 
-    match settings.typo_tolerance {
+    match proximity_precision {
+        Setting::Set(ref precision) => builder.set_proximity_precision((*precision).into()),
+        Setting::Reset => builder.reset_proximity_precision(),
+        Setting::NotSet => (),
+    }
+
+    match typo_tolerance {
         Setting::Set(ref value) => {
             match value.enabled {
                 Setting::Set(val) => builder.set_autorize_typos(val),
@@ -445,7 +547,7 @@ pub fn apply_settings_to_builder(
         Setting::NotSet => (),
     }
 
-    match &settings.faceting {
+    match faceting {
         Setting::Set(FacetingSettings { max_values_per_facet, sort_facet_values_by }) => {
             match max_values_per_facet {
                 Setting::Set(val) => builder.set_max_values_per_facet(*val),
@@ -467,7 +569,7 @@ pub fn apply_settings_to_builder(
         Setting::NotSet => (),
     }
 
-    match settings.pagination {
+    match pagination {
         Setting::Set(ref value) => match value.max_total_hits {
             Setting::Set(val) => builder.set_pagination_max_total_hits(val),
             Setting::Reset => builder.reset_pagination_max_total_hits(),
@@ -476,11 +578,29 @@ pub fn apply_settings_to_builder(
         Setting::Reset => builder.reset_pagination_max_total_hits(),
         Setting::NotSet => (),
     }
+
+    match embedders {
+        Setting::Set(value) => builder.set_embedder_settings(value.clone()),
+        Setting::Reset => builder.reset_embedder_settings(),
+        Setting::NotSet => (),
+    }
+
+    match search_cutoff_ms {
+        Setting::Set(cutoff) => builder.set_search_cutoff(*cutoff),
+        Setting::Reset => builder.reset_search_cutoff(),
+        Setting::NotSet => (),
+    }
+}
+
+pub enum SecretPolicy {
+    RevealSecrets,
+    HideSecrets,
 }
 
 pub fn settings(
     index: &Index,
     rtxn: &crate::heed::RoTxn,
+    secret_policy: SecretPolicy,
 ) -> Result<Settings<Checked>, milli::Error> {
     let displayed_attributes =
         index.displayed_fields(rtxn)?.map(|fields| fields.into_iter().map(String::from).collect());
@@ -509,6 +629,8 @@ pub fn settings(
 
     let distinct_field = index.distinct_field(rtxn)?.map(String::from);
 
+    let proximity_precision = index.proximity_precision(rtxn)?.map(ProximityPrecisionView::from);
+
     let synonyms = index.user_defined_synonyms(rtxn)?;
 
     let min_typo_word_len = MinWordSizeTyposSetting {
@@ -532,7 +654,10 @@ pub fn settings(
 
     let faceting = FacetingSettings {
         max_values_per_facet: Setting::Set(
-            index.max_values_per_facet(rtxn)?.unwrap_or(DEFAULT_VALUES_PER_FACET),
+            index
+                .max_values_per_facet(rtxn)?
+                .map(|x| x as usize)
+                .unwrap_or(DEFAULT_VALUES_PER_FACET),
         ),
         sort_facet_values_by: Setting::Set(
             index
@@ -545,11 +670,23 @@ pub fn settings(
 
     let pagination = PaginationSettings {
         max_total_hits: Setting::Set(
-            index.pagination_max_total_hits(rtxn)?.unwrap_or(DEFAULT_PAGINATION_MAX_TOTAL_HITS),
+            index
+                .pagination_max_total_hits(rtxn)?
+                .map(|x| x as usize)
+                .unwrap_or(DEFAULT_PAGINATION_MAX_TOTAL_HITS),
         ),
     };
 
-    Ok(Settings {
+    let embedders: BTreeMap<_, _> = index
+        .embedding_configs(rtxn)?
+        .into_iter()
+        .map(|(name, config)| (name, Setting::Set(config.into())))
+        .collect();
+    let embedders = if embedders.is_empty() { Setting::NotSet } else { Setting::Set(embedders) };
+
+    let search_cutoff_ms = index.search_cutoff(rtxn)?;
+
+    let mut settings = Settings {
         displayed_attributes: match displayed_attributes {
             Some(attrs) => Setting::Set(attrs),
             None => Setting::Reset,
@@ -569,12 +706,24 @@ pub fn settings(
             Some(field) => Setting::Set(field),
             None => Setting::Reset,
         },
+        proximity_precision: Setting::Set(proximity_precision.unwrap_or_default()),
         synonyms: Setting::Set(synonyms),
         typo_tolerance: Setting::Set(typo_tolerance),
         faceting: Setting::Set(faceting),
         pagination: Setting::Set(pagination),
+        embedders,
+        search_cutoff_ms: match search_cutoff_ms {
+            Some(cutoff) => Setting::Set(cutoff),
+            None => Setting::Reset,
+        },
         _kind: PhantomData,
-    })
+    };
+
+    if let SecretPolicy::HideSecrets = secret_policy {
+        settings.hide_secrets()
+    }
+
+    Ok(settings)
 }
 
 #[derive(Debug, Clone, PartialEq, Eq, Deserr)]
@@ -673,6 +822,32 @@ impl From<RankingRuleView> for Criterion {
     }
 }
 
+#[derive(Default, Debug, Clone, Copy, PartialEq, Eq, Deserr, Serialize, Deserialize)]
+#[serde(deny_unknown_fields, rename_all = "camelCase")]
+#[deserr(error = DeserrJsonError<InvalidSettingsProximityPrecision>, rename_all = camelCase, deny_unknown_fields)]
+pub enum ProximityPrecisionView {
+    #[default]
+    ByWord,
+    ByAttribute,
+}
+
+impl From<ProximityPrecision> for ProximityPrecisionView {
+    fn from(value: ProximityPrecision) -> Self {
+        match value {
+            ProximityPrecision::ByWord => ProximityPrecisionView::ByWord,
+            ProximityPrecision::ByAttribute => ProximityPrecisionView::ByAttribute,
+        }
+    }
+}
+impl From<ProximityPrecisionView> for ProximityPrecision {
+    fn from(value: ProximityPrecisionView) -> Self {
+        match value {
+            ProximityPrecisionView::ByWord => ProximityPrecision::ByWord,
+            ProximityPrecisionView::ByAttribute => ProximityPrecision::ByAttribute,
+        }
+    }
+}
+
 #[cfg(test)]
 pub(crate) mod test {
     use super::*;
@@ -692,9 +867,12 @@ pub(crate) mod test {
             dictionary: Setting::NotSet,
             synonyms: Setting::NotSet,
             distinct_attribute: Setting::NotSet,
+            proximity_precision: Setting::NotSet,
             typo_tolerance: Setting::NotSet,
             faceting: Setting::NotSet,
             pagination: Setting::NotSet,
+            embedders: Setting::NotSet,
+            search_cutoff_ms: Setting::NotSet,
             _kind: PhantomData::<Unchecked>,
         };
 
@@ -716,9 +894,12 @@ pub(crate) mod test {
             dictionary: Setting::NotSet,
             synonyms: Setting::NotSet,
             distinct_attribute: Setting::NotSet,
+            proximity_precision: Setting::NotSet,
             typo_tolerance: Setting::NotSet,
             faceting: Setting::NotSet,
             pagination: Setting::NotSet,
+            embedders: Setting::NotSet,
+            search_cutoff_ms: Setting::NotSet,
             _kind: PhantomData::<Unchecked>,
         };
 

meilisearch-types/src/task_view.rs

@@ -0,0 +1,140 @@
+use serde::Serialize;
+use time::{Duration, OffsetDateTime};
+
+use crate::error::ResponseError;
+use crate::settings::{Settings, Unchecked};
+use crate::tasks::{serialize_duration, Details, IndexSwap, Kind, Status, Task, TaskId};
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct TaskView {
+    pub uid: TaskId,
+    #[serde(default)]
+    pub index_uid: Option<String>,
+    pub status: Status,
+    #[serde(rename = "type")]
+    pub kind: Kind,
+    pub canceled_by: Option<TaskId>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub details: Option<DetailsView>,
+    pub error: Option<ResponseError>,
+    #[serde(serialize_with = "serialize_duration", default)]
+    pub duration: Option<Duration>,
+    #[serde(with = "time::serde::rfc3339")]
+    pub enqueued_at: OffsetDateTime,
+    #[serde(with = "time::serde::rfc3339::option", default)]
+    pub started_at: Option<OffsetDateTime>,
+    #[serde(with = "time::serde::rfc3339::option", default)]
+    pub finished_at: Option<OffsetDateTime>,
+}
+
+impl TaskView {
+    pub fn from_task(task: &Task) -> TaskView {
+        TaskView {
+            uid: task.uid,
+            index_uid: task.index_uid().map(ToOwned::to_owned),
+            status: task.status,
+            kind: task.kind.as_kind(),
+            canceled_by: task.canceled_by,
+            details: task.details.clone().map(DetailsView::from),
+            error: task.error.clone(),
+            duration: task.started_at.zip(task.finished_at).map(|(start, end)| end - start),
+            enqueued_at: task.enqueued_at,
+            started_at: task.started_at,
+            finished_at: task.finished_at,
+        }
+    }
+}
+
+#[derive(Default, Debug, PartialEq, Eq, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct DetailsView {
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub received_documents: Option<u64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub indexed_documents: Option<Option<u64>>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub primary_key: Option<Option<String>>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub provided_ids: Option<usize>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub deleted_documents: Option<Option<u64>>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub matched_tasks: Option<u64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub canceled_tasks: Option<Option<u64>>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub deleted_tasks: Option<Option<u64>>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub original_filter: Option<Option<String>>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub dump_uid: Option<Option<String>>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    #[serde(flatten)]
+    pub settings: Option<Box<Settings<Unchecked>>>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub swaps: Option<Vec<IndexSwap>>,
+}
+
+impl From<Details> for DetailsView {
+    fn from(details: Details) -> Self {
+        match details {
+            Details::DocumentAdditionOrUpdate { received_documents, indexed_documents } => {
+                DetailsView {
+                    received_documents: Some(received_documents),
+                    indexed_documents: Some(indexed_documents),
+                    ..DetailsView::default()
+                }
+            }
+            Details::SettingsUpdate { mut settings } => {
+                settings.hide_secrets();
+                DetailsView { settings: Some(settings), ..DetailsView::default() }
+            }
+            Details::IndexInfo { primary_key } => {
+                DetailsView { primary_key: Some(primary_key), ..DetailsView::default() }
+            }
+            Details::DocumentDeletion {
+                provided_ids: received_document_ids,
+                deleted_documents,
+            } => DetailsView {
+                provided_ids: Some(received_document_ids),
+                deleted_documents: Some(deleted_documents),
+                original_filter: Some(None),
+                ..DetailsView::default()
+            },
+            Details::DocumentDeletionByFilter { original_filter, deleted_documents } => {
+                DetailsView {
+                    provided_ids: Some(0),
+                    original_filter: Some(Some(original_filter)),
+                    deleted_documents: Some(deleted_documents),
+                    ..DetailsView::default()
+                }
+            }
+            Details::ClearAll { deleted_documents } => {
+                DetailsView { deleted_documents: Some(deleted_documents), ..DetailsView::default() }
+            }
+            Details::TaskCancelation { matched_tasks, canceled_tasks, original_filter } => {
+                DetailsView {
+                    matched_tasks: Some(matched_tasks),
+                    canceled_tasks: Some(canceled_tasks),
+                    original_filter: Some(Some(original_filter)),
+                    ..DetailsView::default()
+                }
+            }
+            Details::TaskDeletion { matched_tasks, deleted_tasks, original_filter } => {
+                DetailsView {
+                    matched_tasks: Some(matched_tasks),
+                    deleted_tasks: Some(deleted_tasks),
+                    original_filter: Some(Some(original_filter)),
+                    ..DetailsView::default()
+                }
+            }
+            Details::Dump { dump_uid } => {
+                DetailsView { dump_uid: Some(dump_uid), ..DetailsView::default() }
+            }
+            Details::IndexSwap { swaps } => {
+                DetailsView { swaps: Some(swaps), ..Default::default() }
+            }
+        }
+    }
+}

meilisearch/Cargo.toml

@@ -13,123 +13,126 @@ license.workspace = true
 default-run = "meilisearch"
 
 [dependencies]
-actix-cors = "0.6.4"
-actix-http = { version = "3.3.1", default-features = false, features = [
+actix-cors = "0.7.0"
+actix-http = { version = "3.6.0", default-features = false, features = [
     "compress-brotli",
     "compress-gzip",
-    "rustls",
+    "rustls-0_21",
 ] }
 actix-utils = "3.0.1"
-actix-web = { version = "4.3.1", default-features = false, features = [
+actix-web = { version = "4.5.1", default-features = false, features = [
     "macros",
     "compress-brotli",
     "compress-gzip",
     "cookies",
-    "rustls",
+    "rustls-0_21",
 ] }
 actix-web-static-files = { git = "https://github.com/kilork/actix-web-static-files.git", rev = "2d3b6160", optional = true }
-anyhow = { version = "1.0.70", features = ["backtrace"] }
+anyhow = { version = "1.0.79", features = ["backtrace"] }
 async-stream = "0.3.5"
-async-trait = "0.1.68"
-bstr = "1.4.0"
+async-trait = "0.1.77"
+bstr = "1.9.0"
 byte-unit = { version = "4.0.19", default-features = false, features = [
     "std",
     "serde",
 ] }
-bytes = "1.4.0"
-clap = { version = "4.2.1", features = ["derive", "env"] }
-crossbeam-channel = "0.5.8"
-deserr = { version = "0.6.0", features = ["actix-web"]}
+bytes = "1.5.0"
+clap = { version = "4.4.17", features = ["derive", "env"] }
+crossbeam-channel = "0.5.11"
+deserr = { version = "0.6.1", features = ["actix-web"] }
 dump = { path = "../dump" }
-either = "1.8.1"
-env_logger = "0.10.0"
+either = "1.9.0"
 file-store = { path = "../file-store" }
-flate2 = "1.0.25"
+flate2 = "1.0.28"
 fst = "0.4.7"
-futures = "0.3.28"
-futures-util = "0.3.28"
-http = "0.2.9"
+futures = "0.3.30"
+futures-util = "0.3.30"
+http = "0.2.11"
 index-scheduler = { path = "../index-scheduler" }
-indexmap = { version = "2.0.0", features = ["serde"] }
-is-terminal = "0.4.8"
+indexmap = { version = "2.1.0", features = ["serde"] }
+is-terminal = "0.4.10"
 itertools = "0.11.0"
-jsonwebtoken = "8.3.0"
+jsonwebtoken = "9.2.0"
 lazy_static = "1.4.0"
-log = "0.4.17"
 meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
-mimalloc = { version = "0.1.37", default-features = false }
+mimalloc = { version = "0.1.39", default-features = false }
 mime = "0.3.17"
-num_cpus = "1.15.0"
-obkv = "0.2.0"
-once_cell = "1.17.1"
-ordered-float = "3.7.0"
+num_cpus = "1.16.0"
+obkv = "0.2.1"
+once_cell = "1.19.0"
+ordered-float = "4.2.0"
 parking_lot = "0.12.1"
 permissive-json-pointer = { path = "../permissive-json-pointer" }
-pin-project-lite = "0.2.9"
+pin-project-lite = "0.2.13"
 platform-dirs = "0.3.0"
 prometheus = { version = "0.13.3", features = ["process"] }
 puffin = { version = "0.16.0", features = ["serialization"] }
 rand = "0.8.5"
-rayon = "1.7.0"
-regex = "1.7.3"
-reqwest = { version = "0.11.16", features = [
+rayon = "1.8.0"
+regex = "1.10.2"
+reqwest = { version = "0.11.23", features = [
     "rustls-tls",
     "json",
 ], default-features = false }
-rustls = "0.20.8"
+rustls = "0.21.6"
 rustls-pemfile = "1.0.2"
-segment = { version = "0.2.2", optional = true }
-serde = { version = "1.0.160", features = ["derive"] }
-serde_json = { version = "1.0.95", features = ["preserve_order"] }
-sha2 = "0.10.6"
-siphasher = "0.3.10"
-slice-group-by = "0.3.0"
+segment = { version = "0.2.3", optional = true }
+serde = { version = "1.0.195", features = ["derive"] }
+serde_json = { version = "1.0.111", features = ["preserve_order"] }
+sha2 = "0.10.8"
+siphasher = "1.0.0"
+slice-group-by = "0.3.1"
 static-files = { version = "0.2.3", optional = true }
-sysinfo = "0.29.7"
-tar = "0.4.38"
-tempfile = "3.5.0"
-thiserror = "1.0.40"
-time = { version = "0.3.20", features = [
+sysinfo = "0.30.5"
+tar = "0.4.40"
+tempfile = "3.9.0"
+thiserror = "1.0.56"
+time = { version = "0.3.31", features = [
     "serde-well-known",
     "formatting",
     "parsing",
     "macros",
 ] }
-tokio = { version = "1.27.0", features = ["full"] }
-tokio-stream = "0.1.12"
-toml = "0.7.3"
-uuid = { version = "1.3.1", features = ["serde", "v4"] }
-walkdir = "2.3.3"
+tokio = { version = "1.35.1", features = ["full"] }
+tokio-stream = "0.1.14"
+toml = "0.8.8"
+uuid = { version = "1.6.1", features = ["serde", "v4"] }
+walkdir = "2.4.0"
 yaup = "0.2.1"
 serde_urlencoded = "0.7.1"
-termcolor = "1.2.0"
+termcolor = "1.4.1"
+url = { version = "2.5.0", features = ["serde"] }
+tracing = "0.1.40"
+tracing-subscriber = { version = "0.3.18", features = ["json"] }
+tracing-trace = { version = "0.1.0", path = "../tracing-trace" }
+tracing-actix-web = "0.7.9"
+build-info = { version = "1.7.0", path = "../build-info" }
 
 [dev-dependencies]
-actix-rt = "2.8.0"
+actix-rt = "2.9.0"
 assert-json-diff = "2.0.2"
-brotli = "3.3.4"
-insta = "1.29.0"
-manifest-dir-macros = "0.1.16"
+brotli = "3.4.0"
+insta = "1.34.0"
+manifest-dir-macros = "0.1.18"
 maplit = "1.0.2"
 meili-snap = { path = "../meili-snap" }
-temp-env = "0.3.3"
-urlencoding = "2.1.2"
+temp-env = "0.3.6"
+urlencoding = "2.1.3"
 yaup = "0.2.1"
 
 [build-dependencies]
-anyhow = { version = "1.0.70", optional = true }
-cargo_toml = { version = "0.15.2", optional = true }
+anyhow = { version = "1.0.79", optional = true }
+cargo_toml = { version = "0.18.0", optional = true }
 hex = { version = "0.4.3", optional = true }
-reqwest = { version = "0.11.16", features = [
+reqwest = { version = "0.11.23", features = [
     "blocking",
     "rustls-tls",
 ], default-features = false, optional = true }
 sha-1 = { version = "0.10.1", optional = true }
 static-files = { version = "0.2.3", optional = true }
-tempfile = { version = "3.5.0", optional = true }
-vergen = { version = "7.5.1", default-features = false, features = ["git"] }
-zip = { version = "0.6.4", optional = true }
+tempfile = { version = "3.9.0", optional = true }
+zip = { version = "0.6.6", optional = true }
 
 [features]
 default = ["analytics", "meilisearch-types/all-tokenizations", "mini-dashboard"]
@@ -150,7 +153,9 @@ hebrew = ["meilisearch-types/hebrew"]
 japanese = ["meilisearch-types/japanese"]
 thai = ["meilisearch-types/thai"]
 greek = ["meilisearch-types/greek"]
+khmer = ["meilisearch-types/khmer"]
+vietnamese = ["meilisearch-types/vietnamese"]
 
 [package.metadata.mini-dashboard]
-assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.2.11/build.zip"
-sha1 = "83cd44ed1e5f97ecb581dc9f958a63f4ccc982d9"
+assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.2.13/build.zip"
+sha1 = "e20cc9b390003c6c844f4b8bcc5c5013191a77ff"

meilisearch/build.rs

@@ -1,17 +1,4 @@
-use vergen::{vergen, Config, SemverKind};
-
 fn main() {
-    // Note: any code that needs VERGEN_ environment variables should take care to define them manually in the Dockerfile and pass them
-    // in the corresponding GitHub workflow (publish_docker.yml).
-    // This is due to the Dockerfile building the binary outside of the git directory.
-    let mut config = Config::default();
-    // allow using non-annotated tags
-    *config.git_mut().semver_kind_mut() = SemverKind::Lightweight;
-
-    if let Err(e) = vergen(config) {
-        println!("cargo:warning=vergen: {}", e);
-    }
-
     #[cfg(feature = "mini-dashboard")]
     mini_dashboard::setup_mini_dashboard().expect("Could not load the mini-dashboard assets");
 }

meilisearch/src/analytics/segment_analytics.rs

@@ -18,7 +18,7 @@ use segment::message::{Identify, Track, User};
 use segment::{AutoBatcher, Batcher, HttpClient};
 use serde::Serialize;
 use serde_json::{json, Value};
-use sysinfo::{DiskExt, System, SystemExt};
+use sysinfo::{Disks, System};
 use time::OffsetDateTime;
 use tokio::select;
 use tokio::sync::mpsc::{self, Receiver, Sender};
@@ -28,7 +28,9 @@ use super::{
     config_user_id_path, DocumentDeletionKind, DocumentFetchKind, MEILISEARCH_CONFIG_PATH,
 };
 use crate::analytics::Analytics;
-use crate::option::{default_http_addr, IndexerOpts, MaxMemory, MaxThreads, ScheduleSnapshot};
+use crate::option::{
+    default_http_addr, IndexerOpts, LogMode, MaxMemory, MaxThreads, ScheduleSnapshot,
+};
 use crate::routes::indexes::documents::UpdateDocumentsQuery;
 use crate::routes::indexes::facet_search::FacetSearchQuery;
 use crate::routes::tasks::TasksFilterQuery;
@@ -36,7 +38,7 @@ use crate::routes::{create_all_stats, Stats};
 use crate::search::{
     FacetSearchResult, MatchingStrategy, SearchQuery, SearchQueryWithIndex, SearchResult,
     DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG,
-    DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT,
+    DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT, DEFAULT_SEMANTIC_RATIO,
 };
 use crate::Opt;
 
@@ -250,7 +252,13 @@ impl super::Analytics for SegmentAnalytics {
 struct Infos {
     env: String,
     experimental_enable_metrics: bool,
+    experimental_search_queue_size: usize,
+    experimental_logs_mode: LogMode,
+    experimental_replication_parameters: bool,
+    experimental_enable_logs_route: bool,
     experimental_reduce_indexing_memory_usage: bool,
+    experimental_max_number_of_batched_tasks: usize,
+    gpu_enabled: bool,
     db_path: bool,
     import_dump: bool,
     dump_dir: bool,
@@ -263,6 +271,8 @@ struct Infos {
     ignore_snapshot_if_db_exists: bool,
     http_addr: bool,
     http_payload_size_limit: Byte,
+    task_queue_webhook: bool,
+    task_webhook_authorization_header: bool,
     log_level: String,
     max_indexing_memory: MaxMemory,
     max_indexing_threads: MaxThreads,
@@ -284,10 +294,17 @@ impl From<Opt> for Infos {
         let Opt {
             db_path,
             experimental_enable_metrics,
+            experimental_search_queue_size,
+            experimental_logs_mode,
+            experimental_replication_parameters,
+            experimental_enable_logs_route,
             experimental_reduce_indexing_memory_usage,
+            experimental_max_number_of_batched_tasks,
             http_addr,
             master_key: _,
             env,
+            task_webhook_url,
+            task_webhook_authorization_header,
             max_index_size: _,
             max_task_db_size: _,
             http_payload_size_limit,
@@ -327,7 +344,12 @@ impl From<Opt> for Infos {
         Self {
             env,
             experimental_enable_metrics,
+            experimental_search_queue_size,
+            experimental_logs_mode,
+            experimental_replication_parameters,
+            experimental_enable_logs_route,
             experimental_reduce_indexing_memory_usage,
+            gpu_enabled: meilisearch_types::milli::vector::is_cuda_enabled(),
             db_path: db_path != PathBuf::from("./data.ms"),
             import_dump: import_dump.is_some(),
             dump_dir: dump_dir != PathBuf::from("dumps/"),
@@ -340,6 +362,9 @@ impl From<Opt> for Infos {
             ignore_snapshot_if_db_exists,
             http_addr: http_addr != default_http_addr(),
             http_payload_size_limit,
+            experimental_max_number_of_batched_tasks,
+            task_queue_webhook: task_webhook_url.is_some(),
+            task_webhook_authorization_header: task_webhook_authorization_header.is_some(),
             log_level: log_level.to_string(),
             max_indexing_memory,
             max_indexing_threads,
@@ -377,16 +402,17 @@ impl Segment {
     fn compute_traits(opt: &Opt, stats: Stats) -> Value {
         static FIRST_START_TIMESTAMP: Lazy<Instant> = Lazy::new(Instant::now);
         static SYSTEM: Lazy<Value> = Lazy::new(|| {
+            let disks = Disks::new_with_refreshed_list();
             let mut sys = System::new_all();
             sys.refresh_all();
-            let kernel_version =
-                sys.kernel_version().and_then(|k| k.split_once('-').map(|(k, _)| k.to_string()));
+            let kernel_version = System::kernel_version()
+                .and_then(|k| k.split_once('-').map(|(k, _)| k.to_string()));
             json!({
-                    "distribution": sys.name(),
+                    "distribution": System::name(),
                     "kernel_version": kernel_version,
                     "cores": sys.cpus().len(),
                     "ram_size": sys.total_memory(),
-                    "disk_size": sys.disks().iter().map(|disk| disk.total_space()).max(),
+                    "disk_size": disks.iter().map(|disk| disk.total_space()).max(),
                     "server_provider": std::env::var("MEILI_SERVER_PROVIDER").ok(),
             })
         });
@@ -450,7 +476,9 @@ impl Segment {
             create_all_stats(index_scheduler.into(), auth_controller.into(), &AuthFilter::default())
         {
             // Replace the version number with the prototype name if any.
-            let version = if let Some(prototype) = crate::prototype_name() {
+            let version = if let Some(prototype) = build_info::DescribeResult::from_build()
+                .and_then(|describe| describe.as_prototype())
+            {
                 prototype
             } else {
                 env!("CARGO_PKG_VERSION")
@@ -554,6 +582,8 @@ pub struct SearchAggregator {
     // requests
     total_received: usize,
     total_succeeded: usize,
+    total_degraded: usize,
+    total_used_negative_operator: usize,
     time_spent: BinaryHeap<usize>,
 
     // sort
@@ -583,6 +613,11 @@ pub struct SearchAggregator {
     // vector
     // The maximum number of floats in a vector request
     max_vector_size: usize,
+    // Whether the semantic ratio passed to a hybrid search equals the default ratio.
+    semantic_ratio: bool,
+    // Whether a non-default embedder was specified
+    embedder: bool,
+    hybrid: bool,
 
     // every time a search is done, we increment the counter linked to the used settings
     matching_strategy: HashMap<String, usize>,
@@ -636,6 +671,7 @@ impl SearchAggregator {
             crop_marker,
             matching_strategy,
             attributes_to_search_on,
+            hybrid,
         } = query;
 
         let mut ret = Self::default();
@@ -709,6 +745,12 @@ impl SearchAggregator {
         ret.show_ranking_score = *show_ranking_score;
         ret.show_ranking_score_details = *show_ranking_score_details;
 
+        if let Some(hybrid) = hybrid {
+            ret.semantic_ratio = hybrid.semantic_ratio != DEFAULT_SEMANTIC_RATIO();
+            ret.embedder = hybrid.embedder.is_some();
+            ret.hybrid = true;
+        }
+
         ret
     }
 
@@ -716,14 +758,22 @@ impl SearchAggregator {
         let SearchResult {
             hits: _,
             query: _,
-            vector: _,
             processing_time_ms,
             hits_info: _,
+            semantic_hit_count: _,
             facet_distribution: _,
             facet_stats: _,
+            degraded,
+            used_negative_operator,
         } = result;
 
         self.total_succeeded = self.total_succeeded.saturating_add(1);
+        if *degraded {
+            self.total_degraded = self.total_degraded.saturating_add(1);
+        }
+        if *used_negative_operator {
+            self.total_used_negative_operator = self.total_used_negative_operator.saturating_add(1);
+        }
         self.time_spent.push(*processing_time_ms as usize);
     }
 
@@ -762,6 +812,11 @@ impl SearchAggregator {
             facets_total_number_of_facets,
             show_ranking_score,
             show_ranking_score_details,
+            semantic_ratio,
+            embedder,
+            hybrid,
+            total_degraded,
+            total_used_negative_operator,
         } = other;
 
         if self.timestamp.is_none() {
@@ -776,6 +831,9 @@ impl SearchAggregator {
         // request
         self.total_received = self.total_received.saturating_add(total_received);
         self.total_succeeded = self.total_succeeded.saturating_add(total_succeeded);
+        self.total_degraded = self.total_degraded.saturating_add(total_degraded);
+        self.total_used_negative_operator =
+            self.total_used_negative_operator.saturating_add(total_used_negative_operator);
         self.time_spent.append(time_spent);
 
         // sort
@@ -807,6 +865,9 @@ impl SearchAggregator {
 
         // vector
         self.max_vector_size = self.max_vector_size.max(max_vector_size);
+        self.semantic_ratio |= semantic_ratio;
+        self.hybrid |= hybrid;
+        self.embedder |= embedder;
 
         // pagination
         self.max_limit = self.max_limit.max(max_limit);
@@ -875,6 +936,11 @@ impl SearchAggregator {
             facets_total_number_of_facets,
             show_ranking_score,
             show_ranking_score_details,
+            semantic_ratio,
+            embedder,
+            hybrid,
+            total_degraded,
+            total_used_negative_operator,
         } = self;
 
         if total_received == 0 {
@@ -894,6 +960,8 @@ impl SearchAggregator {
                     "total_succeeded": total_succeeded,
                     "total_failed": total_received.saturating_sub(total_succeeded), // just to be sure we never panics
                     "total_received": total_received,
+                    "total_degraded": total_degraded,
+                    "total_used_negative_operator": total_used_negative_operator,
                 },
                 "sort": {
                     "with_geoPoint": sort_with_geo_point,
@@ -914,6 +982,11 @@ impl SearchAggregator {
                 "vector": {
                     "max_vector_size": max_vector_size,
                 },
+                "hybrid": {
+                    "enabled": hybrid,
+                    "semantic_ratio": semantic_ratio,
+                    "embedder": embedder,
+                },
                 "pagination": {
                    "max_limit": max_limit,
                    "max_offset": max_offset,
@@ -1009,6 +1082,7 @@ impl MultiSearchAggregator {
                     crop_marker: _,
                     matching_strategy: _,
                     attributes_to_search_on: _,
+                    hybrid: _,
                 } = query;
 
                 index_uid.as_str()
@@ -1155,6 +1229,7 @@ impl FacetSearchAggregator {
             filter,
             matching_strategy,
             attributes_to_search_on,
+            hybrid,
         } = query;
 
         let mut ret = Self::default();
@@ -1168,7 +1243,8 @@ impl FacetSearchAggregator {
             || vector.is_some()
             || filter.is_some()
             || *matching_strategy != MatchingStrategy::default()
-            || attributes_to_search_on.is_some();
+            || attributes_to_search_on.is_some()
+            || hybrid.is_some();
 
         ret
     }

meilisearch/src/error.rs

@@ -12,6 +12,8 @@ pub enum MeilisearchHttpError {
     #[error("A Content-Type header is missing. Accepted values for the Content-Type header are: {}",
             .0.iter().map(|s| format!("`{}`", s)).collect::<Vec<_>>().join(", "))]
     MissingContentType(Vec<String>),
+    #[error("The `/logs/stream` route is currently in use by someone else.")]
+    AlreadyUsedLogRoute,
     #[error("The Content-Type `{0}` does not support the use of a csv delimiter. The csv delimiter can only be used with the Content-Type `text/csv`.")]
     CsvDelimiterWithWrongContentType(String),
     #[error(
@@ -21,12 +23,18 @@ pub enum MeilisearchHttpError {
     InvalidContentType(String, Vec<String>),
     #[error("Document `{0}` not found.")]
     DocumentNotFound(String),
+    #[error("Document `{0}` not found.")]
+    InvalidDocumentId(String),
     #[error("Sending an empty filter is forbidden.")]
     EmptyFilter,
     #[error("Invalid syntax for the filter parameter: `expected {}, found: {1}`.", .0.join(", "))]
     InvalidExpression(&'static [&'static str], Value),
     #[error("A {0} payload is missing.")]
     MissingPayload(PayloadType),
+    #[error("Too many search requests running at the same time: {0}. Retry after 10s.")]
+    TooManySearchRequests(usize),
+    #[error("Internal error: Search limiter is down.")]
+    SearchLimiterIsDown,
     #[error("The provided payload reached the size limit. The maximum accepted payload size is {}.",  Byte::from_bytes(*.0 as u64).get_appropriate_unit(true))]
     PayloadTooLarge(usize),
     #[error("Two indexes must be given for each swap. The list `[{}]` contains {} indexes.",
@@ -51,19 +59,25 @@ pub enum MeilisearchHttpError {
     DocumentFormat(#[from] DocumentFormatError),
     #[error(transparent)]
     Join(#[from] JoinError),
+    #[error("Invalid request: missing `hybrid` parameter when both `q` and `vector` are present.")]
+    MissingSearchHybrid,
 }
 
 impl ErrorCode for MeilisearchHttpError {
     fn error_code(&self) -> Code {
         match self {
             MeilisearchHttpError::MissingContentType(_) => Code::MissingContentType,
+            MeilisearchHttpError::AlreadyUsedLogRoute => Code::BadRequest,
             MeilisearchHttpError::CsvDelimiterWithWrongContentType(_) => Code::InvalidContentType,
             MeilisearchHttpError::MissingPayload(_) => Code::MissingPayload,
             MeilisearchHttpError::InvalidContentType(_, _) => Code::InvalidContentType,
             MeilisearchHttpError::DocumentNotFound(_) => Code::DocumentNotFound,
+            MeilisearchHttpError::InvalidDocumentId(_) => Code::InvalidDocumentId,
             MeilisearchHttpError::EmptyFilter => Code::InvalidDocumentFilter,
             MeilisearchHttpError::InvalidExpression(_, _) => Code::InvalidSearchFilter,
             MeilisearchHttpError::PayloadTooLarge(_) => Code::PayloadTooLarge,
+            MeilisearchHttpError::TooManySearchRequests(_) => Code::TooManySearchRequests,
+            MeilisearchHttpError::SearchLimiterIsDown => Code::Internal,
             MeilisearchHttpError::SwapIndexPayloadWrongLength(_) => Code::InvalidSwapIndexes,
             MeilisearchHttpError::IndexUid(e) => e.error_code(),
             MeilisearchHttpError::SerdeJson(_) => Code::Internal,
@@ -74,6 +88,7 @@ impl ErrorCode for MeilisearchHttpError {
             MeilisearchHttpError::FileStore(_) => Code::Internal,
             MeilisearchHttpError::DocumentFormat(e) => e.error_code(),
             MeilisearchHttpError::Join(_) => Code::Internal,
+            MeilisearchHttpError::MissingSearchHybrid => Code::MissingSearchHybrid,
         }
     }
 }

meilisearch/src/extractors/sequential_extractor.rs

@@ -131,6 +131,7 @@ gen_seq! { SeqFromRequestFut3; A B C }
 gen_seq! { SeqFromRequestFut4; A B C D }
 gen_seq! { SeqFromRequestFut5; A B C D E }
 gen_seq! { SeqFromRequestFut6; A B C D E F }
+gen_seq! { SeqFromRequestFut7; A B C D E F G }
 
 pin_project! {
     #[project = ExtractProj]

meilisearch/src/lib.rs

@@ -9,12 +9,14 @@ pub mod middleware;
 pub mod option;
 pub mod routes;
 pub mod search;
+pub mod search_queue;
 
 use std::fs::File;
 use std::io::{BufReader, BufWriter};
+use std::num::NonZeroUsize;
 use std::path::Path;
 use std::sync::Arc;
-use std::thread;
+use std::thread::{self, available_parallelism};
 use std::time::Duration;
 
 use actix_cors::Cors;
@@ -29,7 +31,6 @@ use error::PayloadError;
 use extractors::payload::PayloadConfig;
 use http::header::CONTENT_TYPE;
 use index_scheduler::{IndexScheduler, IndexSchedulerOptions};
-use log::error;
 use meilisearch_auth::AuthController;
 use meilisearch_types::milli::documents::{DocumentsBatchBuilder, DocumentsBatchReader};
 use meilisearch_types::milli::update::{IndexDocumentsConfig, IndexDocumentsMethod};
@@ -39,6 +40,9 @@ use meilisearch_types::versioning::{check_version_file, create_version_file};
 use meilisearch_types::{compression, milli, VERSION_FILE_NAME};
 pub use option::Opt;
 use option::ScheduleSnapshot;
+use search_queue::SearchQueue;
+use tracing::{error, info_span};
+use tracing_subscriber::filter::Targets;
 
 use crate::error::MeilisearchHttpError;
 
@@ -86,10 +90,35 @@ fn is_empty_db(db_path: impl AsRef<Path>) -> bool {
     }
 }
 
+/// The handle used to update the logs at runtime. Must be accessible from the `main.rs` and the `route/logs.rs`.
+pub type LogRouteHandle =
+    tracing_subscriber::reload::Handle<LogRouteType, tracing_subscriber::Registry>;
+
+pub type LogRouteType = tracing_subscriber::filter::Filtered<
+    Option<Box<dyn tracing_subscriber::Layer<tracing_subscriber::Registry> + Send + Sync>>,
+    Targets,
+    tracing_subscriber::Registry,
+>;
+
+pub type SubscriberForSecondLayer = tracing_subscriber::layer::Layered<
+    tracing_subscriber::reload::Layer<LogRouteType, tracing_subscriber::Registry>,
+    tracing_subscriber::Registry,
+>;
+
+pub type LogStderrHandle =
+    tracing_subscriber::reload::Handle<LogStderrType, SubscriberForSecondLayer>;
+
+pub type LogStderrType = tracing_subscriber::filter::Filtered<
+    Box<dyn tracing_subscriber::Layer<SubscriberForSecondLayer> + Send + Sync>,
+    Targets,
+    SubscriberForSecondLayer,
+>;
+
 pub fn create_app(
     index_scheduler: Data<IndexScheduler>,
     auth_controller: Data<AuthController>,
     opt: Opt,
+    logs: (LogRouteHandle, LogStderrHandle),
     analytics: Arc<dyn Analytics>,
     enable_dashboard: bool,
 ) -> actix_web::App<
@@ -108,6 +137,7 @@ pub fn create_app(
                 index_scheduler.clone(),
                 auth_controller.clone(),
                 &opt,
+                logs,
                 analytics.clone(),
             )
         })
@@ -123,11 +153,49 @@ pub fn create_app(
             .allow_any_method()
             .max_age(86_400), // 24h
     )
-    .wrap(actix_web::middleware::Logger::default())
+    .wrap(tracing_actix_web::TracingLogger::<AwebTracingLogger>::new())
     .wrap(actix_web::middleware::Compress::default())
     .wrap(actix_web::middleware::NormalizePath::new(actix_web::middleware::TrailingSlash::Trim))
 }
 
+struct AwebTracingLogger;
+
+impl tracing_actix_web::RootSpanBuilder for AwebTracingLogger {
+    fn on_request_start(request: &actix_web::dev::ServiceRequest) -> tracing::Span {
+        use tracing::field::Empty;
+
+        let conn_info = request.connection_info();
+        let headers = request.headers();
+        let user_agent = headers
+            .get(http::header::USER_AGENT)
+            .map(|value| String::from_utf8_lossy(value.as_bytes()).into_owned())
+            .unwrap_or_default();
+        info_span!("HTTP request", method = %request.method(), host = conn_info.host(), route = %request.path(), query_parameters = %request.query_string(), %user_agent, status_code = Empty, error = Empty)
+    }
+
+    fn on_request_end<B: MessageBody>(
+        span: tracing::Span,
+        outcome: &Result<ServiceResponse<B>, actix_web::Error>,
+    ) {
+        match &outcome {
+            Ok(response) => {
+                let code: i32 = response.response().status().as_u16().into();
+                span.record("status_code", code);
+
+                if let Some(error) = response.response().error() {
+                    // use the status code already constructed for the outgoing HTTP response
+                    span.record("error", &tracing::field::display(error.as_response_error()));
+                }
+            }
+            Err(error) => {
+                let code: i32 = error.error_response().status().as_u16().into();
+                span.record("status_code", code);
+                span.record("error", &tracing::field::display(error.as_response_error()));
+            }
+        };
+    }
+}
+
 enum OnFailure {
     RemoveDb,
     KeepDb,
@@ -200,7 +268,9 @@ pub fn setup_meilisearch(opt: &Opt) -> anyhow::Result<(Arc<IndexScheduler>, Arc<
             .name(String::from("register-snapshot-tasks"))
             .spawn(move || loop {
                 thread::sleep(snapshot_delay);
-                if let Err(e) = index_scheduler.register(KindWithContent::SnapshotCreation) {
+                if let Err(e) =
+                    index_scheduler.register(KindWithContent::SnapshotCreation, None, false)
+                {
                     error!("Error while registering snapshot: {}", e);
                 }
             })
@@ -228,12 +298,16 @@ fn open_or_create_database_unchecked(
             indexes_path: opt.db_path.join("indexes"),
             snapshots_path: opt.snapshot_dir.clone(),
             dumps_path: opt.dump_dir.clone(),
+            webhook_url: opt.task_webhook_url.as_ref().map(|url| url.to_string()),
+            webhook_authorization_header: opt.task_webhook_authorization_header.clone(),
             task_db_size: opt.max_task_db_size.get_bytes() as usize,
             index_base_map_size: opt.max_index_size.get_bytes() as usize,
             enable_mdb_writemap: opt.experimental_reduce_indexing_memory_usage,
             indexer_config: (&opt.indexer_options).try_into()?,
             autobatching_enabled: true,
+            cleanup_enabled: !opt.experimental_replication_parameters,
             max_number_of_tasks: 1_000_000,
+            max_number_of_batched_tasks: opt.experimental_max_number_of_batched_tasks,
             index_growth_amount: byte_unit::Byte::from_str("10GiB").unwrap().get_bytes() as usize,
             index_count: DEFAULT_INDEX_COUNT,
             instance_features,
@@ -277,15 +351,15 @@ fn import_dump(
     let mut dump_reader = dump::DumpReader::open(reader)?;
 
     if let Some(date) = dump_reader.date() {
-        log::info!(
-            "Importing a dump of meilisearch `{:?}` from the {}",
-            dump_reader.version(), // TODO: get the meilisearch version instead of the dump version
-            date
+        tracing::info!(
+            version = ?dump_reader.version(), // TODO: get the meilisearch version instead of the dump version
+            %date,
+            "Importing a dump of meilisearch"
         );
     } else {
-        log::info!(
-            "Importing a dump of meilisearch `{:?}`",
-            dump_reader.version(), // TODO: get the meilisearch version instead of the dump version
+        tracing::info!(
+            version = ?dump_reader.version(), // TODO: get the meilisearch version instead of the dump version
+            "Importing a dump of meilisearch",
         );
     }
 
@@ -319,7 +393,7 @@ fn import_dump(
     for index_reader in dump_reader.indexes()? {
         let mut index_reader = index_reader?;
         let metadata = index_reader.metadata();
-        log::info!("Importing index `{}`.", metadata.uid);
+        tracing::info!("Importing index `{}`.", metadata.uid);
 
         let date = Some((metadata.created_at, metadata.updated_at));
         let index = index_scheduler.create_raw_index(&metadata.uid, date)?;
@@ -333,14 +407,15 @@ fn import_dump(
         }
 
         // 4.2 Import the settings.
-        log::info!("Importing the settings.");
+        tracing::info!("Importing the settings.");
         let settings = index_reader.settings()?;
         apply_settings_to_builder(&settings, &mut builder);
-        builder.execute(|indexing_step| log::debug!("update: {:?}", indexing_step), || false)?;
+        builder
+            .execute(|indexing_step| tracing::debug!("update: {:?}", indexing_step), || false)?;
 
         // 4.3 Import the documents.
         // 4.3.1 We need to recreate the grenad+obkv format accepted by the index.
-        log::info!("Importing the documents.");
+        tracing::info!("Importing the documents.");
         let file = tempfile::tempfile()?;
         let mut builder = DocumentsBatchBuilder::new(BufWriter::new(file));
         for document in index_reader.documents()? {
@@ -354,6 +429,9 @@ fn import_dump(
         let reader = BufReader::new(file);
         let reader = DocumentsBatchReader::from_reader(reader)?;
 
+        let embedder_configs = index.embedding_configs(&wtxn)?;
+        let embedders = index_scheduler.embedders(embedder_configs)?;
+
         let builder = milli::update::IndexDocuments::new(
             &mut wtxn,
             &index,
@@ -362,15 +440,18 @@ fn import_dump(
                 update_method: IndexDocumentsMethod::ReplaceDocuments,
                 ..Default::default()
             },
-            |indexing_step| log::debug!("update: {:?}", indexing_step),
+            |indexing_step| tracing::trace!("update: {:?}", indexing_step),
             || false,
         )?;
 
+        let builder = builder.with_embedders(embedders);
+
         let (builder, user_result) = builder.add_documents(reader)?;
-        log::info!("{} documents found.", user_result?);
+        let user_result = user_result?;
+        tracing::info!(documents_found = user_result, "{} documents found.", user_result);
         builder.execute()?;
         wtxn.commit()?;
-        log::info!("All documents successfully imported.");
+        tracing::info!("All documents successfully imported.");
     }
 
     let mut index_scheduler_dump = index_scheduler.register_dumped_task()?;
@@ -388,15 +469,25 @@ pub fn configure_data(
     index_scheduler: Data<IndexScheduler>,
     auth: Data<AuthController>,
     opt: &Opt,
+    (logs_route, logs_stderr): (LogRouteHandle, LogStderrHandle),
     analytics: Arc<dyn Analytics>,
 ) {
+    let search_queue = SearchQueue::new(
+        opt.experimental_search_queue_size,
+        available_parallelism().unwrap_or(NonZeroUsize::new(2).unwrap()),
+    );
     let http_payload_size_limit = opt.http_payload_size_limit.get_bytes() as usize;
     config
         .app_data(index_scheduler)
         .app_data(auth)
+        .app_data(web::Data::new(search_queue))
         .app_data(web::Data::from(analytics))
+        .app_data(web::Data::new(logs_route))
+        .app_data(web::Data::new(logs_stderr))
+        .app_data(web::Data::new(opt.clone()))
         .app_data(
             web::JsonConfig::default()
+                .limit(http_payload_size_limit)
                 .content_type(|mime| mime == mime::APPLICATION_JSON)
                 .error_handler(|err, req: &HttpRequest| match err {
                     JsonPayloadError::ContentType => match req.headers().get(CONTENT_TYPE) {
@@ -453,30 +544,3 @@ pub fn dashboard(config: &mut web::ServiceConfig, enable_frontend: bool) {
 pub fn dashboard(config: &mut web::ServiceConfig, _enable_frontend: bool) {
     config.service(web::resource("/").route(web::get().to(routes::running)));
 }
-
-/// Parses the output of
-/// [`VERGEN_GIT_SEMVER_LIGHTWEIGHT`](https://docs.rs/vergen/latest/vergen/struct.Git.html#instructions)
-///  as a prototype name.
-///
-/// Returns `Some(prototype_name)` if the following conditions are met on this value:
-///
-/// 1. starts with `prototype-`,
-/// 2. ends with `-<some_number>`,
-/// 3. does not end with `<some_number>-<some_number>`.
-///
-/// Otherwise, returns `None`.
-pub fn prototype_name() -> Option<&'static str> {
-    let prototype: &'static str = option_env!("VERGEN_GIT_SEMVER_LIGHTWEIGHT")?;
-
-    if !prototype.starts_with("prototype-") {
-        return None;
-    }
-
-    let mut rsplit_prototype = prototype.rsplit('-');
-    // last component MUST be a number
-    rsplit_prototype.next()?.parse::<u64>().ok()?;
-    // before than last component SHALL NOT be a number
-    rsplit_prototype.next()?.parse::<u64>().err()?;
-
-    Some(prototype)
-}

meilisearch/src/main.rs

@@ -1,6 +1,7 @@
 use std::env;
-use std::io::{stderr, Write};
+use std::io::{stderr, LineWriter, Write};
 use std::path::PathBuf;
+use std::str::FromStr;
 use std::sync::Arc;
 
 use actix_web::http::KeepAlive;
@@ -9,33 +10,78 @@ use actix_web::HttpServer;
 use index_scheduler::IndexScheduler;
 use is_terminal::IsTerminal;
 use meilisearch::analytics::Analytics;
-use meilisearch::{analytics, create_app, prototype_name, setup_meilisearch, Opt};
+use meilisearch::option::LogMode;
+use meilisearch::{
+    analytics, create_app, setup_meilisearch, LogRouteHandle, LogRouteType, LogStderrHandle,
+    LogStderrType, Opt, SubscriberForSecondLayer,
+};
 use meilisearch_auth::{generate_master_key, AuthController, MASTER_KEY_MIN_SIZE};
+use mimalloc::MiMalloc;
 use termcolor::{Color, ColorChoice, ColorSpec, StandardStream, WriteColor};
+use tracing::level_filters::LevelFilter;
+use tracing_subscriber::layer::SubscriberExt as _;
+use tracing_subscriber::Layer;
 
 #[global_allocator]
-static ALLOC: mimalloc::MiMalloc = mimalloc::MiMalloc;
+static ALLOC: MiMalloc = MiMalloc;
+
+fn default_log_route_layer() -> LogRouteType {
+    None.with_filter(tracing_subscriber::filter::Targets::new().with_target("", LevelFilter::OFF))
+}
+
+fn default_log_stderr_layer(opt: &Opt) -> LogStderrType {
+    let layer = tracing_subscriber::fmt::layer()
+        .with_writer(|| LineWriter::new(std::io::stderr()))
+        .with_span_events(tracing_subscriber::fmt::format::FmtSpan::CLOSE);
+
+    let layer = match opt.experimental_logs_mode {
+        LogMode::Human => Box::new(layer)
+            as Box<dyn tracing_subscriber::Layer<SubscriberForSecondLayer> + Send + Sync>,
+        LogMode::Json => Box::new(layer.json())
+            as Box<dyn tracing_subscriber::Layer<SubscriberForSecondLayer> + Send + Sync>,
+    };
+
+    layer.with_filter(
+        tracing_subscriber::filter::Targets::new()
+            .with_target("", LevelFilter::from_str(&opt.log_level.to_string()).unwrap()),
+    )
+}
 
 /// does all the setup before meilisearch is launched
-fn setup(opt: &Opt) -> anyhow::Result<()> {
-    let mut log_builder = env_logger::Builder::new();
-    log_builder.parse_filters(&opt.log_level.to_string());
+fn setup(opt: &Opt) -> anyhow::Result<(LogRouteHandle, LogStderrHandle)> {
+    let (route_layer, route_layer_handle) =
+        tracing_subscriber::reload::Layer::new(default_log_route_layer());
+    let route_layer: tracing_subscriber::reload::Layer<_, _> = route_layer;
 
-    log_builder.init();
+    let (stderr_layer, stderr_layer_handle) =
+        tracing_subscriber::reload::Layer::new(default_log_stderr_layer(opt));
+    let route_layer: tracing_subscriber::reload::Layer<_, _> = route_layer;
 
-    Ok(())
+    let subscriber = tracing_subscriber::registry().with(route_layer).with(stderr_layer);
+
+    // set the subscriber as the default for the application
+    tracing::subscriber::set_global_default(subscriber).unwrap();
+
+    Ok((route_layer_handle, stderr_layer_handle))
+}
+
+fn on_panic(info: &std::panic::PanicInfo) {
+    let info = info.to_string().replace('\n', " ");
+    tracing::error!(%info);
 }
 
 #[actix_web::main]
 async fn main() -> anyhow::Result<()> {
     let (opt, config_read_from) = Opt::try_build()?;
 
+    std::panic::set_hook(Box::new(on_panic));
+
     anyhow::ensure!(
         !(cfg!(windows) && opt.experimental_reduce_indexing_memory_usage),
         "The `experimental-reduce-indexing-memory-usage` flag is not supported on Windows"
     );
 
-    setup(&opt)?;
+    let log_handle = setup(&opt)?;
 
     match (opt.env.as_ref(), &opt.master_key) {
         ("production", Some(master_key)) if master_key.len() < MASTER_KEY_MIN_SIZE => {
@@ -73,7 +119,7 @@ async fn main() -> anyhow::Result<()> {
 
     print_launch_resume(&opt, analytics.clone(), config_read_from);
 
-    run_http(index_scheduler, auth_controller, opt, analytics).await?;
+    run_http(index_scheduler, auth_controller, opt, log_handle, analytics).await?;
 
     Ok(())
 }
@@ -82,6 +128,7 @@ async fn run_http(
     index_scheduler: Arc<IndexScheduler>,
     auth_controller: Arc<AuthController>,
     opt: Opt,
+    logs: (LogRouteHandle, LogStderrHandle),
     analytics: Arc<dyn Analytics>,
 ) -> anyhow::Result<()> {
     let enable_dashboard = &opt.env == "development";
@@ -94,6 +141,7 @@ async fn run_http(
             index_scheduler.clone(),
             auth_controller.clone(),
             opt.clone(),
+            logs.clone(),
             analytics.clone(),
             enable_dashboard,
         )
@@ -103,7 +151,7 @@ async fn run_http(
     .keep_alive(KeepAlive::Os);
 
     if let Some(config) = opt_clone.get_ssl_config()? {
-        http_server.bind_rustls(opt_clone.http_addr, config)?.run().await?;
+        http_server.bind_rustls_021(opt_clone.http_addr, config)?.run().await?;
     } else {
         http_server.bind(&opt_clone.http_addr)?.run().await?;
     }
@@ -115,8 +163,8 @@ pub fn print_launch_resume(
     analytics: Arc<dyn Analytics>,
     config_read_from: Option<PathBuf>,
 ) {
-    let commit_sha = option_env!("VERGEN_GIT_SHA").unwrap_or("unknown");
-    let commit_date = option_env!("VERGEN_GIT_COMMIT_TIMESTAMP").unwrap_or("unknown");
+    let build_info = build_info::BuildInfo::from_build();
+
     let protocol =
         if opt.ssl_cert_path.is_some() && opt.ssl_key_path.is_some() { "https" } else { "http" };
     let ascii_name = r#"
@@ -141,10 +189,18 @@ pub fn print_launch_resume(
     eprintln!("Database path:\t\t{:?}", opt.db_path);
     eprintln!("Server listening on:\t\"{}://{}\"", protocol, opt.http_addr);
     eprintln!("Environment:\t\t{:?}", opt.env);
-    eprintln!("Commit SHA:\t\t{:?}", commit_sha.to_string());
-    eprintln!("Commit date:\t\t{:?}", commit_date.to_string());
+    eprintln!("Commit SHA:\t\t{:?}", build_info.commit_sha1.unwrap_or("unknown"));
+    eprintln!(
+        "Commit date:\t\t{:?}",
+        build_info
+            .commit_timestamp
+            .and_then(|commit_timestamp| commit_timestamp
+                .format(&time::format_description::well_known::Rfc3339)
+                .ok())
+            .unwrap_or("unknown".into())
+    );
     eprintln!("Package version:\t{:?}", env!("CARGO_PKG_VERSION").to_string());
-    if let Some(prototype) = prototype_name() {
+    if let Some(prototype) = build_info.describe.and_then(|describe| describe.as_prototype()) {
         eprintln!("Prototype:\t\t{:?}", prototype);
     }
 

meilisearch/src/metrics.rs

@@ -4,24 +4,17 @@ use prometheus::{
     register_int_gauge_vec, HistogramVec, IntCounterVec, IntGauge, IntGaugeVec,
 };
 
-/// Create evenly distributed buckets
-fn create_buckets() -> [f64; 29] {
-    (0..10)
-        .chain((10..100).step_by(10))
-        .chain((100..=1000).step_by(100))
-        .map(|i| i as f64 / 1000.)
-        .collect::<Vec<_>>()
-        .try_into()
-        .unwrap()
-}
-
 lazy_static! {
-    pub static ref MEILISEARCH_HTTP_RESPONSE_TIME_CUSTOM_BUCKETS: [f64; 29] = create_buckets();
     pub static ref MEILISEARCH_HTTP_REQUESTS_TOTAL: IntCounterVec = register_int_counter_vec!(
         opts!("meilisearch_http_requests_total", "Meilisearch HTTP requests total"),
-        &["method", "path"]
+        &["method", "path", "status"]
     )
     .expect("Can't create a metric");
+    pub static ref MEILISEARCH_DEGRADED_SEARCH_REQUESTS: IntGauge = register_int_gauge!(opts!(
+        "meilisearch_degraded_search_requests",
+        "Meilisearch number of degraded search requests"
+    ))
+    .expect("Can't create a metric");
     pub static ref MEILISEARCH_DB_SIZE_BYTES: IntGauge =
         register_int_gauge!(opts!("meilisearch_db_size_bytes", "Meilisearch DB Size In Bytes"))
             .expect("Can't create a metric");
@@ -42,7 +35,7 @@ lazy_static! {
         "meilisearch_http_response_time_seconds",
         "Meilisearch HTTP response times",
         &["method", "path"],
-        MEILISEARCH_HTTP_RESPONSE_TIME_CUSTOM_BUCKETS.to_vec()
+        vec![0.005, 0.01, 0.025, 0.05, 0.075, 0.1, 0.25, 0.5, 0.75, 1.0, 2.5, 5.0, 7.5, 10.0]
     )
     .expect("Can't create a metric");
     pub static ref MEILISEARCH_NB_TASKS: IntGaugeVec = register_int_gauge_vec!(

meilisearch/src/middleware.rs

@@ -65,9 +65,6 @@ where
                         .with_label_values(&[&request_method, request_path])
                         .start_timer(),
                 );
-                crate::metrics::MEILISEARCH_HTTP_REQUESTS_TOTAL
-                    .with_label_values(&[&request_method, request_path])
-                    .inc();
             }
         };
 
@@ -76,6 +73,14 @@ where
         Box::pin(async move {
             let res = fut.await?;
 
+            crate::metrics::MEILISEARCH_HTTP_REQUESTS_TOTAL
+                .with_label_values(&[
+                    res.request().method().as_str(),
+                    res.request().path(),
+                    res.status().as_str(),
+                ])
+                .inc();
+
             if let Some(histogram_timer) = histogram_timer {
                 histogram_timer.observe_duration();
             };

meilisearch/src/option.rs

@@ -1,4 +1,3 @@
-use std::convert::TryFrom;
 use std::env::VarError;
 use std::ffi::OsStr;
 use std::fmt::Display;
@@ -20,7 +19,8 @@ use rustls::server::{
 use rustls::RootCertStore;
 use rustls_pemfile::{certs, pkcs8_private_keys, rsa_private_keys};
 use serde::{Deserialize, Serialize};
-use sysinfo::{RefreshKind, System, SystemExt};
+use sysinfo::{MemoryRefreshKind, RefreshKind, System};
+use url::Url;
 
 const POSSIBLE_ENV: [&str; 2] = ["development", "production"];
 
@@ -28,6 +28,8 @@ const MEILI_DB_PATH: &str = "MEILI_DB_PATH";
 const MEILI_HTTP_ADDR: &str = "MEILI_HTTP_ADDR";
 const MEILI_MASTER_KEY: &str = "MEILI_MASTER_KEY";
 const MEILI_ENV: &str = "MEILI_ENV";
+const MEILI_TASK_WEBHOOK_URL: &str = "MEILI_TASK_WEBHOOK_URL";
+const MEILI_TASK_WEBHOOK_AUTHORIZATION_HEADER: &str = "MEILI_TASK_WEBHOOK_AUTHORIZATION_HEADER";
 #[cfg(feature = "analytics")]
 const MEILI_NO_ANALYTICS: &str = "MEILI_NO_ANALYTICS";
 const MEILI_HTTP_PAYLOAD_SIZE_LIMIT: &str = "MEILI_HTTP_PAYLOAD_SIZE_LIMIT";
@@ -48,9 +50,15 @@ const MEILI_IGNORE_MISSING_DUMP: &str = "MEILI_IGNORE_MISSING_DUMP";
 const MEILI_IGNORE_DUMP_IF_DB_EXISTS: &str = "MEILI_IGNORE_DUMP_IF_DB_EXISTS";
 const MEILI_DUMP_DIR: &str = "MEILI_DUMP_DIR";
 const MEILI_LOG_LEVEL: &str = "MEILI_LOG_LEVEL";
+const MEILI_EXPERIMENTAL_LOGS_MODE: &str = "MEILI_EXPERIMENTAL_LOGS_MODE";
+const MEILI_EXPERIMENTAL_REPLICATION_PARAMETERS: &str = "MEILI_EXPERIMENTAL_REPLICATION_PARAMETERS";
+const MEILI_EXPERIMENTAL_ENABLE_LOGS_ROUTE: &str = "MEILI_EXPERIMENTAL_ENABLE_LOGS_ROUTE";
 const MEILI_EXPERIMENTAL_ENABLE_METRICS: &str = "MEILI_EXPERIMENTAL_ENABLE_METRICS";
+const MEILI_EXPERIMENTAL_SEARCH_QUEUE_SIZE: &str = "MEILI_EXPERIMENTAL_SEARCH_QUEUE_SIZE";
 const MEILI_EXPERIMENTAL_REDUCE_INDEXING_MEMORY_USAGE: &str =
     "MEILI_EXPERIMENTAL_REDUCE_INDEXING_MEMORY_USAGE";
+const MEILI_EXPERIMENTAL_MAX_NUMBER_OF_BATCHED_TASKS: &str =
+    "MEILI_EXPERIMENTAL_MAX_NUMBER_OF_BATCHED_TASKS";
 
 const DEFAULT_CONFIG_FILE_PATH: &str = "./config.toml";
 const DEFAULT_DB_PATH: &str = "./data.ms";
@@ -73,6 +81,39 @@ const DEFAULT_LOG_EVERY_N: usize = 100_000;
 pub const INDEX_SIZE: u64 = 2 * 1024 * 1024 * 1024 * 1024; // 2 TiB
 pub const TASK_DB_SIZE: u64 = 20 * 1024 * 1024 * 1024; // 20 GiB
 
+#[derive(Debug, Default, Clone, Copy, Serialize, Deserialize)]
+#[serde(rename_all = "UPPERCASE")]
+pub enum LogMode {
+    #[default]
+    Human,
+    Json,
+}
+
+impl Display for LogMode {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        match self {
+            LogMode::Human => Display::fmt("HUMAN", f),
+            LogMode::Json => Display::fmt("JSON", f),
+        }
+    }
+}
+
+impl FromStr for LogMode {
+    type Err = LogModeError;
+
+    fn from_str(s: &str) -> Result<Self, Self::Err> {
+        match s.trim().to_lowercase().as_str() {
+            "human" => Ok(LogMode::Human),
+            "json" => Ok(LogMode::Json),
+            _ => Err(LogModeError(s.to_owned())),
+        }
+    }
+}
+
+#[derive(Debug, thiserror::Error)]
+#[error("Unsupported log mode level `{0}`. Supported values are `HUMAN` and `JSON`.")]
+pub struct LogModeError(String);
+
 #[derive(Debug, Default, Clone, Copy, Serialize, Deserialize)]
 #[serde(rename_all = "UPPERCASE")]
 pub enum LogLevel {
@@ -154,6 +195,14 @@ pub struct Opt {
     #[serde(default = "default_env")]
     pub env: String,
 
+    /// Called whenever a task finishes so a third party can be notified.
+    #[clap(long, env = MEILI_TASK_WEBHOOK_URL)]
+    pub task_webhook_url: Option<Url>,
+
+    /// The Authorization header to send on the webhook URL whenever a task finishes so a third party can be notified.
+    #[clap(long, env = MEILI_TASK_WEBHOOK_AUTHORIZATION_HEADER)]
+    pub task_webhook_authorization_header: Option<String>,
+
     /// Deactivates Meilisearch's built-in telemetry when provided.
     ///
     /// Meilisearch automatically collects data from all instances that do not opt out using this flag.
@@ -296,11 +345,49 @@ pub struct Opt {
     #[serde(default)]
     pub experimental_enable_metrics: bool,
 
+    /// Experimental search queue size. For more information, see: <https://github.com/orgs/meilisearch/discussions/729>
+    ///
+    /// Lets you customize the size of the search queue. Meilisearch processes your search requests as fast as possible but once the
+    /// queue is full it starts returning HTTP 503, Service Unavailable.
+    /// The default value is 1000.
+    #[clap(long, env = MEILI_EXPERIMENTAL_SEARCH_QUEUE_SIZE, default_value_t = 1000)]
+    #[serde(default)]
+    pub experimental_search_queue_size: usize,
+
+    /// Experimental logs mode feature. For more information, see: <https://github.com/orgs/meilisearch/discussions/723>
+    ///
+    /// Change the mode of the logs on the console.
+    #[clap(long, env = MEILI_EXPERIMENTAL_LOGS_MODE, default_value_t)]
+    #[serde(default)]
+    pub experimental_logs_mode: LogMode,
+
+    /// Experimental logs route feature. For more information, see: <https://github.com/orgs/meilisearch/discussions/721>
+    ///
+    /// Enables the log routes on the `POST /logs/stream`, `POST /logs/stderr` endpoints, and the `DELETE /logs/stream` to stop receiving logs.
+    #[clap(long, env = MEILI_EXPERIMENTAL_ENABLE_LOGS_ROUTE)]
+    #[serde(default)]
+    pub experimental_enable_logs_route: bool,
+
+    /// Enable multiple features that helps you to run meilisearch in a replicated context.
+    /// For more information, see: <https://github.com/orgs/meilisearch/discussions/725>
+    ///
+    /// - /!\ Disable the automatic clean up of old processed tasks, you're in charge of that now
+    /// - Lets you specify a custom task ID upon registering a task
+    /// - Lets you execute dry-register a task (get an answer from the route but nothing is actually registered in meilisearch and it won't be processed)
+    #[clap(long, env = MEILI_EXPERIMENTAL_REPLICATION_PARAMETERS)]
+    #[serde(default)]
+    pub experimental_replication_parameters: bool,
+
     /// Experimental RAM reduction during indexing, do not use in production, see: <https://github.com/meilisearch/product/discussions/652>
     #[clap(long, env = MEILI_EXPERIMENTAL_REDUCE_INDEXING_MEMORY_USAGE)]
     #[serde(default)]
     pub experimental_reduce_indexing_memory_usage: bool,
 
+    /// Experimentally reduces the maximum number of tasks that will be processed at once, see: <https://github.com/orgs/meilisearch/discussions/713>
+    #[clap(long, env = MEILI_EXPERIMENTAL_MAX_NUMBER_OF_BATCHED_TASKS, default_value_t = default_limit_batched_tasks())]
+    #[serde(default = "default_limit_batched_tasks")]
+    pub experimental_max_number_of_batched_tasks: usize,
+
     #[serde(flatten)]
     #[clap(flatten)]
     pub indexer_options: IndexerOpts,
@@ -368,9 +455,12 @@ impl Opt {
             http_addr,
             master_key,
             env,
+            task_webhook_url,
+            task_webhook_authorization_header,
             max_index_size: _,
             max_task_db_size: _,
             http_payload_size_limit,
+            experimental_max_number_of_batched_tasks,
             ssl_cert_path,
             ssl_key_path,
             ssl_auth_path,
@@ -392,8 +482,12 @@ impl Opt {
             config_file_path: _,
             #[cfg(feature = "analytics")]
             no_analytics,
-            experimental_enable_metrics: enable_metrics_route,
-            experimental_reduce_indexing_memory_usage: reduce_indexing_memory_usage,
+            experimental_enable_metrics,
+            experimental_search_queue_size,
+            experimental_logs_mode,
+            experimental_enable_logs_route,
+            experimental_replication_parameters,
+            experimental_reduce_indexing_memory_usage,
         } = self;
         export_to_env_if_not_present(MEILI_DB_PATH, db_path);
         export_to_env_if_not_present(MEILI_HTTP_ADDR, http_addr);
@@ -401,6 +495,16 @@ impl Opt {
             export_to_env_if_not_present(MEILI_MASTER_KEY, master_key);
         }
         export_to_env_if_not_present(MEILI_ENV, env);
+        if let Some(task_webhook_url) = task_webhook_url {
+            export_to_env_if_not_present(MEILI_TASK_WEBHOOK_URL, task_webhook_url.to_string());
+        }
+        if let Some(task_webhook_authorization_header) = task_webhook_authorization_header {
+            export_to_env_if_not_present(
+                MEILI_TASK_WEBHOOK_AUTHORIZATION_HEADER,
+                task_webhook_authorization_header,
+            );
+        }
+
         #[cfg(feature = "analytics")]
         {
             export_to_env_if_not_present(MEILI_NO_ANALYTICS, no_analytics.to_string());
@@ -409,6 +513,10 @@ impl Opt {
             MEILI_HTTP_PAYLOAD_SIZE_LIMIT,
             http_payload_size_limit.to_string(),
         );
+        export_to_env_if_not_present(
+            MEILI_EXPERIMENTAL_MAX_NUMBER_OF_BATCHED_TASKS,
+            experimental_max_number_of_batched_tasks.to_string(),
+        );
         if let Some(ssl_cert_path) = ssl_cert_path {
             export_to_env_if_not_present(MEILI_SSL_CERT_PATH, ssl_cert_path);
         }
@@ -433,11 +541,27 @@ impl Opt {
         export_to_env_if_not_present(MEILI_LOG_LEVEL, log_level.to_string());
         export_to_env_if_not_present(
             MEILI_EXPERIMENTAL_ENABLE_METRICS,
-            enable_metrics_route.to_string(),
+            experimental_enable_metrics.to_string(),
+        );
+        export_to_env_if_not_present(
+            MEILI_EXPERIMENTAL_SEARCH_QUEUE_SIZE,
+            experimental_search_queue_size.to_string(),
+        );
+        export_to_env_if_not_present(
+            MEILI_EXPERIMENTAL_LOGS_MODE,
+            experimental_logs_mode.to_string(),
+        );
+        export_to_env_if_not_present(
+            MEILI_EXPERIMENTAL_REPLICATION_PARAMETERS,
+            experimental_replication_parameters.to_string(),
+        );
+        export_to_env_if_not_present(
+            MEILI_EXPERIMENTAL_ENABLE_LOGS_ROUTE,
+            experimental_enable_logs_route.to_string(),
         );
         export_to_env_if_not_present(
             MEILI_EXPERIMENTAL_REDUCE_INDEXING_MEMORY_USAGE,
-            reduce_indexing_memory_usage.to_string(),
+            experimental_reduce_indexing_memory_usage.to_string(),
         );
         indexer_options.export_to_env();
     }
@@ -455,11 +579,11 @@ impl Opt {
                     }
                     if self.ssl_require_auth {
                         let verifier = AllowAnyAuthenticatedClient::new(client_auth_roots);
-                        config.with_client_cert_verifier(verifier)
+                        config.with_client_cert_verifier(Arc::from(verifier))
                     } else {
                         let verifier =
                             AllowAnyAnonymousOrAuthenticatedClient::new(client_auth_roots);
-                        config.with_client_cert_verifier(verifier)
+                        config.with_client_cert_verifier(Arc::from(verifier))
                     }
                 }
                 None => config.with_no_client_auth(),
@@ -489,7 +613,10 @@ impl Opt {
     }
 
     pub(crate) fn to_instance_features(&self) -> InstanceTogglableFeatures {
-        InstanceTogglableFeatures { metrics: self.experimental_enable_metrics }
+        InstanceTogglableFeatures {
+            metrics: self.experimental_enable_metrics,
+            logs_route: self.experimental_enable_logs_route,
+        }
     }
 }
 
@@ -598,8 +725,8 @@ impl MaxMemory {
 
 /// Returns the total amount of bytes available or `None` if this system isn't supported.
 fn total_memory_bytes() -> Option<u64> {
-    if System::IS_SUPPORTED {
-        let memory_kind = RefreshKind::new().with_memory();
+    if sysinfo::IS_SUPPORTED_SYSTEM {
+        let memory_kind = RefreshKind::new().with_memory(MemoryRefreshKind::new().with_ram());
         let mut system = System::new_with_specifics(memory_kind);
         system.refresh_memory();
         Some(system.total_memory())
@@ -727,6 +854,10 @@ fn default_http_payload_size_limit() -> Byte {
     Byte::from_str(DEFAULT_HTTP_PAYLOAD_SIZE_LIMIT).unwrap()
 }
 
+fn default_limit_batched_tasks() -> usize {
+    usize::MAX
+}
+
 fn default_snapshot_dir() -> PathBuf {
     PathBuf::from(DEFAULT_SNAPSHOT_DIR)
 }

meilisearch/src/routes/api_key.rs

@@ -10,7 +10,7 @@ use meilisearch_types::deserr::query_params::Param;
 use meilisearch_types::deserr::{DeserrJsonError, DeserrQueryParamError};
 use meilisearch_types::error::deserr_codes::*;
 use meilisearch_types::error::{Code, ResponseError};
-use meilisearch_types::keys::{Action, CreateApiKey, Key, PatchApiKey};
+use meilisearch_types::keys::{CreateApiKey, Key, PatchApiKey};
 use serde::{Deserialize, Serialize};
 use time::OffsetDateTime;
 use uuid::Uuid;

meilisearch/src/routes/dump.rs

@@ -1,17 +1,18 @@
 use actix_web::web::Data;
 use actix_web::{web, HttpRequest, HttpResponse};
 use index_scheduler::IndexScheduler;
-use log::debug;
 use meilisearch_auth::AuthController;
 use meilisearch_types::error::ResponseError;
 use meilisearch_types::tasks::KindWithContent;
 use serde_json::json;
+use tracing::debug;
 
 use crate::analytics::Analytics;
 use crate::extractors::authentication::policies::*;
 use crate::extractors::authentication::GuardedData;
 use crate::extractors::sequential_extractor::SeqHandler;
-use crate::routes::SummarizedTaskView;
+use crate::routes::{get_task_id, is_dry_run, SummarizedTaskView};
+use crate::Opt;
 
 pub fn configure(cfg: &mut web::ServiceConfig) {
     cfg.service(web::resource("").route(web::post().to(SeqHandler(create_dump))));
@@ -21,6 +22,7 @@ pub async fn create_dump(
     index_scheduler: GuardedData<ActionPolicy<{ actions::DUMPS_CREATE }>, Data<IndexScheduler>>,
     auth_controller: GuardedData<ActionPolicy<{ actions::DUMPS_CREATE }>, Data<AuthController>>,
     req: HttpRequest,
+    opt: web::Data<Opt>,
     analytics: web::Data<dyn Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     analytics.publish("Dump Created".to_string(), json!({}), Some(&req));
@@ -29,9 +31,13 @@ pub async fn create_dump(
         keys: auth_controller.list_keys()?,
         instance_uid: analytics.instance_uid().cloned(),
     };
+    let uid = get_task_id(&req, &opt)?;
+    let dry_run = is_dry_run(&req, &opt)?;
     let task: SummarizedTaskView =
-        tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
+        tokio::task::spawn_blocking(move || index_scheduler.register(task, uid, dry_run))
+            .await??
+            .into();
 
-    debug!("returns: {:?}", task);
+    debug!(returns = ?task, "Create dump");
     Ok(HttpResponse::Accepted().json(task))
 }

meilisearch/src/routes/features.rs

@@ -3,11 +3,11 @@ use actix_web::{HttpRequest, HttpResponse};
 use deserr::actix_web::AwebJson;
 use deserr::Deserr;
 use index_scheduler::IndexScheduler;
-use log::debug;
 use meilisearch_types::deserr::DeserrJsonError;
 use meilisearch_types::error::ResponseError;
 use meilisearch_types::keys::actions;
 use serde_json::json;
+use tracing::debug;
 
 use crate::analytics::Analytics;
 use crate::extractors::authentication::policies::ActionPolicy;
@@ -33,20 +33,21 @@ async fn get_features(
     let features = index_scheduler.features();
 
     analytics.publish("Experimental features Seen".to_string(), json!(null), Some(&req));
-    debug!("returns: {:?}", features.runtime_features());
-    HttpResponse::Ok().json(features.runtime_features())
+    let features = features.runtime_features();
+    debug!(returns = ?features, "Get features");
+    HttpResponse::Ok().json(features)
 }
 
 #[derive(Debug, Deserr)]
 #[deserr(error = DeserrJsonError, rename_all = camelCase, deny_unknown_fields)]
 pub struct RuntimeTogglableFeatures {
-    #[deserr(default)]
-    pub score_details: Option<bool>,
     #[deserr(default)]
     pub vector_store: Option<bool>,
     #[deserr(default)]
     pub metrics: Option<bool>,
     #[deserr(default)]
+    pub logs_route: Option<bool>,
+    #[deserr(default)]
     pub export_puffin_reports: Option<bool>,
 }
 
@@ -60,12 +61,13 @@ async fn patch_features(
     analytics: Data<dyn Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let features = index_scheduler.features();
+    debug!(parameters = ?new_features, "Patch features");
 
     let old_features = features.runtime_features();
     let new_features = meilisearch_types::features::RuntimeTogglableFeatures {
-        score_details: new_features.0.score_details.unwrap_or(old_features.score_details),
         vector_store: new_features.0.vector_store.unwrap_or(old_features.vector_store),
         metrics: new_features.0.metrics.unwrap_or(old_features.metrics),
+        logs_route: new_features.0.logs_route.unwrap_or(old_features.logs_route),
         export_puffin_reports: new_features
             .0
             .export_puffin_reports
@@ -76,22 +78,23 @@ async fn patch_features(
     // the it renames to camelCase, which we don't want for analytics.
     // **Do not** ignore fields with `..` or `_` here, because we want to add them in the future.
     let meilisearch_types::features::RuntimeTogglableFeatures {
-        score_details,
         vector_store,
         metrics,
+        logs_route,
         export_puffin_reports,
     } = new_features;
 
     analytics.publish(
         "Experimental features Updated".to_string(),
         json!({
-            "score_details": score_details,
             "vector_store": vector_store,
             "metrics": metrics,
+            "logs_route": logs_route,
             "export_puffin_reports": export_puffin_reports,
         }),
         Some(&req),
     );
     index_scheduler.put_runtime_features(new_features)?;
+    debug!(returns = ?new_features, "Patch features");
     Ok(HttpResponse::Ok().json(new_features))
 }

meilisearch/src/routes/indexes/documents.rs

@@ -3,12 +3,11 @@ use std::io::ErrorKind;
 use actix_web::http::header::CONTENT_TYPE;
 use actix_web::web::Data;
 use actix_web::{web, HttpMessage, HttpRequest, HttpResponse};
-use bstr::ByteSlice;
+use bstr::ByteSlice as _;
 use deserr::actix_web::{AwebJson, AwebQueryParameter};
 use deserr::Deserr;
 use futures::StreamExt;
-use index_scheduler::IndexScheduler;
-use log::debug;
+use index_scheduler::{IndexScheduler, TaskId};
 use meilisearch_types::deserr::query_params::Param;
 use meilisearch_types::deserr::{DeserrJsonError, DeserrQueryParamError};
 use meilisearch_types::document_formats::{read_csv, read_json, read_ndjson, PayloadType};
@@ -28,6 +27,7 @@ use serde_json::Value;
 use tempfile::tempfile;
 use tokio::fs::File;
 use tokio::io::{AsyncSeekExt, AsyncWriteExt, BufWriter};
+use tracing::debug;
 
 use crate::analytics::{Analytics, DocumentDeletionKind, DocumentFetchKind};
 use crate::error::MeilisearchHttpError;
@@ -36,8 +36,11 @@ use crate::extractors::authentication::policies::*;
 use crate::extractors::authentication::GuardedData;
 use crate::extractors::payload::Payload;
 use crate::extractors::sequential_extractor::SeqHandler;
-use crate::routes::{PaginationView, SummarizedTaskView, PAGINATION_DEFAULT_LIMIT};
+use crate::routes::{
+    get_task_id, is_dry_run, PaginationView, SummarizedTaskView, PAGINATION_DEFAULT_LIMIT,
+};
 use crate::search::parse_filter;
+use crate::Opt;
 
 static ACCEPTED_CONTENT_TYPE: Lazy<Vec<String>> = Lazy::new(|| {
     vec!["application/json".to_string(), "application/x-ndjson".to_string(), "text/csv".to_string()]
@@ -101,6 +104,7 @@ pub async fn get_document(
     analytics: web::Data<dyn Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let DocumentParam { index_uid, document_id } = document_param.into_inner();
+    debug!(parameters = ?params, "Get document");
     let index_uid = IndexUid::try_from(index_uid)?;
 
     analytics.get_fetch_documents(&DocumentFetchKind::PerDocumentId, &req);
@@ -110,7 +114,7 @@ pub async fn get_document(
 
     let index = index_scheduler.index(&index_uid)?;
     let document = retrieve_document(&index, &document_id, attributes_to_retrieve)?;
-    debug!("returns: {:?}", document);
+    debug!(returns = ?document, "Get document");
     Ok(HttpResponse::Ok().json(document))
 }
 
@@ -118,6 +122,7 @@ pub async fn delete_document(
     index_scheduler: GuardedData<ActionPolicy<{ actions::DOCUMENTS_DELETE }>, Data<IndexScheduler>>,
     path: web::Path<DocumentParam>,
     req: HttpRequest,
+    opt: web::Data<Opt>,
     analytics: web::Data<dyn Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let DocumentParam { index_uid, document_id } = path.into_inner();
@@ -129,8 +134,12 @@ pub async fn delete_document(
         index_uid: index_uid.to_string(),
         documents_ids: vec![document_id],
     };
+    let uid = get_task_id(&req, &opt)?;
+    let dry_run = is_dry_run(&req, &opt)?;
     let task: SummarizedTaskView =
-        tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
+        tokio::task::spawn_blocking(move || index_scheduler.register(task, uid, dry_run))
+            .await??
+            .into();
     debug!("returns: {:?}", task);
     Ok(HttpResponse::Accepted().json(task))
 }
@@ -168,9 +177,8 @@ pub async fn documents_by_query_post(
     req: HttpRequest,
     analytics: web::Data<dyn Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
-    debug!("called with body: {:?}", body);
-
     let body = body.into_inner();
+    debug!(parameters = ?body, "Get documents POST");
 
     analytics.post_fetch_documents(
         &DocumentFetchKind::Normal {
@@ -191,7 +199,7 @@ pub async fn get_documents(
     req: HttpRequest,
     analytics: web::Data<dyn Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
-    debug!("called with params: {:?}", params);
+    debug!(parameters = ?params, "Get documents GET");
 
     let BrowseQueryGet { limit, offset, fields, filter } = params.into_inner();
 
@@ -235,7 +243,7 @@ fn documents_by_query(
 
     let ret = PaginationView::new(offset, limit, total as usize, documents);
 
-    debug!("returns: {:?}", ret);
+    debug!(returns = ?ret, "Get documents");
     Ok(HttpResponse::Ok().json(ret))
 }
 
@@ -267,16 +275,19 @@ pub async fn replace_documents(
     params: AwebQueryParameter<UpdateDocumentsQuery, DeserrQueryParamError>,
     body: Payload,
     req: HttpRequest,
+    opt: web::Data<Opt>,
     analytics: web::Data<dyn Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
 
-    debug!("called with params: {:?}", params);
+    debug!(parameters = ?params, "Replace documents");
     let params = params.into_inner();
 
     analytics.add_documents(&params, index_scheduler.index(&index_uid).is_err(), &req);
 
     let allow_index_creation = index_scheduler.filters().allow_index_creation(&index_uid);
+    let uid = get_task_id(&req, &opt)?;
+    let dry_run = is_dry_run(&req, &opt)?;
     let task = document_addition(
         extract_mime_type(&req)?,
         index_scheduler,
@@ -285,9 +296,12 @@ pub async fn replace_documents(
         params.csv_delimiter,
         body,
         IndexDocumentsMethod::ReplaceDocuments,
+        uid,
+        dry_run,
         allow_index_creation,
     )
     .await?;
+    debug!(returns = ?task, "Replace documents");
 
     Ok(HttpResponse::Accepted().json(task))
 }
@@ -298,16 +312,19 @@ pub async fn update_documents(
     params: AwebQueryParameter<UpdateDocumentsQuery, DeserrQueryParamError>,
     body: Payload,
     req: HttpRequest,
+    opt: web::Data<Opt>,
     analytics: web::Data<dyn Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
 
-    debug!("called with params: {:?}", params);
     let params = params.into_inner();
+    debug!(parameters = ?params, "Update documents");
 
     analytics.update_documents(&params, index_scheduler.index(&index_uid).is_err(), &req);
 
     let allow_index_creation = index_scheduler.filters().allow_index_creation(&index_uid);
+    let uid = get_task_id(&req, &opt)?;
+    let dry_run = is_dry_run(&req, &opt)?;
     let task = document_addition(
         extract_mime_type(&req)?,
         index_scheduler,
@@ -316,9 +333,12 @@ pub async fn update_documents(
         params.csv_delimiter,
         body,
         IndexDocumentsMethod::UpdateDocuments,
+        uid,
+        dry_run,
         allow_index_creation,
     )
     .await?;
+    debug!(returns = ?task, "Update documents");
 
     Ok(HttpResponse::Accepted().json(task))
 }
@@ -332,6 +352,8 @@ async fn document_addition(
     csv_delimiter: Option<u8>,
     mut body: Payload,
     method: IndexDocumentsMethod,
+    task_id: Option<TaskId>,
+    dry_run: bool,
     allow_index_creation: bool,
 ) -> Result<SummarizedTaskView, MeilisearchHttpError> {
     let format = match (
@@ -364,7 +386,7 @@ async fn document_addition(
         }
     };
 
-    let (uuid, mut update_file) = index_scheduler.create_update_file()?;
+    let (uuid, mut update_file) = index_scheduler.create_update_file(dry_run)?;
 
     let temp_file = match tempfile() {
         Ok(file) => file,
@@ -403,11 +425,9 @@ async fn document_addition(
     let read_file = buffer.into_inner().into_std().await;
     let documents_count = tokio::task::spawn_blocking(move || {
         let documents_count = match format {
-            PayloadType::Json => read_json(&read_file, update_file.as_file_mut())?,
-            PayloadType::Csv { delimiter } => {
-                read_csv(&read_file, update_file.as_file_mut(), delimiter)?
-            }
-            PayloadType::Ndjson => read_ndjson(&read_file, update_file.as_file_mut())?,
+            PayloadType::Json => read_json(&read_file, &mut update_file)?,
+            PayloadType::Csv { delimiter } => read_csv(&read_file, &mut update_file, delimiter)?,
+            PayloadType::Ndjson => read_ndjson(&read_file, &mut update_file)?,
         };
         // we NEED to persist the file here because we moved the `udpate_file` in another task.
         update_file.persist()?;
@@ -427,7 +447,10 @@ async fn document_addition(
                 Err(index_scheduler::Error::FileStore(file_store::Error::IoError(e)))
                     if e.kind() == ErrorKind::NotFound => {}
                 Err(e) => {
-                    log::warn!("Unknown error happened while deleting a malformed update file with uuid {uuid}: {e}");
+                    tracing::warn!(
+                        index_uuid = %uuid,
+                        "Unknown error happened while deleting a malformed update file: {e}"
+                    );
                 }
             }
             // We still want to return the original error to the end user.
@@ -445,7 +468,9 @@ async fn document_addition(
     };
 
     let scheduler = index_scheduler.clone();
-    let task = match tokio::task::spawn_blocking(move || scheduler.register(task)).await? {
+    let task = match tokio::task::spawn_blocking(move || scheduler.register(task, task_id, dry_run))
+        .await?
+    {
         Ok(task) => task,
         Err(e) => {
             index_scheduler.delete_update_file(uuid)?;
@@ -453,7 +478,6 @@ async fn document_addition(
         }
     };
 
-    debug!("returns: {:?}", task);
     Ok(task.into())
 }
 
@@ -462,9 +486,10 @@ pub async fn delete_documents_batch(
     index_uid: web::Path<String>,
     body: web::Json<Vec<Value>>,
     req: HttpRequest,
+    opt: web::Data<Opt>,
     analytics: web::Data<dyn Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
-    debug!("called with params: {:?}", body);
+    debug!(parameters = ?body, "Delete documents by batch");
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
 
     analytics.delete_documents(DocumentDeletionKind::PerBatch, &req);
@@ -476,10 +501,14 @@ pub async fn delete_documents_batch(
 
     let task =
         KindWithContent::DocumentDeletion { index_uid: index_uid.to_string(), documents_ids: ids };
+    let uid = get_task_id(&req, &opt)?;
+    let dry_run = is_dry_run(&req, &opt)?;
     let task: SummarizedTaskView =
-        tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
+        tokio::task::spawn_blocking(move || index_scheduler.register(task, uid, dry_run))
+            .await??
+            .into();
 
-    debug!("returns: {:?}", task);
+    debug!(returns = ?task, "Delete documents by batch");
     Ok(HttpResponse::Accepted().json(task))
 }
 
@@ -495,9 +524,10 @@ pub async fn delete_documents_by_filter(
     index_uid: web::Path<String>,
     body: AwebJson<DocumentDeletionByFilter, DeserrJsonError>,
     req: HttpRequest,
+    opt: web::Data<Opt>,
     analytics: web::Data<dyn Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
-    debug!("called with params: {:?}", body);
+    debug!(parameters = ?body, "Delete documents by filter");
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
     let index_uid = index_uid.into_inner();
     let filter = body.into_inner().filter;
@@ -512,10 +542,14 @@ pub async fn delete_documents_by_filter(
     .map_err(|err| ResponseError::from_msg(err.message, Code::InvalidDocumentFilter))?;
     let task = KindWithContent::DocumentDeletionByFilter { index_uid, filter_expr: filter };
 
+    let uid = get_task_id(&req, &opt)?;
+    let dry_run = is_dry_run(&req, &opt)?;
     let task: SummarizedTaskView =
-        tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
+        tokio::task::spawn_blocking(move || index_scheduler.register(task, uid, dry_run))
+            .await??
+            .into();
 
-    debug!("returns: {:?}", task);
+    debug!(returns = ?task, "Delete documents by filter");
     Ok(HttpResponse::Accepted().json(task))
 }
 
@@ -523,16 +557,21 @@ pub async fn clear_all_documents(
     index_scheduler: GuardedData<ActionPolicy<{ actions::DOCUMENTS_DELETE }>, Data<IndexScheduler>>,
     index_uid: web::Path<String>,
     req: HttpRequest,
+    opt: web::Data<Opt>,
     analytics: web::Data<dyn Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
     analytics.delete_documents(DocumentDeletionKind::ClearAll, &req);
 
     let task = KindWithContent::DocumentClear { index_uid: index_uid.to_string() };
+    let uid = get_task_id(&req, &opt)?;
+    let dry_run = is_dry_run(&req, &opt)?;
     let task: SummarizedTaskView =
-        tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
+        tokio::task::spawn_blocking(move || index_scheduler.register(task, uid, dry_run))
+            .await??
+            .into();
 
-    debug!("returns: {:?}", task);
+    debug!(returns = ?task, "Delete all documents");
     Ok(HttpResponse::Accepted().json(task))
 }
 
@@ -612,8 +651,8 @@ fn retrieve_document<S: AsRef<str>>(
     let all_fields: Vec<_> = fields_ids_map.iter().map(|(id, _)| id).collect();
 
     let internal_id = index
-        .external_documents_ids(&txn)?
-        .get(doc_id.as_bytes())
+        .external_documents_ids()
+        .get(&txn, doc_id)?
         .ok_or_else(|| MeilisearchHttpError::DocumentNotFound(doc_id.to_string()))?;
 
     let document = index

meilisearch/src/routes/indexes/facet_search.rs

@@ -2,21 +2,23 @@ use actix_web::web::Data;
 use actix_web::{web, HttpRequest, HttpResponse};
 use deserr::actix_web::AwebJson;
 use index_scheduler::IndexScheduler;
-use log::debug;
 use meilisearch_types::deserr::DeserrJsonError;
 use meilisearch_types::error::deserr_codes::*;
 use meilisearch_types::error::ResponseError;
 use meilisearch_types::index_uid::IndexUid;
 use serde_json::Value;
+use tracing::debug;
 
 use crate::analytics::{Analytics, FacetSearchAggregator};
 use crate::extractors::authentication::policies::*;
 use crate::extractors::authentication::GuardedData;
+use crate::routes::indexes::search::search_kind;
 use crate::search::{
-    add_search_rules, perform_facet_search, MatchingStrategy, SearchQuery, DEFAULT_CROP_LENGTH,
-    DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG,
-    DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET,
+    add_search_rules, perform_facet_search, HybridQuery, MatchingStrategy, SearchQuery,
+    DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG,
+    DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET,
 };
+use crate::search_queue::SearchQueue;
 
 pub fn configure(cfg: &mut web::ServiceConfig) {
     cfg.service(web::resource("").route(web::post().to(search)));
@@ -36,6 +38,8 @@ pub struct FacetSearchQuery {
     pub q: Option<String>,
     #[deserr(default, error = DeserrJsonError<InvalidSearchVector>)]
     pub vector: Option<Vec<f32>>,
+    #[deserr(default, error = DeserrJsonError<InvalidHybridQuery>)]
+    pub hybrid: Option<HybridQuery>,
     #[deserr(default, error = DeserrJsonError<InvalidSearchFilter>)]
     pub filter: Option<Value>,
     #[deserr(default, error = DeserrJsonError<InvalidSearchMatchingStrategy>, default)]
@@ -46,6 +50,7 @@ pub struct FacetSearchQuery {
 
 pub async fn search(
     index_scheduler: GuardedData<ActionPolicy<{ actions::SEARCH }>, Data<IndexScheduler>>,
+    search_queue: Data<SearchQueue>,
     index_uid: web::Path<String>,
     params: AwebJson<FacetSearchQuery, DeserrJsonError>,
     req: HttpRequest,
@@ -54,7 +59,7 @@ pub async fn search(
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
 
     let query = params.into_inner();
-    debug!("facet search called with params: {:?}", query);
+    debug!(parameters = ?query, "Facet search");
 
     let mut aggregate = FacetSearchAggregator::from_query(&query, &req);
 
@@ -69,8 +74,10 @@ pub async fn search(
 
     let index = index_scheduler.index(&index_uid)?;
     let features = index_scheduler.features();
+    let search_kind = search_kind(&search_query, &index_scheduler, &index, features)?;
+    let _permit = search_queue.try_get_search_permit().await?;
     let search_result = tokio::task::spawn_blocking(move || {
-        perform_facet_search(&index, search_query, facet_query, facet_name, features)
+        perform_facet_search(&index, search_query, facet_query, facet_name, search_kind)
     })
     .await?;
 
@@ -81,7 +88,7 @@ pub async fn search(
 
     let search_result = search_result?;
 
-    debug!("returns: {:?}", search_result);
+    debug!(returns = ?search_result, "Facet search");
     Ok(HttpResponse::Ok().json(search_result))
 }
 
@@ -95,6 +102,7 @@ impl From<FacetSearchQuery> for SearchQuery {
             filter,
             matching_strategy,
             attributes_to_search_on,
+            hybrid,
         } = value;
 
         SearchQuery {
@@ -119,6 +127,7 @@ impl From<FacetSearchQuery> for SearchQuery {
             matching_strategy,
             vector,
             attributes_to_search_on,
+            hybrid,
         }
     }
 }

meilisearch/src/routes/indexes/mod.rs

@@ -5,7 +5,6 @@ use actix_web::{web, HttpRequest, HttpResponse};
 use deserr::actix_web::{AwebJson, AwebQueryParameter};
 use deserr::{DeserializeError, Deserr, ValuePointerRef};
 use index_scheduler::IndexScheduler;
-use log::debug;
 use meilisearch_types::deserr::query_params::Param;
 use meilisearch_types::deserr::{immutable_field_error, DeserrJsonError, DeserrQueryParamError};
 use meilisearch_types::error::deserr_codes::*;
@@ -16,15 +15,19 @@ use meilisearch_types::tasks::KindWithContent;
 use serde::Serialize;
 use serde_json::json;
 use time::OffsetDateTime;
+use tracing::debug;
 
-use super::{Pagination, SummarizedTaskView, PAGINATION_DEFAULT_LIMIT};
+use super::{get_task_id, Pagination, SummarizedTaskView, PAGINATION_DEFAULT_LIMIT};
 use crate::analytics::Analytics;
 use crate::extractors::authentication::policies::*;
 use crate::extractors::authentication::{AuthenticationError, GuardedData};
 use crate::extractors::sequential_extractor::SeqHandler;
+use crate::routes::is_dry_run;
+use crate::Opt;
 
 pub mod documents;
 pub mod facet_search;
+pub mod recommend;
 pub mod search;
 pub mod settings;
 
@@ -46,6 +49,7 @@ pub fn configure(cfg: &mut web::ServiceConfig) {
             .service(web::scope("/documents").configure(documents::configure))
             .service(web::scope("/search").configure(search::configure))
             .service(web::scope("/facet-search").configure(facet_search::configure))
+            .service(web::scope("/recommend").configure(recommend::configure))
             .service(web::scope("/settings").configure(settings::configure)),
     );
 }
@@ -93,6 +97,7 @@ pub async fn list_indexes(
     index_scheduler: GuardedData<ActionPolicy<{ actions::INDEXES_GET }>, Data<IndexScheduler>>,
     paginate: AwebQueryParameter<ListIndexes, DeserrQueryParamError>,
 ) -> Result<HttpResponse, ResponseError> {
+    debug!(parameters = ?paginate, "List indexes");
     let filters = index_scheduler.filters();
     let indexes: Vec<Option<IndexView>> =
         index_scheduler.try_for_each_index(|uid, index| -> Result<Option<IndexView>, _> {
@@ -105,7 +110,7 @@ pub async fn list_indexes(
     let indexes: Vec<IndexView> = indexes.into_iter().flatten().collect();
     let ret = paginate.as_pagination().auto_paginate_sized(indexes.into_iter());
 
-    debug!("returns: {:?}", ret);
+    debug!(returns = ?ret, "List indexes");
     Ok(HttpResponse::Ok().json(ret))
 }
 
@@ -122,8 +127,10 @@ pub async fn create_index(
     index_scheduler: GuardedData<ActionPolicy<{ actions::INDEXES_CREATE }>, Data<IndexScheduler>>,
     body: AwebJson<IndexCreateRequest, DeserrJsonError>,
     req: HttpRequest,
+    opt: web::Data<Opt>,
     analytics: web::Data<dyn Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
+    debug!(parameters = ?body, "Create index");
     let IndexCreateRequest { primary_key, uid } = body.into_inner();
 
     let allow_index_creation = index_scheduler.filters().allow_index_creation(&uid);
@@ -135,8 +142,13 @@ pub async fn create_index(
         );
 
         let task = KindWithContent::IndexCreation { index_uid: uid.to_string(), primary_key };
+        let uid = get_task_id(&req, &opt)?;
+        let dry_run = is_dry_run(&req, &opt)?;
         let task: SummarizedTaskView =
-            tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
+            tokio::task::spawn_blocking(move || index_scheduler.register(task, uid, dry_run))
+                .await??
+                .into();
+        debug!(returns = ?task, "Create index");
 
         Ok(HttpResponse::Accepted().json(task))
     } else {
@@ -177,7 +189,7 @@ pub async fn get_index(
     let index = index_scheduler.index(&index_uid)?;
     let index_view = IndexView::new(index_uid.into_inner(), &index)?;
 
-    debug!("returns: {:?}", index_view);
+    debug!(returns = ?index_view, "Get index");
 
     Ok(HttpResponse::Ok().json(index_view))
 }
@@ -187,9 +199,10 @@ pub async fn update_index(
     index_uid: web::Path<String>,
     body: AwebJson<UpdateIndexRequest, DeserrJsonError>,
     req: HttpRequest,
+    opt: web::Data<Opt>,
     analytics: web::Data<dyn Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
-    debug!("called with params: {:?}", body);
+    debug!(parameters = ?body, "Update index");
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
     let body = body.into_inner();
     analytics.publish(
@@ -203,21 +216,32 @@ pub async fn update_index(
         primary_key: body.primary_key,
     };
 
+    let uid = get_task_id(&req, &opt)?;
+    let dry_run = is_dry_run(&req, &opt)?;
     let task: SummarizedTaskView =
-        tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
+        tokio::task::spawn_blocking(move || index_scheduler.register(task, uid, dry_run))
+            .await??
+            .into();
 
-    debug!("returns: {:?}", task);
+    debug!(returns = ?task, "Update index");
     Ok(HttpResponse::Accepted().json(task))
 }
 
 pub async fn delete_index(
     index_scheduler: GuardedData<ActionPolicy<{ actions::INDEXES_DELETE }>, Data<IndexScheduler>>,
     index_uid: web::Path<String>,
+    req: HttpRequest,
+    opt: web::Data<Opt>,
 ) -> Result<HttpResponse, ResponseError> {
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
     let task = KindWithContent::IndexDeletion { index_uid: index_uid.into_inner() };
+    let uid = get_task_id(&req, &opt)?;
+    let dry_run = is_dry_run(&req, &opt)?;
     let task: SummarizedTaskView =
-        tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
+        tokio::task::spawn_blocking(move || index_scheduler.register(task, uid, dry_run))
+            .await??
+            .into();
+    debug!(returns = ?task, "Delete index");
 
     Ok(HttpResponse::Accepted().json(task))
 }
@@ -255,6 +279,6 @@ pub async fn get_index_stats(
 
     let stats = IndexStats::from(index_scheduler.index_stats(&index_uid)?);
 
-    debug!("returns: {:?}", stats);
+    debug!(returns = ?stats, "Get index stats");
     Ok(HttpResponse::Ok().json(stats))
 }

meilisearch/src/routes/indexes/recommend.rs

@@ -0,0 +1,53 @@
+use actix_web::web::{self, Data};
+use actix_web::{HttpRequest, HttpResponse};
+use deserr::actix_web::AwebJson;
+use index_scheduler::IndexScheduler;
+use meilisearch_types::deserr::DeserrJsonError;
+use meilisearch_types::error::ResponseError;
+use meilisearch_types::index_uid::IndexUid;
+use meilisearch_types::keys::actions;
+use tracing::debug;
+
+use super::ActionPolicy;
+use crate::analytics::Analytics;
+use crate::extractors::authentication::GuardedData;
+use crate::extractors::sequential_extractor::SeqHandler;
+use crate::search::{perform_recommend, RecommendQuery, SearchKind};
+
+pub fn configure(cfg: &mut web::ServiceConfig) {
+    cfg.service(web::resource("").route(web::post().to(SeqHandler(recommend))));
+}
+
+pub async fn recommend(
+    index_scheduler: GuardedData<ActionPolicy<{ actions::SEARCH }>, Data<IndexScheduler>>,
+    index_uid: web::Path<String>,
+    params: AwebJson<RecommendQuery, DeserrJsonError>,
+    _req: HttpRequest,
+    _analytics: web::Data<dyn Analytics>,
+) -> Result<HttpResponse, ResponseError> {
+    let index_uid = IndexUid::try_from(index_uid.into_inner())?;
+
+    // TODO analytics
+
+    let query = params.into_inner();
+    debug!(parameters = ?query, "Recommend post");
+
+    let index = index_scheduler.index(&index_uid)?;
+
+    let features = index_scheduler.features();
+
+    features.check_vector("Using the recommend API.")?;
+
+    let (embedder_name, embedder) =
+        SearchKind::embedder(&index_scheduler, &index, query.embedder.as_deref(), None)?;
+
+    let recommendations = tokio::task::spawn_blocking(move || {
+        perform_recommend(&index, query, embedder_name, embedder)
+    })
+    .await?;
+
+    let recommendations = recommendations?;
+
+    debug!(returns = ?recommendations, "Recommend post");
+    Ok(HttpResponse::Ok().json(recommendations))
+}