Use Debian instead of Alpine in Dockerfile

.cargo/config.toml

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

.github/ISSUE_TEMPLATE/bug_report.md

@@ -23,8 +23,7 @@ A clear and concise description of what you expected to happen.
 **Screenshots**
 If applicable, add screenshots to help explain your problem.
 
-**Meilisearch version:**
-[e.g. v0.20.0]
+**Meilisearch version:** [e.g. v0.20.0]
 
 **Additional context**
 Additional information that may be relevant to the issue.

.github/ISSUE_TEMPLATE/new_feature_issue.md

@@ -1,56 +0,0 @@
----
-name: New feature issue
-about: ⚠️ Should only be used by the internal Meili team ⚠️
-title: ''
-labels: 'impacts docs, impacts integrations'
-assignees: ''
-
----
-
-Related product team resources: [PRD]() (_internal only_)
-
-## Usage
-
-<!---Link to the public part of the PRD, or to the related product discussion for experimental features-->
-
-TBD
-
-## TODO
-
-<!---If necessary, create a list with technical/product steps-->
-
-### Are you modifying a database?
-
-- [ ] If not, add the `no db change` label to your PR, and you're good to merge.
-- [ ] If yes, add the `db change` label to your PR. You'll receive a message explaining you what to do.
-
-### Reminders when modifying the API
-
-- [ ] Update the openAPI file with utoipa:
-  - [ ] If a new module has been introduced, create a new structure deriving [the OpenAPI proc-macro](https://docs.rs/utoipa/latest/utoipa/derive.OpenApi.html) and nest it in the main [openAPI structure](https://github.com/meilisearch/meilisearch/blob/f2185438eed60fa32d25b15480c5ee064f6fba4a/crates/meilisearch/src/routes/mod.rs#L64-L78).
-  - [ ] If a new route has been introduced, add the [path decorator](https://docs.rs/utoipa/latest/utoipa/attr.path.html) to it and add the route at the top of the file in its openAPI structure.
-  - [ ] If a structure which is deserialized or serialized in the API has been introduced or modified, it must derive the [`schema`](https://docs.rs/utoipa/latest/utoipa/macro.schema.html) or the [`IntoParams`](https://docs.rs/utoipa/latest/utoipa/derive.IntoParams.html) proc-macro.
-        If it's a **new** structure you must also add it to the big list of structures [in the main `OpenApi` structure](https://github.com/meilisearch/meilisearch/blob/f2185438eed60fa32d25b15480c5ee064f6fba4a/crates/meilisearch/src/routes/mod.rs#L88).
-  - [ ] Once everything is done, start Meilisearch with the swagger flag: `cargo run --features swagger`, open `http://localhost:7700/scalar` on your browser, and ensure everything works as expected.
-  - For more info, refer to [this presentation](https://pitch.com/v/generating-the-openapi-file-jrn3nh).
-
-### 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 on Slack if any hesitation-->
-<!---@meilisearch/docs-team and @meilisearch/integration-team when there is any API change, e.g. settings addition-->

.github/pull_request_template.md

@@ -1,16 +0,0 @@
-## Related issue
-
-Fixes #...
-
-## Requirements
-
-⚠️ Ensure the following requirements before merging ⚠️
-- [ ] Automated tests have been added.
-- [ ] If some tests cannot be automated, manual rigorous tests should be applied.
-- [ ] ⚠️ If there is any change in the DB: 
-    - [ ] Test that any impacted DB still works as expected after using `--experimental-dumpless-upgrade` on a DB created with the last released Meilisearch
-    - [ ] Test that during the upgrade, **search is still available** (artificially make the upgrade longer if needed)
-    - [ ] Set the `db change` label.
-- [ ] If necessary, the feature have been tested in the Cloud production environment (with [prototypes](./documentation/prototypes.md)) and the Cloud UI is ready.
-- [ ] If necessary, the [documentation](https://github.com/meilisearch/documentation) related to the implemented feature in the PR is ready.
-- [ ] If necessary, the [integrations](https://github.com/meilisearch/integration-guides) related to the implemented feature in the PR are ready.

.github/release-draft-template.yml

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

.github/scripts/check-release.sh

@@ -1,41 +1,24 @@
-#!/usr/bin/env bash
-set -eu -o pipefail
+#!/bin/bash
 
-check_tag() {
-    local expected=$1
-    local actual=$2
-    local filename=$3
-
-    if [[ $actual != $expected ]]; then
-        echo >&2 "Error: the current tag does not match the version in $filename: found $actual, expected $expected"
-        return 1
-    fi
+# check_tag $current_tag $file_tag $file_name
+function check_tag {
+  if [[ "$1" != "$2" ]]; then
+      echo "Error: the current tag does not match the version in Cargo.toml: found $2 - expected $1"
+      ret=1
+  fi
 }
 
-read_version() {
-    grep '^version = ' | cut -d \" -f 2
-}
-
-if [[ -z "${GITHUB_REF:-}" ]]; then
-    echo >&2 "Error: GITHUB_REF is not set"
-    exit 1
-fi
-
-if [[ ! "$GITHUB_REF" =~ ^refs/tags/v[0-9]+\.[0-9]+\.[0-9]+(-[a-z0-9]+)?$ ]]; then
-    echo >&2 "Error: GITHUB_REF is not a valid tag: $GITHUB_REF"
-    exit 1
-fi
-
-current_tag=${GITHUB_REF#refs/tags/v}
 ret=0
+current_tag=${GITHUB_REF#'refs/tags/v'}
 
-toml_tag="$(cat Cargo.toml | read_version)"
-check_tag "$current_tag" "$toml_tag" Cargo.toml || ret=1
+file_tag="$(grep '^version = ' Cargo.toml | cut -d '=' -f 2 | tr -d '"' | tr -d ' ')"
+check_tag $current_tag $file_tag
 
-lock_tag=$(grep -A 1 '^name = "meilisearch-auth"' Cargo.lock | read_version)
-check_tag "$current_tag" "$lock_tag" Cargo.lock || ret=1
+lock_file='Cargo.lock'
+lock_tag=$(grep -A 1 'name = "meilisearch-auth"' $lock_file | grep version | cut -d '=' -f 2 | tr -d '"' | tr -d ' ')
+check_tag $current_tag $lock_tag $lock_file
 
-if (( ret == 0 )); then
-    echo 'OK'
+if [[ "$ret" -eq 0 ]] ; then
+  echo 'OK'
 fi
 exit $ret

.github/templates/dependency-issue.md

@@ -1,22 +0,0 @@
-This issue is about updating Meilisearch dependencies:
-  - [ ] Update Meilisearch dependencies with the help of `cargo +nightly udeps --all-targets` (remove unused dependencies) and `cargo upgrade` (upgrade dependencies versions) - ⚠️ Some repositories may contain subdirectories (like heed, charabia, or deserr). Take care of updating these in the main crate as well. This won't be done automatically by `cargo upgrade`.
-    - [ ] [deserr](https://github.com/meilisearch/deserr)
-    - [ ] [charabia](https://github.com/meilisearch/charabia/)
-    - [ ] [heed](https://github.com/meilisearch/heed/)
-    - [ ] [roaring-rs](https://github.com/RoaringBitmap/roaring-rs/)
-    - [ ] [obkv](https://github.com/meilisearch/obkv)
-    - [ ] [grenad](https://github.com/meilisearch/grenad/)
-    - [ ] [arroy](https://github.com/meilisearch/arroy/)
-    - [ ] [segment](https://github.com/meilisearch/segment)
-    - [ ] [bumparaw-collections](https://github.com/meilisearch/bumparaw-collections)
-    - [ ] [bbqueue](https://github.com/meilisearch/bbqueue)
-    - [ ] Finally, [Meilisearch](https://github.com/meilisearch/MeiliSearch)
-  - [ ] If new Rust versions have been released, update the minimal Rust version in use at Meilisearch:
-    - [ ] in this [GitHub Action file](https://github.com/meilisearch/meilisearch/blob/main/.github/workflows/test-suite.yml), by changing the `toolchain` field of the `rustfmt` job to the latest available nightly (of the day before or the current day).
-    - [ ] in every [GitHub Action files](https://github.com/meilisearch/meilisearch/blob/main/.github/workflows), by changing all the `dtolnay/rust-toolchain@` references to use the latest stable version.
-    - [ ] in this [`rust-toolchain.toml`](https://github.com/meilisearch/meilisearch/blob/main/rust-toolchain.toml), by changing the `channel` field to the latest stable version.
-    - [ ] in the [Dockerfile](https://github.com/meilisearch/meilisearch/blob/main/Dockerfile), by changing the base image to `rust:<target_rust_version>-alpine<alpine_version>`. Check that the image exists on [Dockerhub](https://hub.docker.com/_/rust/tags?page=1&name=alpine). Also, build and run the image to check everything still works!
-
-⚠️ This issue should be prioritized to avoid any deprecation and vulnerability issues.
-
-The GitHub action dependencies are managed by [Dependabot](https://github.com/meilisearch/meilisearch/blob/main/.github/dependabot.yml), so no need to update them when solving this issue.

.github/uffizzi/Dockerfile

@@ -0,0 +1,48 @@
+# Compile
+FROM    rust:alpine3.16 AS compiler
+
+RUN     apk add -q --update-cache --no-cache build-base openssl-dev
+
+WORKDIR /meilisearch
+
+ARG     COMMIT_SHA
+ARG     COMMIT_DATE
+ARG     GIT_TAG
+ENV     COMMIT_SHA=${COMMIT_SHA} COMMIT_DATE=${COMMIT_DATE} VERGEN_GIT_SEMVER_LIGHTWEIGHT=${GIT_TAG}
+ENV     RUSTFLAGS="-C target-feature=-crt-static"
+
+COPY    . .
+RUN     set -eux; \
+        apkArch="$(apk --print-arch)"; \
+        if [ "$apkArch" = "aarch64" ]; then \
+            export JEMALLOC_SYS_WITH_LG_PAGE=16; \
+        fi && \
+        cargo build --release
+
+# Run
+FROM    uffizzi/ttyd:alpine
+
+ENV     MEILI_HTTP_ADDR 0.0.0.0:7700
+ENV     MEILI_SERVER_PROVIDER docker
+ENV     MEILI_NO_ANALYTICS true
+
+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
+# 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
+
+# This directory should hold all the data related to meilisearch so we're going
+# to move our PWD in there.
+# We don't want to put the meilisearch binary
+WORKDIR /meili_data
+
+
+EXPOSE  7700/tcp
+
+ENTRYPOINT ["tini", "--"]
+CMD     ["ttyd", "/bin/zsh"]

.github/uffizzi/docker-compose.uffizzi.yml

@@ -0,0 +1,26 @@
+version: "3"
+
+x-uffizzi:
+  ingress:
+    service: nginx
+    port: 8081
+
+services:
+  meilisearch:
+    image: "${MEILISEARCH_IMAGE}"
+    restart: unless-stopped
+    ports:
+    - "7681:7681"
+    - "7700:7700"
+    deploy:
+      resources:
+        limits:
+          memory: 500M
+  
+  nginx:
+    image: nginx:alpine
+    restart: unless-stopped
+    ports:
+    - "8081:8081"
+    volumes:
+    - ./.github/uffizzi/nginx:/etc/nginx

.github/uffizzi/nginx/nginx.conf

@@ -0,0 +1,28 @@
+
+events {
+  worker_connections  4096;  ## Default: 1024
+}
+
+http {
+    map $http_upgrade $connection_upgrade {
+        default upgrade;
+        '' close;
+    }
+
+    server {
+        listen 8081;
+
+        location / {
+            proxy_pass http://localhost:7681;
+            proxy_http_version 1.1;
+            proxy_set_header Upgrade $http_upgrade;
+            proxy_set_header Connection $connection_upgrade;
+        }
+
+        location /meilisearch/ {
+            # rewrite /meilisearch/(.*) /$1  break;
+            proxy_pass http://localhost:7700/;
+        }
+    }
+}
+

.github/workflows/bench-manual.yml

@@ -1,27 +0,0 @@
-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@v5
-      - uses: dtolnay/rust-toolchain@1.89
-        with:
-          profile: minimal
-
-      - 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

@@ -1,82 +0,0 @@
-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 permissions
-        id: permission
-        env:
-          PR_AUTHOR: ${{github.event.issue.user.login }}
-          COMMENT_AUTHOR: ${{github.event.comment.user.login }}
-          REPOSITORY: ${{github.repository}}
-          PR_ID: ${{github.event.issue.number}}
-        run: |
-          PR_REPOSITORY=$(gh api /repos/"$REPOSITORY"/pulls/"$PR_ID" --jq .head.repo.full_name)
-          if $(gh api /repos/"$REPOSITORY"/collaborators/"$PR_AUTHOR"/permission --jq .user.permissions.push)
-          then
-            echo "::notice title=Authentication success::PR author authenticated"
-          else
-            echo "::error title=Authentication error::PR author doesn't have push permission on this repository"
-            exit 1
-          fi
-          if $(gh api /repos/"$REPOSITORY"/collaborators/"$COMMENT_AUTHOR"/permission --jq .user.permissions.push)
-          then
-            echo "::notice title=Authentication success::Comment author authenticated"
-          else
-            echo "::error title=Authentication error::Comment author doesn't have push permission on this repository"
-            exit 1
-          fi
-          if [ "$PR_REPOSITORY" = "$REPOSITORY" ]
-          then
-            echo "::notice title=Authentication success::PR started from main repository"
-          else
-            echo "::error title=Authentication error::PR started from a fork"
-            exit 1
-          fi
-
-      - 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@v3
-        id: comment-branch
-        with:
-          repo_token: ${{ env.GH_TOKEN }}
-
-      - uses: actions/checkout@v5
-        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: dtolnay/rust-toolchain@1.89
-        with:
-          profile: minimal
-
-      - 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 }} > benchlinks.txt
-
-      - name: Send comment in PR
-        run: |
-          gh pr comment ${{github.event.issue.number}} --body-file benchlinks.txt

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

@@ -1,22 +0,0 @@
-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@v5
-      - uses: dtolnay/rust-toolchain@1.89
-        with:
-          profile: minimal
-
-      # 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

@@ -1,127 +0,0 @@
-name: Benchmarks (PR)
-on: issue_comment
-permissions:
-  issues: write
-
-env:
-  GH_TOKEN: ${{ secrets.MEILI_BOT_GH_PAT }}
-
-jobs:
-  run-benchmarks-on-comment:
-    if: startsWith(github.event.comment.body, '/benchmark')
-    name: Run and upload benchmarks
-    runs-on: benchmarks
-    timeout-minutes: 4320 # 72h
-    steps:
-      - name: Check permissions
-        id: permission
-        env:
-          PR_AUTHOR: ${{github.event.issue.user.login }}
-          COMMENT_AUTHOR: ${{github.event.comment.user.login }}
-          REPOSITORY: ${{github.repository}}
-          PR_ID: ${{github.event.issue.number}}
-        run: |
-          PR_REPOSITORY=$(gh api /repos/"$REPOSITORY"/pulls/"$PR_ID" --jq .head.repo.full_name)
-          if $(gh api /repos/"$REPOSITORY"/collaborators/"$PR_AUTHOR"/permission --jq .user.permissions.push)
-          then
-            echo "::notice title=Authentication success::PR author authenticated"
-          else
-            echo "::error title=Authentication error::PR author doesn't have push permission on this repository"
-            exit 1
-          fi
-          if $(gh api /repos/"$REPOSITORY"/collaborators/"$COMMENT_AUTHOR"/permission --jq .user.permissions.push)
-          then
-            echo "::notice title=Authentication success::Comment author authenticated"
-          else
-            echo "::error title=Authentication error::Comment author doesn't have push permission on this repository"
-            exit 1
-          fi
-          if [ "$PR_REPOSITORY" = "$REPOSITORY" ]
-          then
-            echo "::notice title=Authentication success::PR started from main repository"
-          else
-            echo "::error title=Authentication error::PR started from a fork"
-            exit 1
-          fi
-
-      - uses: dtolnay/rust-toolchain@1.89
-        with:
-          profile: minimal
-
-      - name: Check for Command
-        id: command
-        uses: xt0rted/slash-command-action@v2
-        with:
-          command: benchmark
-          reaction-type: "eyes"
-          repo-token: ${{ env.GH_TOKEN }}
-
-      - uses: xt0rted/pull-request-comment-branch@v3
-        id: comment-branch
-        with:
-          repo_token: ${{ env.GH_TOKEN }}
-
-      - uses: actions/checkout@v5
-        if: success()
-        with:
-          fetch-depth: 0 # fetch full history to be able to get main commit sha
-          ref: ${{ steps.comment-branch.outputs.head_ref }}
-
-      # Set variables
-      - name: Set current branch name
-        shell: bash
-        run: echo "name=$(git rev-parse --abbrev-ref HEAD)" >> $GITHUB_OUTPUT
-        id: current_branch
-      - name: Set normalized current branch name # Replace `/` by `_` in branch name to avoid issues when pushing to S3
-        shell: bash
-        run: echo "name=$(git rev-parse --abbrev-ref HEAD | tr '/' '_')" >> $GITHUB_OUTPUT
-        id: normalized_current_branch
-      - name: Set shorter commit SHA
-        shell: bash
-        run: echo "short=$(echo $GITHUB_SHA | cut -c1-8)" >> $GITHUB_OUTPUT
-        id: commit_sha
-      - name: Set file basename with format "dataset_branch_commitSHA"
-        shell: bash
-        run: echo "basename=$(echo ${{ steps.command.outputs.command-arguments }}_${{ steps.normalized_current_branch.outputs.name }}_${{ steps.commit_sha.outputs.short }})" >> $GITHUB_OUTPUT
-        id: file
-
-      # Run benchmarks
-      - name: Run benchmarks - Dataset ${{ steps.command.outputs.command-arguments }} - Branch ${{ steps.current_branch.outputs.name }} - Commit ${{ steps.commit_sha.outputs.short }}
-        run: |
-          cd crates/benchmarks
-          cargo bench --bench ${{ steps.command.outputs.command-arguments }} -- --save-baseline ${{ steps.file.outputs.basename }}
-
-      # Generate critcmp files
-      - name: Install critcmp
-        uses: taiki-e/install-action@v2
-        with:
-          tool: critcmp
-      - name: Export cripcmp file
-        run: |
-          critcmp --export ${{ steps.file.outputs.basename }} > ${{ steps.file.outputs.basename }}.json
-
-      # Upload benchmarks
-      - name: Upload ${{ steps.file.outputs.basename }}.json to DO Spaces # DigitalOcean Spaces = S3
-        uses: BetaHuhn/do-spaces-action@v2
-        with:
-          access_key: ${{ secrets.DO_SPACES_ACCESS_KEY }}
-          secret_key: ${{ secrets.DO_SPACES_SECRET_KEY }}
-          space_name: ${{ secrets.DO_SPACES_SPACE_NAME }}
-          space_region: ${{ secrets.DO_SPACES_SPACE_REGION }}
-          source: ${{ steps.file.outputs.basename }}.json
-          out_dir: critcmp_results
-
-      # Compute the diff of the benchmarks and send a message on the GitHub PR
-      - name: Compute and send a message in the PR
-        env:
-          GITHUB_TOKEN: ${{ secrets.MEILI_BOT_GH_PAT }}
-        run: |
-          set -x
-          export base_ref=$(git merge-base origin/main ${{ steps.comment-branch.outputs.head_ref }} | head -c8)
-          export base_filename=$(echo ${{ steps.command.outputs.command-arguments }}_main_${base_ref}.json)
-          export bench_name=$(echo ${{ steps.command.outputs.command-arguments }})
-          echo "Here are your $bench_name benchmarks diff 👊" >> body.txt
-          echo '```' >> body.txt
-          ./benchmarks/scripts/compare.sh $base_filename ${{ steps.file.outputs.basename }}.json >> body.txt
-          echo '```' >> body.txt
-          gh pr comment ${{ steps.current_branch.outputs.name }} --body-file body.txt

.github/workflows/create-issue-dependencies.yml

@@ -0,0 +1,28 @@
+name: Create issue to upgrade dependencies
+on:
+  schedule:
+    # Run the first of the month, every 3 month
+    - cron: '0 0 1 */3 *'
+  workflow_dispatch:
+
+jobs:
+  create-issue:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v3
+    - name: Create an issue
+      uses: actions-ecosystem/action-create-issue@v1
+      with:
+        github_token: ${{ secrets.MEILI_BOT_GH_PAT }}
+        title: Upgrade dependencies
+        body: |
+          This issue is about updating Meilisearch dependencies:
+          - [ ] Cargo toml dependencies of Meilisearch; but also the main engine-team repositories that Meilisearch depends on (charabia, heed...)
+          - [ ] If new Rust versions have been released, update the Rust version in the Clippy job of this [GitHub Action file](./.github/workflows/rust.yml)
+
+          ⚠️ To avoid last minute bugs, this issue should only be done at the beginning of the sprint!
+
+          The GitHub action dependencies are managed by [Dependabot](./.github/dependabot.yml)
+        labels: |
+          dependencies
+          maintenance

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

@@ -1,57 +0,0 @@
-name: Comment when db change labels are added
-
-on:
-  pull_request:
-    types: [labeled]
-
-env:
-  MESSAGE: |
-    ### Hello, I'm a bot 🤖 
-
-    You are receiving this message because you declared that this PR make changes to the Meilisearch database.
-    Depending on the nature of the change, additional actions might be required on your part. The following sections detail the additional actions depending on the nature of the change, please copy the relevant section in the description of your PR, and make sure to perform the required actions.
-
-    Thank you for contributing to Meilisearch :heart:
-
-    ## This PR makes forward-compatible changes
-
-    *Forward-compatible changes are changes to the database such that databases created in an older version of Meilisearch are still valid in the new version of Meilisearch. They usually represent additive changes, like adding a new optional attribute or setting.*
-
-    - [ ] Detail the change to the DB format and why they are forward compatible
-    - [ ] Forward-compatibility: A database created before this PR and using the features touched by this PR was able to be opened by a Meilisearch produced by the code of this PR.
-
-
-    ## This PR makes breaking changes
-
-    *Breaking changes are changes to the database such that databases created in an older version of Meilisearch need changes to remain valid in the new version of Meilisearch. This typically happens when the way to store the data changed (change of database, new required key, etc). This can also happen due to breaking changes in the API of an experimental feature. ⚠️ This kind of changes are more difficult to achieve safely, so proceed with caution and test dumpless upgrade right before merging the PR.*
-
-    - [ ] Detail the changes to the DB format,
-        - [ ] which are compatible, and why
-        - [ ] which are not compatible, why, and how they will be fixed up in the upgrade
-     - [ ] /!\ Ensure all the read operations still work!
-        - If the change happened in milli, you may need to check the version of the database before doing any read operation
-        - If the change happened in the index-scheduler, make sure the new code can immediately read the old database
-        - If the change happened in the meilisearch-auth database, reach out to the team; we don't know yet how to handle these changes
-      - [ ] Write the code to go from the old database to the new one
-        - If the change happened in milli, the upgrade function should be written and called [here](https://github.com/meilisearch/meilisearch/blob/3fd86e8d76d7d468b0095d679adb09211ca3b6c0/crates/milli/src/update/upgrade/mod.rs#L24-L47)
-        - If the change happened in the index-scheduler, we've never done it yet, but the right place to do it should be [here](https://github.com/meilisearch/meilisearch/blob/3fd86e8d76d7d468b0095d679adb09211ca3b6c0/crates/index-scheduler/src/scheduler/process_upgrade/mod.rs#L13)
-      - [ ] Write an integration test [here](https://github.com/meilisearch/meilisearch/blob/main/crates/meilisearch/tests/upgrade/mod.rs) ensuring you can read the old database, upgrade to the new database, and read the new database as expected
-    
-
-jobs:
-  add-comment:
-    runs-on: ubuntu-latest
-    if: github.event.label.name == 'db change'
-    steps:
-      - name: Add comment
-        uses: actions/github-script@v7
-        with:
-          github-token: ${{ secrets.GITHUB_TOKEN }}
-          script: |
-            const message = process.env.MESSAGE;
-            github.rest.issues.createComment({
-              issue_number: context.issue.number,
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              body: message
-            })

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

@@ -1,28 +0,0 @@
-name: Check db change labels
-
-on:
-  pull_request:
-    types: [opened, synchronize, reopened, labeled, unlabeled]
-
-jobs:
-  check-labels:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v5
-      - name: Check db change labels
-        id: check_labels
-        env:
-          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: |
-          URL=/repos/meilisearch/meilisearch/pulls/${{ github.event.pull_request.number }}/labels
-          echo ${{ github.event.pull_request.number }}
-          echo $URL
-          LABELS=$(gh api -H "Accept: application/vnd.github+json" -H "X-GitHub-Api-Version: 2022-11-28" /repos/${{ github.repository }}/issues/${{ github.event.pull_request.number }}/labels -q .[].name)
-          echo "Labels: $LABELS"
-          if [[ ! "$LABELS" =~ "db change" && ! "$LABELS" =~ "no db change" ]]; then
-            echo "::error::Pull request must contain either the 'db change' or 'no db change' label."
-            exit 1
-          else
-            echo "The label is set"
-          fi

.github/workflows/dependency-issue.yml

@@ -1,24 +0,0 @@
-name: Create issue to upgrade dependencies
-
-on:
-  schedule:
-    # Run the first of the month, every 6 month
-    - cron: '0 0 1 */6 *'
-  workflow_dispatch:
-
-jobs:
-  create-issue:
-    runs-on: ubuntu-latest
-    env:
-      ISSUE_TEMPLATE: issue-template.md
-      GH_TOKEN: ${{ secrets.MEILI_BOT_GH_PAT }}
-    steps:
-    - uses: actions/checkout@v5
-    - name: Download the issue template
-      run: curl -s https://raw.githubusercontent.com/meilisearch/meilisearch/main/.github/templates/dependency-issue.md > $ISSUE_TEMPLATE
-    - name: Create issue
-      run: |
-        gh issue create \
-          --title 'Upgrade dependencies' \
-          --label 'dependencies,maintenance' \
-          --body-file $ISSUE_TEMPLATE

.github/workflows/flaky-tests.yml

@@ -1,30 +0,0 @@
-name: Look for flaky tests
-
-on:
-  workflow_dispatch:
-  schedule:
-    - cron: '0 4 * * *' # Every day at 4:00AM
-
-jobs:
-  flaky:
-    runs-on: ubuntu-latest
-    container:
-      # Use ubuntu-22.04 to compile with glibc 2.35
-      image: ubuntu:22.04
-    steps:
-      - uses: actions/checkout@v5
-      - name: Install needed dependencies
-        run: |
-          apt-get update && apt-get install -y curl
-          apt-get install build-essential -y
-      - uses: dtolnay/rust-toolchain@1.89
-      - name: Install cargo-flaky
-        run: cargo install cargo-flaky
-      - name: Run cargo flaky in the dumps
-        run: cd crates/dump; cargo flaky -i 100 --release
-      - name: Run cargo flaky in the index-scheduler
-        run: cd crates/index-scheduler; cargo flaky -i 100 --release
-      - name: Run cargo flaky in the auth
-        run: cd crates/meilisearch-auth; cargo flaky -i 100 --release
-      - name: Run cargo flaky in meilisearch
-        run: cd crates/meilisearch; cargo flaky -i 100 --release

.github/workflows/flaky.yml

@@ -0,0 +1,32 @@
+name: Look for flaky tests
+on:
+  workflow_dispatch:
+  schedule:
+    - cron: "0 12 * * FRI" # Every Friday at 12:00PM
+
+jobs:
+  flaky:
+    runs-on: ubuntu-latest
+    container:
+      # Use ubuntu-18.04 to compile with glibc 2.27, which are the production expectations
+      image: ubuntu:18.04
+    steps:
+    - uses: actions/checkout@v3
+    - name: Install needed dependencies
+      run: |
+        apt-get update && apt-get install -y curl
+        apt-get install build-essential -y
+    - uses: actions-rs/toolchain@v1
+      with:
+        toolchain: stable
+        override: true
+    - name: Install cargo-flaky
+      run: cargo install cargo-flaky
+    - name: Run cargo flaky in the dumps
+      run: cd dump; cargo flaky -i 100 --release
+    - name: Run cargo flaky in the index-scheduler
+      run: cd index-scheduler; cargo flaky -i 100 --release
+    - name: Run cargo flaky in the auth
+      run: cd meilisearch-auth; cargo flaky -i 100 --release
+    - name: Run cargo flaky in meilisearch
+      run: cd meilisearch; cargo flaky -i 100 --release

.github/workflows/fuzzer-indexing.yml

@@ -1,22 +0,0 @@
-name: Run the indexing fuzzer
-
-on:
-  push:
-    branches:
-      - main
-
-jobs:
-  fuzz:
-    name: Setup the action
-    runs-on: ubuntu-latest
-    timeout-minutes: 4320 # 72h
-    steps:
-      - uses: actions/checkout@v5
-      - uses: dtolnay/rust-toolchain@1.89
-        with:
-          profile: minimal
-
-      # Run benchmarks
-      - name: Run the fuzzer
-        run: |
-          cargo run --release --bin fuzz-indexing

.github/workflows/latest-git-tag.yml

@@ -10,7 +10,7 @@ jobs:
     name: Check the version validity
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v3
       - name: Check release validity
         if: github.event_name == 'release'
         run: bash .github/scripts/check-release.sh
@@ -19,7 +19,7 @@ jobs:
     runs-on: ubuntu-latest
     needs: check-version
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v3
       - uses: rickstaa/action-create-tag@v1
         with:
           tag: "latest"

.github/workflows/manual_benchmarks.yml

@@ -1,12 +1,12 @@
-name: Benchmarks (manual)
+name: Benchmarks
 
 on:
   workflow_dispatch:
     inputs:
       dataset_name:
-        description: "The name of the dataset used to benchmark (search_songs, search_wiki, search_geo or indexing)"
+        description: 'The name of the dataset used to benchmark (search_songs, search_wiki, search_geo or indexing)'
         required: false
-        default: "search_songs"
+        default: 'search_songs'
 
 env:
   BENCH_NAME: ${{ github.event.inputs.dataset_name }}
@@ -17,10 +17,12 @@ jobs:
     runs-on: benchmarks
     timeout-minutes: 4320 # 72h
     steps:
-      - uses: actions/checkout@v5
-      - uses: dtolnay/rust-toolchain@1.89
+      - uses: actions/checkout@v3
+      - uses: actions-rs/toolchain@v1
         with:
           profile: minimal
+          toolchain: stable
+          override: true
 
       # Set variables
       - name: Set current branch name
@@ -43,7 +45,7 @@ jobs:
       # Run benchmarks
       - name: Run benchmarks - Dataset ${BENCH_NAME} - Branch ${{ steps.current_branch.outputs.name }} - Commit ${{ steps.commit_sha.outputs.short }}
         run: |
-          cd crates/benchmarks
+          cd benchmarks
           cargo bench --bench ${BENCH_NAME} -- --save-baseline ${{ steps.file.outputs.basename }}
 
       # Generate critcmp files
@@ -67,9 +69,9 @@ jobs:
           out_dir: critcmp_results
 
       # Helper
-      - name: "README: compare with another benchmark"
+      - name: 'README: compare with another benchmark'
         run: |
           echo "${{ steps.file.outputs.basename }}.json has just been pushed."
           echo 'How to compare this benchmark with another one?'
           echo '  - Check the available files with: ./benchmarks/scripts/list.sh'
-          echo "  - Run the following command: ./benchmaks/scripts/compare.sh <file-to-compare-with> ${{ steps.file.outputs.basename }}.json"
+          echo "  - Run the following command: ./benchmaks/scipts/compare.sh <file-to-compare-with> ${{ steps.file.outputs.basename }}.json"

.github/workflows/milestone-workflow.yml

@@ -0,0 +1,154 @@
+name: Milestone's workflow
+
+# /!\ No git flow are handled here
+
+# For each Milestone created (not opened!), and if the release is NOT a patch release (only the patch changed)
+# - the roadmap issue is created, see https://github.com/meilisearch/engine-team/blob/main/issue-templates/roadmap-issue.md
+# - the changelog issue is created, see https://github.com/meilisearch/engine-team/blob/main/issue-templates/changelog-issue.md
+
+# For each Milestone closed
+# - the `release_version` label is created
+# - this label is applied to all issues/PRs in the Milestone
+
+on:
+  milestone:
+    types: [created, closed]
+
+env:
+  MILESTONE_VERSION: ${{ github.event.milestone.title }}
+  MILESTONE_URL: ${{ github.event.milestone.html_url }}
+  MILESTONE_DUE_ON: ${{ github.event.milestone.due_on }}
+  GH_TOKEN: ${{ secrets.MEILI_BOT_GH_PAT }}
+
+jobs:
+
+# -----------------
+# MILESTONE CREATED
+# -----------------
+
+  get-release-version:
+    if: github.event.action == 'created'
+    runs-on: ubuntu-latest
+    outputs:
+      is-patch: ${{ steps.check-patch.outputs.is-patch }}
+    steps:
+      - uses: actions/checkout@v3
+      - name: Check if this release is a patch release only
+        id: check-patch
+        run: |
+          echo version: $MILESTONE_VERSION
+          if [[ $MILESTONE_VERSION =~ ^v[0-9]+\.[0-9]+\.0$ ]]; then
+            echo 'This is NOT a patch release'
+            echo "is-patch=false" >> $GITHUB_OUTPUT
+          elif [[ $MILESTONE_VERSION =~ ^v[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
+            echo 'This is a patch release'
+            echo "is-patch=true" >> $GITHUB_OUTPUT
+          else
+            echo "Not a valid format of release, check the Milestone's title."
+            echo 'Should be vX.Y.Z'
+            exit 1
+          fi
+
+  create-roadmap-issue:
+    needs: get-release-version
+    # Create the roadmap 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/roadmap-issue.md > $ISSUE_TEMPLATE
+      - name: Replace all empty occurrences in the templates
+        run: |
+          # Replace all <<version>> occurrences
+          sed -i "s/<<version>>/$MILESTONE_VERSION/g" $ISSUE_TEMPLATE
+
+          # Replace all <<milestone_id>> occurrences
+          milestone_id=$(echo $MILESTONE_URL | cut -d '/' -f 7)
+          sed -i "s/<<milestone_id>>/$milestone_id/g" $ISSUE_TEMPLATE
+
+          # Replace release date if exists
+          if [[ ! -z $MILESTONE_DUE_ON ]]; then
+            date=$(echo $MILESTONE_DUE_ON | cut -d 'T' -f 1)
+            sed -i "s/Release date\: 20XX-XX-XX/Release date\: $date/g" $ISSUE_TEMPLATE
+          fi
+      - name: Create the issue
+        run: |
+          gh issue create \
+            --title "$MILESTONE_VERSION ROADMAP" \
+            --label 'epic,impacts docs,impacts integrations,impacts cloud' \
+            --body-file $ISSUE_TEMPLATE \
+            --milestone $MILESTONE_VERSION
+
+  create-changelog-issue:
+    needs: get-release-version
+    # Create the changelog 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/changelog-issue.md > $ISSUE_TEMPLATE
+      - name: Replace all empty occurrences in the templates
+        run: |
+          # Replace all <<version>> occurrences
+          sed -i "s/<<version>>/$MILESTONE_VERSION/g" $ISSUE_TEMPLATE
+
+          # Replace all <<milestone_id>> occurrences
+          milestone_id=$(echo $MILESTONE_URL | cut -d '/' -f 7)
+          sed -i "s/<<milestone_id>>/$milestone_id/g" $ISSUE_TEMPLATE
+      - name: Create the issue
+        run: |
+          gh issue create \
+            --title "Create release changelogs for $MILESTONE_VERSION" \
+            --label 'impacts docs,documentation' \
+            --body-file $ISSUE_TEMPLATE \
+            --milestone $MILESTONE_VERSION \
+            --assignee curquiza
+
+# ----------------
+# MILESTONE CLOSED
+# ----------------
+
+  create-release-label:
+    if: github.event.action == 'closed'
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Create the ${{ env.MILESTONE_VERSION }} label
+        run: |
+          label_description="PRs/issues solved in $MILESTONE_VERSION"
+          if [[ ! -z $MILESTONE_DUE_ON ]]; then
+            date=$(echo $MILESTONE_DUE_ON | cut -d 'T' -f 1)
+            label_description="$label_description released on $date"
+          fi
+
+          gh api repos/meilisearch/meilisearch/labels \
+            --method POST \
+            -H "Accept: application/vnd.github+json" \
+            -f name="$MILESTONE_VERSION" \
+            -f description="$label_description" \
+            -f color='ff5ba3'
+
+  labelize-all-milestone-content:
+    if: github.event.action == 'closed'
+    needs: create-release-label
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Add label ${{ env.MILESTONE_VERSION }} to all PRs in the Milestone
+        run: |
+          prs=$(gh pr list --search milestone:"$MILESTONE_VERSION" --limit 1000 --state all --json number --template '{{range .}}{{tablerow (printf "%v" .number)}}{{end}}')
+          for pr in $prs; do
+              gh pr edit $pr --add-label $MILESTONE_VERSION
+          done
+      - name: Add label ${{ env.MILESTONE_VERSION }} to all issues in the Milestone
+        run: |
+          issues=$(gh issue list --search milestone:"$MILESTONE_VERSION" --limit 1000 --state all --json number --template '{{range .}}{{tablerow (printf "%v" .number)}}{{end}}')
+          for issue in $issues; do
+              gh issue edit $issue --add-label $MILESTONE_VERSION
+          done

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

@@ -1,55 +0,0 @@
-name: Publish to APT & Homebrew
-
-on:
-  release:
-    types: [released]
-
-jobs:
-  check-version:
-    name: Check the version validity
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v5
-      - name: Check release validity
-        run: bash .github/scripts/check-release.sh
-
-  debian:
-    name: Publish debian packagge
-    runs-on: ubuntu-latest
-    needs: check-version
-    container:
-      # Use ubuntu-22.04 to compile with glibc 2.35
-      image: ubuntu:22.04
-    steps:
-      - name: Install needed dependencies
-        run: |
-          apt-get update && apt-get install -y curl
-          apt-get install build-essential -y
-      - uses: dtolnay/rust-toolchain@1.89
-      - name: Install cargo-deb
-        run: cargo install cargo-deb
-      - uses: actions/checkout@v5
-      - name: Build deb package
-        run: cargo deb -p meilisearch -o target/debian/meilisearch.deb
-      - name: Upload debian pkg to release
-        uses: svenstaro/upload-release-action@2.11.2
-        with:
-          repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
-          file: target/debian/meilisearch.deb
-          asset_name: meilisearch.deb
-          tag: ${{ github.ref }}
-      - name: Upload debian pkg to apt repository
-        run: curl -F package=@target/debian/meilisearch.deb https://${{ secrets.GEMFURY_PUSH_TOKEN }}@push.fury.io/meilisearch/
-
-  homebrew:
-    name: Bump Homebrew formula
-    runs-on: ubuntu-latest
-    needs: check-version
-    steps:
-      - name: Create PR to Homebrew
-        uses: mislav/bump-homebrew-formula-action@v3
-        with:
-          formula-name: meilisearch
-          formula-path: Formula/m/meilisearch.rb
-        env:
-          COMMITTER_TOKEN: ${{ secrets.HOMEBREW_COMMITTER_TOKEN }}

.github/workflows/publish-binaries.yml

@@ -1,19 +1,19 @@
-name: Publish assets to GitHub release
-
 on:
   workflow_dispatch:
   schedule:
-    - cron: "0 2 * * *" # Every day at 2:00am
+    - cron: '0 2 * * *' # Every day at 2:00am
   release:
     types: [published]
 
+name: Publish binaries to release
+
 jobs:
   check-version:
     name: Check the version validity
     runs-on: ubuntu-latest
     # No need to check the version for dry run (cron)
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v3
       # Check if the tag has the v<nmumber>.<number>.<number> format.
       # If yes, it means we are publishing an official release.
       # If no, we are releasing a RC, so no need to check the version.
@@ -37,26 +37,29 @@ jobs:
     runs-on: ubuntu-latest
     needs: check-version
     container:
-      # Use ubuntu-22.04 to compile with glibc 2.35
-      image: ubuntu:22.04
+      # Use ubuntu-18.04 to compile with glibc 2.27
+      image: ubuntu:18.04
     steps:
-      - uses: actions/checkout@v5
-      - name: Install needed dependencies
-        run: |
-          apt-get update && apt-get install -y curl
-          apt-get install build-essential -y
-      - uses: dtolnay/rust-toolchain@1.89
-      - name: Build
-        run: cargo build --release --locked
-      # No need to upload binaries for dry run (cron)
-      - name: Upload binaries to release
-        if: github.event_name == 'release'
-        uses: svenstaro/upload-release-action@2.11.2
-        with:
-          repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
-          file: target/release/meilisearch
-          asset_name: meilisearch-linux-amd64
-          tag: ${{ github.ref }}
+    - uses: actions/checkout@v3
+    - name: Install needed dependencies
+      run: |
+        apt-get update && apt-get install -y curl
+        apt-get install build-essential -y
+    - uses: actions-rs/toolchain@v1
+      with:
+        toolchain: stable
+        override: true
+    - name: Build
+      run: cargo build --release --locked
+    # No need to upload binaries for dry run (cron)
+    - name: Upload binaries to release
+      if: github.event_name == 'release'
+      uses: svenstaro/upload-release-action@2.4.0
+      with:
+        repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
+        file: target/release/meilisearch
+        asset_name: meilisearch-linux-amd64
+        tag: ${{ github.ref }}
 
   publish-macos-windows:
     name: Publish binary for ${{ matrix.os }}
@@ -65,46 +68,53 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        os: [macos-13, windows-2022]
+        os: [macos-12, windows-2022]
         include:
-          - os: macos-13
+          - os: macos-12
             artifact_name: meilisearch
             asset_name: meilisearch-macos-amd64
           - os: windows-2022
             artifact_name: meilisearch.exe
             asset_name: meilisearch-windows-amd64.exe
     steps:
-      - uses: actions/checkout@v5
-      - uses: dtolnay/rust-toolchain@1.89
-      - name: Build
-        run: cargo build --release --locked
-      # No need to upload binaries for dry run (cron)
-      - name: Upload binaries to release
-        if: github.event_name == 'release'
-        uses: svenstaro/upload-release-action@2.11.2
-        with:
-          repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
-          file: target/release/${{ matrix.artifact_name }}
-          asset_name: ${{ matrix.asset_name }}
-          tag: ${{ github.ref }}
+    - uses: actions/checkout@v3
+    - uses: actions-rs/toolchain@v1
+      with:
+        toolchain: stable
+        override: true
+    - name: Build
+      run: cargo build --release --locked
+    # No need to upload binaries for dry run (cron)
+    - name: Upload binaries to release
+      if: github.event_name == 'release'
+      uses: svenstaro/upload-release-action@2.4.0
+      with:
+        repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
+        file: target/release/${{ matrix.artifact_name }}
+        asset_name: ${{ matrix.asset_name }}
+        tag: ${{ github.ref }}
 
   publish-macos-apple-silicon:
     name: Publish binary for macOS silicon
-    runs-on: macos-13
+    runs-on: ${{ matrix.os }}
     needs: check-version
     strategy:
+      fail-fast: false
       matrix:
         include:
-          - target: aarch64-apple-darwin
+          - os: macos-12
+            target: aarch64-apple-darwin
             asset_name: meilisearch-macos-apple-silicon
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v5
+        uses: actions/checkout@v3
       - name: Installing Rust toolchain
-        uses: dtolnay/rust-toolchain@1.89
+        uses: actions-rs/toolchain@v1
         with:
+          toolchain: stable
           profile: minimal
           target: ${{ matrix.target }}
+          override: true
       - name: Cargo build
         uses: actions-rs/cargo@v1
         with:
@@ -113,7 +123,7 @@ jobs:
       - name: Upload the binary to release
         # No need to upload binaries for dry run (cron)
         if: github.event_name == 'release'
-        uses: svenstaro/upload-release-action@2.11.2
+        uses: svenstaro/upload-release-action@2.4.0
         with:
           repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
           file: target/${{ matrix.target }}/release/meilisearch
@@ -122,37 +132,37 @@ jobs:
 
   publish-aarch64:
     name: Publish binary for aarch64
-    runs-on: ubuntu-latest
+    runs-on: ${{ matrix.os }}
     needs: check-version
-    env:
-      DEBIAN_FRONTEND: noninteractive
-    container:
-      # Use ubuntu-22.04 to compile with glibc 2.35
-      image: ubuntu:22.04
     strategy:
+      fail-fast: false
       matrix:
         include:
-          - target: aarch64-unknown-linux-gnu
+          - build: aarch64
+            os: ubuntu-18.04
+            target: aarch64-unknown-linux-gnu
+            linker: gcc-aarch64-linux-gnu
+            use-cross: true
             asset_name: meilisearch-linux-aarch64
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v5
-      - name: Install needed dependencies
-        run: |
-          apt-get update -y && apt upgrade -y
-          apt-get install -y curl build-essential gcc-aarch64-linux-gnu
-      - name: Set up Docker for cross compilation
-        run: |
-          apt-get install -y curl apt-transport-https ca-certificates software-properties-common
-          curl -fsSL https://download.docker.com/linux/ubuntu/gpg | apt-key add -
-          add-apt-repository "deb [arch=$(dpkg --print-architecture)] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable"
-          apt-get update -y && apt-get install -y docker-ce
+        uses: actions/checkout@v3
       - name: Installing Rust toolchain
-        uses: dtolnay/rust-toolchain@1.89
+        uses: actions-rs/toolchain@v1
         with:
+          toolchain: stable
           profile: minimal
           target: ${{ matrix.target }}
+          override: true
+      - name: APT update
+        run: |
+          sudo apt update
+      - name: Install target specific tools
+        if: matrix.use-cross
+        run: |
+          sudo apt-get install -y ${{ matrix.linker }}
       - name: Configure target aarch64 GNU
+        if: matrix.target == 'aarch64-unknown-linux-gnu'
         ## Environment variable is not passed using env:
         ## LD gold won't work with MUSL
         # env:
@@ -162,50 +172,20 @@ jobs:
           echo '[target.aarch64-unknown-linux-gnu]' >> ~/.cargo/config
           echo 'linker = "aarch64-linux-gnu-gcc"' >> ~/.cargo/config
           echo 'JEMALLOC_SYS_WITH_LG_PAGE=16' >> $GITHUB_ENV
-      - name: Install a default toolchain that will be used to build cargo cross
-        run: |
-          rustup default stable
       - name: Cargo build
         uses: actions-rs/cargo@v1
         with:
           command: build
-          use-cross: true
+          use-cross: ${{ matrix.use-cross }}
           args: --release --target ${{ matrix.target }}
-        env:
-          CROSS_DOCKER_IN_DOCKER: true
       - name: List target output files
         run: ls -lR ./target
       - name: Upload the binary to release
         # No need to upload binaries for dry run (cron)
         if: github.event_name == 'release'
-        uses: svenstaro/upload-release-action@2.11.2
+        uses: svenstaro/upload-release-action@2.4.0
         with:
           repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
           file: target/${{ matrix.target }}/release/meilisearch
           asset_name: ${{ matrix.asset_name }}
           tag: ${{ github.ref }}
-
-  publish-openapi-file:
-    name: Publish OpenAPI file
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v5
-      - name: Setup Rust
-        uses: actions-rs/toolchain@v1
-        with:
-          toolchain: stable
-          override: true
-      - name: Generate OpenAPI file
-        run: |
-          cd crates/openapi-generator
-          cargo run --release -- --pretty --output ../../meilisearch.json
-      - name: Upload OpenAPI to Release
-        # No need to upload for dry run (cron)
-        if: github.event_name == 'release'
-        uses: svenstaro/upload-release-action@2.11.2
-        with:
-          repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
-          file: ./meilisearch.json
-          asset_name: meilisearch-openapi.json
-          tag: ${{ github.ref }}

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

@@ -0,0 +1,57 @@
+name: Publish to APT repository & Homebrew
+
+on:
+  release:
+    types: [released]
+
+jobs:
+  check-version:
+    name: Check the version validity
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Check release validity
+        run: bash .github/scripts/check-release.sh
+
+  debian:
+    name: Publish debian packagge
+    runs-on: ubuntu-latest
+    needs: check-version
+    container:
+      # Use ubuntu-18.04 to compile with glibc 2.27
+      image: ubuntu:18.04
+    steps:
+    - name: Install needed dependencies
+      run: |
+        apt-get update && apt-get install -y curl
+        apt-get install build-essential -y
+    - uses: actions-rs/toolchain@v1
+      with:
+        toolchain: stable
+        override: true
+    - name: Install cargo-deb
+      run: cargo install cargo-deb
+    - uses: actions/checkout@v3
+    - name: Build deb package
+      run: cargo deb -p meilisearch -o target/debian/meilisearch.deb
+    - name: Upload debian pkg to release
+      uses: svenstaro/upload-release-action@2.4.0
+      with:
+        repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
+        file: target/debian/meilisearch.deb
+        asset_name: meilisearch.deb
+        tag: ${{ github.ref }}
+    - name: Upload debian pkg to apt repository
+      run: curl -F package=@target/debian/meilisearch.deb https://${{ secrets.GEMFURY_PUSH_TOKEN }}@push.fury.io/meilisearch/
+
+  homebrew:
+    name: Bump Homebrew formula
+    runs-on: ubuntu-latest
+    needs: check-version
+    steps:
+      - name: Create PR to Homebrew
+        uses: mislav/bump-homebrew-formula-action@v2
+        with:
+          formula-name: meilisearch
+        env:
+          COMMITTER_TOKEN: ${{ secrets.HOMEBREW_COMMITTER_TOKEN }}

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

@@ -1,5 +1,4 @@
-name: Publish images to Docker Hub
-
+---
 on:
   push:
     # Will run for every tag pushed except `latest`
@@ -13,13 +12,13 @@ on:
     - cron: '0 23 * * *' # Every day at 11:00pm
   workflow_dispatch:
 
+name: Publish tagged images to Docker Hub
+
 jobs:
   docker:
     runs-on: docker
-    permissions:
-      id-token: write # This is needed to use Cosign in keyless mode
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v3
 
       # If we are running a cron or manual job ('schedule' or 'workflow_dispatch' event), it means we are publishing the `nightly` tag, so not considered stable.
       # If we have pushed a tag, and the tag has the v<nmumber>.<number>.<number> format, it means we are publishing an official release, so considered stable.
@@ -59,23 +58,20 @@ jobs:
           echo "date=$commit_date" >> $GITHUB_OUTPUT
 
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
+        uses: docker/setup-qemu-action@v2
 
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-
-      - name: Install cosign
-        uses: sigstore/cosign-installer@d58896d6a1865668819e1d91763c7751a165e159 # tag=v3.9.2
+        uses: docker/setup-buildx-action@v2
 
       - name: Login to Docker Hub
-        uses: docker/login-action@v3
+        uses: docker/login-action@v2
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
       - name: Docker meta
         id: meta
-        uses: docker/metadata-action@v5
+        uses: docker/metadata-action@v4
         with:
           images: getmeili/meilisearch
           # Prevent `latest` to be updated for each new tag pushed.
@@ -85,12 +81,10 @@ jobs:
             type=ref,event=tag
             type=raw,value=nightly,enable=${{ github.event_name != 'push' }}
             type=semver,pattern=v{{major}}.{{minor}},enable=${{ steps.check-tag-format.outputs.stable == 'true' }}
-            type=semver,pattern=v{{major}},enable=${{ steps.check-tag-format.outputs.stable == 'true' }}
             type=raw,value=latest,enable=${{ steps.check-tag-format.outputs.stable == 'true' && steps.check-tag-format.outputs.latest == 'true' }}
 
       - name: Build and push
-        uses: docker/build-push-action@v6
-        id: build-and-push
+        uses: docker/build-push-action@v4
         with:
           push: true
           platforms: linux/amd64,linux/arm64
@@ -100,43 +94,13 @@ jobs:
             COMMIT_DATE=${{ steps.build-metadata.outputs.date }}
             GIT_TAG=${{ github.ref_name }}
 
-      - name: Sign the images with GitHub OIDC Token
-        env:
-          DIGEST: ${{ steps.build-and-push.outputs.digest }}
-          TAGS: ${{ steps.meta.outputs.tags }}
-        run: |
-          images=""
-          for tag in ${TAGS}; do
-            images+="${tag}@${DIGEST} "
-          done
-          cosign sign --yes ${images}
-
       # /!\ Don't touch this without checking with Cloud team
       - 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@v3
+        uses: peter-evans/repository-dispatch@v2
         with:
           token: ${{ secrets.MEILI_BOT_GH_PAT }}
           repository: meilisearch/meilisearch-cloud
           event-type: cloud-docker-build
           client-payload: '{ "meilisearch_version": "${{ github.ref_name }}", "stable": "${{ steps.check-tag-format.outputs.stable }}" }'
-
-      # Send notification to Swarmia to notify of a deployment: https://app.swarmia.com
-      # - name: 'Setup jq'
-      #   uses: dcarbone/install-jq-action
-      # - name: Send deployment to Swarmia
-      #   if: github.event_name == 'push' && success()
-      #   run: |
-      #     JSON_STRING=$( jq --null-input --compact-output \
-      #     --arg version "${{ github.ref_name }}" \
-      #     --arg appName "meilisearch" \
-      #     --arg environment "production" \
-      #     --arg commitSha "${{ github.sha }}" \
-      #     --arg repositoryFullName "${{ github.repository }}" \
-      #     '{"version": $version, "appName": $appName, "environment": $environment, "commitSha": $commitSha, "repositoryFullName": $repositoryFullName}' )
-
-      #     curl -H "Authorization: ${{ secrets.SWARMIA_DEPLOYMENTS_AUTHORIZATION }}" \
-      #       -H "Content-Type: application/json" \
-      #       -d "$JSON_STRING" \
-      #       https://hook.swarmia.com/deployments

.github/workflows/push_benchmarks_indexing.yml

@@ -1,4 +1,4 @@
-name: Benchmarks of indexing (push)
+name: Benchmarks indexing (push)
 
 on:
   push:
@@ -15,10 +15,12 @@ jobs:
     runs-on: benchmarks
     timeout-minutes: 4320 # 72h
     steps:
-      - uses: actions/checkout@v5
-      - uses: dtolnay/rust-toolchain@1.89
+      - uses: actions/checkout@v3
+      - uses: actions-rs/toolchain@v1
         with:
           profile: minimal
+          toolchain: stable
+          override: true
 
       # Set variables
       - name: Set current branch name
@@ -41,7 +43,7 @@ jobs:
       # Run benchmarks
       - name: Run benchmarks - Dataset ${BENCH_NAME} - Branch ${{ steps.current_branch.outputs.name }} - Commit ${{ steps.commit_sha.outputs.short }}
         run: |
-          cd crates/benchmarks
+          cd benchmarks
           cargo bench --bench ${BENCH_NAME} -- --save-baseline ${{ steps.file.outputs.basename }}
 
       # Generate critcmp files
@@ -69,7 +71,7 @@ jobs:
         run: telegraf --config https://eu-central-1-1.aws.cloud2.influxdata.com/api/v2/telegrafs/08b52e34a370b000 --once --debug
 
       # Helper
-      - name: "README: compare with another benchmark"
+      - name: 'README: compare with another benchmark'
         run: |
           echo "${{ steps.file.outputs.basename }}.json has just been pushed."
           echo 'How to compare this benchmark with another one?'

.github/workflows/push_benchmarks_search_geo.yml

@@ -1,4 +1,4 @@
-name: Benchmarks of search for geo (push)
+name: Benchmarks search geo (push)
 
 on:
   push:
@@ -14,10 +14,12 @@ jobs:
     name: Run and upload benchmarks
     runs-on: benchmarks
     steps:
-      - uses: actions/checkout@v5
-      - uses: dtolnay/rust-toolchain@1.89
+      - uses: actions/checkout@v3
+      - uses: actions-rs/toolchain@v1
         with:
           profile: minimal
+          toolchain: stable
+          override: true
 
       # Set variables
       - name: Set current branch name
@@ -40,7 +42,7 @@ jobs:
       # Run benchmarks
       - name: Run benchmarks - Dataset ${BENCH_NAME} - Branch ${{ steps.current_branch.outputs.name }} - Commit ${{ steps.commit_sha.outputs.short }}
         run: |
-          cd crates/benchmarks
+          cd benchmarks
           cargo bench --bench ${BENCH_NAME} -- --save-baseline ${{ steps.file.outputs.basename }}
 
       # Generate critcmp files
@@ -68,7 +70,7 @@ jobs:
         run: telegraf --config https://eu-central-1-1.aws.cloud2.influxdata.com/api/v2/telegrafs/08b52e34a370b000 --once --debug
 
       # Helper
-      - name: "README: compare with another benchmark"
+      - name: 'README: compare with another benchmark'
         run: |
           echo "${{ steps.file.outputs.basename }}.json has just been pushed."
           echo 'How to compare this benchmark with another one?'

.github/workflows/push_benchmarks_search_songs.yml

@@ -1,4 +1,4 @@
-name: Benchmarks of search for songs (push)
+name: Benchmarks search songs (push)
 
 on:
   push:
@@ -14,10 +14,12 @@ jobs:
     name: Run and upload benchmarks
     runs-on: benchmarks
     steps:
-      - uses: actions/checkout@v5
-      - uses: dtolnay/rust-toolchain@1.89
+      - uses: actions/checkout@v3
+      - uses: actions-rs/toolchain@v1
         with:
           profile: minimal
+          toolchain: stable
+          override: true
 
       # Set variables
       - name: Set current branch name
@@ -40,7 +42,7 @@ jobs:
       # Run benchmarks
       - name: Run benchmarks - Dataset ${BENCH_NAME} - Branch ${{ steps.current_branch.outputs.name }} - Commit ${{ steps.commit_sha.outputs.short }}
         run: |
-          cd crates/benchmarks
+          cd benchmarks
           cargo bench --bench ${BENCH_NAME} -- --save-baseline ${{ steps.file.outputs.basename }}
 
       # Generate critcmp files
@@ -68,7 +70,7 @@ jobs:
         run: telegraf --config https://eu-central-1-1.aws.cloud2.influxdata.com/api/v2/telegrafs/08b52e34a370b000 --once --debug
 
       # Helper
-      - name: "README: compare with another benchmark"
+      - name: 'README: compare with another benchmark'
         run: |
           echo "${{ steps.file.outputs.basename }}.json has just been pushed."
           echo 'How to compare this benchmark with another one?'

.github/workflows/push_benchmarks_search_wiki.yml

@@ -1,4 +1,4 @@
-name: Benchmarks of search for Wikipedia articles (push)
+name: Benchmarks search wikipedia articles (push)
 
 on:
   push:
@@ -14,10 +14,12 @@ jobs:
     name: Run and upload benchmarks
     runs-on: benchmarks
     steps:
-      - uses: actions/checkout@v5
-      - uses: dtolnay/rust-toolchain@1.89
+      - uses: actions/checkout@v3
+      - uses: actions-rs/toolchain@v1
         with:
           profile: minimal
+          toolchain: stable
+          override: true
 
       # Set variables
       - name: Set current branch name
@@ -40,7 +42,7 @@ jobs:
       # Run benchmarks
       - name: Run benchmarks - Dataset ${BENCH_NAME} - Branch ${{ steps.current_branch.outputs.name }} - Commit ${{ steps.commit_sha.outputs.short }}
         run: |
-          cd crates/benchmarks
+          cd benchmarks
           cargo bench --bench ${BENCH_NAME} -- --save-baseline ${{ steps.file.outputs.basename }}
 
       # Generate critcmp files
@@ -68,7 +70,7 @@ jobs:
         run: telegraf --config https://eu-central-1-1.aws.cloud2.influxdata.com/api/v2/telegrafs/08b52e34a370b000 --once --debug
 
       # Helper
-      - name: "README: compare with another benchmark"
+      - name: 'README: compare with another benchmark'
         run: |
           echo "${{ steps.file.outputs.basename }}.json has just been pushed."
           echo 'How to compare this benchmark with another one?'

.github/workflows/release-drafter.yml

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

.github/workflows/rust.yml

@@ -0,0 +1,145 @@
+name: Rust
+
+on:
+  workflow_dispatch:
+  schedule:
+    # Everyday at 5:00am
+    - cron: '0 5 * * *'
+  pull_request:
+  push:
+    # trying and staging branches are for Bors config
+    branches:
+      - trying
+      - staging
+
+env:
+  CARGO_TERM_COLOR: always
+  RUST_BACKTRACE: 1
+  RUSTFLAGS: "-D warnings"
+
+jobs:
+  test-linux:
+    name: Tests on ubuntu-18.04
+    runs-on: ubuntu-latest
+    container:
+      # Use ubuntu-18.04 to compile with glibc 2.27, which are the production expectations
+      image: ubuntu:18.04
+    steps:
+    - uses: actions/checkout@v3
+    - name: Install needed dependencies
+      run: |
+        apt-get update && apt-get install -y curl
+        apt-get install build-essential -y
+    - name: Run test with Rust stable
+      if: github.event_name != 'schedule'
+      uses: actions-rs/toolchain@v1
+      with:
+        toolchain: stable
+        override: true
+    - name: Run test with Rust nightly
+      if: github.event_name == 'schedule'
+      uses: actions-rs/toolchain@v1
+      with:
+        toolchain: nightly
+        override: true
+    # Disable cache due to disk space issues with Windows workers in CI
+    # - name: Cache dependencies
+    #   uses: Swatinem/rust-cache@v2.2.0
+    - name: Run cargo check without any default features
+      uses: actions-rs/cargo@v1
+      with:
+        command: build
+        args: --locked --release --no-default-features --all
+    - name: Run cargo test
+      uses: actions-rs/cargo@v1
+      with:
+        command: test
+        args: --locked --release --all
+
+  test-others:
+    name: Tests on ${{ matrix.os }}
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [macos-12, windows-2022]
+    steps:
+    - uses: actions/checkout@v3
+#     - name: Cache dependencies
+#       uses: Swatinem/rust-cache@v2.2.0
+    - name: Run cargo check without any default features
+      uses: actions-rs/cargo@v1
+      with:
+        command: build
+        args: --locked --release --no-default-features --all
+    - name: Run cargo test
+      uses: actions-rs/cargo@v1
+      with:
+        command: test
+        args: --locked --release --all
+
+  # We run tests in debug also, to make sure that the debug_assertions are hit
+  test-debug:
+    name: Run tests in debug
+    runs-on: ubuntu-latest
+    container:
+      # Use ubuntu-18.04 to compile with glibc 2.27, which are the production expectations
+      image: ubuntu:18.04
+    steps:
+      - uses: actions/checkout@v3
+      - name: Install needed dependencies
+        run: |
+          apt-get update && apt-get install -y curl
+          apt-get install build-essential -y
+      - uses: actions-rs/toolchain@v1
+        with:
+          toolchain: stable
+          override: true
+      # - name: Cache dependencies
+      #   uses: Swatinem/rust-cache@v2.2.0
+      - name: Run tests in debug
+        uses: actions-rs/cargo@v1
+        with:
+          command: test
+          args: --locked --all
+
+  clippy:
+    name: Run Clippy
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions-rs/toolchain@v1
+        with:
+          profile: minimal
+          toolchain: 1.67.0
+          override: true
+          components: clippy
+      # - name: Cache dependencies
+      #   uses: Swatinem/rust-cache@v2.2.0
+      - name: Run cargo clippy
+        uses: actions-rs/cargo@v1
+        with:
+          command: clippy
+          # allow unlined_format_args https://github.com/rust-lang/rust-clippy/issues/10087
+          args: --all-targets -- --deny warnings --allow clippy::uninlined_format_args
+
+  fmt:
+    name: Run Rustfmt
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions-rs/toolchain@v1
+        with:
+          profile: minimal
+          toolchain: nightly
+          override: true
+          components: rustfmt
+      # - name: Cache dependencies
+      #   uses: Swatinem/rust-cache@v2.2.0
+      - name: Run cargo fmt
+        # Since we never ran the `build.rs` script in the benchmark directory we are missing one auto-generated import file.
+        # Since we want to trigger (and fail) this action as fast as possible, instead of building the benchmark crate
+        # we are going to create an empty file where rustfmt expects it.
+        run: |
+          echo -ne "\n" > benchmarks/benches/datasets_paths.rs
+          cargo fmt --all -- --check

.github/workflows/sdks-tests.yml

@@ -1,394 +0,0 @@
-# If any test fails, the engine team should ensure the "breaking" changes are expected and contact the integration team
-name: SDKs tests
-
-on:
-  workflow_dispatch:
-    inputs:
-      docker_image:
-        description: 'The Meilisearch Docker image used'
-        required: false
-        default: nightly
-  schedule:
-    - cron: '0 6 * * *' # Every day at 6:00am
-
-env:
-  MEILI_MASTER_KEY: 'masterKey'
-  MEILI_NO_ANALYTICS: 'true'
-  DISABLE_COVERAGE: 'true'
-
-jobs:
-  define-docker-image:
-    runs-on: ubuntu-latest
-    outputs:
-      docker-image: ${{ steps.define-image.outputs.docker-image }}
-    steps:
-      - uses: actions/checkout@v5
-      - name: Define the Docker image we need to use
-        id: define-image
-        run: |
-          event=${{ github.event_name }}
-          echo "docker-image=nightly" >> $GITHUB_OUTPUT
-          if [[ $event == 'workflow_dispatch' ]]; then
-            echo "docker-image=${{ github.event.inputs.docker_image }}" >> $GITHUB_OUTPUT
-          fi
-      - name: Docker image is ${{ steps.define-image.outputs.docker-image }}
-        run: echo "Docker image is ${{ steps.define-image.outputs.docker-image }}"
-
-##########
-## SDKs ##
-##########
-
-  meilisearch-dotnet-tests:
-    needs: define-docker-image
-    name: .NET SDK tests
-    runs-on: ubuntu-latest
-    env:
-      MEILISEARCH_VERSION: ${{ needs.define-docker-image.outputs.docker-image }}
-
-    steps:
-      - uses: actions/checkout@v5
-        with:
-          repository: meilisearch/meilisearch-dotnet
-      - name: Setup .NET Core
-        uses: actions/setup-dotnet@v4
-        with:
-          dotnet-version: "8.0.x"
-      - name: Install dependencies
-        run: dotnet restore
-      - name: Build
-        run: dotnet build --configuration Release --no-restore
-      - name: Meilisearch (latest version) setup with Docker
-        run: docker compose up -d
-      - name: Run tests
-        run: dotnet test --no-restore --verbosity normal
-
-  meilisearch-dart-tests:
-    needs: define-docker-image
-    name: Dart SDK tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - uses: actions/checkout@v5
-        with:
-          repository: meilisearch/meilisearch-dart
-      - uses: dart-lang/setup-dart@v1
-        with:
-          sdk: 'latest'
-      - name: Install dependencies
-        run: dart pub get
-      - name: Run integration tests
-        run: dart test --concurrency=4
-
-  meilisearch-go-tests:
-    needs: define-docker-image
-    name: Go SDK tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - name: Set up Go
-        uses: actions/setup-go@v5
-        with:
-          go-version: stable
-      - uses: actions/checkout@v5
-        with:
-          repository: meilisearch/meilisearch-go
-      - name: Get dependencies
-        run: |
-          go get -v -t -d ./...
-          if [ -f Gopkg.toml ]; then
-            curl https://raw.githubusercontent.com/golang/dep/master/install.sh | sh
-            dep ensure
-          fi
-      - name: Run integration tests
-        run: go test --race -v ./integration
-
-  meilisearch-java-tests:
-    needs: define-docker-image
-    name: Java SDK tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - uses: actions/checkout@v5
-        with:
-          repository: meilisearch/meilisearch-java
-      - name: Set up Java
-        uses: actions/setup-java@v5
-        with:
-          java-version: 8
-          distribution: 'zulu'
-          cache: gradle
-      - name: Grant execute permission for gradlew
-        run: chmod +x gradlew
-      - name: Build and run unit and integration tests
-        run: ./gradlew build integrationTest
-
-  meilisearch-js-tests:
-    needs: define-docker-image
-    name: JS SDK tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - uses: actions/checkout@v5
-        with:
-          repository: meilisearch/meilisearch-js
-      - name: Setup node
-        uses: actions/setup-node@v4
-        with:
-          cache: 'yarn'
-      - name: Install dependencies
-        run: yarn --dev
-      - name: Run tests
-        run: yarn test
-      - name: Build project
-        run: yarn build
-      - name: Run ESM env
-        run: yarn test:env:esm
-      - name: Run Node.js env
-        run: yarn test:env:nodejs
-      - name: Run node typescript env
-        run: yarn test:env:node-ts
-      - name: Run Browser env
-        run: yarn test:env:browser
-
-  meilisearch-php-tests:
-    needs: define-docker-image
-    name: PHP SDK tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - uses: actions/checkout@v5
-        with:
-          repository: meilisearch/meilisearch-php
-      - name: Install PHP
-        uses: shivammathur/setup-php@v2
-      - name: Validate composer.json and composer.lock
-        run: composer validate
-      - name: Install dependencies
-        run: |
-          composer remove --dev friendsofphp/php-cs-fixer --no-update --no-interaction
-          composer update --prefer-dist --no-progress
-      - name: Run test suite - default HTTP client (Guzzle 7)
-        run: |
-          sh scripts/tests.sh
-          composer remove --dev guzzlehttp/guzzle http-interop/http-factory-guzzle
-
-  meilisearch-python-tests:
-    needs: define-docker-image
-    name: Python SDK tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - uses: actions/checkout@v5
-        with:
-          repository: meilisearch/meilisearch-python
-      - name: Set up Python
-        uses: actions/setup-python@v5
-      - name: Install pipenv
-        uses: dschep/install-pipenv-action@v1
-      - name: Install dependencies
-        run: pipenv install --dev --python=${{ matrix.python-version }}
-      - name: Test with pytest
-        run: pipenv run pytest
-
-  meilisearch-ruby-tests:
-    needs: define-docker-image
-    name: Ruby SDK tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - uses: actions/checkout@v5
-        with:
-          repository: meilisearch/meilisearch-ruby
-      - name: Set up Ruby 3
-        uses: ruby/setup-ruby@v1
-        with:
-          ruby-version: 3
-      - name: Install ruby dependencies
-        run: bundle install --with test
-      - name: Run test suite
-        run: bundle exec rspec
-
-  meilisearch-rust-tests:
-    needs: define-docker-image
-    name: Rust SDK tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - uses: actions/checkout@v5
-        with:
-          repository: meilisearch/meilisearch-rust
-      - name: Build
-        run: cargo build --verbose
-      - name: Run tests
-        run: cargo test --verbose
-
-  meilisearch-swift-tests:
-    needs: define-docker-image
-    name: Swift SDK tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - uses: actions/checkout@v5
-        with:
-          repository: meilisearch/meilisearch-swift
-      - name: Run tests
-        run: swift test
-
-########################
-## FRONT-END PLUGINS ##
-########################
-
-  meilisearch-js-plugins-tests:
-    needs: define-docker-image
-    name: meilisearch-js-plugins tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - uses: actions/checkout@v5
-        with:
-          repository: meilisearch/meilisearch-js-plugins
-      - name: Setup node
-        uses: actions/setup-node@v4
-        with:
-          cache: yarn
-      - name: Install dependencies
-        run: yarn install
-      - name: Run tests
-        run: yarn test
-      - name: Build all the playgrounds and the packages
-        run: yarn build
-
-########################
-## BACK-END PLUGINS ###
-########################
-
-  meilisearch-rails-tests:
-    needs: define-docker-image
-    name: meilisearch-rails tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    env:
-      RAILS_VERSION: '7.0'
-    steps:
-      - uses: actions/checkout@v5
-        with:
-          repository: meilisearch/meilisearch-rails
-      - name: Install SQLite dependencies
-        run: sudo apt-get update && sudo apt-get install -y libsqlite3-dev
-      - name: Set up Ruby
-        uses: ruby/setup-ruby@v1
-        with:
-          ruby-version: 3
-          bundler-cache: true
-      - name: Start MongoDB
-        uses: supercharge/mongodb-github-action@1.12.0
-        with:
-          mongodb-version: 8.0
-      - name: Run tests
-        run: bundle exec rspec
-
-  meilisearch-symfony-tests:
-    needs: define-docker-image
-    name: meilisearch-symfony tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - uses: actions/checkout@v5
-        with:
-          repository: meilisearch/meilisearch-symfony
-      - name: Install PHP
-        uses: shivammathur/setup-php@v2
-        with:
-          tools: composer:v2, flex
-      - name: Validate composer.json and composer.lock
-        run: composer validate
-      - name: Install dependencies
-        run: composer install --prefer-dist --no-progress --quiet
-      - name: Remove doctrine/annotations
-        run: composer remove --dev doctrine/annotations
-      - name: Run test suite
-        run: composer test:unit

.github/workflows/test-suite.yml

@@ -1,201 +0,0 @@
-name: Test suite
-
-on:
-  workflow_dispatch:
-  schedule:
-    # Every day at 5:00am
-    - cron: "0 5 * * *"
-  pull_request:
-  merge_group:
-
-env:
-  CARGO_TERM_COLOR: always
-  RUST_BACKTRACE: 1
-  RUSTFLAGS: "-D warnings"
-
-jobs:
-  test-linux:
-    name: Tests on ubuntu-22.04
-    runs-on: ubuntu-latest
-    container:
-      # Use ubuntu-22.04 to compile with glibc 2.35
-      image: ubuntu:22.04
-    steps:
-      - uses: actions/checkout@v5
-      - name: Install needed dependencies
-        run: |
-          apt-get update && apt-get install -y curl
-          apt-get install build-essential -y
-      - name: Setup test with Rust stable
-        uses: dtolnay/rust-toolchain@1.89
-      - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.8.0
-      - name: Run cargo check without any default features
-        uses: actions-rs/cargo@v1
-        with:
-          command: build
-          args: --locked --release --no-default-features --all
-      - name: Run cargo test
-        uses: actions-rs/cargo@v1
-        with:
-          command: test
-          args: --locked --release --all
-
-  test-others:
-    name: Tests on ${{ matrix.os }}
-    runs-on: ${{ matrix.os }}
-    strategy:
-      fail-fast: false
-      matrix:
-        os: [macos-13, windows-2022]
-    steps:
-      - uses: actions/checkout@v5
-      - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.8.0
-      - uses: dtolnay/rust-toolchain@1.89
-      - name: Run cargo check without any default features
-        uses: actions-rs/cargo@v1
-        with:
-          command: build
-          args: --locked --release --no-default-features --all
-      - name: Run cargo test
-        uses: actions-rs/cargo@v1
-        with:
-          command: test
-          args: --locked --release --all
-
-  test-all-features:
-    name: Tests almost all features
-    runs-on: ubuntu-latest
-    container:
-      # Use ubuntu-22.04 to compile with glibc 2.35
-      image: ubuntu:22.04
-    if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
-    steps:
-      - uses: actions/checkout@v5
-      - name: Install needed dependencies
-        run: |
-          apt-get update
-          apt-get install --assume-yes build-essential curl
-      - uses: dtolnay/rust-toolchain@1.89
-      - name: Run cargo build with almost all features
-        run: |
-          cargo build --workspace --locked --release --features "$(cargo xtask list-features --exclude-feature cuda,test-ollama)"
-      - name: Run cargo test with almost all features
-        run: |
-          cargo test --workspace --locked --release --features "$(cargo xtask list-features --exclude-feature cuda,test-ollama)"
-
-  ollama-ubuntu:
-    name: Test with Ollama
-    runs-on: ubuntu-latest
-    env:
-      MEILI_TEST_OLLAMA_SERVER: "http://localhost:11434"
-    steps:
-      - uses: actions/checkout@v5
-      - name: Install Ollama
-        run: |
-          curl -fsSL https://ollama.com/install.sh | sudo -E sh
-      - name: Start serving
-        run: |
-          # Run it in the background, there is no way to daemonise at the moment
-          ollama serve &
-
-          # A short pause is required before the HTTP port is opened
-          sleep 5
-
-          # This endpoint blocks until ready
-          time curl -i http://localhost:11434
-
-      - name: Pull nomic-embed-text & all-minilm
-        run: |
-          ollama pull nomic-embed-text
-          ollama pull all-minilm
-
-      - name: Run cargo test
-        uses: actions-rs/cargo@v1
-        with:
-          command: test
-          args: --locked --release --all --features test-ollama ollama
-
-  test-disabled-tokenization:
-    name: Test disabled tokenization
-    runs-on: ubuntu-latest
-    container:
-      image: ubuntu:22.04
-    if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
-    steps:
-      - uses: actions/checkout@v5
-      - name: Install needed dependencies
-        run: |
-          apt-get update
-          apt-get install --assume-yes build-essential curl
-      - uses: dtolnay/rust-toolchain@1.89
-      - name: Run cargo tree without default features and check lindera is not present
-        run: |
-          if cargo tree -f '{p} {f}' -e normal --no-default-features | grep -qz lindera; then
-            echo "lindera has been found in the sources and it shouldn't"
-            exit 1
-          fi
-      - name: Run cargo tree with default features and check lindera is pressent
-        run: |
-          cargo tree -f '{p} {f}' -e normal | grep lindera -qz
-
-  # We run tests in debug also, to make sure that the debug_assertions are hit
-  test-debug:
-    name: Run tests in debug
-    runs-on: ubuntu-latest
-    container:
-      # Use ubuntu-22.04 to compile with glibc 2.35
-      image: ubuntu:22.04
-    steps:
-      - uses: actions/checkout@v5
-      - name: Install needed dependencies
-        run: |
-          apt-get update && apt-get install -y curl
-          apt-get install build-essential -y
-      - uses: dtolnay/rust-toolchain@1.89
-      - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.8.0
-      - name: Run tests in debug
-        uses: actions-rs/cargo@v1
-        with:
-          command: test
-          args: --locked --all
-
-  clippy:
-    name: Run Clippy
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v5
-      - uses: dtolnay/rust-toolchain@1.89
-        with:
-          profile: minimal
-          components: clippy
-      - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.8.0
-      - name: Run cargo clippy
-        uses: actions-rs/cargo@v1
-        with:
-          command: clippy
-          args: --all-targets -- --deny warnings
-
-  fmt:
-    name: Run Rustfmt
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v5
-      - uses: dtolnay/rust-toolchain@1.89
-        with:
-          profile: minimal
-          toolchain: nightly-2024-07-09
-          override: true
-          components: rustfmt
-      - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.8.0
-      - name: Run cargo fmt
-        # Since we never ran the `build.rs` script in the benchmark directory we are missing one auto-generated import file.
-        # Since we want to trigger (and fail) this action as fast as possible, instead of building the benchmark crate
-        # we are going to create an empty file where rustfmt expects it.
-        run: |
-          echo -ne "\n" > crates/benchmarks/benches/datasets_paths.rs
-          cargo fmt --all -- --check

.github/workflows/uffizzi-build.yml

@@ -0,0 +1,100 @@
+name: Uffizzi - Build PR Image
+on:
+  pull_request:
+    types: [opened,synchronize,reopened,closed]
+
+jobs:
+  build-meilisearch:
+    name: Build and push `meilisearch`
+    runs-on: ubuntu-latest
+    outputs:
+      tags: ${{ steps.meta.outputs.tags }}
+    if: ${{ github.event.action != 'closed' }}
+    steps:
+      - name: checkout
+        uses: actions/checkout@v3
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v2
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+
+      - name: Generate UUID image name
+        id: uuid
+        run: echo "UUID_TAG=$(uuidgen)" >> $GITHUB_ENV
+
+      - name: Docker metadata
+        id: meta
+        uses: docker/metadata-action@v3
+        with:
+          images: registry.uffizzi.com/${{ env.UUID_TAG }}
+          tags: | 
+            type=raw,value=60d
+
+      - name: Build Image
+        uses: docker/build-push-action@v3
+        with:
+          context: ./
+          file: .github/uffizzi/Dockerfile
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+          push: true
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+
+  render-compose-file:
+    name: Render Docker Compose File
+    # Pass output of this workflow to another triggered by `workflow_run` event.
+    runs-on: ubuntu-latest
+    needs: 
+      - build-meilisearch
+    outputs:
+      compose-file-cache-key:  ${{ env.COMPOSE_FILE_HASH }}
+    steps:
+      - name: Checkout git repo
+        uses: actions/checkout@v3
+      - name: Render Compose File
+        run: |
+          MEILISEARCH_IMAGE=$(echo ${{ needs.build-meilisearch.outputs.tags }})
+          export MEILISEARCH_IMAGE
+          # Render simple template from environment variables.
+          envsubst < .github/uffizzi/docker-compose.uffizzi.yml > docker-compose.rendered.yml
+          cat docker-compose.rendered.yml
+      - name: Upload Rendered Compose File as Artifact
+        uses: actions/upload-artifact@v3
+        with:
+          name: preview-spec 
+          path: docker-compose.rendered.yml
+          retention-days: 2
+      - name: Serialize PR Event to File
+        run:  |
+          cat << EOF > event.json
+          ${{ toJSON(github.event) }} 
+          
+          EOF
+      - name: Upload PR Event as Artifact
+        uses: actions/upload-artifact@v3
+        with:
+          name: preview-spec
+          path: event.json
+          retention-days: 2
+
+  delete-preview:
+    name: Call for Preview Deletion
+    runs-on: ubuntu-latest
+    if: ${{ github.event.action == 'closed' }}
+    steps:
+      # If this PR is closing, we will not render a compose file nor pass it to the next workflow.
+      - name: Serialize PR Event to File
+        run:  |
+          cat << EOF > event.json
+          ${{ toJSON(github.event) }} 
+          
+          EOF
+      - name: Upload PR Event as Artifact
+        uses: actions/upload-artifact@v3
+        with:
+          name: preview-spec
+          path: event.json
+          retention-days: 2

.github/workflows/uffizzi-preview-deploy.yml

@@ -0,0 +1,103 @@
+name: Uffizzi - Deploy Preview
+
+on:
+  workflow_run:
+    workflows:
+      - "Uffizzi - Build PR Image"
+    types:
+      - completed
+
+jobs:
+  cache-compose-file:
+    name: Cache Compose File
+    runs-on: ubuntu-latest
+    if: ${{ github.event.workflow_run.conclusion == 'success' }}
+    outputs:
+      compose-file-cache-key: ${{ env.COMPOSE_FILE_HASH }}
+      pr-number: ${{ env.PR_NUMBER }}
+      expected-url: ${{ env.EXPECTED_URL }}
+    steps:
+      - name: 'Download artifacts'
+        # Fetch output (zip archive) from the workflow run that triggered this workflow.
+        uses: actions/github-script@v6
+        with:
+          script: |
+            let allArtifacts = await github.rest.actions.listWorkflowRunArtifacts({
+               owner: context.repo.owner,
+               repo: context.repo.repo,
+               run_id: context.payload.workflow_run.id,
+            });
+            let matchArtifact = allArtifacts.data.artifacts.filter((artifact) => {
+              return artifact.name == "preview-spec"
+            })[0];
+            let download = await github.rest.actions.downloadArtifact({
+               owner: context.repo.owner,
+               repo: context.repo.repo,
+               artifact_id: matchArtifact.id,
+               archive_format: 'zip',
+            });
+            let fs = require('fs');
+            fs.writeFileSync(`${process.env.GITHUB_WORKSPACE}/preview-spec.zip`, Buffer.from(download.data));
+      
+      - name: 'Unzip artifact'
+        run: unzip preview-spec.zip
+      
+      - name: Read Event into ENV
+        run: |
+          echo 'EVENT_JSON<<EOF' >> $GITHUB_ENV
+          cat event.json >> $GITHUB_ENV
+          echo 'EOF' >> $GITHUB_ENV
+      
+      - name: Hash Rendered Compose File
+        id: hash
+        # If the previous workflow was triggered by a PR close event, we will not have a compose file artifact.
+        if: ${{ fromJSON(env.EVENT_JSON).action != 'closed' }}
+        run: echo "COMPOSE_FILE_HASH=$(md5sum docker-compose.rendered.yml | awk '{ print $1 }')" >> $GITHUB_ENV
+      
+      - name: Cache Rendered Compose File
+        if: ${{ fromJSON(env.EVENT_JSON).action != 'closed' }}
+        uses: actions/cache@v3
+        with:
+          path: docker-compose.rendered.yml
+          key: ${{ env.COMPOSE_FILE_HASH }}
+
+      - name: Read PR Number From Event Object
+        id: pr
+        run: echo "PR_NUMBER=${{ fromJSON(env.EVENT_JSON).number }}" >> $GITHUB_ENV
+      
+      - name: DEBUG - Print Job Outputs
+        if: ${{ runner.debug }}
+        run: |
+          echo "PR number: ${{ env.PR_NUMBER }}"
+          echo "Compose file hash: ${{ env.COMPOSE_FILE_HASH }}"
+          cat event.json
+
+      - name: Add expected URL env var
+        if: ${{ runner.debug }}
+        run: |
+          REPO=$(echo ${{ github.repository }} | sed 's/\./+/g')
+          echo "EXPECTED_URL=${{ inputs.server }}/github.com/$REPO/pull/${{ env.PR_NUMBER }}" >> $GITHUB_ENV
+
+  deploy-uffizzi-preview:
+    name: Use Remote Workflow to Preview on Uffizzi
+    needs:
+      - cache-compose-file
+    uses: UffizziCloud/preview-action/.github/workflows/reusable.yaml@desc
+    with:
+      # If this workflow was triggered by a PR close event, cache-key will be an empty string
+      # and this reusable workflow will delete the preview deployment.
+      compose-file-cache-key: ${{ needs.cache-compose-file.outputs.compose-file-cache-key }}
+      compose-file-cache-path: docker-compose.rendered.yml
+      server: https://app.uffizzi.com
+      pr-number: ${{ needs.cache-compose-file.outputs.pr-number }}
+      description: |
+        The meilisearch preview environment contains a web terminal from where you can run the
+        `meilisearch` command. You should be able to access this instance of meilisearch running in
+        the preview from the link Meilisearch Endpoint link given below.
+         
+        Web Terminal Endpoint : ${{ needs.cache-compose-file.outputs.expected-url }}
+        Meilisearch Endpoint : ${{ needs.cache-compose-file.outputs.expected-url }}/meilisearch
+    permissions:
+      contents: read
+      pull-requests: write
+      id-token: write

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

@@ -1,10 +1,10 @@
-name: Update Meilisearch version in Cargo.toml
+name: Update Meilisearch version in all Cargo.toml files
 
 on:
   workflow_dispatch:
     inputs:
       new_version:
-        description: "The new version (vX.Y.Z)"
+        description: 'The new version (vX.Y.Z)'
         required: true
 
 env:
@@ -14,16 +14,18 @@ env:
 
 jobs:
   update-version-cargo-toml:
-    name: Update version in Cargo.toml
+    name: Update version in Cargo.toml files
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v5
-      - uses: dtolnay/rust-toolchain@1.89
+      - uses: actions/checkout@v3
+      - uses: actions-rs/toolchain@v1
         with:
           profile: minimal
+          toolchain: stable
+          override: true
       - name: Install sd
         run: cargo install sd
-      - name: Update Cargo.toml file
+      - name: Update Cargo.toml files
         run: |
           raw_new_version=$(echo $NEW_VERSION | cut -d 'v' -f 2)
           new_string="version = \"$raw_new_version\""
@@ -33,12 +35,13 @@ jobs:
       - name: Commit and push the changes to the ${{ env.NEW_BRANCH }} branch
         uses: EndBug/add-and-commit@v9
         with:
-          message: "Update version for the next release (${{ env.NEW_VERSION }}) in Cargo.toml"
+          message: "Update version for the next release (${{ env.NEW_VERSION }}) in Cargo.toml files"
           new_branch: ${{ env.NEW_BRANCH }}
       - name: Create the PR pointing to ${{ github.ref_name }}
         run: |
           gh pr create \
-            --title "Update version for the next release ($NEW_VERSION) in Cargo.toml" \
-            --body '⚠️ This PR is automatically generated. Check the new version is the expected one and Cargo.lock has been updated before merging.' \
+            --title "Update version for the next release ($NEW_VERSION) in Cargo.toml files" \
+            --body '⚠️ This PR is automatically generated. Check the new version is the expected one before merging.' \
             --label 'skip changelog' \
+            --milestone $NEW_VERSION \
             --base $GITHUB_REF_NAME

.gitignore

@@ -5,27 +5,16 @@
 **/*.json_lines
 **/*.rs.bk
 /*.mdb
-/*.ms
+/query-history.txt
+/data.ms
 /snapshots
 /dumps
-/bench
-/_xtask_benchmark.ms
-/benchmarks
-.DS_Store
 
 # Snapshots
 ## ... large
 *.full.snap
-## ... unreviewed
+##  ... unreviewed
 *.snap.new
-## ... pending
-*.pending-snap
-
-# Tmp files
-.tmp*
-
-# Database snapshot
-crates/meilisearch/db.snapshot
 
 # Fuzzcheck data for the facet indexing fuzz test
-crates/milli/fuzz/update::facet::incremental::fuzz::fuzz/
+milli/fuzz/update::facet::incremental::fuzz::fuzz/

BENCHMARKS.md

@@ -1,392 +0,0 @@
-# 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).
-
-#### Sending a workload by hand
-
-Sometimes you want to visualize the metrics of a worlkoad that comes from a custom report.
-It is not quite easy to trick the benchboard in thinking that your report is legitimate but here are the commands you can run to upload your firefox report on a running benchboard.
-
-```bash
-# Name this hostname whatever you want
-echo '{ "hostname": "the-best-place" }' | xh PUT 'http://127.0.0.1:9001/api/v1/machine'
-
-# You'll receive an UUID from this command that we will call $invocation_uuid
-echo '{ "commit": { "sha1": "1234567", "commit_date": "2024-09-05 12:00:12.0 +00:00:00", "message": "A cool message" }, "machine_hostname": "the-best-place", "max_workloads": 1 }' | xh PUT 'http://127.0.0.1:9001/api/v1/invocation'
-
-# Just use UUID from the previous command
-# and you'll receive another UUID that we will call $workload_uuid
-echo '{ "invocation_uuid": "$invocation_uuid", "name": "toto", "max_runs": 1 }' | xh PUT 'http://127.0.0.1:9001/api/v1/workload'
-
-# And now use your $workload_uuid and the content of your firefox report
-# but don't forget to convert your firefox report from JSONLines into an object
-echo '{ "workload_uuid": "$workload_uuid", "data": $REPORT_JSON_DATA }' | xh PUT 'http://127.0.0.1:9001/api/v1/run'
-```
-
-### 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"],
-  // An expression that can be parsed as a comma-separated list of targets and levels
-  // as described in [tracing_subscriber's documentation](https://docs.rs/tracing-subscriber/latest/tracing_subscriber/filter/targets/struct.Targets.html#examples).
-  // The expression is used to filter the spans that are measured for profiling purposes.
-  // Optional, defaults to "indexing::=trace" (for indexing workloads), common other values is
-  // "search::=trace"
-  "target": "indexing::=trace",
-  // 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.
-  // Optional: A precommand is a request to the Meilisearch instance that is executed before the profiling runs.
-  "precommands": [
-    {
-      // 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": "WaitForTask"
-    }
-  ],
-  // A command is a request to the Meilisearch instance that is executed while the profiling runs.
-  "commands": [
-    {
-      "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)...
 
-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/).
+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/).
 
 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.
 
@@ -18,9 +18,9 @@ If Meilisearch does not offer optimized support for your language, please consid
 
 ## Assumptions
 
-1. **You're familiar with [GitHub](https://github.com) and the [Pull Requests (PR)](https://help.github.com/en/github/collaborating-with-issues-and-pull-requests/about-pull-requests) workflow.**
-2. **You've read the Meilisearch [documentation](https://www.meilisearch.com/docs).**
-3. **You know about the [Meilisearch community on Discord](https://discord.meilisearch.com).
+1. **You're familiar with [GitHub](https://github.com) and the [Pull Requests](https://help.github.com/en/github/collaborating-with-issues-and-pull-requests/about-pull-requests)(PR) workflow.**
+2. **You've read the Meilisearch [documentation](https://docs.meilisearch.com).**
+3. **You know about the [Meilisearch community](https://docs.meilisearch.com/learn/what_is_meilisearch/contact.html).
    Please use this for help.**
 
 ## How to Contribute
@@ -52,28 +52,6 @@ cargo test
 
 This command will be triggered to each PR as a requirement for merging it.
 
-#### Faster build
-
-You can set the `LINDERA_CACHE` environment variable to speed up your successive builds by up to 2 minutes.
-It'll store some built artifacts in the directory of your choice.
-
-We recommend using the `$HOME/.cache/meili/lindera` directory:
-```sh
-export LINDERA_CACHE=$HOME/.cache/meili/lindera
-```
-
-You can set the `MILLI_BENCH_DATASETS_PATH` environment variable to further speed up your builds.
-It'll store some big files used for the benchmarks in the directory of your choice.
-
-We recommend using the `$HOME/.cache/meili/benches` directory:
-```sh
-export MILLI_BENCH_DATASETS_PATH=$HOME/.cache/meili/benches
-```
-
-Furthermore, you can improve incremental compilation by setting the `MEILI_NO_VERGEN` environment variable.
-Setting this variable will prevent the Meilisearch binary from being rebuilt each time the directory that hosts the Meilisearch repository changes.
-Do not enable this environment variable for production builds (as it will break the `version` route, among other things).
-
 #### Snapshot-based tests
 
 We are using [insta](https://insta.rs) to perform snapshot-based testing.
@@ -85,7 +63,7 @@ Furthermore, we provide some macros on top of insta, notably a way to use snapsh
 
 To effectively debug snapshot-based hashes, we recommend you export the `MEILI_TEST_FULL_SNAPS` environment variable so that snapshot are fully created locally:
 
-```sh
+```
 export MEILI_TEST_FULL_SNAPS=true # add this to your .bashrc, .zshrc, ...
 ```
 
@@ -97,53 +75,6 @@ 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.
-
-#### Update the openAPI file if the API changed
-
-To update the openAPI file in the code, see [sprint_issue.md](https://github.com/meilisearch/meilisearch/blob/main/.github/ISSUE_TEMPLATE/sprint_issue.md#reminders-when-modifying-the-api).
-
-If you want to generate OpenAPI file manually:
-
-With swagger:
-- Starts Meilisearch with the `swagger` feature flag: `cargo run --features swagger`
-- On a browser, open the following URL: http://localhost:7700/scalar
-- Click the « Download openAPI file »
-
-With the internal crate:
-```bash
-cd crates/openapi-generator
-cargo run --release -- --pretty --output meilisearch.json
-```
-
-### 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
@@ -170,39 +101,48 @@ Some notes on GitHub PRs:
 - The PR title should be accurate and descriptive of the changes.
 - [Convert your PR as a draft](https://help.github.com/en/github/collaborating-with-issues-and-pull-requests/changing-the-stage-of-a-pull-request) if your changes are a work in progress: no one will review it until you pass your PR as ready for review.<br>
   The draft PRs are recommended when you want to show that you are working on something and make your work visible.
-- The branch related to the PR must be **up-to-date with `main`** before merging. Fortunately, this project uses [GitHub Merge Queues](https://github.blog/news-insights/product-news/github-merge-queue-is-generally-available/) to automatically enforce this requirement without the PR author having to rebase manually.
+- The branch related to the PR must be **up-to-date with `main`** before merging. Fortunately, this project uses [Bors](https://github.com/bors-ng/bors-ng) to automatically enforce this requirement without the PR author having to rebase manually.
 
-## Merging PRs
-
-This project uses GitHub Merge Queues that helps us manage pull requests merging.
-
-Before merging a PR, the maintainer should ensure the following requirements are met
-- Automated tests have been added.
-- If some tests cannot be automated, manual rigorous tests should be applied.
-- ⚠️ If there is an change in the DB: it's mandatory to manually test the `--experimental-dumpless-upgrade` on a DB of the previous Meilisearch minor version (e.g. v1.13 for the v1.14 release).
-- If necessary, the feature have been tested in the Cloud production environment (with [prototypes](./documentation/prototypes.md)) and the Cloud UI is ready.
-- If necessary, the [documentation](https://github.com/meilisearch/documentation) related to the implemented feature in the PR is ready.
-- If necessary, the [integrations](https://github.com/meilisearch/integration-guides) related to the implemented feature in the PR are ready.
-
-## Publish Process (for internal team only)
+## Release Process (for internal team only)
 
 Meilisearch tools follow the [Semantic Versioning Convention](https://semver.org/).
 
-### How to publish a new release
+### Automation to rebase and Merge the PRs
 
-The full Meilisearch release process is described in [this guide](./documentation/release.md).
+This project integrates a bot that helps us manage pull requests merging.<br>
+_[Read more about this](https://github.com/meilisearch/integration-guides/blob/main/resources/bors.md)._
+
+### How to Publish a new Release
+
+The full Meilisearch release process is described in [this guide](https://github.com/meilisearch/engine-team/blob/main/resources/meilisearch-release.md). Please follow it carefully before doing any release.
 
 ### How to publish a prototype
 
 Depending on the developed feature, you might need to provide a prototyped version of Meilisearch to make it easier to test by the users.
 
-This happens in two steps:
-- [Release the prototype](./documentation/prototypes.md#how-to-publish-a-prototype)
-- [Communicate about it](./documentation/prototypes.md#communication)
+The prototype name must follow this convention: `prototype-X-Y` where
+- `X` is the feature name formatted in `kebab-case`. It should not end with a single number.
+- `Y` is the version of the prototype, starting from `0`.
 
-### How to implement and publish an experimental feature
+✅ Example: `prototype-auto-resize-0`. </br>
+❌ Bad example: `auto-resize-0`: lacks the `prototype` prefix. </br>
+❌ Bad example: `prototype-auto-resize`: lacks the version suffix. </br>
+❌ Bad example: `prototype-auto-resize-0-0`: feature name ends with a single number.
 
-Here is our [guidelines and process](./documentation/experimental-features.md) to implement and publish an experimental feature.
+Steps to create a prototype:
+
+1. In your terminal, go to the last commit of your branch (the one you want to provide as a prototype).
+2. Create a tag following the convention: `git tag prototype-X-Y`
+3. Run Meilisearch and check that its launch summary features a line: `Prototype: prototype-X-Y` (you may need to switch branches and back after tagging for this to work).
+3. Push the tag: `git push origin prototype-X-Y`
+4. Check the [Docker CI](https://github.com/meilisearch/meilisearch/actions/workflows/publish-docker-images.yml) is now running.
+
+🐳 Once the CI has finished to run (~1h30), a Docker image named `prototype-X-Y` will be available on [DockerHub](https://hub.docker.com/repository/docker/getmeili/meilisearch/general). People can use it with the following command: `docker run -p 7700:7700 -v $(pwd)/meili_data:/meili_data getmeili/meilisearch:prototype-X-Y`. <br>
+More information about [how to run Meilisearch with Docker](https://docs.meilisearch.com/learn/cookbooks/docker.html#download-meilisearch-with-docker).
+
+⚙️ However, no binaries will be created. If the users do not use Docker, they can go to the `prototype-X-Y` tag in the Meilisearch repository and compile from the source code.
+
+⚠️ When sharing a prototype with users, remind them to not use it in production. Prototypes are solely for test purposes.
 
 ### Release assets
 

Cargo.toml

@@ -1,33 +1,24 @@
 [workspace]
 resolver = "2"
 members = [
-    "crates/meilisearch",
-    "crates/meilitool",
-    "crates/meilisearch-types",
-    "crates/meilisearch-auth",
-    "crates/meili-snap",
-    "crates/index-scheduler",
-    "crates/dump",
-    "crates/file-store",
-    "crates/permissive-json-pointer",
-    "crates/milli",
-    "crates/filter-parser",
-    "crates/flatten-serde-json",
-    "crates/json-depth-checker",
-    "crates/benchmarks",
-    "crates/fuzzers",
-    "crates/tracing-trace",
-    "crates/xtask",
-    "crates/build-info",
-    "crates/openapi-generator",
+    "meilisearch",
+    "meilisearch-types",
+    "meilisearch-auth",
+    "meili-snap",
+    "index-scheduler",
+    "dump",
+    "file-store",
+    "permissive-json-pointer",
+    "milli",
+    "filter-parser",
+    "flatten-serde-json",
+    "json-depth-checker",
+    "benchmarks"
 ]
 
 [workspace.package]
-version = "1.22.3"
-authors = [
-    "Quentin de Quelen <quentin@dequelen.me>",
-    "Clément Renault <clement@meilisearch.com>",
-]
+version = "1.0.0"
+authors = ["Quentin de Quelen <quentin@dequelen.me>", "Clément Renault <clement@meilisearch.com>"]
 description = "Meilisearch HTTP server"
 homepage = "https://meilisearch.com"
 readme = "README.md"
@@ -37,12 +28,6 @@ license = "MIT"
 [profile.release]
 codegen-units = 1
 
-# We now compile heed without the NDEBUG define for better performance.
-# However, we still enable debug assertions for a better detection of
-# disk corruption on the cloud or in OSS.
-[profile.release.package.heed]
-debug-assertions = true
-
 [profile.dev.package.flate2]
 opt-level = 3
 
@@ -50,3 +35,24 @@ opt-level = 3
 opt-level = 3
 [profile.dev.package.roaring]
 opt-level = 3
+
+[profile.dev.package.lindera-ipadic-builder]
+opt-level = 3
+[profile.dev.package.encoding]
+opt-level = 3
+[profile.dev.package.yada]
+opt-level = 3
+
+[profile.release.package.lindera-ipadic-builder]
+opt-level = 3
+[profile.release.package.encoding]
+opt-level = 3
+[profile.release.package.yada]
+opt-level = 3
+
+[profile.bench.package.lindera-ipadic-builder]
+opt-level = 3
+[profile.bench.package.encoding]
+opt-level = 3
+[profile.bench.package.yada]
+opt-level = 3

Dockerfile

@@ -1,37 +1,34 @@
 # Compile
-FROM    rust:1.89-alpine3.20 AS compiler
+FROM    rust:bullseye AS compiler
 
-RUN     apk add -q --no-cache build-base openssl-dev
-
-WORKDIR /
+WORKDIR /meilisearch
 
 ARG     COMMIT_SHA
 ARG     COMMIT_DATE
 ARG     GIT_TAG
-ENV     VERGEN_GIT_SHA=${COMMIT_SHA} VERGEN_GIT_COMMIT_TIMESTAMP=${COMMIT_DATE} VERGEN_GIT_DESCRIBE=${GIT_TAG}
+ENV     VERGEN_GIT_SHA=${COMMIT_SHA} VERGEN_GIT_COMMIT_TIMESTAMP=${COMMIT_DATE} VERGEN_GIT_SEMVER_LIGHTWEIGHT=${GIT_TAG}
 ENV     RUSTFLAGS="-C target-feature=-crt-static"
 
 COPY    . .
 RUN     set -eux; \
-        apkArch="$(apk --print-arch)"; \
-        if [ "$apkArch" = "aarch64" ]; then \
+        arch="$(dpkg --print-architecture)"; \
+        if [ "$arch" = "aarch64" ]; then \
             export JEMALLOC_SYS_WITH_LG_PAGE=16; \
         fi && \
-        cargo build --release -p meilisearch -p meilitool
+        cargo build --release
 
 # Run
-FROM    alpine:3.20
-LABEL   org.opencontainers.image.source="https://github.com/meilisearch/meilisearch"
+FROM    debian:11.6
 
 ENV     MEILI_HTTP_ADDR 0.0.0.0:7700
 ENV     MEILI_SERVER_PROVIDER docker
 
-RUN     apk add -q --no-cache libgcc tini curl
+RUN     apt update -q \
+        && apt install -q -y tini
 
-# add meilisearch and meilitool to the `/bin` so you can run it from anywhere
-# and it's easy to find.
-COPY    --from=compiler /target/release/meilisearch /bin/meilisearch
-COPY    --from=compiler /target/release/meilitool /bin/meilitool
+# add meilisearch to the `/bin` so you can run it from anywhere and it's easy
+# to find.
+COPY    --from=compiler /meilisearch/target/release/meilisearch /bin/meilisearch
 # To stay compatible with the older version of the container (pre v0.27.0) we're
 # going to symlink the meilisearch binary in the path to `/meilisearch`
 RUN     ln -s /bin/meilisearch /meilisearch

LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2019-2025 Meili SAS
+Copyright (c) 2019-2022 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
@@ -19,11 +19,3 @@ AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 SOFTWARE.
-
----
-
-🔒 Meilisearch Enterprise Edition (EE)
-
-Certain parts of this codebase are not licensed under the MIT license and governed by the Business Source License 1.1.
-
-See the LICENSE-EE file for details.

LICENSE-EE

@@ -1,67 +0,0 @@
-Business Source License 1.1 – Adapted for Meili SAS
-This license is based on the Business Source License version 1.1, as published by MariaDB Corporation Ab.
-
-Parameters
-
-Licensor: Meili SAS
-
-Licensed Work: Any file explicitly marked as “Enterprise Edition (EE)” or “governed by the Business Source License” residing in enterprise_editions modules/folders.
-
-Additional Use Grant:
-You may use, modify, and distribute the Licensed Work for non-production purposes only, such as testing, development, or evaluation.
-
-Production use of the Licensed Work requires a commercial license agreement with Meilisearch. Contact bonjour@meilisearch.com for licensing.
-
-Change License: MIT
-
-Change Date: Four years from the date the Licensed Work is published.
-
-This License does not apply to any code outside of the Licensed Work, which remains under the MIT license.
-
-For information about alternative licensing arrangements for the Licensed Work,
-please contact bonjour@meilisearch.com or sales@meilisearch.com.
-
-Notice
-
-Business Source License 1.1
-
-Terms
-
-The Licensor hereby grants you the right to copy, modify, create derivative
-works, redistribute, and make non-production use of the Licensed Work. The
-Licensor may make an Additional Use Grant, above, permitting limited production use.
-
-Effective on the Change Date, or the fourth anniversary of the first publicly
-available distribution of a specific version of the Licensed Work under this
-License, whichever comes first, the Licensor hereby grants you rights under
-the terms of the Change License, and the rights granted in the paragraph
-above terminate.
-
-If your use of the Licensed Work does not comply with the requirements
-currently in effect as described in this License, you must purchase a
-commercial license from the Licensor, its affiliated entities, or authorized
-resellers, or you must refrain from using the Licensed Work.
-
-All copies of the original and modified Licensed Work, and derivative works
-of the Licensed Work, are subject to this License. This License applies
-separately for each version of the Licensed Work and the Change Date may vary
-for each version of the Licensed Work released by Licensor.
-
-You must conspicuously display this License on each original or modified copy
-of the Licensed Work. If you receive the Licensed Work in original or
-modified form from a third party, the terms and conditions set forth in this
-License apply to your use of that work.
-
-Any use of the Licensed Work in violation of this License will automatically
-terminate your rights under this License for the current and all other
-versions of the Licensed Work.
-
-This License does not grant you any right in any trademark or logo of
-Licensor or its affiliates (provided that you may use a trademark or logo of
-Licensor as expressly required by this License).
-
-TO THE EXTENT PERMITTED BY APPLICABLE LAW, THE LICENSED WORK IS PROVIDED ON
-AN "AS IS" BASIS. LICENSOR HEREBY DISCLAIMS ALL WARRANTIES AND CONDITIONS,
-EXPRESS OR IMPLIED, INCLUDING (WITHOUT LIMITATION) WARRANTIES OF
-MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, NON-INFRINGEMENT, AND
-TITLE.

PROFILING.md

@@ -1,19 +0,0 @@
-# Profiling Meilisearch
-
-Search engine technologies are complex pieces of software that require thorough profiling tools. We chose to use [Puffin](https://github.com/EmbarkStudios/puffin), which the Rust gaming industry uses extensively. You can export and import the profiling reports using the top bar's _File_ menu options [in Puffin Viewer](https://github.com/embarkstudios/puffin#ui).
-
-![An example profiling with Puffin viewer](assets/profiling-example.png)
-
-## Profiling the Indexing Process
-
-When you enable [the `exportPuffinReports` experimental feature](https://www.meilisearch.com/docs/learn/experimental/overview) of Meilisearch, Puffin reports with the `.puffin` extension will be automatically exported to disk. When this option is enabled, the engine will automatically create a "frame" whenever it executes the `IndexScheduler::tick` method.
-
-[Puffin Viewer](https://github.com/EmbarkStudios/puffin/tree/main/puffin_viewer) is used to analyze the reports. Those reports show areas where Meilisearch spent time during indexing.
-
-Another piece of advice on the Puffin viewer UI interface is to consider the _Merge children with same ID_ option. It can hide the exact actual timings at which events were sent. Please turn it off when you see strange gaps on the Flamegraph. It can help.
-
-## Profiling the Search Process
-
-We still need to take the time to profile the search side of the engine with Puffin. It would require time to profile the filtering phase, query parsing, creation, and execution. We could even profile the Actix HTTP server.
-
-The only issue we see is the framing system. Puffin requires a global frame-based profiling phase, which collides with Meilisearch's ability to accept and answer multiple requests on different threads simultaneously.

README.md

@@ -1,125 +1,94 @@
 <p align="center">
-  <a href="https://www.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=logo#gh-light-mode-only" target="_blank">
-    <img src="assets/meilisearch-logo-light.svg?sanitize=true#gh-light-mode-only">
-  </a>
-  <a href="https://www.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=logo#gh-dark-mode-only" target="_blank">
-    <img src="assets/meilisearch-logo-dark.svg?sanitize=true#gh-dark-mode-only">
-  </a>
+  <img src="assets/meilisearch-logo-light.svg?sanitize=true#gh-light-mode-only">
+  <img src="assets/meilisearch-logo-dark.svg?sanitize=true#gh-dark-mode-only">
 </p>
 
 <h4 align="center">
-  <a href="https://www.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=nav">Website</a> |
+  <a href="https://www.meilisearch.com">Website</a> |
   <a href="https://roadmap.meilisearch.com/tabs/1-under-consideration">Roadmap</a> |
-  <a href="https://www.meilisearch.com/pricing?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=nav">Meilisearch Cloud</a> |
-  <a href="https://blog.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=nav">Blog</a> |
-  <a href="https://www.meilisearch.com/docs?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=nav">Documentation</a> |
-  <a href="https://www.meilisearch.com/docs/faq?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=nav">FAQ</a> |
-  <a href="https://discord.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=nav">Discord</a>
+  <a href="https://blog.meilisearch.com">Blog</a> |
+  <a href="https://docs.meilisearch.com">Documentation</a> |
+  <a href="https://docs.meilisearch.com/faq/">FAQ</a> |
+  <a href="https://discord.meilisearch.com">Discord</a>
 </h4>
 
 <p align="center">
   <a href="https://deps.rs/repo/github/meilisearch/meilisearch"><img src="https://deps.rs/repo/github/meilisearch/meilisearch/status.svg" alt="Dependency status"></a>
   <a href="https://github.com/meilisearch/meilisearch/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-MIT-informational" alt="License"></a>
-  <a href="https://github.com/meilisearch/meilisearch/queue"><img alt="Merge Queues enabled" src="https://img.shields.io/badge/Merge_Queues-enabled-%2357cf60?logo=github"></a>
+  <a href="https://app.bors.tech/repositories/26457"><img src="https://bors.tech/images/badge_small.svg" alt="Bors enabled"></a>
 </p>
 
 <p align="center">⚡ A lightning-fast search engine that fits effortlessly into your apps, websites, and workflow 🔍</p>
 
-[Meilisearch](https://www.meilisearch.com?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=intro) helps you shape a delightful search experience in a snap, offering features that work out of the box to speed up your workflow.
+Meilisearch helps you shape a delightful search experience in a snap, offering features that work out-of-the-box to speed up your workflow.
 
 <p align="center" name="demo">
-  <a href="https://where2watch.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demo-gif#gh-light-mode-only" target="_blank">
+  <a href="https://where2watch.meilisearch.com/#gh-light-mode-only" target="_blank">
     <img src="assets/demo-light.gif#gh-light-mode-only" alt="A bright colored application for finding movies screening near the user">
   </a>
-  <a href="https://where2watch.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demo-gif#gh-dark-mode-only" target="_blank">
+  <a href="https://where2watch.meilisearch.com/#gh-dark-mode-only" target="_blank">
     <img src="assets/demo-dark.gif#gh-dark-mode-only" alt="A dark colored application for finding movies screening near the user">
   </a>
 </p>
 
-## 🖥 Examples
-
-- [**Movies**](https://where2watch.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=organization) — An application to help you find streaming platforms to watch movies using [hybrid search](https://www.meilisearch.com/solutions/hybrid-search?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos).
-- [**Ecommerce**](https://ecommerce.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos) — Ecommerce website using disjunctive [facets](https://www.meilisearch.com/docs/learn/fine_tuning_results/faceted_search?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos), range and rating filtering, and pagination.
-- [**Songs**](https://music.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos) — Search through 47 million of songs.
-- [**SaaS**](https://saas.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos) — Search for contacts, deals, and companies in this [multi-tenant](https://www.meilisearch.com/docs/learn/security/multitenancy_tenant_tokens?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos) CRM application.
-
-See the list of all our example apps in our [demos repository](https://github.com/meilisearch/demos).
+🔥 [**Try it!**](https://where2watch.meilisearch.com/) 🔥
 
 ## ✨ Features
-- **Hybrid search:** Combine the best of both [semantic](https://www.meilisearch.com/docs/learn/experimental/vector_search?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features) & full-text search to get the most relevant results
-- **Search-as-you-type:** Find & display results in less than 50 milliseconds to provide an intuitive experience
-- **[Typo tolerance](https://www.meilisearch.com/docs/learn/relevancy/typo_tolerance_settings?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/relevancy/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
-- **[Multi-Tenancy](https://www.meilisearch.com/docs/learn/security/multitenancy_tenant_tokens?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** personalize search results for any number of application tenants
+
+- **Search-as-you-type:** find search results in less than 50 milliseconds
+- **[Typo tolerance](https://docs.meilisearch.com/learn/getting_started/customizing_relevancy.html#typo-tolerance):** get relevant matches even when queries contain typos and misspellings
+- **[Filtering and faceted search](https://docs.meilisearch.com/learn/advanced/filtering_and_faceted_search.html):** enhance your user's search experience with custom filters and build a faceted search interface in a few lines of code
+- **[Sorting](https://docs.meilisearch.com/learn/advanced/sorting.html):** sort results based on price, date, or pretty much anything else your users need
+- **[Synonym support](https://docs.meilisearch.com/learn/getting_started/customizing_relevancy.html#synonyms):** configure synonyms to include more relevant content in your search results
+- **[Geosearch](https://docs.meilisearch.com/learn/advanced/geosearch.html):** filter and sort documents based on geographic data
+- **[Extensive language support](https://docs.meilisearch.com/learn/what_is_meilisearch/language.html):** search datasets in any language, with optimized support for Chinese, Japanese, Hebrew, and languages using the Latin alphabet
+- **[Security management](https://docs.meilisearch.com/learn/security/master_api_keys.html):** control which users can access what data with API keys that allow fine-grained permissions handling
+- **[Multi-Tenancy](https://docs.meilisearch.com/learn/security/tenant_tokens.html):** personalize search results for any number of application tenants
 - **Highly Customizable:** customize Meilisearch to your specific needs or use our out-of-the-box and hassle-free presets
-- **[RESTful API](https://www.meilisearch.com/docs/reference/api/overview?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** integrate Meilisearch in your technical stack with our plugins and SDKs
-- **AI-ready:** works out of the box with [langchain](https://www.meilisearch.com/with/langchain) and the [model context protocol](https://github.com/meilisearch/meilisearch-mcp)
+- **[RESTful API](https://docs.meilisearch.com/reference/api/overview.html):** integrate Meilisearch in your technical stack with our plugins and SDKs
 - **Easy to install, deploy, and maintain**
 
 ## 📖 Documentation
 
-You can consult Meilisearch's documentation at [meilisearch.com/docs](https://www.meilisearch.com/docs/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=docs).
+You can consult Meilisearch's documentation at [https://docs.meilisearch.com](https://docs.meilisearch.com/).
 
 ## 🚀 Getting started
 
-For basic instructions on how to set up Meilisearch, add documents to an index, and search for documents, take a look at our [documentation](https://www.meilisearch.com/docs?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=get-started) guide.
+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://docs.meilisearch.com/learn/getting_started/quick_start.html) guide.
 
-## 🌍 Supercharge your Meilisearch experience
+You may also want to check out [Meilisearch 101](https://docs.meilisearch.com/learn/getting_started/filtering_and_sorting.html) for an introduction to some of Meilisearch's most popular features.
 
-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). Additional features include analytics & monitoring in many regions around the world. No credit card is required.
+## ☁️ Meilisearch cloud
+
+Let us manage your infrastructure so you can focus on integrating a great search experience. Try [Meilisearch Cloud](https://meilisearch.com/pricing) today.
 
 ## 🧰 SDKs & integration tools
 
 Install one of our SDKs in your project for seamless integration between Meilisearch and your favorite language or framework!
 
-Take a look at the complete [Meilisearch integration list](https://www.meilisearch.com/docs/learn/what_is_meilisearch/sdks?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=sdks-link).
+Take a look at the complete [Meilisearch integration list](https://docs.meilisearch.com/learn/what_is_meilisearch/sdks.html).
 
-[![Logos belonging to different languages and frameworks supported by Meilisearch, including React, Ruby on Rails, Go, Rust, and PHP](assets/integrations.png)](https://www.meilisearch.com/docs/learn/what_is_meilisearch/sdks?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=sdks-logos)
+[![Logos belonging to different languages and frameworks supported by Meilisearch, including React, Ruby on Rails, Go, Rust, and PHP](assets/integrations.png)](https://docs.meilisearch.com/learn/what_is_meilisearch/sdks.html)
 
 ## ⚙️ Advanced usage
 
-Experienced users will want to keep our [API Reference](https://www.meilisearch.com/docs/reference/api/overview?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=advanced) close at hand.
+Experienced users will want to keep our [API Reference](https://docs.meilisearch.com/reference/api) close at hand.
 
-We also offer a wide range of dedicated guides to all Meilisearch features, such as [filtering](https://www.meilisearch.com/docs/learn/fine_tuning_results/filtering?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=advanced), [sorting](https://www.meilisearch.com/docs/learn/fine_tuning_results/sorting?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=advanced), [geosearch](https://www.meilisearch.com/docs/learn/fine_tuning_results/geosearch?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=advanced), [API keys](https://www.meilisearch.com/docs/learn/security/master_api_keys?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=advanced), and [tenant tokens](https://www.meilisearch.com/docs/learn/security/tenant_tokens?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=advanced).
+We also offer a wide range of dedicated guides to all Meilisearch features, such as [filtering](https://docs.meilisearch.com/learn/advanced/filtering_and_faceted_search.html), [sorting](https://docs.meilisearch.com/learn/advanced/sorting.html), [geosearch](https://docs.meilisearch.com/learn/advanced/geosearch.html), [API keys](https://docs.meilisearch.com/learn/security/master_api_keys.html), and [tenant tokens](https://docs.meilisearch.com/learn/security/tenant_tokens.html).
 
-Finally, for more in-depth information, refer to our articles explaining fundamental Meilisearch concepts such as [documents](https://www.meilisearch.com/docs/learn/core_concepts/documents?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=advanced) and [indexes](https://www.meilisearch.com/docs/learn/core_concepts/indexes?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=advanced).
-
-## 🧾 Editions & Licensing
-
-Meilisearch is available in two editions:
-
-### 🧪 Community Edition (CE)
-
-- Fully open source under the [MIT license](./LICENSE)
-- Core search engine with fast and relevant full-text, semantic or hybrid search
-- Free to use for anyone, including commercial usage
-
-### 🏢 Enterprise Edition (EE)
-
-- Includes advanced features such as:
-  - Sharding
-- Governed by a [commercial license](./LICENSE-EE) or the [Business Source License 1.1](https://mariadb.com/bsl11)
-- Not allowed in production without a commercial agreement with Meilisearch.
-  - You may use, modify, and distribute the Licensed Work for non-production purposes only, such as testing, development, or evaluation.
-
-Want access to Enterprise features? → Contact us at [sales@meilisearch.com](maito:sales@meilisearch.com).
+Finally, for more in-depth information, refer to our articles explaining fundamental Meilisearch concepts such as [documents](https://docs.meilisearch.com/learn/core_concepts/documents.html) and [indexes](https://docs.meilisearch.com/learn/core_concepts/indexes.html).
 
 ## 📊 Telemetry
 
-Meilisearch collects **anonymized** user data to help us improve our product. You can [deactivate this](https://www.meilisearch.com/docs/learn/what_is_meilisearch/telemetry?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=telemetry#how-to-disable-data-collection) whenever you want.
+Meilisearch collects **anonymized** data from users to help us improve our product. You can [deactivate this](https://docs.meilisearch.com/learn/what_is_meilisearch/telemetry.html#how-to-disable-data-collection) whenever you want.
 
-To request deletion of collected data, please write to us at [privacy@meilisearch.com](mailto:privacy@meilisearch.com). Remember to include your `Instance UID` in the message, as this helps us quickly find and delete your data.
+To request deletion of collected data, please write to us at [privacy@meilisearch.com](mailto:privacy@meilisearch.com). Don't forget to include your `Instance UID` in the message, as this helps us quickly find and delete your data.
 
-If you want to know more about the kind of data we collect and what we use it for, check the [telemetry section](https://www.meilisearch.com/docs/learn/what_is_meilisearch/telemetry?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=telemetry#how-to-disable-data-collection) of our documentation.
+If you want to know more about the kind of data we collect and what we use it for, check the [telemetry section](https://docs.meilisearch.com/learn/what_is_meilisearch/telemetry.html) of our documentation.
 
 ## 📫 Get in touch!
 
-Meilisearch is a search engine created by [Meili](https://www.meilisearch.com/careers), a software development company headquartered in France and with team members all over the world. Want to know more about us? [Check out our blog!](https://blog.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=contact)
+Meilisearch is a search engine created by [Meili](https://www.welcometothejungle.com/en/companies/meilisearch), a software development company based in France and with team members all over the world. Want to know more about us? [Check out our blog!](https://blog.meilisearch.com/)
 
 🗞 [Subscribe to our newsletter](https://meilisearch.us2.list-manage.com/subscribe?u=27870f7b71c908a8b359599fb&id=79582d828e) if you don't want to miss any updates! We promise we won't clutter your mailbox: we only send one edition every two months.
 
@@ -127,18 +96,19 @@ Meilisearch is a search engine created by [Meili](https://www.meilisearch.com/ca
 
 - 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.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=contact)
+- Want to be part of our Discord community? [Join us!](https://discord.gg/meilisearch)
+- For everything else, please check [this page listing some of the other places where you can find us](https://docs.meilisearch.com/learn/what_is_meilisearch/contact.html)
 
 Thank you for your support!
 
 ## 👩‍💻 Contributing
 
-Meilisearch is, and will always be, open-source! If you want to contribute to the project, please look at [our contribution guidelines](CONTRIBUTING.md).
+Meilisearch is, and will always be, open-source! If you want to contribute to the project, please take a look at [our contribution guidelines](CONTRIBUTING.md).
 
 ## 📦 Versioning
 
-Meilisearch releases and their associated binaries are available on the project's [releases page](https://github.com/meilisearch/meilisearch/releases).
+Meilisearch releases and their associated binaries are available [in this GitHub page](https://github.com/meilisearch/meilisearch/releases).
 
-The binaries are versioned following [SemVer conventions](https://semver.org/). To know more, read our [versioning policy](./documentation/versioning-policy.md).
+The binaries are versioned following [SemVer conventions](https://semver.org/). To know more, read our [versioning policy](https://github.com/meilisearch/engine-team/blob/main/resources/versioning-policy.md).
 
 Differently from the binaries, crates in this repository are not currently available on [crates.io](https://crates.io/) and do not follow [SemVer conventions](https://semver.org).

assets/prometheus-basic-scraper.yml

@@ -1,19 +0,0 @@
-global:
-  scrape_interval:     15s # By default, scrape targets every 15 seconds.
-
-  # Attach these labels to any time series or alerts when communicating with
-  # external systems (federation, remote storage, Alertmanager).
-  external_labels:
-    monitor: 'codelab-monitor'
-
-# A scrape configuration containing exactly one endpoint to scrape:
-# Here it's Prometheus itself.
-scrape_configs:
-  # The job name is added as a label `job=<job_name>` to any timeseries scraped from this config.
-  - job_name: 'meilisearch'
-
-    # Override the global default and scrape targets from this job every 5 seconds.
-    scrape_interval: 5s
-
-    static_configs:
-      - targets: ['localhost:7700']

benchmarks/Cargo.toml

@@ -11,30 +11,27 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-anyhow = "1.0.98"
-bumpalo = "3.18.1"
-csv = "1.3.1"
-memmap2 = "0.9.7"
-milli = { path = "../milli" }
-mimalloc = { version = "0.1.47", default-features = false }
-serde_json = { version = "1.0.140", features = ["preserve_order"] }
-tempfile = "3.20.0"
+anyhow = "1.0.65"
+csv = "1.1.6"
+milli = { path = "../milli", default-features = false }
+mimalloc = { version = "0.1.29", default-features = false }
+serde_json = { version = "1.0.85", features = ["preserve_order"] }
 
 [dev-dependencies]
-criterion = { version = "0.6.0", features = ["html_reports"] }
+criterion = { version = "0.4.0", features = ["html_reports"] }
 rand = "0.8.5"
 rand_chacha = "0.3.1"
-roaring = "0.10.12"
+roaring = "0.10.1"
 
 [build-dependencies]
-anyhow = "1.0.98"
-bytes = "1.10.1"
-convert_case = "0.8.0"
-flate2 = "1.1.2"
-reqwest = { version = "0.12.20", features = ["blocking", "rustls-tls"], default-features = false }
+anyhow = "1.0.65"
+bytes = "1.2.1"
+convert_case = "0.6.0"
+flate2 = "1.0.24"
+reqwest = { version = "0.11.12", features = ["blocking", "rustls-tls"], default-features = false }
 
 [features]
-default = ["milli/all-tokenizations"]
+default = ["milli/default"]
 
 [[bench]]
 name = "search_songs"
@@ -53,9 +50,5 @@ name = "indexing"
 harness = false
 
 [[bench]]
-name = "sort"
-harness = false
-
-[[bench]]
-name = "filter_starts_with"
+name = "formatting"
 harness = false

benchmarks/README.md

@@ -119,9 +119,9 @@ _[Download the `smol-wiki` dataset](https://milli-benchmarks.fra1.digitaloceansp
 
 ### Movies
 
-`movies` is a really small dataset we uses as our example in the [getting started](https://www.meilisearch.com/docs/learn/getting_started/quick_start)
+`movies` is a really small dataset we uses as our example in the [getting started](https://docs.meilisearch.com/learn/getting_started/)
 
-_[Download the `movies` dataset](https://www.meilisearch.com/movies.json)._
+_[Download the `movies` dataset](https://docs.meilisearch.com/movies.json)._
 
 
 ### All Countries

benchmarks/benches/formatting.rs

@@ -0,0 +1,67 @@
+use std::rc::Rc;
+
+use criterion::{criterion_group, criterion_main};
+use milli::tokenizer::TokenizerBuilder;
+use milli::{FormatOptions, MatcherBuilder, MatchingWord, MatchingWords};
+
+#[global_allocator]
+static ALLOC: mimalloc::MiMalloc = mimalloc::MiMalloc;
+
+struct Conf<'a> {
+    name: &'a str,
+    text: &'a str,
+    matching_words: MatcherBuilder<'a, Vec<u8>>,
+}
+
+fn bench_formatting(c: &mut criterion::Criterion) {
+    #[rustfmt::skip]
+    let confs = &[
+    	Conf {
+    		name: "'the door d'",
+			text: r#"He used to do the door sounds in "Star Trek" with his mouth, phssst, phssst. The MD-11 passenger and cargo doors also tend to behave like electromagnetic apertures, because the doors do not have continuous electrical contact with the door frames around the door perimeter. But Theodor said that the doors don't work."#,
+			matching_words: MatcherBuilder::new(MatchingWords::new(vec![
+	            (vec![Rc::new(MatchingWord::new("t".to_string(), 0, false).unwrap()), Rc::new(MatchingWord::new("he".to_string(), 0, false).unwrap())], vec![0]),
+	            (vec![Rc::new(MatchingWord::new("the".to_string(), 0, false).unwrap())], vec![0]),
+	            (vec![Rc::new(MatchingWord::new("door".to_string(), 1, false).unwrap())], vec![1]),
+	            (vec![Rc::new(MatchingWord::new("do".to_string(), 0, false).unwrap()), Rc::new(MatchingWord::new("or".to_string(), 0, false).unwrap())], vec![0]),
+	            (vec![Rc::new(MatchingWord::new("thedoor".to_string(), 1, false).unwrap())], vec![0, 1]),
+	            (vec![Rc::new(MatchingWord::new("d".to_string(), 0, true).unwrap())], vec![2]),
+	            (vec![Rc::new(MatchingWord::new("thedoord".to_string(), 1, true).unwrap())], vec![0, 1, 2]),
+	            (vec![Rc::new(MatchingWord::new("doord".to_string(), 1, true).unwrap())], vec![1, 2]),
+        	]
+            ), TokenizerBuilder::default().build()),
+		},
+    ];
+
+    let format_options = &[
+        FormatOptions { highlight: false, crop: None },
+        FormatOptions { highlight: true, crop: None },
+        FormatOptions { highlight: false, crop: Some(10) },
+        FormatOptions { highlight: true, crop: Some(10) },
+        FormatOptions { highlight: false, crop: Some(20) },
+        FormatOptions { highlight: true, crop: Some(20) },
+    ];
+
+    for option in format_options {
+        let highlight = if option.highlight { "highlight" } else { "no-highlight" };
+
+        let name = match option.crop {
+            Some(size) => format!("{}-crop({})", highlight, size),
+            None => format!("{}-no-crop", highlight),
+        };
+
+        let mut group = c.benchmark_group(&name);
+        for conf in confs {
+            group.bench_function(conf.name, |b| {
+                b.iter(|| {
+                    let mut matcher = conf.matching_words.build(conf.text);
+                    matcher.format(*option);
+                })
+            });
+        }
+        group.finish();
+    }
+}
+
+criterion_group!(benches, bench_formatting);
+criterion_main!(benches);

benchmarks/benches/search_geo.rs

@@ -3,10 +3,8 @@ mod utils;
 
 use criterion::{criterion_group, criterion_main};
 use milli::update::Settings;
-use milli::FilterableAttributesRule;
 use utils::Conf;
 
-#[cfg(not(windows))]
 #[global_allocator]
 static ALLOC: mimalloc::MiMalloc = mimalloc::MiMalloc;
 
@@ -22,10 +20,8 @@ fn base_conf(builder: &mut Settings) {
         ["name", "alternatenames", "elevation"].iter().map(|s| s.to_string()).collect();
     builder.set_searchable_fields(searchable_fields);
 
-    let filterable_fields = ["_geo", "population", "elevation"]
-        .iter()
-        .map(|s| FilterableAttributesRule::Field(s.to_string()))
-        .collect();
+    let filterable_fields =
+        ["_geo", "population", "elevation"].iter().map(|s| s.to_string()).collect();
     builder.set_filterable_fields(filterable_fields);
 
     let sortable_fields =

benchmarks/benches/search_songs.rs

@@ -3,10 +3,8 @@ mod utils;
 
 use criterion::{criterion_group, criterion_main};
 use milli::update::Settings;
-use milli::FilterableAttributesRule;
 use utils::Conf;
 
-#[cfg(not(windows))]
 #[global_allocator]
 static ALLOC: mimalloc::MiMalloc = mimalloc::MiMalloc;
 
@@ -23,7 +21,7 @@ fn base_conf(builder: &mut Settings) {
 
     let faceted_fields = ["released-timestamp", "duration-float", "genre", "country", "artist"]
         .iter()
-        .map(|s| FilterableAttributesRule::Field(s.to_string()))
+        .map(|s| s.to_string())
         .collect();
     builder.set_filterable_fields(faceted_fields);
 }

benchmarks/benches/search_wiki.rs

@@ -5,7 +5,6 @@ use criterion::{criterion_group, criterion_main};
 use milli::update::Settings;
 use utils::Conf;
 
-#[cfg(not(windows))]
 #[global_allocator]
 static ALLOC: mimalloc::MiMalloc = mimalloc::MiMalloc;
 

benchmarks/benches/utils.rs

@@ -0,0 +1,256 @@
+#![allow(dead_code)]
+
+use std::fs::{create_dir_all, remove_dir_all, File};
+use std::io::{self, BufRead, BufReader, Cursor, Read, Seek};
+use std::num::ParseFloatError;
+use std::path::Path;
+use std::str::FromStr;
+
+use criterion::BenchmarkId;
+use milli::documents::{DocumentsBatchBuilder, DocumentsBatchReader};
+use milli::heed::EnvOpenOptions;
+use milli::update::{
+    IndexDocuments, IndexDocumentsConfig, IndexDocumentsMethod, IndexerConfig, Settings,
+};
+use milli::{Criterion, Filter, Index, Object, TermsMatchingStrategy};
+use serde_json::Value;
+
+pub struct Conf<'a> {
+    /// where we are going to create our database.mmdb directory
+    /// each benchmark will first try to delete it and then recreate it
+    pub database_name: &'a str,
+    /// the dataset to be used, it must be an uncompressed csv
+    pub dataset: &'a str,
+    /// The format of the dataset
+    pub dataset_format: &'a str,
+    pub group_name: &'a str,
+    pub queries: &'a [&'a str],
+    /// here you can change which criterion are used and in which order.
+    /// - if you specify something all the base configuration will be thrown out
+    /// - if you don't specify anything (None) the default configuration will be kept
+    pub criterion: Option<&'a [&'a str]>,
+    /// the last chance to configure your database as you want
+    pub configure: fn(&mut Settings),
+    pub filter: Option<&'a str>,
+    pub sort: Option<Vec<&'a str>>,
+    /// enable or disable the optional words on the query
+    pub optional_words: bool,
+    /// primary key, if there is None we'll auto-generate docids for every documents
+    pub primary_key: Option<&'a str>,
+}
+
+impl Conf<'_> {
+    pub const BASE: Self = Conf {
+        database_name: "benches.mmdb",
+        dataset_format: "csv",
+        dataset: "",
+        group_name: "",
+        queries: &[],
+        criterion: None,
+        configure: |_| (),
+        filter: None,
+        sort: None,
+        optional_words: true,
+        primary_key: None,
+    };
+}
+
+pub fn base_setup(conf: &Conf) -> Index {
+    match remove_dir_all(conf.database_name) {
+        Ok(_) => (),
+        Err(e) if e.kind() == std::io::ErrorKind::NotFound => (),
+        Err(e) => panic!("{}", e),
+    }
+    create_dir_all(conf.database_name).unwrap();
+
+    let mut options = EnvOpenOptions::new();
+    options.map_size(100 * 1024 * 1024 * 1024); // 100 GB
+    options.max_readers(10);
+    let index = Index::new(options, conf.database_name).unwrap();
+
+    let config = IndexerConfig::default();
+    let mut wtxn = index.write_txn().unwrap();
+    let mut builder = Settings::new(&mut wtxn, &index, &config);
+
+    if let Some(primary_key) = conf.primary_key {
+        builder.set_primary_key(primary_key.to_string());
+    }
+
+    if let Some(criterion) = conf.criterion {
+        builder.reset_filterable_fields();
+        builder.reset_criteria();
+        builder.reset_stop_words();
+
+        let criterion = criterion.iter().map(|s| Criterion::from_str(s).unwrap()).collect();
+        builder.set_criteria(criterion);
+    }
+
+    (conf.configure)(&mut builder);
+
+    builder.execute(|_| (), || false).unwrap();
+    wtxn.commit().unwrap();
+
+    let config = IndexerConfig::default();
+    let mut wtxn = index.write_txn().unwrap();
+    let indexing_config = IndexDocumentsConfig {
+        autogenerate_docids: conf.primary_key.is_none(),
+        update_method: IndexDocumentsMethod::ReplaceDocuments,
+        ..Default::default()
+    };
+    let builder =
+        IndexDocuments::new(&mut wtxn, &index, &config, indexing_config, |_| (), || false).unwrap();
+    let documents = documents_from(conf.dataset, conf.dataset_format);
+    let (builder, user_error) = builder.add_documents(documents).unwrap();
+    user_error.unwrap();
+    builder.execute().unwrap();
+    wtxn.commit().unwrap();
+
+    index
+}
+
+pub fn run_benches(c: &mut criterion::Criterion, confs: &[Conf]) {
+    for conf in confs {
+        let index = base_setup(conf);
+
+        let file_name = Path::new(conf.dataset).file_name().and_then(|f| f.to_str()).unwrap();
+        let name = format!("{}: {}", file_name, conf.group_name);
+        let mut group = c.benchmark_group(&name);
+
+        for &query in conf.queries {
+            group.bench_with_input(BenchmarkId::from_parameter(query), &query, |b, &query| {
+                b.iter(|| {
+                    let rtxn = index.read_txn().unwrap();
+                    let mut search = index.search(&rtxn);
+                    search.query(query).terms_matching_strategy(TermsMatchingStrategy::default());
+                    if let Some(filter) = conf.filter {
+                        let filter = Filter::from_str(filter).unwrap().unwrap();
+                        search.filter(filter);
+                    }
+                    if let Some(sort) = &conf.sort {
+                        let sort = sort.iter().map(|sort| sort.parse().unwrap()).collect();
+                        search.sort_criteria(sort);
+                    }
+                    let _ids = search.execute().unwrap();
+                });
+            });
+        }
+        group.finish();
+
+        index.prepare_for_closing().wait();
+    }
+}
+
+pub fn documents_from(filename: &str, filetype: &str) -> DocumentsBatchReader<impl BufRead + Seek> {
+    let reader = File::open(filename)
+        .unwrap_or_else(|_| panic!("could not find the dataset in: {}", filename));
+    let reader = BufReader::new(reader);
+    let documents = match filetype {
+        "csv" => documents_from_csv(reader).unwrap(),
+        "json" => documents_from_json(reader).unwrap(),
+        "jsonl" => documents_from_jsonl(reader).unwrap(),
+        otherwise => panic!("invalid update format {:?}", otherwise),
+    };
+    DocumentsBatchReader::from_reader(Cursor::new(documents)).unwrap()
+}
+
+fn documents_from_jsonl(reader: impl BufRead) -> anyhow::Result<Vec<u8>> {
+    let mut documents = DocumentsBatchBuilder::new(Vec::new());
+
+    for result in serde_json::Deserializer::from_reader(reader).into_iter::<Object>() {
+        let object = result?;
+        documents.append_json_object(&object)?;
+    }
+
+    documents.into_inner().map_err(Into::into)
+}
+
+fn documents_from_json(reader: impl BufRead) -> anyhow::Result<Vec<u8>> {
+    let mut documents = DocumentsBatchBuilder::new(Vec::new());
+
+    documents.append_json_array(reader)?;
+
+    documents.into_inner().map_err(Into::into)
+}
+
+fn documents_from_csv(reader: impl BufRead) -> anyhow::Result<Vec<u8>> {
+    let csv = csv::Reader::from_reader(reader);
+
+    let mut documents = DocumentsBatchBuilder::new(Vec::new());
+    documents.append_csv(csv)?;
+
+    documents.into_inner().map_err(Into::into)
+}
+
+enum AllowedType {
+    String,
+    Number,
+}
+
+fn parse_csv_header(header: &str) -> (String, AllowedType) {
+    // if there are several separators we only split on the last one.
+    match header.rsplit_once(':') {
+        Some((field_name, field_type)) => match field_type {
+            "string" => (field_name.to_string(), AllowedType::String),
+            "number" => (field_name.to_string(), AllowedType::Number),
+            // we may return an error in this case.
+            _otherwise => (header.to_string(), AllowedType::String),
+        },
+        None => (header.to_string(), AllowedType::String),
+    }
+}
+
+struct CSVDocumentDeserializer<R>
+where
+    R: Read,
+{
+    documents: csv::StringRecordsIntoIter<R>,
+    headers: Vec<(String, AllowedType)>,
+}
+
+impl<R: Read> CSVDocumentDeserializer<R> {
+    fn from_reader(reader: R) -> io::Result<Self> {
+        let mut records = csv::Reader::from_reader(reader);
+
+        let headers = records.headers()?.into_iter().map(parse_csv_header).collect();
+
+        Ok(Self { documents: records.into_records(), headers })
+    }
+}
+
+impl<R: Read> Iterator for CSVDocumentDeserializer<R> {
+    type Item = anyhow::Result<Object>;
+
+    fn next(&mut self) -> Option<Self::Item> {
+        let csv_document = self.documents.next()?;
+
+        match csv_document {
+            Ok(csv_document) => {
+                let mut document = Object::new();
+
+                for ((field_name, field_type), value) in
+                    self.headers.iter().zip(csv_document.into_iter())
+                {
+                    let parsed_value: Result<Value, ParseFloatError> = match field_type {
+                        AllowedType::Number => {
+                            value.parse::<f64>().map(Value::from).map_err(Into::into)
+                        }
+                        AllowedType::String => Ok(Value::String(value.to_string())),
+                    };
+
+                    match parsed_value {
+                        Ok(value) => drop(document.insert(field_name.to_string(), value)),
+                        Err(_e) => {
+                            return Some(Err(anyhow::anyhow!(
+                                "Value '{}' is not a valid number",
+                                value
+                            )))
+                        }
+                    }
+                }
+
+                Some(Ok(document))
+            }
+            Err(e) => Some(Err(anyhow::anyhow!("Error parsing csv document: {}", e))),
+        }
+    }
+}

benchmarks/build.rs

@@ -67,7 +67,7 @@ fn main() -> anyhow::Result<()> {
         writeln!(
             &mut manifest_paths_file,
             r#"pub const {}: &str = {:?};"#,
-            dataset.to_case(Case::UpperSnake),
+            dataset.to_case(Case::ScreamingSnake),
             out_file.display(),
         )?;
 

bors.toml

@@ -0,0 +1,11 @@
+status = [
+    'Tests on ubuntu-18.04',
+    'Tests on macos-12',
+    'Tests on windows-2022',
+    'Run Clippy',
+    'Run Rustfmt',
+    'Run tests in debug',
+]
+pr_status = ['Milestone Check']
+# 3 hours timeout
+timeout-sec = 10800

config.toml

@@ -1,134 +1,120 @@
 # This file shows the default configuration of Meilisearch.
-# All variables are defined here: https://www.meilisearch.com/docs/learn/configuration/instance_options#environment-variables
+# All variables are defined here: https://docs.meilisearch.com/learn/configuration/instance_options.html#environment-variables
 
-# Designates the location where database files will be created and retrieved.
-# https://www.meilisearch.com/docs/learn/configuration/instance_options#database-path
 db_path = "./data.ms"
+# Designates the location where database files will be created and retrieved.
+# https://docs.meilisearch.com/learn/configuration/instance_options.html#database-path
 
-# Configures the instance's environment. Value must be either `production` or `development`.
-# https://www.meilisearch.com/docs/learn/configuration/instance_options#environment
 env = "development"
+# Configures the instance's environment. Value must be either `production` or `development`.
+# https://docs.meilisearch.com/learn/configuration/instance_options.html#environment
 
-# The address on which the HTTP server will listen.
 http_addr = "localhost:7700"
+# The address on which the HTTP server will listen.
 
-# Sets the instance's master key, automatically protecting all routes except GET /health.
-# https://www.meilisearch.com/docs/learn/configuration/instance_options#master-key
 # master_key = "YOUR_MASTER_KEY_VALUE"
+# Sets the instance's master key, automatically protecting all routes except GET /health.
+# https://docs.meilisearch.com/learn/configuration/instance_options.html#master-key
 
+# no_analytics = true
 # Deactivates Meilisearch's built-in telemetry when provided.
 # Meilisearch automatically collects data from all instances that do not opt out using this flag.
 # All gathered data is used solely for the purpose of improving Meilisearch, and can be deleted at any time.
-# https://www.meilisearch.com/docs/learn/configuration/instance_options#disable-analytics
-# no_analytics = true
+# https://docs.meilisearch.com/learn/configuration/instance_options.html#disable-analytics
 
-# Sets the maximum size of accepted payloads.
-# https://www.meilisearch.com/docs/learn/configuration/instance_options#payload-limit-size
 http_payload_size_limit = "100 MB"
+# Sets the maximum size of accepted payloads.
+# https://docs.meilisearch.com/learn/configuration/instance_options.html#payload-limit-size
 
+log_level = "INFO"
 # Defines how much detail should be present in Meilisearch's logs.
 # Meilisearch currently supports six log levels, listed in order of increasing verbosity:  `OFF`, `ERROR`, `WARN`, `INFO`, `DEBUG`, `TRACE`
-# https://www.meilisearch.com/docs/learn/configuration/instance_options#log-level
-log_level = "INFO"
+# https://docs.meilisearch.com/learn/configuration/instance_options.html#log-level
 
-# Sets the maximum amount of RAM Meilisearch can use when indexing.
-# https://www.meilisearch.com/docs/learn/configuration/instance_options#max-indexing-memory
 # max_indexing_memory = "2 GiB"
+# Sets the maximum amount of RAM Meilisearch can use when indexing.
+# https://docs.meilisearch.com/learn/configuration/instance_options.html#max-indexing-memory
 
-# Sets the maximum number of threads Meilisearch can use during indexing.
-# https://www.meilisearch.com/docs/learn/configuration/instance_options#max-indexing-threads
 # max_indexing_threads = 4
+# Sets the maximum number of threads Meilisearch can use during indexing.
+# https://docs.meilisearch.com/learn/configuration/instance_options.html#max-indexing-threads
 
 #############
 ### DUMPS ###
 #############
 
-# Sets the directory where Meilisearch will create dump files.
-# https://www.meilisearch.com/docs/learn/configuration/instance_options#dump-directory
 dump_dir = "dumps/"
+# Sets the directory where Meilisearch will create dump files.
+# https://docs.meilisearch.com/learn/configuration/instance_options.html#dump-directory
 
-# Imports the dump file located at the specified path. Path must point to a .dump file.
-# https://www.meilisearch.com/docs/learn/configuration/instance_options#import-dump
 # import_dump = "./path/to/my/file.dump"
+# Imports the dump file located at the specified path. Path must point to a .dump file.
+# https://docs.meilisearch.com/learn/configuration/instance_options.html#import-dump
 
-# Prevents Meilisearch from throwing an error when `import_dump` does not point to a valid dump file.
-# https://www.meilisearch.com/docs/learn/configuration/instance_options#ignore-missing-dump
 ignore_missing_dump = false
+# Prevents Meilisearch from throwing an error when `import_dump` does not point to a valid dump file.
+# https://docs.meilisearch.com/learn/configuration/instance_options.html#ignore-missing-dump
 
-# Prevents a Meilisearch instance with an existing database from throwing an error when using `import_dump`.
-# https://www.meilisearch.com/docs/learn/configuration/instance_options#ignore-dump-if-db-exists
 ignore_dump_if_db_exists = false
+# Prevents a Meilisearch instance with an existing database from throwing an error when using `import_dump`.
+# https://docs.meilisearch.com/learn/configuration/instance_options.html#ignore-dump-if-db-exists
 
 
 #################
 ### SNAPSHOTS ###
 #################
 
+schedule_snapshot = false
 # Enables scheduled snapshots when true, disable when false (the default).
 # If the value is given as an integer, then enables the scheduled snapshot with the passed value as the interval
 # between each snapshot, in seconds.
-# https://www.meilisearch.com/docs/learn/configuration/instance_options#schedule-snapshot-creation
-schedule_snapshot = false
+# https://docs.meilisearch.com/learn/configuration/instance_options.html#schedule-snapshot-creation
 
-# Sets the directory where Meilisearch will store snapshots.
-# https://www.meilisearch.com/docs/learn/configuration/instance_options#snapshot-destination
 snapshot_dir = "snapshots/"
+# Sets the directory where Meilisearch will store snapshots.
+# https://docs.meilisearch.com/learn/configuration/instance_options.html#snapshot-destination
 
-# Launches Meilisearch after importing a previously-generated snapshot at the given filepath.
-# https://www.meilisearch.com/docs/learn/configuration/instance_options#import-snapshot
 # import_snapshot = "./path/to/my/snapshot"
+# Launches Meilisearch after importing a previously-generated snapshot at the given filepath.
+# https://docs.meilisearch.com/learn/configuration/instance_options.html#import-snapshot
 
-# Prevents a Meilisearch instance from throwing an error when `import_snapshot` does not point to a valid snapshot file.
-# https://www.meilisearch.com/docs/learn/configuration/instance_options#ignore-missing-snapshot
 ignore_missing_snapshot = false
+# Prevents a Meilisearch instance from throwing an error when `import_snapshot` does not point to a valid snapshot file.
+# https://docs.meilisearch.com/learn/configuration/instance_options.html#ignore-missing-snapshot
 
-# Prevents a Meilisearch instance with an existing database from throwing an error when using `import_snapshot`.
-# https://www.meilisearch.com/docs/learn/configuration/instance_options#ignore-snapshot-if-db-exists
 ignore_snapshot_if_db_exists = false
+# Prevents a Meilisearch instance with an existing database from throwing an error when using `import_snapshot`.
+# https://docs.meilisearch.com/learn/configuration/instance_options.html#ignore-snapshot-if-db-exists
 
 
 ###########
 ### SSL ###
 ###########
 
-# Enables client authentication in the specified path.
-# https://www.meilisearch.com/docs/learn/configuration/instance_options#ssl-authentication-path
 # ssl_auth_path = "./path/to/root"
+# Enables client authentication in the specified path.
+# https://docs.meilisearch.com/learn/configuration/instance_options.html#ssl-authentication-path
 
-# Sets the server's SSL certificates.
-# https://www.meilisearch.com/docs/learn/configuration/instance_options#ssl-certificates-path
 # ssl_cert_path = "./path/to/certfile"
+# Sets the server's SSL certificates.
+# https://docs.meilisearch.com/learn/configuration/instance_options.html#ssl-certificates-path
 
-# Sets the server's SSL key files.
-# https://www.meilisearch.com/docs/learn/configuration/instance_options#ssl-key-path
 # ssl_key_path = "./path/to/private-key"
+# Sets the server's SSL key files.
+# https://docs.meilisearch.com/learn/configuration/instance_options.html#ssl-key-path
 
-# Sets the server's OCSP file.
-# https://www.meilisearch.com/docs/learn/configuration/instance_options#ssl-ocsp-path
 # ssl_ocsp_path = "./path/to/ocsp-file"
+# Sets the server's OCSP file.
+# https://docs.meilisearch.com/learn/configuration/instance_options.html#ssl-ocsp-path
 
-# Makes SSL authentication mandatory.
-# https://www.meilisearch.com/docs/learn/configuration/instance_options#ssl-require-auth
 ssl_require_auth = false
+# Makes SSL authentication mandatory.
+# https://docs.meilisearch.com/learn/configuration/instance_options.html#ssl-require-auth
 
-# Activates SSL session resumption.
-# https://www.meilisearch.com/docs/learn/configuration/instance_options#ssl-resumption
 ssl_resumption = false
+# Activates SSL session resumption.
+# https://docs.meilisearch.com/learn/configuration/instance_options.html#ssl-resumption
 
-# Activates SSL tickets.
-# https://www.meilisearch.com/docs/learn/configuration/instance_options#ssl-tickets
 ssl_tickets = false
-
-#############################
-### Experimental features ###
-#############################
-
-# Experimental metrics feature. For more information, see: <https://github.com/meilisearch/meilisearch/discussions/3518>
-# Enables the Prometheus metrics on the `GET /metrics` endpoint.
-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
+# Activates SSL tickets.
+# https://docs.meilisearch.com/learn/configuration/instance_options.html#ssl-tickets

crates/benchmarks/benches/filter_starts_with.rs

@@ -1,66 +0,0 @@
-mod datasets_paths;
-mod utils;
-
-use criterion::{criterion_group, criterion_main};
-use milli::update::Settings;
-use milli::FilterableAttributesRule;
-use utils::Conf;
-
-#[cfg(not(windows))]
-#[global_allocator]
-static ALLOC: mimalloc::MiMalloc = mimalloc::MiMalloc;
-
-fn base_conf(builder: &mut Settings) {
-    let displayed_fields = ["geonameid", "name"].iter().map(|s| s.to_string()).collect();
-    builder.set_displayed_fields(displayed_fields);
-
-    let filterable_fields =
-        ["name"].iter().map(|s| FilterableAttributesRule::Field(s.to_string())).collect();
-    builder.set_filterable_fields(filterable_fields);
-}
-
-#[rustfmt::skip]
-const BASE_CONF: Conf = Conf {
-    dataset: datasets_paths::SMOL_ALL_COUNTRIES,
-    dataset_format: "jsonl",
-    queries: &[
-        "",
-    ],
-    configure: base_conf,
-    primary_key: Some("geonameid"),
-    ..Conf::BASE
-};
-
-fn filter_starts_with(c: &mut criterion::Criterion) {
-    #[rustfmt::skip]
-    let confs = &[
-        utils::Conf {
-            group_name: "1 letter",
-            filter: Some("name STARTS WITH e"),
-            ..BASE_CONF
-        },
-
-        utils::Conf {
-            group_name: "2 letters",
-            filter: Some("name STARTS WITH es"),
-            ..BASE_CONF
-        },
-
-        utils::Conf {
-            group_name: "3 letters",
-            filter: Some("name STARTS WITH est"),
-            ..BASE_CONF
-        },
-
-        utils::Conf {
-            group_name: "6 letters",
-            filter: Some("name STARTS WITH estoni"),
-            ..BASE_CONF
-        }
-    ];
-
-    utils::run_benches(c, confs);
-}
-
-criterion_group!(benches, filter_starts_with);
-criterion_main!(benches);

crates/benchmarks/benches/sort.rs

@@ -1,114 +0,0 @@
-//! This benchmark module is used to compare the performance of sorting documents in /search VS /documents
-//!
-//! The tests/benchmarks were designed in the context of a query returning only 20 documents.
-
-mod datasets_paths;
-mod utils;
-
-use criterion::{criterion_group, criterion_main};
-use milli::update::Settings;
-use utils::Conf;
-
-#[cfg(not(windows))]
-#[global_allocator]
-static ALLOC: mimalloc::MiMalloc = mimalloc::MiMalloc;
-
-fn base_conf(builder: &mut Settings) {
-    let displayed_fields =
-        ["geonameid", "name", "asciiname", "alternatenames", "_geo", "population"]
-            .iter()
-            .map(|s| s.to_string())
-            .collect();
-    builder.set_displayed_fields(displayed_fields);
-
-    let sortable_fields =
-        ["_geo", "name", "population", "elevation", "timezone", "modification-date"]
-            .iter()
-            .map(|s| s.to_string())
-            .collect();
-    builder.set_sortable_fields(sortable_fields);
-}
-
-#[rustfmt::skip]
-const BASE_CONF: Conf = Conf {
-    dataset: datasets_paths::SMOL_ALL_COUNTRIES,
-    dataset_format: "jsonl",
-    configure: base_conf,
-    primary_key: Some("geonameid"),
-    queries: &[""],
-    offsets: &[
-        Some((0, 20)), // The most common query in the real world
-        Some((0, 500)), // A query that ranges over many documents
-        Some((980, 20)), // The worst query that could happen in the real world
-        Some((800_000, 20)) // The worst query
-    ],
-    get_documents: true,
-    ..Conf::BASE
-};
-
-fn bench_sort(c: &mut criterion::Criterion) {
-    #[rustfmt::skip]
-    let confs = &[
-        utils::Conf {
-            group_name: "without sort",
-            sort: None,
-            ..BASE_CONF
-        },
-
-        utils::Conf {
-            group_name: "sort on many different values",
-            sort: Some(vec!["name:asc"]),
-            ..BASE_CONF
-        },
-
-        utils::Conf {
-            group_name: "sort on many similar values",
-            sort: Some(vec!["timezone:desc"]),
-            ..BASE_CONF
-        },
-
-        utils::Conf {
-            group_name: "sort on many similar then different values",
-            sort: Some(vec!["timezone:desc", "name:asc"]),
-            ..BASE_CONF
-        },
-
-        utils::Conf {
-            group_name: "sort on many different then similar values",
-            sort: Some(vec!["timezone:desc", "name:asc"]),
-            ..BASE_CONF
-        },
-
-        utils::Conf {
-            group_name: "geo sort",
-            sample_size: Some(10),
-            sort: Some(vec!["_geoPoint(45.4777599, 9.1967508):asc"]),
-            ..BASE_CONF
-        },
-
-        utils::Conf {
-            group_name: "sort on many similar values then geo sort",
-            sample_size: Some(50),
-            sort: Some(vec!["timezone:desc", "_geoPoint(45.4777599, 9.1967508):asc"]),
-            ..BASE_CONF
-        },
-
-        utils::Conf {
-            group_name: "sort on many different values then geo sort",
-            sample_size: Some(50),
-            sort: Some(vec!["name:desc", "_geoPoint(45.4777599, 9.1967508):asc"]),
-            ..BASE_CONF
-        },
-
-        utils::Conf {
-            group_name: "sort on many fields",
-            sort: Some(vec!["population:asc", "name:asc", "elevation:asc", "timezone:asc"]),
-            ..BASE_CONF
-        },
-    ];
-
-    utils::run_benches(c, confs);
-}
-
-criterion_group!(benches, bench_sort);
-criterion_main!(benches);

crates/benchmarks/benches/utils.rs

@@ -1,402 +0,0 @@
-#![allow(dead_code)]
-
-use std::fs::{create_dir_all, remove_dir_all, File};
-use std::io::{self, BufReader, BufWriter, Read};
-use std::path::Path;
-use std::str::FromStr as _;
-
-use anyhow::Context;
-use bumpalo::Bump;
-use criterion::BenchmarkId;
-use memmap2::Mmap;
-use milli::documents::sort::recursive_sort;
-use milli::heed::EnvOpenOptions;
-use milli::progress::Progress;
-use milli::update::new::indexer;
-use milli::update::{IndexerConfig, Settings};
-use milli::vector::RuntimeEmbedders;
-use milli::{Criterion, Filter, Index, Object, TermsMatchingStrategy};
-use serde_json::Value;
-
-pub struct Conf<'a> {
-    /// where we are going to create our database.mmdb directory
-    /// each benchmark will first try to delete it and then recreate it
-    pub database_name: &'a str,
-    /// the dataset to be used, it must be an uncompressed csv
-    pub dataset: &'a str,
-    /// The format of the dataset
-    pub dataset_format: &'a str,
-    pub group_name: &'a str,
-    pub queries: &'a [&'a str],
-    /// here you can change which criterion are used and in which order.
-    /// - if you specify something all the base configuration will be thrown out
-    /// - if you don't specify anything (None) the default configuration will be kept
-    pub criterion: Option<&'a [&'a str]>,
-    /// the last chance to configure your database as you want
-    pub configure: fn(&mut Settings),
-    pub filter: Option<&'a str>,
-    pub sort: Option<Vec<&'a str>>,
-    /// set to skip documents (offset, limit)
-    pub offsets: &'a [Option<(usize, usize)>],
-    /// enable if you want to bench getting documents without querying
-    pub get_documents: bool,
-    /// configure the benchmark sample size
-    pub sample_size: Option<usize>,
-    /// enable or disable the optional words on the query
-    pub optional_words: bool,
-    /// primary key, if there is None we'll auto-generate docids for every documents
-    pub primary_key: Option<&'a str>,
-}
-
-impl Conf<'_> {
-    pub const BASE: Self = Conf {
-        database_name: "benches.mmdb",
-        dataset_format: "csv",
-        dataset: "",
-        group_name: "",
-        queries: &[],
-        criterion: None,
-        configure: |_| (),
-        filter: None,
-        sort: None,
-        offsets: &[None],
-        get_documents: false,
-        sample_size: None,
-        optional_words: true,
-        primary_key: None,
-    };
-}
-
-pub fn base_setup(conf: &Conf) -> Index {
-    match remove_dir_all(conf.database_name) {
-        Ok(_) => (),
-        Err(e) if e.kind() == std::io::ErrorKind::NotFound => (),
-        Err(e) => panic!("{}", e),
-    }
-    create_dir_all(conf.database_name).unwrap();
-
-    let options = EnvOpenOptions::new();
-    let mut options = options.read_txn_without_tls();
-    options.map_size(100 * 1024 * 1024 * 1024); // 100 GB
-    options.max_readers(100);
-    let index = Index::new(options, conf.database_name, true).unwrap();
-
-    let config = IndexerConfig::default();
-    let mut wtxn = index.write_txn().unwrap();
-    let mut builder = Settings::new(&mut wtxn, &index, &config);
-
-    if let Some(primary_key) = conf.primary_key {
-        builder.set_primary_key(primary_key.to_string());
-    }
-
-    if let Some(criterion) = conf.criterion {
-        builder.reset_filterable_fields();
-        builder.reset_criteria();
-        builder.reset_stop_words();
-
-        let criterion = criterion.iter().map(|s| Criterion::from_str(s).unwrap()).collect();
-        builder.set_criteria(criterion);
-    }
-
-    (conf.configure)(&mut builder);
-
-    builder.execute(&|| false, &Progress::default(), Default::default()).unwrap();
-    wtxn.commit().unwrap();
-
-    let config = IndexerConfig::default();
-    let mut wtxn = index.write_txn().unwrap();
-    let rtxn = index.read_txn().unwrap();
-    let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
-    let mut new_fields_ids_map = db_fields_ids_map.clone();
-
-    let documents = documents_from(conf.dataset, conf.dataset_format);
-    let mut indexer = indexer::DocumentOperation::new();
-    indexer.replace_documents(&documents).unwrap();
-
-    let indexer_alloc = Bump::new();
-    let (document_changes, _operation_stats, primary_key) = indexer
-        .into_changes(
-            &indexer_alloc,
-            &index,
-            &rtxn,
-            None,
-            &mut new_fields_ids_map,
-            &|| false,
-            Progress::default(),
-            None,
-        )
-        .unwrap();
-
-    indexer::index(
-        &mut wtxn,
-        &index,
-        &milli::ThreadPoolNoAbortBuilder::new().build().unwrap(),
-        config.grenad_parameters(),
-        &db_fields_ids_map,
-        new_fields_ids_map,
-        primary_key,
-        &document_changes,
-        RuntimeEmbedders::default(),
-        &|| false,
-        &Progress::default(),
-        &Default::default(),
-    )
-    .unwrap();
-
-    wtxn.commit().unwrap();
-    drop(rtxn);
-
-    index
-}
-
-pub fn run_benches(c: &mut criterion::Criterion, confs: &[Conf]) {
-    for conf in confs {
-        let index = base_setup(conf);
-
-        let file_name = Path::new(conf.dataset).file_name().and_then(|f| f.to_str()).unwrap();
-        let name = format!("{}: {}", file_name, conf.group_name);
-        let mut group = c.benchmark_group(&name);
-        if let Some(sample_size) = conf.sample_size {
-            group.sample_size(sample_size);
-        }
-
-        for &query in conf.queries {
-            for offset in conf.offsets {
-                let parameter = match offset {
-                    None => query.to_string(),
-                    Some((offset, limit)) => format!("{query}[{offset}:{limit}]"),
-                };
-                group.bench_with_input(
-                    BenchmarkId::from_parameter(parameter),
-                    &query,
-                    |b, &query| {
-                        b.iter(|| {
-                            let rtxn = index.read_txn().unwrap();
-                            let mut search = index.search(&rtxn);
-                            search
-                                .query(query)
-                                .terms_matching_strategy(TermsMatchingStrategy::default());
-                            if let Some(filter) = conf.filter {
-                                let filter = Filter::from_str(filter).unwrap().unwrap();
-                                search.filter(filter);
-                            }
-                            if let Some(sort) = &conf.sort {
-                                let sort = sort.iter().map(|sort| sort.parse().unwrap()).collect();
-                                search.sort_criteria(sort);
-                            }
-                            if let Some((offset, limit)) = offset {
-                                search.offset(*offset).limit(*limit);
-                            }
-
-                            let _ids = search.execute().unwrap();
-                        });
-                    },
-                );
-            }
-        }
-
-        if conf.get_documents {
-            for offset in conf.offsets {
-                let parameter = match offset {
-                    None => String::from("get_documents"),
-                    Some((offset, limit)) => format!("get_documents[{offset}:{limit}]"),
-                };
-                group.bench_with_input(BenchmarkId::from_parameter(parameter), &(), |b, &()| {
-                    b.iter(|| {
-                        let rtxn = index.read_txn().unwrap();
-                        if let Some(sort) = &conf.sort {
-                            let sort = sort.iter().map(|sort| sort.parse().unwrap()).collect();
-                            let all_docs = index.documents_ids(&rtxn).unwrap();
-                            let facet_sort =
-                                recursive_sort(&index, &rtxn, sort, &all_docs).unwrap();
-                            let iter = facet_sort.iter().unwrap();
-                            if let Some((offset, limit)) = offset {
-                                let _results = iter.skip(*offset).take(*limit).collect::<Vec<_>>();
-                            } else {
-                                let _results = iter.collect::<Vec<_>>();
-                            }
-                        } else {
-                            let all_docs = index.documents_ids(&rtxn).unwrap();
-                            if let Some((offset, limit)) = offset {
-                                let _results =
-                                    all_docs.iter().skip(*offset).take(*limit).collect::<Vec<_>>();
-                            } else {
-                                let _results = all_docs.iter().collect::<Vec<_>>();
-                            }
-                        }
-                    });
-                });
-            }
-        }
-
-        group.finish();
-
-        index.prepare_for_closing().wait();
-    }
-}
-
-pub fn documents_from(filename: &str, filetype: &str) -> Mmap {
-    let file = File::open(filename)
-        .unwrap_or_else(|_| panic!("could not find the dataset in: {filename}"));
-    match filetype {
-        "csv" => documents_from_csv(file).unwrap(),
-        "json" => documents_from_json(file).unwrap(),
-        "jsonl" => documents_from_jsonl(file).unwrap(),
-        otherwise => panic!("invalid update format {otherwise:?}"),
-    }
-}
-
-fn documents_from_jsonl(file: File) -> anyhow::Result<Mmap> {
-    unsafe { Mmap::map(&file).map_err(Into::into) }
-}
-
-fn documents_from_json(file: File) -> anyhow::Result<Mmap> {
-    let reader = BufReader::new(file);
-    let documents: Vec<milli::Object> = serde_json::from_reader(reader)?;
-    let mut output = tempfile::tempfile().map(BufWriter::new)?;
-
-    for document in documents {
-        serde_json::to_writer(&mut output, &document)?;
-    }
-
-    let file = output.into_inner()?;
-    unsafe { Mmap::map(&file).map_err(Into::into) }
-}
-
-fn documents_from_csv(file: File) -> anyhow::Result<Mmap> {
-    let output = tempfile::tempfile()?;
-    let mut output = BufWriter::new(output);
-    let mut reader = csv::ReaderBuilder::new().from_reader(file);
-
-    let headers = reader.headers().context("while retrieving headers")?.clone();
-    let typed_fields: Vec<_> = headers.iter().map(parse_csv_header).collect();
-    let mut object: serde_json::Map<_, _> =
-        typed_fields.iter().map(|(k, _)| (k.to_string(), Value::Null)).collect();
-
-    let mut line = 0;
-    let mut record = csv::StringRecord::new();
-    while reader.read_record(&mut record).context("while reading a record")? {
-        // We increment here and not at the end of the loop
-        // to take the header offset into account.
-        line += 1;
-
-        // Reset the document values
-        object.iter_mut().for_each(|(_, v)| *v = Value::Null);
-
-        for (i, (name, atype)) in typed_fields.iter().enumerate() {
-            let value = &record[i];
-            let trimmed_value = value.trim();
-            let value = match atype {
-                AllowedType::Number if trimmed_value.is_empty() => Value::Null,
-                AllowedType::Number => {
-                    match trimmed_value.parse::<i64>() {
-                        Ok(integer) => Value::from(integer),
-                        Err(_) => match trimmed_value.parse::<f64>() {
-                            Ok(float) => Value::from(float),
-                            Err(error) => {
-                                anyhow::bail!("document format error on line {line}: {error}. For value: {value}")
-                            }
-                        },
-                    }
-                }
-                AllowedType::Boolean if trimmed_value.is_empty() => Value::Null,
-                AllowedType::Boolean => match trimmed_value.parse::<bool>() {
-                    Ok(bool) => Value::from(bool),
-                    Err(error) => {
-                        anyhow::bail!(
-                            "document format error on line {line}: {error}. For value: {value}"
-                        )
-                    }
-                },
-                AllowedType::String if value.is_empty() => Value::Null,
-                AllowedType::String => Value::from(value),
-            };
-
-            *object.get_mut(name).expect("encountered an unknown field") = value;
-        }
-
-        serde_json::to_writer(&mut output, &object).context("while writing to disk")?;
-    }
-
-    let output = output.into_inner()?;
-    unsafe { Mmap::map(&output).map_err(Into::into) }
-}
-
-enum AllowedType {
-    String,
-    Boolean,
-    Number,
-}
-
-fn parse_csv_header(header: &str) -> (String, AllowedType) {
-    // if there are several separators we only split on the last one.
-    match header.rsplit_once(':') {
-        Some((field_name, field_type)) => match field_type {
-            "string" => (field_name.to_string(), AllowedType::String),
-            "boolean" => (field_name.to_string(), AllowedType::Boolean),
-            "number" => (field_name.to_string(), AllowedType::Number),
-            // if the pattern isn't recognized, we keep the whole field.
-            _otherwise => (header.to_string(), AllowedType::String),
-        },
-        None => (header.to_string(), AllowedType::String),
-    }
-}
-
-struct CSVDocumentDeserializer<R>
-where
-    R: Read,
-{
-    documents: csv::StringRecordsIntoIter<R>,
-    headers: Vec<(String, AllowedType)>,
-}
-
-impl<R: Read> CSVDocumentDeserializer<R> {
-    fn from_reader(reader: R) -> io::Result<Self> {
-        let mut records = csv::Reader::from_reader(reader);
-
-        let headers = records.headers()?.into_iter().map(parse_csv_header).collect();
-
-        Ok(Self { documents: records.into_records(), headers })
-    }
-}
-
-impl<R: Read> Iterator for CSVDocumentDeserializer<R> {
-    type Item = anyhow::Result<Object>;
-
-    fn next(&mut self) -> Option<Self::Item> {
-        let csv_document = self.documents.next()?;
-
-        match csv_document {
-            Ok(csv_document) => {
-                let mut document = Object::new();
-
-                for ((field_name, field_type), value) in
-                    self.headers.iter().zip(csv_document.into_iter())
-                {
-                    let parsed_value: anyhow::Result<Value> = match field_type {
-                        AllowedType::Number => {
-                            value.parse::<f64>().map(Value::from).map_err(Into::into)
-                        }
-                        AllowedType::Boolean => {
-                            value.parse::<bool>().map(Value::from).map_err(Into::into)
-                        }
-                        AllowedType::String => Ok(Value::String(value.to_string())),
-                    };
-
-                    match parsed_value {
-                        Ok(value) => drop(document.insert(field_name.to_string(), value)),
-                        Err(_e) => {
-                            return Some(Err(anyhow::anyhow!(
-                                "Value '{}' is not a valid number",
-                                value
-                            )))
-                        }
-                    }
-                }
-
-                Some(Ok(document))
-            }
-            Err(e) => Some(Err(anyhow::anyhow!("Error parsing csv document: {}", e))),
-        }
-    }
-}

crates/build-info/Cargo.toml

@@ -1,18 +0,0 @@
-[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 = "0.3.41", features = ["parsing"] }
-
-[build-dependencies]
-anyhow = "1.0.98"
-vergen-git2 = "1.0.7"

crates/build-info/build.rs

@@ -1,29 +0,0 @@
-fn main() {
-    if let Err(err) = emit_git_variables() {
-        println!("cargo:warning=vergen: {}", err);
-    }
-}
-
-fn emit_git_variables() -> anyhow::Result<()> {
-    println!("cargo::rerun-if-env-changed=MEILI_NO_VERGEN");
-
-    let has_vergen =
-        !matches!(std::env::var_os("MEILI_NO_VERGEN"), Some(x) if x != "false" && x != "0");
-
-    anyhow::ensure!(has_vergen, "disabled via `MEILI_NO_VERGEN`");
-
-    // 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()
-}

crates/build-info/src/lib.rs

@@ -1,203 +0,0 @@
-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);
-    }
-}

crates/dump/Cargo.toml

@@ -1,34 +0,0 @@
-[package]
-name = "dump"
-publish = false
-
-version.workspace = true
-authors.workspace = true
-description.workspace = true
-edition.workspace = true
-homepage.workspace = true
-readme.workspace = true
-license.workspace = true
-
-[dependencies]
-anyhow = "1.0.98"
-flate2 = "1.1.2"
-http = "1.3.1"
-meilisearch-types = { path = "../meilisearch-types" }
-once_cell = "1.21.3"
-regex = "1.11.1"
-roaring = { version = "0.10.12", features = ["serde"] }
-serde = { version = "1.0.219", features = ["derive"] }
-serde_json = { version = "1.0.140", features = ["preserve_order"] }
-tar = "0.4.44"
-tempfile = "3.20.0"
-thiserror = "2.0.12"
-time = { version = "0.3.41", features = ["serde-well-known", "formatting", "parsing", "macros"] }
-tracing = "0.1.41"
-uuid = { version = "1.17.0", features = ["serde", "v4"] }
-
-[dev-dependencies]
-big_s = "1.0.2"
-maplit = "1.0.2"
-meili-snap = { path = "../meili-snap" }
-meilisearch-types = { path = "../meilisearch-types" }

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

@@ -1,57 +0,0 @@
----
-source: crates/dump/src/reader/mod.rs
-expression: vector_index.settings().unwrap()
----
-{
-  "displayedAttributes": [
-    "*"
-  ],
-  "searchableAttributes": [
-    "*"
-  ],
-  "filterableAttributes": [],
-  "sortableAttributes": [],
-  "rankingRules": [
-    "words",
-    "typo",
-    "proximity",
-    "attribute",
-    "sort",
-    "exactness"
-  ],
-  "stopWords": [],
-  "nonSeparatorTokens": [],
-  "separatorTokens": [],
-  "dictionary": [],
-  "synonyms": {},
-  "distinctAttribute": null,
-  "proximityPrecision": "byWord",
-  "typoTolerance": {
-    "enabled": true,
-    "minWordSizeForTypos": {
-      "oneTypo": 5,
-      "twoTypos": 9
-    },
-    "disableOnWords": [],
-    "disableOnAttributes": []
-  },
-  "faceting": {
-    "maxValuesPerFacet": 100,
-    "sortFacetValuesBy": {
-      "*": "alpha"
-    }
-  },
-  "pagination": {
-    "maxTotalHits": 1000
-  },
-  "embedders": {
-    "default": {
-      "source": "huggingFace",
-      "model": "BAAI/bge-base-en-v1.5",
-      "revision": "617ca489d9e86b49b8167676d8220688b99db36e",
-      "pooling": "forceMean",
-      "documentTemplate": "{% for field in fields %} {{ field.name }}: {{ field.value }}\n{% endfor %}"
-    }
-  },
-  "searchCutoffMs": null
-}

crates/dump/src/reader/snapshots/dump__reader__test__import_dump_v6_with_vectors-6.snap

@@ -1,783 +0,0 @@
----
-source: dump/src/reader/mod.rs
-expression: document
----
-{
-  "id": "e3",
-  "desc": "overriden vector + map",
-  "_vectors": {
-    "default": [
-      0.2,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1
-    ],
-    "toto": [
-      0.1
-    ]
-  }
-}

crates/dump/src/reader/snapshots/dump__reader__test__import_dump_v6_with_vectors-7.snap

@@ -1,786 +0,0 @@
----
-source: dump/src/reader/mod.rs
-expression: document
----
-{
-  "id": "e2",
-  "desc": "natural vector + map",
-  "_vectors": {
-    "toto": [],
-    "default": {
-      "embeddings": [
-        [
-          -0.05189208313822746,
-          -0.9273212552070618,
-          0.1443813145160675,
-          0.0932632014155388,
-          0.2665371894836426,
-          0.36266782879829407,
-          0.6402910947799683,
-          0.32014018297195435,
-          0.030915971845388412,
-          -0.9312191605567932,
-          -0.3718109726905823,
-          -0.2700554132461548,
-          -1.1014580726623535,
-          0.9154956936836244,
-          -0.3406888246536255,
-          1.0077725648880005,
-          0.6577560901641846,
-          -0.3955195546150207,
-          -0.4148270785808563,
-          0.1855088472366333,
-          0.5062315464019775,
-          -0.3632686734199524,
-          -0.2277890294790268,
-          0.2560805082321167,
-          -0.3853609561920166,
-          -0.1604762226343155,
-          -0.13947471976280212,
-          -0.20147813856601715,
-          -0.4466346800327301,
-          -0.3761846721172333,
-          0.1443382054567337,
-          0.18205296993255615,
-          0.49359792470932007,
-          -0.22538000345230105,
-          -0.4996317625045776,
-          -0.22734887897968292,
-          -0.6034309267997742,
-          -0.7857939600944519,
-          -0.34923747181892395,
-          -0.3466345965862274,
-          0.21176661550998688,
-          -0.5101462006568909,
-          -0.3403083384037018,
-          0.000315118464641273,
-          0.236465722322464,
-          -0.10246097296476364,
-          -1.3013339042663574,
-          0.3419138789176941,
-          -0.32963496446609497,
-          -0.0901619717478752,
-          -0.5426247119903564,
-          0.22656650841236117,
-          -0.44758284091949463,
-          0.14151698350906372,
-          -0.1089438870549202,
-          0.5500766634941101,
-          -0.670711100101471,
-          -0.6227269768714905,
-          0.3894464075565338,
-          -0.27609574794769287,
-          0.7028202414512634,
-          -0.19697771966457367,
-          0.328511506319046,
-          0.5063360929489136,
-          0.4065195322036743,
-          0.2614171802997589,
-          -0.30274391174316406,
-          1.0393824577331543,
-          -0.7742937207221985,
-          -0.7874112129211426,
-          -0.6749666929244995,
-          0.5190866589546204,
-          0.004123548045754433,
-          -0.28312963247299194,
-          -0.038731709122657776,
-          -1.0142987966537476,
-          -0.09519586712121964,
-          0.8755272626876831,
-          0.4876938760280609,
-          0.7811151742935181,
-          0.85174959897995,
-          0.11826585978269576,
-          0.5373436808586121,
-          0.3649002015590668,
-          0.19064077734947205,
-          -0.00287026260048151,
-          -0.7305403351783752,
-          -0.015206154435873032,
-          -0.7899249196052551,
-          0.19407285749912265,
-          0.08596625179052353,
-          -0.28976231813430786,
-          -0.1525907665491104,
-          0.3798313438892365,
-          0.050306469202041626,
-          -0.5697937607765198,
-          0.4219021201133728,
-          0.276252806186676,
-          0.1559903472661972,
-          0.10030482709407806,
-          -0.4043720066547394,
-          -0.1969818025827408,
-          0.5739826560020447,
-          0.2116064727306366,
-          -1.4620544910430908,
-          -0.7802462577819824,
-          -0.24739810824394223,
-          -0.09791352599859238,
-          -0.4413802027702331,
-          0.21549351513385773,
-          -0.9520436525344848,
-          -0.08762510865926743,
-          0.08154498040676117,
-          -0.6154940724372864,
-          -1.01079523563385,
-          0.885427713394165,
-          0.6967288851737976,
-          0.27186504006385803,
-          -0.43194177746772766,
-          -0.11248451471328735,
-          0.7576630711555481,
-          0.4998855590820313,
-          0.0264343973249197,
-          0.9872855544090272,
-          0.5634694695472717,
-          0.053698331117630005,
-          0.19410227239131927,
-          0.3570743501186371,
-          -0.23670297861099243,
-          -0.9114483594894408,
-          0.07884842902421951,
-          0.7318344116210938,
-          0.44630110263824463,
-          0.08745364099740982,
-          -0.347101628780365,
-          -0.4314247667789459,
-          -0.5060274004936218,
-          0.003706763498485088,
-          0.44320008158683777,
-          -0.00788921769708395,
-          -0.1368623524904251,
-          -0.17391923069953918,
-          0.14473655819892883,
-          0.10927865654230118,
-          0.6974599361419678,
-          0.005052129738032818,
-          -0.016953065991401672,
-          -0.1256176233291626,
-          -0.036742497235536575,
-          0.5591985583305359,
-          -0.37619709968566895,
-          0.22429119050502777,
-          0.5403043031692505,
-          -0.8603790998458862,
-          -0.3456307053565979,
-          0.9292937517166138,
-          0.5074859261512756,
-          0.6310645937919617,
-          -0.3091641068458557,
-          0.46902573108673096,
-          0.7891915440559387,
-          0.4499550759792328,
-          0.2744995653629303,
-          0.2712305784225464,
-          -0.04349074140191078,
-          -0.3638863265514374,
-          0.7839881777763367,
-          0.7352104783058167,
-          -0.19457511603832245,
-          -0.5957832932472229,
-          -0.43704694509506226,
-          -1.084769368171692,
-          0.4904985725879669,
-          0.5385226011276245,
-          0.1891629993915558,
-          0.12338479608297348,
-          0.8315675258636475,
-          -0.07830192148685455,
-          1.0916285514831543,
-          -0.28066861629486084,
-          -1.3585069179534912,
-          0.5203898549079895,
-          0.08678033947944641,
-          -0.2566044330596924,
-          0.09484415501356123,
-          -0.0180208683013916,
-          1.0264745950698853,
-          -0.023572135716676712,
-          0.5864979028701782,
-          0.7625196576118469,
-          -0.2543414533138275,
-          -0.8877770900726318,
-          0.7611982822418213,
-          -0.06220436468720436,
-          0.937336564064026,
-          0.2704363465309143,
-          -0.37733694911003113,
-          0.5076137781143188,
-          -0.30641937255859375,
-          0.6252772808074951,
-          -0.0823579877614975,
-          -0.03736555948853493,
-          0.4131673276424408,
-          -0.6514252424240112,
-          0.12918265163898468,
-          -0.4483584463596344,
-          0.6750786304473877,
-          -0.37008383870124817,
-          -0.02324833907186985,
-          0.38027650117874146,
-          -0.26374951004981995,
-          0.4346931278705597,
-          0.42882832884788513,
-          -0.48798441886901855,
-          1.1882442235946655,
-          0.5132288336753845,
-          0.5284568667411804,
-          -0.03538886830210686,
-          0.29620853066444397,
-          -1.0683696269989014,
-          0.25936177372932434,
-          0.10404160618782043,
-          -0.25796034932136536,
-          0.027896970510482788,
-          -0.09225251525640488,
-          1.4811025857925415,
-          0.641173779964447,
-          -0.13838383555412292,
-          -0.3437179923057556,
-          0.5667019486427307,
-          -0.5400741696357727,
-          0.31090837717056274,
-          0.6470608115196228,
-          -0.3747067153453827,
-          -0.7364534735679626,
-          -0.07431528717279434,
-          0.5173454880714417,
-          -0.6578747034072876,
-          0.7107478976249695,
-          -0.7918999791145325,
-          -0.0648345872759819,
-          0.609937846660614,
-          -0.7329513430595398,
-          0.9741371870040894,
-          0.17912346124649048,
-          -0.02658769302070141,
-          0.5162150859832764,
-          -0.3978803157806397,
-          -0.7833885550498962,
-          -0.6497276425361633,
-          -0.3898126780986786,
-          -0.0952848568558693,
-          0.2663288116455078,
-          -0.1604052186012268,
-          0.373076468706131,
-          -0.8357769250869751,
-          -0.05217683315277099,
-          -0.2680160701274872,
-          0.8389158248901367,
-          0.6833611130714417,
-          -0.6712407469749451,
-          0.7406917214393616,
-          -0.44522786140441895,
-          -0.34645363688468933,
-          -0.27384576201438904,
-          -0.9878405928611756,
-          -0.8166060447692871,
-          0.06268279999494553,
-          0.38567957282066345,
-          -0.3274703919887543,
-          0.5296315550804138,
-          -0.11810623109340668,
-          0.23029841482639313,
-          0.08616159111261368,
-          -0.2195747196674347,
-          0.09430307894945145,
-          0.4057176411151886,
-          0.4892159104347229,
-          -0.1636916548013687,
-          -0.6071445345878601,
-          0.41256585717201233,
-          0.622254490852356,
-          -0.41223976016044617,
-          -0.6686707139015198,
-          -0.7474371790885925,
-          -0.8509522080421448,
-          -0.16754287481307983,
-          -0.9078601002693176,
-          -0.29653599858283997,
-          -0.5020652413368225,
-          0.4692700505256653,
-          0.01281109917908907,
-          -0.16071580350399017,
-          0.03388889133930206,
-          -0.020511148497462273,
-          0.5027827024459839,
-          -0.20729811489582065,
-          0.48107290267944336,
-          0.33669769763946533,
-          -0.5275911688804626,
-          0.48271527886390686,
-          0.2738940715789795,
-          -0.033152539283037186,
-          -0.13629786670207977,
-          -0.05965912342071533,
-          -0.26200807094573975,
-          0.04002794995903969,
-          -0.34095603227615356,
-          -3.986898899078369,
-          -0.46819332242012024,
-          -0.422744482755661,
-          -0.169097900390625,
-          0.6008929014205933,
-          0.058016058057546616,
-          -0.11401277780532836,
-          -0.3077819049358368,
-          -0.09595538675785063,
-          0.6723822355270386,
-          0.19367831945419312,
-          0.28304359316825867,
-          0.1609862744808197,
-          0.7567598819732666,
-          0.6889985799789429,
-          0.06907720118761063,
-          -0.04188092052936554,
-          -0.7434936165809631,
-          0.13321782648563385,
-          0.8456063270568848,
-          -0.10364038497209548,
-          -0.45084846019744873,
-          -0.4758241474628449,
-          0.43882066011428833,
-          -0.6432598829269409,
-          0.7217311859130859,
-          -0.24189773201942444,
-          0.12737572193145752,
-          -1.1008601188659668,
-          -0.3305315673351288,
-          0.14614742994308472,
-          -0.7819333076477051,
-          0.5287120342254639,
-          -0.055538054555654526,
-          0.1877404749393463,
-          -0.6907662153244019,
-          0.5616975426673889,
-          -0.4611121714115143,
-          -0.26109233498573303,
-          -0.12898315489292145,
-          -0.3724522292613983,
-          -0.7191406488418579,
-          -0.4425233602523804,
-          -0.644108235836029,
-          0.8424481153488159,
-          0.17532426118850708,
-          -0.5121750235557556,
-          -0.6467239260673523,
-          -0.0008507720194756985,
-          0.7866212129592896,
-          -0.02644744887948036,
-          -0.005045140627771616,
-          0.015782782807946205,
-          0.16334445774555206,
-          -0.1913367658853531,
-          -0.13697923719882965,
-          -0.6684983372688293,
-          0.18346354365348816,
-          -0.341105580329895,
-          0.5427411198616028,
-          0.3779832422733307,
-          -0.6778115034103394,
-          -0.2931850254535675,
-          -0.8805161714553833,
-          -0.4212774932384491,
-          -0.5368952751159668,
-          -1.3937891721725464,
-          -1.225494146347046,
-          0.4276703894138336,
-          1.1205668449401855,
-          -0.6005299687385559,
-          0.15732505917549133,
-          -0.3914784789085388,
-          -1.357046604156494,
-          -0.4707142114639282,
-          -0.1497287154197693,
-          -0.25035548210144043,
-          -0.34328439831733704,
-          0.39083412289619446,
-          0.1623048633337021,
-          -0.9275814294815063,
-          -0.6430015563964844,
-          0.2973862886428833,
-          0.5580436587333679,
-          -0.6232585310935974,
-          -0.6611042022705078,
-          0.4015969038009643,
-          -1.0232892036437988,
-          -0.2585645020008087,
-          -0.5431421399116516,
-          0.5021264553070068,
-          -0.48601630330085754,
-          -0.010242084041237833,
-          0.5862035155296326,
-          0.7316920161247253,
-          0.4036808013916016,
-          0.4269520044326782,
-          -0.705938458442688,
-          0.7747307419776917,
-          0.10164368897676468,
-          0.7887958884239197,
-          -0.9612497091293336,
-          0.12755516171455383,
-          0.06812842190265656,
-          -0.022603651508688927,
-          0.14722754061222076,
-          -0.5588505268096924,
-          -0.20689940452575684,
-          0.3557641804218292,
-          -0.6812759637832642,
-          0.2860803008079529,
-          -0.38954633474349976,
-          0.1759403496980667,
-          -0.5678874850273132,
-          -0.1692986786365509,
-          -0.14578519761562347,
-          0.5711379051208496,
-          1.0208125114440918,
-          0.7759483456611633,
-          -0.372348427772522,
-          -0.5460885763168335,
-          0.7190321683883667,
-          -0.6914990544319153,
-          0.13365162909030914,
-          -0.4854792356491089,
-          0.4054908752441406,
-          0.4502798914909363,
-          -0.3041122555732727,
-          -0.06726965308189392,
-          -0.05570871382951737,
-          -0.0455719493329525,
-          0.4785125255584717,
-          0.8867972493171692,
-          0.4107886850833893,
-          0.6121342182159424,
-          -0.20477132499217987,
-          -0.5598517656326294,
-          -0.6443566679954529,
-          -0.5905212759971619,
-          -0.5571200251579285,
-          0.17573799192905426,
-          -0.28621870279312134,
-          0.1685224026441574,
-          0.09719007462263109,
-          -0.04223639518022537,
-          -0.28623101115226746,
-          -0.1449810117483139,
-          -0.3789580464363098,
-          -0.5227636098861694,
-          -0.049728814512491226,
-          0.7849089503288269,
-          0.16792525351047516,
-          0.9849340915679932,
-          -0.6559549570083618,
-          0.35723909735679626,
-          -0.6822739243507385,
-          1.2873116731643677,
-          0.19993330538272855,
-          0.03512010723352432,
-          -0.6972134113311768,
-          0.18453484773635864,
-          -0.2437680810689926,
-          0.2156416028738022,
-          0.5230382680892944,
-          0.22020135819911957,
-          0.8314080238342285,
-          0.15627102553844452,
-          -0.7330264449119568,
-          0.3888184726238251,
-          -0.22034703195095065,
-          0.5457669496536255,
-          -0.48084837198257446,
-          -0.45576658844947815,
-          -0.09287727624177931,
-          -0.06968110054731369,
-          0.35125672817230225,
-          -0.4278119504451752,
-          0.2038476765155792,
-          0.11392722278833388,
-          0.9433983564376832,
-          -0.4097744226455689,
-          0.035297419875860214,
-          -0.4274404048919678,
-          -0.25100165605545044,
-          1.0943366289138794,
-          -0.07634022831916809,
-          -0.2925529479980469,
-          -0.7512530088424683,
-          0.2649727463722229,
-          -0.4078235328197479,
-          -0.3372223973274231,
-          0.05190162733197212,
-          0.005654910113662481,
-          -0.0001571219472680241,
-          -0.35445958375930786,
-          -0.7837416529655457,
-          0.1500556766986847,
-          0.4383024573326111,
-          0.6099548935890198,
-          0.05951934307813645,
-          -0.21325334906578064,
-          0.0199207104742527,
-          -0.22704418003559113,
-          -0.6481077671051025,
-          0.37442275881767273,
-          -1.015955924987793,
-          0.38637226819992065,
-          -0.06489371508359909,
-          -0.494120329618454,
-          0.3469836115837097,
-          0.15402406454086304,
-          -0.7660972476005554,
-          -0.7053225040435791,
-          -0.25964751839637756,
-          0.014004424214363098,
-          -0.2860170006752014,
-          -0.17565494775772095,
-          -0.45117494463920593,
-          -0.0031954257283359766,
-          0.09676837921142578,
-          -0.514464259147644,
-          0.41698193550109863,
-          -0.21642713248729703,
-          -0.5398141145706177,
-          -0.3647628426551819,
-          0.37005379796028137,
-          0.239425927400589,
-          -0.08833975344896317,
-          0.934946596622467,
-          -0.48340797424316406,
-          0.6241437792778015,
-          -0.7253676652908325,
-          -0.04303571209311485,
-          1.1125205755233765,
-          -0.15692919492721558,
-          -0.2914651036262512,
-          -0.5117168426513672,
-          0.21365483105182648,
-          0.4924402534961701,
-          0.5269662141799927,
-          0.0352792888879776,
-          -0.149167999625206,
-          -0.6019760370254517,
-          0.08245442807674408,
-          0.4900692105293274,
-          0.518824577331543,
-          -0.00005570516441366635,
-          -0.553304135799408,
-          0.22217543423175812,
-          0.5047767758369446,
-          0.135724738240242,
-          1.1511540412902832,
-          -0.3541218340396881,
-          -0.9712511897087096,
-          0.8353699445724487,
-          -0.39227569103240967,
-          -0.9117669463157654,
-          -0.26349931955337524,
-          0.05597023293375969,
-          0.20695461332798004,
-          0.3178807199001312,
-          1.0663238763809204,
-          0.5062212347984314,
-          0.7288597822189331,
-          0.09899299591779707,
-          0.553720235824585,
-          0.675009548664093,
-          -0.20067055523395536,
-          0.3138423264026642,
-          -0.6886593103408813,
-          -0.2910398542881012,
-          -1.3186300992965698,
-          -0.4684459865093231,
-          -0.095743365585804,
-          -0.1257995069026947,
-          -0.4858281314373016,
-          -0.4935407340526581,
-          -0.3266896903514862,
-          -0.3928797245025635,
-          -0.40803104639053345,
-          -0.9975396394729614,
-          0.4229583740234375,
-          0.37309643626213074,
-          0.4431034922599793,
-          0.30364808440208435,
-          -0.3765178918838501,
-          0.5616499185562134,
-          0.16904796659946442,
-          -0.7343707084655762,
-          0.2560209631919861,
-          0.6166825294494629,
-          0.3200829327106476,
-          -0.4483652710914612,
-          0.16224201023578644,
-          -0.31495288014411926,
-          -0.42713335156440735,
-          0.7270734906196594,
-          0.7049484848976135,
-          -0.0571461021900177,
-          0.04477125033736229,
-          -0.6647796034812927,
-          1.183672308921814,
-          0.36199676990509033,
-          0.046881116926670074,
-          0.4515796303749085,
-          0.9278061985969543,
-          0.31471705436706543,
-          -0.7073333859443665,
-          -0.3443860113620758,
-          0.5440067052841187,
-          -0.15020819008350372,
-          -0.541202962398529,
-          0.5203295946121216,
-          1.2192286252975464,
-          -0.9983593225479126,
-          -0.18758884072303772,
-          0.2758221924304962,
-          -0.6511523723602295,
-          -0.1584404855966568,
-          -0.236241415143013,
-          0.2692437767982483,
-          -0.4941152036190033,
-          0.4987454116344452,
-          -0.3331359028816223,
-          0.3163745701313019,
-          0.745529294013977,
-          -0.2905873656272888,
-          0.13602906465530396,
-          0.4679684340953827,
-          1.0555986166000366,
-          1.075700044631958,
-          0.5368486046791077,
-          -0.5118206739425659,
-          0.8668332099914551,
-          -0.5726966857910156,
-          -0.7811751961708069,
-          0.1938626915216446,
-          -0.1929349899291992,
-          0.1757766306400299,
-          0.6384295225143433,
-          0.26462844014167786,
-          0.9542630314826964,
-          0.19313029944896695,
-          1.264248013496399,
-          -0.6304428577423096,
-          0.0487106591463089,
-          -0.16211535036563873,
-          -0.7894763350486755,
-          0.3582514822483063,
-          -0.04153040423989296,
-          0.635784387588501,
-          0.6554391980171204,
-          -0.47010496258735657,
-          -0.8302040696144104,
-          -0.1350124627351761,
-          0.2568812072277069,
-          0.13614831864833832,
-          -0.2563649117946625,
-          -1.0434694290161133,
-          0.3232482671737671,
-          0.47882452607154846,
-          0.4298652410507202,
-          1.0563770532608032,
-          -0.28917592763900757,
-          -0.8533256649971008,
-          0.10648339986801147,
-          0.6376127004623413,
-          -0.20832888782024384,
-          0.2370245456695557,
-          0.0018312990432605147,
-          -0.2034837007522583,
-          0.01051164511591196,
-          -1.105310082435608,
-          0.29724350571632385,
-          0.15604574978351593,
-          0.1973688006401062,
-          0.44394731521606445,
-          0.3974513411521912,
-          -0.13625948131084442,
-          0.9571986198425292,
-          0.2257384955883026,
-          0.2323588728904724,
-          -0.5583669543266296,
-          -0.7854922413825989,
-          0.1647188365459442,
-          -1.6098142862319946,
-          0.318587988615036,
-          -0.13399995863437653,
-          -0.2172701060771942,
-          -0.767514705657959,
-          -0.5813586711883545,
-          -0.3195130527019501,
-          -0.04894036799669266,
-          0.2929930090904236,
-          -0.8213384747505188,
-          0.07181350141763687,
-          0.7469993829727173,
-          0.6407455801963806,
-          0.16365697979927063,
-          0.7870153188705444,
-          0.6524736881256104,
-          0.6399973630905151,
-          -0.04992736503481865,
-          -0.03959266096353531,
-          -0.2512352466583252,
-          0.8448855876922607,
-          -0.1422702670097351,
-          0.1216789186000824,
-          -1.2647287845611572,
-          0.5931149125099182,
-          0.7186052203178406,
-          -0.06118432432413101,
-          -1.1942816972732544,
-          -0.17677085101604462,
-          0.31543800234794617,
-          -0.32252824306488037,
-          0.8255583047866821,
-          -0.14529970288276672,
-          -0.2695446312427521,
-          -0.33378756046295166,
-          -0.1653425395488739,
-          0.1454019844532013,
-          -0.3920115828514099,
-          0.912214994430542,
-          -0.7279734015464783,
-          0.7374742031097412,
-          0.933980405330658,
-          0.13429680466651917,
-          -0.514870285987854,
-          0.3989711999893189,
-          -0.11613689363002776,
-          0.4022413492202759,
-          -0.9990655779838562,
-          -0.33749932050704956,
-          -0.4334589838981629,
-          -1.376373291015625,
-          -0.2993924915790558,
-          -0.09454808384180068,
-          -0.01314175222069025,
-          -0.001090060803107917,
-          0.2137461006641388,
-          0.2938512861728668,
-          0.17508235573768616,
-          0.8260607123374939,
-          -0.7218498587608337,
-          0.2414487451314926,
-          -0.47296759486198425,
-          -0.3002610504627228,
-          -1.238540768623352,
-          0.08663805574178696,
-          0.6805586218833923,
-          0.5909030437469482,
-          -0.42807504534721375,
-          -0.22887496650218964,
-          0.47537800669670105,
-          -1.0474627017974854,
-          0.6338009238243103,
-          0.06548397243022919,
-          0.4971011281013489,
-          1.3484878540039063
-        ]
-      ],
-      "regenerate": true
-    }
-  }
-}

crates/dump/src/reader/snapshots/dump__reader__test__import_dump_v6_with_vectors-8.snap

@@ -1,785 +0,0 @@
----
-source: dump/src/reader/mod.rs
-expression: document
----
-{
-  "id": "e1",
-  "desc": "natural vector",
-  "_vectors": {
-    "default": {
-      "embeddings": [
-        [
-          -0.2979458272457123,
-          -0.5288640856742859,
-          -0.019957859069108963,
-          -0.18495318293571472,
-          0.7429973483085632,
-          0.5238497257232666,
-          0.432366281747818,
-          0.32744166254997253,
-          0.0020762972999364138,
-          -0.9507834911346436,
-          -0.35097137093544006,
-          0.08469701558351517,
-          -1.4176613092422483,
-          0.4647577106952667,
-          -0.69340580701828,
-          1.0372896194458008,
-          0.3716741800308227,
-          0.06031008064746857,
-          -0.6152024269104004,
-          0.007914665155112743,
-          0.7954924702644348,
-          -0.20773003995418549,
-          0.09376765787601472,
-          0.04508133605122566,
-          -0.2084471583366394,
-          -0.1518009901046753,
-          0.018195509910583496,
-          -0.07044368237257004,
-          -0.18119366466999057,
-          -0.4480230510234833,
-          0.3822529911994934,
-          0.1911812424659729,
-          0.4674372375011444,
-          0.06963984668254852,
-          -0.09341949224472046,
-          0.005675444379448891,
-          -0.6774799227714539,
-          -0.7066726684570313,
-          -0.39256376028060913,
-          0.04005039855837822,
-          0.2084812968969345,
-          -0.7872875928878784,
-          -0.8205880522727966,
-          0.2919981777667999,
-          -0.06004738807678223,
-          -0.4907574355602264,
-          -1.5937862396240234,
-          0.24249385297298431,
-          -0.14709846675395966,
-          -0.11860740929841997,
-          -0.8299489617347717,
-          0.472964346408844,
-          -0.497518390417099,
-          -0.22205302119255063,
-          -0.4196169078350067,
-          0.32697558403015137,
-          -0.360930860042572,
-          -0.9789686799049376,
-          0.1887447088956833,
-          -0.403737336397171,
-          0.18524253368377688,
-          0.3768732249736786,
-          0.3666233420372009,
-          0.3511938452720642,
-          0.6985810995101929,
-          0.41721710562705994,
-          0.09754953533411026,
-          0.6204307079315186,
-          -1.0762996673583984,
-          -0.06263761967420578,
-          -0.7376511693000793,
-          0.6849768161773682,
-          -0.1745152473449707,
-          -0.40449759364128113,
-          0.20757411420345304,
-          -0.8424443006515503,
-          0.330015629529953,
-          0.3489064872264862,
-          1.0954371690750122,
-          0.8487558960914612,
-          1.1076823472976685,
-          0.61430823802948,
-          0.4155903458595276,
-          0.4111340939998626,
-          0.05753209814429283,
-          -0.06429877132177353,
-          -0.765606164932251,
-          -0.41703930497169495,
-          -0.508820652961731,
-          0.19859947264194489,
-          -0.16607828438282013,
-          -0.28112146258354187,
-          0.11032675206661224,
-          0.38809511065483093,
-          -0.36498191952705383,
-          -0.48671194911003113,
-          0.6755134463310242,
-          0.03958442434668541,
-          0.4478721618652344,
-          -0.10335399955511092,
-          -0.9546685814857484,
-          -0.6087718605995178,
-          0.17498846352100372,
-          0.08320838958024979,
-          -1.4478336572647097,
-          -0.605027437210083,
-          -0.5867993235588074,
-          -0.14711688458919525,
-          -0.5447602272033691,
-          -0.026259321719408035,
-          -0.6997418403625488,
-          -0.07349082082509995,
-          0.10638900846242905,
-          -0.7133527398109436,
-          -0.9396815299987792,
-          1.087092399597168,
-          1.1885089874267578,
-          0.4011896848678589,
-          -0.4089202582836151,
-          -0.10938972979784012,
-          0.6726722121238708,
-          0.24576938152313232,
-          -0.24247920513153076,
-          1.1499971151351929,
-          0.47813335061073303,
-          -0.05331678315997124,
-          0.32338133454322815,
-          0.4870913326740265,
-          -0.23144258558750153,
-          -1.2023426294326782,
-          0.2349330335855484,
-          1.080536961555481,
-          0.29334118962287903,
-          0.391574501991272,
-          -0.15818795561790466,
-          -0.2948290705680847,
-          -0.024689948186278343,
-          0.06602869182825089,
-          0.5937030911445618,
-          -0.047901444137096405,
-          -0.512734591960907,
-          -0.35780075192451477,
-          0.28751692175865173,
-          0.4298716187477112,
-          0.9242428541183472,
-          -0.17208744585514069,
-          0.11515070497989656,
-          -0.0335976779460907,
-          -0.3422986567020416,
-          0.5344581604003906,
-          0.19895796477794647,
-          0.33001241087913513,
-          0.6390730142593384,
-          -0.6074934005737305,
-          -0.2553696632385254,
-          0.9644920229911804,
-          0.2699219584465027,
-          0.6403993368148804,
-          -0.6380003690719604,
-          -0.027310986071825027,
-          0.638815701007843,
-          0.27719101309776306,
-          -0.13553589582443237,
-          0.750195324420929,
-          0.1224869191646576,
-          -0.20613941550254825,
-          0.8444448709487915,
-          0.16200250387191772,
-          -0.24750925600528717,
-          -0.739950954914093,
-          -0.28443849086761475,
-          -1.176282525062561,
-          0.516107976436615,
-          0.3774825632572174,
-          0.10906043648719788,
-          0.07962015271186829,
-          0.7384604215621948,
-          -0.051241904497146606,
-          1.1730090379714966,
-          -0.4828610122203827,
-          -1.404372215270996,
-          0.8811132311820984,
-          -0.3839482367038727,
-          0.022516896948218346,
-          -0.0491158664226532,
-          -0.43027013540267944,
-          1.2049334049224854,
-          -0.27309560775756836,
-          0.6883630752563477,
-          0.8264574408531189,
-          -0.5020735263824463,
-          -0.4874092042446137,
-          0.6007202863693237,
-          -0.4965405762195587,
-          1.1302915811538696,
-          0.032572727650403976,
-          -0.3731859028339386,
-          0.658271849155426,
-          -0.9023059010505676,
-          0.7400162220001221,
-          0.014550759457051754,
-          -0.19699542224407196,
-          0.2319706380367279,
-          -0.789058268070221,
-          -0.14905710518360138,
-          -0.5826214551925659,
-          0.207652747631073,
-          -0.4507439732551574,
-          -0.3163885474205017,
-          0.3604124188423157,
-          -0.45119962096214294,
-          0.3428427278995514,
-          0.3005594313144684,
-          -0.36026081442832947,
-          1.1014249324798584,
-          0.40884315967559814,
-          0.34991952776908875,
-          -0.1806638240814209,
-          0.27440476417541504,
-          -0.7118373513221741,
-          0.4645499587059021,
-          0.214790478348732,
-          -0.2343102991580963,
-          0.10500429570674896,
-          -0.28034430742263794,
-          1.2267805337905884,
-          1.0561333894729614,
-          -0.497364342212677,
-          -0.6143305897712708,
-          0.24963727593421936,
-          -0.33136463165283203,
-          -0.01473914459347725,
-          0.495918869972229,
-          -0.6985538005828857,
-          -1.0033197402954102,
-          0.35937801003456116,
-          0.6325868368148804,
-          -0.6808838844299316,
-          1.0354058742523191,
-          -0.7214401960372925,
-          -0.33318862318992615,
-          0.874398410320282,
-          -0.6594992280006409,
-          0.6830640435218811,
-          -0.18534131348133087,
-          0.024834271520376205,
-          0.19901277124881744,
-          -0.5992477536201477,
-          -1.2126628160476685,
-          -0.9245557188987732,
-          -0.3898217976093292,
-          -0.1286519467830658,
-          0.4217943847179413,
-          -0.1143646091222763,
-          0.5630772709846497,
-          -0.5240639448165894,
-          0.21152715384960177,
-          -0.3792001008987427,
-          0.8266305327415466,
-          1.170984387397766,
-          -0.8072142004966736,
-          0.11382893472909927,
-          -0.17953898012638092,
-          -0.1789460331201553,
-          -0.15078622102737427,
-          -1.2082908153533936,
-          -0.7812382578849792,
-          -0.10903695970773696,
-          0.7303897142410278,
-          -0.39054441452026367,
-          0.19511254131793976,
-          -0.09121843427419662,
-          0.22400228679180145,
-          0.30143046379089355,
-          0.1141919493675232,
-          0.48112115263938904,
-          0.7307931780815125,
-          0.09701362252235413,
-          -0.2795647978782654,
-          -0.3997688889503479,
-          0.5540812611579895,
-          0.564578115940094,
-          -0.40065160393714905,
-          -0.3629159033298493,
-          -0.3789091110229492,
-          -0.7298538088798523,
-          -0.6996853351593018,
-          -0.4477842152118683,
-          -0.289089560508728,
-          -0.6430277824401855,
-          0.2344944179058075,
-          0.3742927014827728,
-          -0.5079357028007507,
-          0.28841453790664673,
-          0.06515737622976303,
-          0.707315981388092,
-          0.09498685598373412,
-          0.8365515470504761,
-          0.10002726316452026,
-          -0.7695478200912476,
-          0.6264724135398865,
-          0.7562043070793152,
-          -0.23112858831882477,
-          -0.2871039807796478,
-          -0.25010058283805847,
-          0.2783474028110504,
-          -0.03224996477365494,
-          -0.9119359850883484,
-          -3.6940200328826904,
-          -0.5099936127662659,
-          -0.1604711413383484,
-          0.17453284561634064,
-          0.41759559512138367,
-          0.1419190913438797,
-          -0.11362407356500626,
-          -0.33312007784843445,
-          0.11511333286762238,
-          0.4667884409427643,
-          -0.0031647447030991316,
-          0.15879854559898376,
-          0.3042248487472534,
-          0.5404849052429199,
-          0.8515422344207764,
-          0.06286454200744629,
-          0.43790125846862793,
-          -0.8682025074958801,
-          -0.06363756954669952,
-          0.5547921657562256,
-          -0.01483887154608965,
-          -0.07361344993114471,
-          -0.929947018623352,
-          0.3502565622329712,
-          -0.5080993175506592,
-          1.0380364656448364,
-          -0.2017953395843506,
-          0.21319580078125,
-          -1.0763001441955566,
-          -0.556368887424469,
-          0.1949922740459442,
-          -0.6445739269256592,
-          0.6791343688964844,
-          0.21188358962535855,
-          0.3736183941364288,
-          -0.21800459921360016,
-          0.7597446441650391,
-          -0.3732394874095917,
-          -0.4710160195827484,
-          0.025146087631583217,
-          0.05341297015547752,
-          -0.9522109627723694,
-          -0.6000866889953613,
-          -0.08469046652317047,
-          0.5966026186943054,
-          0.3444081246852875,
-          -0.461188405752182,
-          -0.5279349088668823,
-          0.10296865552663804,
-          0.5175143480300903,
-          -0.20671147108078003,
-          0.13392412662506104,
-          0.4812754988670349,
-          0.2993808686733246,
-          -0.3005635440349579,
-          0.5141698122024536,
-          -0.6239235401153564,
-          0.2877119481563568,
-          -0.4452739953994751,
-          0.5621107816696167,
-          0.5047508478164673,
-          -0.4226335883140564,
-          -0.18578553199768064,
-          -1.1967322826385498,
-          0.28178197145462036,
-          -0.8692031502723694,
-          -1.1812998056411743,
-          -1.4526212215423584,
-          0.4645712077617645,
-          0.9327932000160216,
-          -0.6560136675834656,
-          0.461549699306488,
-          -0.5621527433395386,
-          -1.328449010848999,
-          -0.08676894754171371,
-          0.00021918353741057217,
-          -0.18864136934280396,
-          0.1259666532278061,
-          0.18240638077259064,
-          -0.14919660985469818,
-          -0.8965857625007629,
-          -0.7539900541305542,
-          0.013973715715110302,
-          0.504276692867279,
-          -0.704748272895813,
-          -0.6428424119949341,
-          0.6303996443748474,
-          -0.5404738187789917,
-          -0.31176653504371643,
-          -0.21262824535369873,
-          0.18736739456653595,
-          -0.7998970746994019,
-          0.039946746081113815,
-          0.7390344738960266,
-          0.4283199906349182,
-          0.3795057237148285,
-          0.07204607129096985,
-          -0.9230587482452391,
-          0.9440426230430604,
-          0.26272690296173096,
-          0.5598306655883789,
-          -1.0520871877670288,
-          -0.2677186131477356,
-          -0.1888762265443802,
-          0.30426350235939026,
-          0.4746131896972656,
-          -0.5746733546257019,
-          -0.4197768568992615,
-          0.8565112948417664,
-          -0.6767723560333252,
-          0.23448683321475983,
-          -0.2010004222393036,
-          0.4112907350063324,
-          -0.6497949957847595,
-          -0.418667733669281,
-          -0.4950824975967407,
-          0.44438859820365906,
-          1.026281714439392,
-          0.482397586107254,
-          -0.26220494508743286,
-          -0.3640787005424499,
-          0.5907743573188782,
-          -0.8771642446517944,
-          0.09708411991596222,
-          -0.3671700060367584,
-          0.4331349730491638,
-          0.619417667388916,
-          -0.2684665620326996,
-          -0.5123821496963501,
-          -0.1502324342727661,
-          -0.012190685607492924,
-          0.3580845892429352,
-          0.8617186546325684,
-          0.3493645489215851,
-          1.0270192623138428,
-          0.18297909200191495,
-          -0.5881339311599731,
-          -0.1733516901731491,
-          -0.5040576457977295,
-          -0.340370237827301,
-          -0.26767754554748535,
-          -0.28570041060447693,
-          -0.032928116619586945,
-          0.6029254794120789,
-          0.17397655546665192,
-          0.09346921741962431,
-          0.27815181016921997,
-          -0.46699589490890503,
-          -0.8148876428604126,
-          -0.3964351713657379,
-          0.3812595009803772,
-          0.13547226786613464,
-          0.7126688361167908,
-          -0.3473474085330963,
-          -0.06573959439992905,
-          -0.6483767032623291,
-          1.4808889627456665,
-          0.30924928188323975,
-          -0.5085946917533875,
-          -0.8613000512123108,
-          0.3048902451992035,
-          -0.4241599142551422,
-          0.15909206867218018,
-          0.5764641761779785,
-          -0.07879110425710678,
-          1.015336513519287,
-          0.07599356025457382,
-          -0.7025855779647827,
-          0.30047643184661865,
-          -0.35094937682151794,
-          0.2522146999835968,
-          -0.2338722199201584,
-          -0.8326804637908936,
-          -0.13695412874221802,
-          -0.03452421352267265,
-          0.47974953055381775,
-          -0.18385636806488037,
-          0.32438594102859497,
-          0.1797013282775879,
-          0.787494957447052,
-          -0.12579888105392456,
-          -0.07507286965847015,
-          -0.4389670491218567,
-          0.2720070779323578,
-          0.8138866424560547,
-          0.01974171027541161,
-          -0.3057698905467987,
-          -0.6709924936294556,
-          0.0885881632566452,
-          -0.2862754464149475,
-          0.03475658595561981,
-          -0.1285519152879715,
-          0.3838353455066681,
-          -0.2944154739379883,
-          -0.4204859137535095,
-          -0.4416137933731079,
-          0.13426260650157928,
-          0.36733248829841614,
-          0.573428750038147,
-          -0.14928072690963745,
-          -0.026076916605234143,
-          0.33286052942276,
-          -0.5340145826339722,
-          -0.17279052734375,
-          -0.01154550164937973,
-          -0.6620771884918213,
-          0.18390542268753052,
-          -0.08265615254640579,
-          -0.2489682286977768,
-          0.2429984211921692,
-          -0.044153645634651184,
-          -0.986578404903412,
-          -0.33574509620666504,
-          -0.5387663841247559,
-          0.19767941534519196,
-          0.12540718913078308,
-          -0.3403128981590271,
-          -0.4154576361179352,
-          0.17275673151016235,
-          0.09407442808151244,
-          -0.5414086580276489,
-          0.4393929839134216,
-          0.1725579798221588,
-          -0.4998118281364441,
-          -0.6926208138465881,
-          0.16552448272705078,
-          0.6659538149833679,
-          -0.10949844866991044,
-          0.986426830291748,
-          0.01748848147690296,
-          0.4003709554672241,
-          -0.5430638194084167,
-          0.35347291827201843,
-          0.6887399554252625,
-          0.08274628221988678,
-          0.13407137989997864,
-          -0.591465950012207,
-          0.3446292281150818,
-          0.6069018244743347,
-          0.1935492902994156,
-          -0.0989871397614479,
-          0.07008486241102219,
-          -0.8503749370574951,
-          -0.09507356584072112,
-          0.6259510517120361,
-          0.13934025168418884,
-          0.06392545253038406,
-          -0.4112265408039093,
-          -0.08475656062364578,
-          0.4974113404750824,
-          -0.30606114864349365,
-          1.111435890197754,
-          -0.018766529858112335,
-          -0.8422622680664063,
-          0.4325508773326874,
-          -0.2832120656967163,
-          -0.4859798848628998,
-          -0.41498348116874695,
-          0.015977520495653152,
-          0.5292825698852539,
-          0.4538311660289765,
-          1.1328668594360352,
-          0.22632671892642975,
-          0.7918671369552612,
-          0.33401933312416077,
-          0.7306135296821594,
-          0.3548600673675537,
-          0.12506209313869476,
-          0.8573207855224609,
-          -0.5818327069282532,
-          -0.6953738927841187,
-          -1.6171947717666626,
-          -0.1699674427509308,
-          0.6318262815475464,
-          -0.05671752244234085,
-          -0.28145185112953186,
-          -0.3976689279079437,
-          -0.2041076272726059,
-          -0.5495951175689697,
-          -0.5152917504310608,
-          -0.9309796094894408,
-          0.101932130753994,
-          0.1367802917957306,
-          0.1490798443555832,
-          0.5304336547851563,
-          -0.5082434415817261,
-          0.06688683480024338,
-          0.14657628536224365,
-          -0.782435953617096,
-          0.2962816655635834,
-          0.6965363621711731,
-          0.8496337532997131,
-          -0.3042965829372406,
-          0.04343798756599426,
-          0.0330701619386673,
-          -0.5662598013877869,
-          1.1086925268173218,
-          0.756072998046875,
-          -0.204134538769722,
-          0.2404300570487976,
-          -0.47848284244537354,
-          1.3659011125564575,
-          0.5645433068275452,
-          -0.15836156904697418,
-          0.43395575881004333,
-          0.5944653749465942,
-          1.0043466091156006,
-          -0.49446743726730347,
-          -0.5954391360282898,
-          0.5341240763664246,
-          0.020598189905285835,
-          -0.4036853015422821,
-          0.4473709762096405,
-          1.1998231410980225,
-          -0.9317775368690492,
-          -0.23321466147899628,
-          0.2052552700042725,
-          -0.7423108816146851,
-          -0.19917210936546328,
-          -0.1722569614648819,
-          -0.034072667360305786,
-          -0.00671181408688426,
-          0.46396249532699585,
-          -0.1372445821762085,
-          0.053376372903585434,
-          0.7392690777778625,
-          -0.38447609543800354,
-          0.07497968524694443,
-          0.5197252631187439,
-          1.3746477365493774,
-          0.9060075879096984,
-          0.20000585913658145,
-          -0.4053704142570496,
-          0.7497360110282898,
-          -0.34087055921554565,
-          -1.101803183555603,
-          0.273650586605072,
-          -0.5125769376754761,
-          0.22472351789474487,
-          0.480757474899292,
-          -0.19845178723335263,
-          0.8857700824737549,
-          0.30752456188201904,
-          1.1109285354614258,
-          -0.6768012642860413,
-          0.524367094039917,
-          -0.22495046257972717,
-          -0.4224412739276886,
-          0.40753406286239624,
-          -0.23133376240730288,
-          0.3297771215438843,
-          0.4905449151992798,
-          -0.6813114285469055,
-          -0.7543983459472656,
-          -0.5599071383476257,
-          0.14351597428321838,
-          -0.029278717935085297,
-          -0.3970443606376648,
-          -0.303079217672348,
-          0.24161772429943085,
-          0.008353390730917454,
-          -0.0062365154735744,
-          1.0824860334396362,
-          -0.3704061508178711,
-          -1.0337258577346802,
-          0.04638749733567238,
-          1.163011074066162,
-          -0.31737643480300903,
-          0.013986887410283089,
-          0.19223114848136905,
-          -0.2260770797729492,
-          -0.210910826921463,
-          -1.0191949605941772,
-          0.22356095910072327,
-          0.09353553503751756,
-          0.18096882104873657,
-          0.14867214858531952,
-          0.43408671021461487,
-          -0.33312076330184937,
-          0.8173948526382446,
-          0.6428242921829224,
-          0.20215003192424777,
-          -0.6634518504142761,
-          -0.4132290482521057,
-          0.29815030097961426,
-          -1.579406976699829,
-          -0.0981958732008934,
-          -0.03941014781594277,
-          0.1709178239107132,
-          -0.5481140613555908,
-          -0.5338194966316223,
-          -0.3528362512588501,
-          -0.11561278253793716,
-          -0.21793591976165771,
-          -1.1570470333099363,
-          0.2157980799674988,
-          0.42083489894866943,
-          0.9639263153076172,
-          0.09747201204299928,
-          0.15671424567699432,
-          0.4034591615200043,
-          0.6728067994117737,
-          -0.5216875672340393,
-          0.09657668322324751,
-          -0.2416689097881317,
-          0.747975766658783,
-          0.1021689772605896,
-          0.11652665585279463,
-          -1.0484966039657593,
-          0.8489304780960083,
-          0.7169828414916992,
-          -0.09012343734502792,
-          -1.3173753023147583,
-          0.057890523225069046,
-          -0.006231260951608419,
-          -0.1018214002251625,
-          0.936040461063385,
-          -0.0502331368625164,
-          -0.4284322261810303,
-          -0.38209280371665955,
-          -0.22668412327766416,
-          0.0782942995429039,
-          -0.4881664514541626,
-          0.9268959760665894,
-          0.001867273123934865,
-          0.42261114716529846,
-          0.8283362984657288,
-          0.4256294071674347,
-          -0.7965338826179504,
-          0.4840078353881836,
-          -0.19861412048339844,
-          0.33977967500686646,
-          -0.4604192078113556,
-          -0.3107339143753052,
-          -0.2839638590812683,
-          -1.5734281539916992,
-          0.005220232997089624,
-          0.09239906817674635,
-          -0.7828494906425476,
-          -0.1397123783826828,
-          0.2576255202293396,
-          0.21372435986995697,
-          -0.23169949650764465,
-          0.4016408920288086,
-          -0.462497353553772,
-          -0.2186472862958908,
-          -0.5617868900299072,
-          -0.3649831712245941,
-          -1.1585862636566162,
-          -0.08222806453704834,
-          0.931126832962036,
-          0.4327389597892761,
-          -0.46451422572135925,
-          -0.5430706143379211,
-          -0.27434298396110535,
-          -0.9479129314422609,
-          0.1845661848783493,
-          0.3972720205783844,
-          0.4883299469947815,
-          1.04031240940094
-        ]
-      ],
-      "regenerate": true
-    }
-  }
-}

crates/dump/src/reader/snapshots/dump__reader__test__import_dump_v6_with_vectors-9.snap

@@ -1,780 +0,0 @@
----
-source: dump/src/reader/mod.rs
-expression: document
----
-{
-  "id": "e0",
-  "desc": "overriden vector",
-  "_vectors": {
-    "default": [
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1,
-      0.1
-    ]
-  }
-}

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

@@ -1,330 +0,0 @@
-use std::ffi::OsStr;
-use std::fs::{self, File};
-use std::io::{BufRead, BufReader, ErrorKind};
-use std::path::Path;
-
-pub use meilisearch_types::milli;
-use meilisearch_types::milli::vector::embedder::hf::OverridePooling;
-use tempfile::TempDir;
-use time::OffsetDateTime;
-use tracing::debug;
-use uuid::Uuid;
-
-use super::Document;
-use crate::{Error, IndexMetadata, Result, Version};
-
-pub type Metadata = crate::Metadata;
-
-pub type Settings<T> = meilisearch_types::settings::Settings<T>;
-pub type Checked = meilisearch_types::settings::Checked;
-pub type Unchecked = meilisearch_types::settings::Unchecked;
-
-pub type Task = crate::TaskDump;
-pub type Batch = meilisearch_types::batches::Batch;
-pub type Key = meilisearch_types::keys::Key;
-pub type ChatCompletionSettings = meilisearch_types::features::ChatCompletionSettings;
-pub type RuntimeTogglableFeatures = meilisearch_types::features::RuntimeTogglableFeatures;
-pub type Network = meilisearch_types::enterprise_edition::network::Network;
-pub type Webhooks = meilisearch_types::webhooks::WebhooksDumpView;
-
-// ===== Other types to clarify the code of the compat module
-// everything related to the tasks
-pub type Status = meilisearch_types::tasks::Status;
-pub type Kind = crate::KindDump;
-pub type Details = meilisearch_types::tasks::Details;
-
-// everything related to the settings
-pub type Setting<T> = meilisearch_types::milli::update::Setting<T>;
-pub type TypoTolerance = meilisearch_types::settings::TypoSettings;
-pub type MinWordSizeForTypos = meilisearch_types::settings::MinWordSizeTyposSetting;
-pub type FacetingSettings = meilisearch_types::settings::FacetingSettings;
-pub type PaginationSettings = meilisearch_types::settings::PaginationSettings;
-
-// everything related to the api keys
-pub type Action = meilisearch_types::keys::Action;
-pub type IndexUidPattern = meilisearch_types::index_uid_pattern::IndexUidPattern;
-
-// everything related to the errors
-pub type ResponseError = meilisearch_types::error::ResponseError;
-pub type Code = meilisearch_types::error::Code;
-pub type RankingRuleView = meilisearch_types::settings::RankingRuleView;
-
-pub type FilterableAttributesRule = meilisearch_types::milli::FilterableAttributesRule;
-
-pub struct V6Reader {
-    dump: TempDir,
-    instance_uid: Option<Uuid>,
-    metadata: Metadata,
-    tasks: BufReader<File>,
-    batches: Option<BufReader<File>>,
-    keys: BufReader<File>,
-    features: Option<RuntimeTogglableFeatures>,
-    network: Option<Network>,
-    webhooks: Option<Webhooks>,
-}
-
-impl V6Reader {
-    pub fn open(dump: TempDir) -> Result<Self> {
-        let meta_file = fs::read(dump.path().join("metadata.json"))?;
-        let instance_uid = match fs::read_to_string(dump.path().join("instance_uid.uuid")) {
-            Ok(uuid) => Some(Uuid::parse_str(&uuid)?),
-            Err(e) if e.kind() == ErrorKind::NotFound => None,
-            Err(e) => return Err(e.into()),
-        };
-
-        let feature_file = match fs::read(dump.path().join("experimental-features.json")) {
-            Ok(feature_file) => Some(feature_file),
-            Err(error) => match error.kind() {
-                // Allows the file to be missing, this will only result in all experimental features disabled.
-                ErrorKind::NotFound => {
-                    debug!("`experimental-features.json` not found in dump");
-                    None
-                }
-                _ => return Err(error.into()),
-            },
-        };
-        let features = if let Some(feature_file) = feature_file {
-            Some(serde_json::from_reader(&*feature_file)?)
-        } else {
-            None
-        };
-        let batches = match File::open(dump.path().join("batches").join("queue.jsonl")) {
-            Ok(file) => Some(BufReader::new(file)),
-            // The batch file was only introduced during the v1.13, anything prior to that won't have batches
-            Err(err) if err.kind() == ErrorKind::NotFound => None,
-            Err(e) => return Err(e.into()),
-        };
-
-        let network = match fs::read(dump.path().join("network.json")) {
-            Ok(network_file) => Some(serde_json::from_reader(&*network_file)?),
-            Err(error) => match error.kind() {
-                // Allows the file to be missing, this will only result in all experimental features disabled.
-                ErrorKind::NotFound => {
-                    debug!("`network.json` not found in dump");
-                    None
-                }
-                _ => return Err(error.into()),
-            },
-        };
-
-        let webhooks = match fs::read(dump.path().join("webhooks.json")) {
-            Ok(webhooks_file) => Some(serde_json::from_reader(&*webhooks_file)?),
-            Err(error) => match error.kind() {
-                ErrorKind::NotFound => {
-                    debug!("`webhooks.json` not found in dump");
-                    None
-                }
-                _ => return Err(error.into()),
-            },
-        };
-
-        Ok(V6Reader {
-            metadata: serde_json::from_reader(&*meta_file)?,
-            instance_uid,
-            tasks: BufReader::new(File::open(dump.path().join("tasks").join("queue.jsonl"))?),
-            batches,
-            keys: BufReader::new(File::open(dump.path().join("keys.jsonl"))?),
-            features,
-            network,
-            dump,
-            webhooks,
-        })
-    }
-
-    pub fn version(&self) -> Version {
-        Version::V6
-    }
-
-    pub fn date(&self) -> Option<OffsetDateTime> {
-        Some(self.metadata.dump_date)
-    }
-
-    pub fn instance_uid(&self) -> Result<Option<Uuid>> {
-        Ok(self.instance_uid)
-    }
-
-    pub fn indexes(&self) -> Result<Box<dyn Iterator<Item = Result<V6IndexReader>> + '_>> {
-        let entries = fs::read_dir(self.dump.path().join("indexes"))?;
-        Ok(Box::new(
-            entries
-                .map(|entry| -> Result<Option<_>> {
-                    let entry = entry?;
-                    if entry.file_type()?.is_dir() {
-                        let index = V6IndexReader::new(
-                            entry.file_name().to_str().ok_or(Error::BadIndexName)?.to_string(),
-                            &entry.path(),
-                        )?;
-                        Ok(Some(index))
-                    } else {
-                        Ok(None)
-                    }
-                })
-                .filter_map(|entry| entry.transpose()),
-        ))
-    }
-
-    pub fn tasks(
-        &mut self,
-    ) -> Box<dyn Iterator<Item = Result<(Task, Option<Box<super::UpdateFile>>)>> + '_> {
-        Box::new((&mut self.tasks).lines().map(|line| -> Result<_> {
-            let task: Task = serde_json::from_str(&line?)?;
-
-            let update_file_path = self
-                .dump
-                .path()
-                .join("tasks")
-                .join("update_files")
-                .join(format!("{}.jsonl", task.uid));
-
-            if update_file_path.exists() {
-                Ok((
-                    task,
-                    Some(Box::new(UpdateFile::new(&update_file_path)?) as Box<super::UpdateFile>),
-                ))
-            } else {
-                Ok((task, None))
-            }
-        }))
-    }
-
-    pub fn batches(&mut self) -> Box<dyn Iterator<Item = Result<Batch>> + '_> {
-        match self.batches.as_mut() {
-            Some(batches) => Box::new((batches).lines().map(|line| -> Result<_> {
-                let batch = serde_json::from_str(&line?)?;
-                Ok(batch)
-            })),
-            None => Box::new(std::iter::empty()) as Box<dyn Iterator<Item = Result<Batch>> + '_>,
-        }
-    }
-
-    pub fn keys(&mut self) -> Box<dyn Iterator<Item = Result<Key>> + '_> {
-        Box::new(
-            (&mut self.keys).lines().map(|line| -> Result<_> { Ok(serde_json::from_str(&line?)?) }),
-        )
-    }
-
-    pub fn chat_completions_settings(
-        &mut self,
-    ) -> Result<Box<dyn Iterator<Item = Result<(String, ChatCompletionSettings)>> + '_>> {
-        let entries = match fs::read_dir(self.dump.path().join("chat-completions-settings")) {
-            Ok(entries) => entries,
-            Err(e) if e.kind() == ErrorKind::NotFound => return Ok(Box::new(std::iter::empty())),
-            Err(e) => return Err(e.into()),
-        };
-        Ok(Box::new(
-            entries
-                .map(|entry| -> Result<Option<_>> {
-                    let entry = entry?;
-                    let file_name = entry.file_name();
-                    let path = Path::new(&file_name);
-                    if entry.file_type()?.is_file() && path.extension() == Some(OsStr::new("json"))
-                    {
-                        let name = path.file_stem().unwrap().to_str().unwrap().to_string();
-                        let file = File::open(entry.path())?;
-                        let settings = serde_json::from_reader(file)?;
-                        Ok(Some((name, settings)))
-                    } else {
-                        Ok(None)
-                    }
-                })
-                .filter_map(|entry| entry.transpose()),
-        ))
-    }
-
-    pub fn features(&self) -> Option<RuntimeTogglableFeatures> {
-        self.features
-    }
-
-    pub fn network(&self) -> Option<&Network> {
-        self.network.as_ref()
-    }
-
-    pub fn webhooks(&self) -> Option<&Webhooks> {
-        self.webhooks.as_ref()
-    }
-}
-
-pub struct UpdateFile {
-    reader: BufReader<File>,
-}
-
-impl UpdateFile {
-    fn new(path: &Path) -> Result<Self> {
-        Ok(UpdateFile { reader: BufReader::new(File::open(path)?) })
-    }
-}
-
-impl Iterator for UpdateFile {
-    type Item = Result<Document>;
-
-    fn next(&mut self) -> Option<Self::Item> {
-        (&mut self.reader)
-            .lines()
-            .map(|line| {
-                line.map_err(Error::from)
-                    .and_then(|line| serde_json::from_str(&line).map_err(Error::from))
-            })
-            .next()
-    }
-}
-
-pub struct V6IndexReader {
-    metadata: IndexMetadata,
-    documents: BufReader<File>,
-    settings: BufReader<File>,
-}
-
-impl V6IndexReader {
-    pub fn new(_name: String, path: &Path) -> Result<Self> {
-        let metadata = File::open(path.join("metadata.json"))?;
-
-        let ret = V6IndexReader {
-            metadata: serde_json::from_reader(metadata)?,
-            documents: BufReader::new(File::open(path.join("documents.jsonl"))?),
-            settings: BufReader::new(File::open(path.join("settings.json"))?),
-        };
-
-        Ok(ret)
-    }
-
-    pub fn metadata(&self) -> &IndexMetadata {
-        &self.metadata
-    }
-
-    pub fn documents(&mut self) -> Result<impl Iterator<Item = Result<Document>> + '_> {
-        Ok((&mut self.documents)
-            .lines()
-            .map(|line| -> Result<_> { Ok(serde_json::from_str(&line?)?) }))
-    }
-
-    pub fn documents_file(&self) -> &File {
-        self.documents.get_ref()
-    }
-
-    pub fn settings(&mut self) -> Result<Settings<Checked>> {
-        let mut settings: Settings<Unchecked> = serde_json::from_reader(&mut self.settings)?;
-        patch_embedders(&mut settings);
-        Ok(settings.check())
-    }
-}
-
-fn patch_embedders(settings: &mut Settings<Unchecked>) {
-    if let Setting::Set(embedders) = &mut settings.embedders {
-        for settings in embedders.values_mut() {
-            let Setting::Set(settings) = &mut settings.inner else {
-                continue;
-            };
-            if settings.source != Setting::Set(milli::vector::settings::EmbedderSource::HuggingFace)
-            {
-                continue;
-            }
-            settings.pooling = match settings.pooling {
-                Setting::Set(pooling) => Setting::Set(pooling),
-                // if the pooling for a hugging face embedder is not set, force it to `forceMean`
-                // for backward compatibility with v1.13
-                // dumps created in v1.14 and up will have the setting set for hugging face embedders
-                Setting::Reset | Setting::NotSet => Setting::Set(OverridePooling::ForceMean),
-            };
-        }
-    }
-}

crates/filter-parser/src/condition.rs

@@ -1,257 +0,0 @@
-//! BNF grammar:
-//!
-//! ```text
-//! condition      = value ("==" | ">" ...) value
-//! to             = value value TO value
-//! ```
-
-use nom::branch::alt;
-use nom::bytes::complete::tag;
-use nom::character::complete::{char, multispace0, multispace1};
-use nom::combinator::{cut, map, value};
-use nom::sequence::{preceded, terminated, tuple};
-use Condition::*;
-
-use crate::error::IResultExt;
-use crate::value::{parse_vector_value, parse_vector_value_cut};
-use crate::{parse_value, Error, ErrorKind, FilterCondition, IResult, Span, Token, VectorFilter};
-
-#[derive(Debug, Clone, PartialEq, Eq)]
-pub enum Condition<'a> {
-    GreaterThan(Token<'a>),
-    GreaterThanOrEqual(Token<'a>),
-    Equal(Token<'a>),
-    NotEqual(Token<'a>),
-    Null,
-    Empty,
-    Exists,
-    LowerThan(Token<'a>),
-    LowerThanOrEqual(Token<'a>),
-    Between { from: Token<'a>, to: Token<'a> },
-    Contains { keyword: Token<'a>, word: Token<'a> },
-    StartsWith { keyword: Token<'a>, word: Token<'a> },
-}
-
-impl Condition<'_> {
-    pub fn operator(&self) -> &str {
-        match self {
-            Condition::GreaterThan(_) => ">",
-            Condition::GreaterThanOrEqual(_) => ">=",
-            Condition::Equal(_) => "=",
-            Condition::NotEqual(_) => "!=",
-            Condition::Null => "IS NULL",
-            Condition::Empty => "IS EMPTY",
-            Condition::Exists => "EXISTS",
-            Condition::LowerThan(_) => "<",
-            Condition::LowerThanOrEqual(_) => "<=",
-            Condition::Between { .. } => "TO",
-            Condition::Contains { .. } => "CONTAINS",
-            Condition::StartsWith { .. } => "STARTS WITH",
-        }
-    }
-}
-
-/// condition      = value ("==" | ">" ...) value
-pub fn parse_condition(input: Span) -> IResult<FilterCondition> {
-    let operator = alt((tag("<="), tag(">="), tag("!="), tag("<"), tag(">"), tag("=")));
-    let (input, (fid, op, value)) = tuple((parse_value, operator, cut(parse_value)))(input)?;
-
-    let condition = match *op.fragment() {
-        "<=" => FilterCondition::Condition { fid, op: LowerThanOrEqual(value) },
-        ">=" => FilterCondition::Condition { fid, op: GreaterThanOrEqual(value) },
-        "!=" => FilterCondition::Condition { fid, op: NotEqual(value) },
-        "<" => FilterCondition::Condition { fid, op: LowerThan(value) },
-        ">" => FilterCondition::Condition { fid, op: GreaterThan(value) },
-        "=" => FilterCondition::Condition { fid, op: Equal(value) },
-        _ => unreachable!(),
-    };
-
-    Ok((input, condition))
-}
-
-/// null          = value "IS" WS+ "NULL"
-pub fn parse_is_null(input: Span) -> IResult<FilterCondition> {
-    let (input, key) = parse_value(input)?;
-
-    let (input, _) = tuple((tag("IS"), multispace1, tag("NULL")))(input)?;
-    Ok((input, FilterCondition::Condition { fid: key, op: Null }))
-}
-
-/// null          = value "IS" WS+ "NOT" WS+ "NULL"
-pub fn parse_is_not_null(input: Span) -> IResult<FilterCondition> {
-    let (input, key) = parse_value(input)?;
-
-    let (input, _) = tuple((tag("IS"), multispace1, tag("NOT"), multispace1, tag("NULL")))(input)?;
-    Ok((input, FilterCondition::Not(Box::new(FilterCondition::Condition { fid: key, op: Null }))))
-}
-
-/// empty          = value "IS" WS+ "EMPTY"
-pub fn parse_is_empty(input: Span) -> IResult<FilterCondition> {
-    let (input, key) = parse_value(input)?;
-
-    let (input, _) = tuple((tag("IS"), multispace1, tag("EMPTY")))(input)?;
-    Ok((input, FilterCondition::Condition { fid: key, op: Empty }))
-}
-
-/// empty          = value "IS" WS+ "NOT" WS+ "EMPTY"
-pub fn parse_is_not_empty(input: Span) -> IResult<FilterCondition> {
-    let (input, key) = parse_value(input)?;
-
-    let (input, _) = tuple((tag("IS"), multispace1, tag("NOT"), multispace1, tag("EMPTY")))(input)?;
-    Ok((input, FilterCondition::Not(Box::new(FilterCondition::Condition { fid: key, op: Empty }))))
-}
-
-/// exist          = value "EXISTS"
-pub fn parse_exists(input: Span) -> IResult<FilterCondition> {
-    let (input, key) = terminated(parse_value, tag("EXISTS"))(input)?;
-
-    Ok((input, FilterCondition::Condition { fid: key, op: Exists }))
-}
-/// exist          = value "NOT" WS+ "EXISTS"
-pub fn parse_not_exists(input: Span) -> IResult<FilterCondition> {
-    let (input, key) = parse_value(input)?;
-
-    let (input, _) = tuple((tag("NOT"), multispace1, tag("EXISTS")))(input)?;
-    Ok((input, FilterCondition::Not(Box::new(FilterCondition::Condition { fid: key, op: Exists }))))
-}
-
-fn parse_vectors(input: Span) -> IResult<(Token, Option<Token>, VectorFilter)> {
-    let (input, _) = multispace0(input)?;
-    let (input, fid) = tag("_vectors")(input)?;
-
-    if let Ok((input, _)) = multispace1::<_, crate::Error>(input) {
-        return Ok((input, (Token::from(fid), None, VectorFilter::None)));
-    }
-
-    let (input, _) = char('.')(input)?;
-
-    // From this point, we are certain this is a vector filter, so our errors must be final.
-    // We could use nom's `cut` but it's better to be explicit about the errors
-
-    if let Ok((_, space)) = tag::<_, _, ()>(" ")(input) {
-        return Err(crate::Error::failure_from_kind(space, ErrorKind::VectorFilterMissingEmbedder));
-    }
-
-    let (input, embedder_name) =
-        parse_vector_value_cut(input, ErrorKind::VectorFilterInvalidEmbedder)?;
-
-    let (input, filter) = alt((
-        map(
-            preceded(tag(".fragments"), |input| {
-                let (input, _) = tag(".")(input).map_cut(ErrorKind::VectorFilterMissingFragment)?;
-                parse_vector_value_cut(input, ErrorKind::VectorFilterInvalidFragment)
-            }),
-            VectorFilter::Fragment,
-        ),
-        value(VectorFilter::UserProvided, tag(".userProvided")),
-        value(VectorFilter::DocumentTemplate, tag(".documentTemplate")),
-        value(VectorFilter::Regenerate, tag(".regenerate")),
-        value(VectorFilter::None, nom::combinator::success("")),
-    ))(input)?;
-
-    if let Ok((input, point)) = tag::<_, _, ()>(".")(input) {
-        let opt_value = parse_vector_value(input).ok().map(|(_, v)| v);
-        let value =
-            opt_value.as_ref().map(|v| v.value().to_owned()).unwrap_or_else(|| point.to_string());
-        let context = opt_value.map(|v| v.original_span()).unwrap_or(point);
-        let previous_kind = match filter {
-            VectorFilter::Fragment(_) => Some("fragments"),
-            VectorFilter::DocumentTemplate => Some("documentTemplate"),
-            VectorFilter::UserProvided => Some("userProvided"),
-            VectorFilter::Regenerate => Some("regenerate"),
-            VectorFilter::None => None,
-        };
-        return Err(Error::failure_from_kind(
-            context,
-            ErrorKind::VectorFilterUnknownSuffix(previous_kind, value),
-        ));
-    }
-
-    let (input, _) = multispace1(input).map_cut(ErrorKind::VectorFilterLeftover)?;
-
-    Ok((input, (Token::from(fid), Some(embedder_name), filter)))
-}
-
-/// vectors_exists          = vectors ("EXISTS" | ("NOT" WS+ "EXISTS"))
-pub fn parse_vectors_exists(input: Span) -> IResult<FilterCondition> {
-    let (input, (fid, embedder, filter)) = parse_vectors(input)?;
-
-    // Try parsing "EXISTS" first
-    if let Ok((input, _)) = tag::<_, _, ()>("EXISTS")(input) {
-        return Ok((input, FilterCondition::VectorExists { fid, embedder, filter }));
-    }
-
-    // Try parsing "NOT EXISTS"
-    if let Ok((input, _)) = tuple::<_, _, (), _>((tag("NOT"), multispace1, tag("EXISTS")))(input) {
-        return Ok((
-            input,
-            FilterCondition::Not(Box::new(FilterCondition::VectorExists { fid, embedder, filter })),
-        ));
-    }
-
-    Err(crate::Error::failure_from_kind(input, ErrorKind::VectorFilterOperation))
-}
-
-/// contains        = value "CONTAINS" value
-pub fn parse_contains(input: Span) -> IResult<FilterCondition> {
-    let (input, (fid, contains, value)) =
-        tuple((parse_value, tag("CONTAINS"), cut(parse_value)))(input)?;
-    Ok((
-        input,
-        FilterCondition::Condition {
-            fid,
-            op: Contains { keyword: Token { span: contains, value: None }, word: value },
-        },
-    ))
-}
-
-/// contains        = value "NOT" WS+ "CONTAINS" value
-pub fn parse_not_contains(input: Span) -> IResult<FilterCondition> {
-    let keyword = tuple((tag("NOT"), multispace1, tag("CONTAINS")));
-    let (input, (fid, (_not, _spaces, contains), value)) =
-        tuple((parse_value, keyword, cut(parse_value)))(input)?;
-
-    Ok((
-        input,
-        FilterCondition::Not(Box::new(FilterCondition::Condition {
-            fid,
-            op: Contains { keyword: Token { span: contains, value: None }, word: value },
-        })),
-    ))
-}
-
-/// starts with        = value "CONTAINS" value
-pub fn parse_starts_with(input: Span) -> IResult<FilterCondition> {
-    let (input, (fid, starts_with, value)) =
-        tuple((parse_value, tag("STARTS WITH"), cut(parse_value)))(input)?;
-    Ok((
-        input,
-        FilterCondition::Condition {
-            fid,
-            op: StartsWith { keyword: Token { span: starts_with, value: None }, word: value },
-        },
-    ))
-}
-
-/// starts with        = value "NOT" WS+ "CONTAINS" value
-pub fn parse_not_starts_with(input: Span) -> IResult<FilterCondition> {
-    let keyword = tuple((tag("NOT"), multispace1, tag("STARTS WITH")));
-    let (input, (fid, (_not, _spaces, starts_with), value)) =
-        tuple((parse_value, keyword, cut(parse_value)))(input)?;
-
-    Ok((
-        input,
-        FilterCondition::Not(Box::new(FilterCondition::Condition {
-            fid,
-            op: StartsWith { keyword: Token { span: starts_with, value: None }, word: value },
-        })),
-    ))
-}
-
-/// to             = value value "TO" WS+ value
-pub fn parse_to(input: Span) -> IResult<FilterCondition> {
-    let (input, (key, from, _, _, to)) =
-        tuple((parse_value, parse_value, tag("TO"), multispace1, cut(parse_value)))(input)?;
-
-    Ok((input, FilterCondition::Condition { fid: key, op: Between { from, to } }))
-}

crates/fuzzers/Cargo.toml

@@ -1,22 +0,0 @@
-[package]
-name = "fuzzers"
-publish = false
-
-version.workspace = true
-authors.workspace = true
-description.workspace = true
-homepage.workspace = true
-readme.workspace = true
-edition.workspace = true
-license.workspace = true
-
-[dependencies]
-arbitrary = { version = "1.4.1", features = ["derive"] }
-bumpalo = "3.18.1"
-clap = { version = "4.5.40", features = ["derive"] }
-either = "1.15.0"
-fastrand = "2.3.0"
-milli = { path = "../milli" }
-serde = { version = "1.0.219", features = ["derive"] }
-serde_json = { version = "1.0.140", features = ["preserve_order"] }
-tempfile = "3.20.0"

crates/fuzzers/README.md

@@ -1,3 +0,0 @@
-# Fuzzers
-
-The purpose of this crate is to contains all the handmade "fuzzer" we may need.

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

@@ -1,193 +0,0 @@
-use std::num::NonZeroUsize;
-use std::path::PathBuf;
-use std::sync::atomic::{AtomicBool, AtomicUsize, Ordering};
-use std::time::Duration;
-
-use arbitrary::{Arbitrary, Unstructured};
-use bumpalo::Bump;
-use clap::Parser;
-use either::Either;
-use fuzzers::Operation;
-use milli::documents::mmap_from_objects;
-use milli::heed::EnvOpenOptions;
-use milli::progress::Progress;
-use milli::update::new::indexer;
-use milli::update::IndexerConfig;
-use milli::vector::RuntimeEmbedders;
-use milli::Index;
-use serde_json::Value;
-use tempfile::TempDir;
-
-#[derive(Debug, Arbitrary)]
-struct Batch([Operation; 5]);
-
-#[derive(Debug, Clone, Parser)]
-struct Opt {
-    /// The number of fuzzer to run in parallel.
-    #[clap(long)]
-    par: Option<NonZeroUsize>,
-    // We need to put a lot of newlines in the following documentation or else everything gets collapsed on one line
-    /// The path in which the databases will be created.
-    /// Using a ramdisk is recommended.
-    ///
-    /// Linux:
-    ///
-    /// sudo mount -t tmpfs -o size=2g tmpfs ramdisk # to create it
-    ///
-    /// sudo umount ramdisk # to remove it
-    ///
-    /// MacOS:
-    ///
-    /// diskutil erasevolume HFS+ 'RAM Disk' `hdiutil attach -nobrowse -nomount ram://4194304 # create it
-    ///
-    /// hdiutil detach /dev/:the_disk
-    #[clap(long)]
-    path: Option<PathBuf>,
-}
-
-fn main() {
-    let opt = Opt::parse();
-    let progression: &'static AtomicUsize = Box::leak(Box::new(AtomicUsize::new(0)));
-    let stop: &'static AtomicBool = Box::leak(Box::new(AtomicBool::new(false)));
-
-    let par = opt.par.unwrap_or_else(|| std::thread::available_parallelism().unwrap()).get();
-    let mut handles = Vec::with_capacity(par);
-
-    for _ in 0..par {
-        let opt = opt.clone();
-
-        let handle = std::thread::spawn(move || {
-            let options = EnvOpenOptions::new();
-            let mut options = options.read_txn_without_tls();
-            options.map_size(1024 * 1024 * 1024 * 1024);
-            let tempdir = match opt.path {
-                Some(path) => TempDir::new_in(path).unwrap(),
-                None => TempDir::new().unwrap(),
-            };
-            let index = Index::new(options, tempdir.path(), true).unwrap();
-            let indexer_config = IndexerConfig::default();
-
-            std::thread::scope(|s| {
-                loop {
-                    if stop.load(Ordering::Relaxed) {
-                        return;
-                    }
-                    let v: Vec<u8> =
-                        std::iter::repeat_with(|| fastrand::u8(..)).take(1000).collect();
-
-                    let mut data = Unstructured::new(&v);
-                    let batches = <[Batch; 5]>::arbitrary(&mut data).unwrap();
-                    // will be used to display the error once a thread crashes
-                    let dbg_input = format!("{:#?}", batches);
-
-                    let handle = s.spawn(|| {
-                        let mut wtxn = index.write_txn().unwrap();
-                        let rtxn = index.read_txn().unwrap();
-
-                        for batch in batches {
-                            let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
-                            let mut new_fields_ids_map = db_fields_ids_map.clone();
-
-                            let indexer_alloc = Bump::new();
-                            let embedders = RuntimeEmbedders::default();
-                            let mut indexer = indexer::DocumentOperation::new();
-
-                            let mut operations = Vec::new();
-                            for op in batch.0 {
-                                match op {
-                                    Operation::AddDoc(doc) => {
-                                        let object = match doc.to_d() {
-                                            Value::Object(object) => object,
-                                            _ => unreachable!(),
-                                        };
-                                        let documents = mmap_from_objects(vec![object]);
-                                        operations.push(Either::Left(documents));
-                                    }
-                                    Operation::DeleteDoc(id) => {
-                                        let id = indexer_alloc.alloc_str(&id.to_s());
-                                        let ids = indexer_alloc.alloc_slice_copy(&[&*id]);
-                                        operations.push(Either::Right(ids));
-                                    }
-                                }
-                            }
-
-                            for op in &operations {
-                                match op {
-                                    Either::Left(documents) => {
-                                        indexer.replace_documents(documents).unwrap()
-                                    }
-                                    Either::Right(ids) => indexer.delete_documents(ids),
-                                }
-                            }
-
-                            let (document_changes, _operation_stats, primary_key) = indexer
-                                .into_changes(
-                                    &indexer_alloc,
-                                    &index,
-                                    &rtxn,
-                                    None,
-                                    &mut new_fields_ids_map,
-                                    &|| false,
-                                    Progress::default(),
-                                    None,
-                                )
-                                .unwrap();
-
-                            indexer::index(
-                                &mut wtxn,
-                                &index,
-                                &milli::ThreadPoolNoAbortBuilder::new().build().unwrap(),
-                                indexer_config.grenad_parameters(),
-                                &db_fields_ids_map,
-                                new_fields_ids_map,
-                                primary_key,
-                                &document_changes,
-                                embedders,
-                                &|| false,
-                                &Progress::default(),
-                                &Default::default(),
-                            )
-                            .unwrap();
-
-                            // after executing a batch we check if the database is corrupted
-                            let res = index.search(&wtxn).execute().unwrap();
-                            index.documents(&wtxn, res.documents_ids).unwrap();
-                            progression.fetch_add(1, Ordering::Relaxed);
-                        }
-                        wtxn.abort();
-                    });
-                    if let err @ Err(_) = handle.join() {
-                        stop.store(true, Ordering::Relaxed);
-                        err.expect(&dbg_input);
-                    }
-                }
-            });
-        });
-        handles.push(handle);
-    }
-
-    std::thread::spawn(|| {
-        let mut last_value = 0;
-        let start = std::time::Instant::now();
-        loop {
-            let total = progression.load(Ordering::Relaxed);
-            let elapsed = start.elapsed().as_secs();
-            if elapsed > 3600 {
-                // after 1 hour, stop the fuzzer, success
-                std::process::exit(0);
-            }
-            println!(
-                "Has been running for {:?} seconds. Tested {} new values for a total of {}.",
-                elapsed,
-                total - last_value,
-                total
-            );
-            last_value = total;
-            std::thread::sleep(Duration::from_secs(1));
-        }
-    });
-
-    for handle in handles {
-        handle.join().unwrap();
-    }
-}

crates/fuzzers/src/lib.rs

@@ -1,46 +0,0 @@
-use arbitrary::Arbitrary;
-use serde_json::{json, Value};
-
-#[derive(Debug, Arbitrary)]
-pub enum Document {
-    One,
-    Two,
-    Three,
-    Four,
-    Five,
-    Six,
-}
-
-impl Document {
-    pub fn to_d(&self) -> Value {
-        match self {
-            Document::One => json!({ "id": 0, "doggo": "bernese" }),
-            Document::Two => json!({ "id": 0, "doggo": "golden" }),
-            Document::Three => json!({ "id": 0, "catto": "jorts" }),
-            Document::Four => json!({ "id": 1, "doggo": "bernese" }),
-            Document::Five => json!({ "id": 1, "doggo": "golden" }),
-            Document::Six => json!({ "id": 1, "catto": "jorts" }),
-        }
-    }
-}
-
-#[derive(Debug, Arbitrary)]
-pub enum DocId {
-    Zero,
-    One,
-}
-
-impl DocId {
-    pub fn to_s(&self) -> String {
-        match self {
-            DocId::Zero => "0".to_string(),
-            DocId::One => "1".to_string(),
-        }
-    }
-}
-
-#[derive(Debug, Arbitrary)]
-pub enum Operation {
-    AddDoc(Document),
-    DeleteDoc(DocId),
-}

crates/index-scheduler/Cargo.toml

@@ -1,55 +0,0 @@
-[package]
-name = "index-scheduler"
-publish = false
-
-version.workspace = true
-authors.workspace = true
-description.workspace = true
-homepage.workspace = true
-readme.workspace = true
-edition.workspace = true
-license.workspace = true
-
-[dependencies]
-anyhow = "1.0.98"
-bincode = "1.3.3"
-byte-unit = "5.1.6"
-bumpalo = "3.18.1"
-bumparaw-collections = "0.1.4"
-convert_case = "0.8.0"
-csv = "1.3.1"
-derive_builder = "0.20.2"
-dump = { path = "../dump" }
-enum-iterator = "2.1.0"
-file-store = { path = "../file-store" }
-flate2 = "1.1.2"
-indexmap = "2.9.0"
-meilisearch-auth = { path = "../meilisearch-auth" }
-meilisearch-types = { path = "../meilisearch-types" }
-memmap2 = "0.9.7"
-page_size = "0.6.0"
-rayon = "1.10.0"
-roaring = { version = "0.10.12", features = ["serde"] }
-serde = { version = "1.0.219", features = ["derive"] }
-serde_json = { version = "1.0.140", features = ["preserve_order"] }
-synchronoise = "1.0.1"
-tempfile = "3.20.0"
-thiserror = "2.0.12"
-time = { version = "0.3.41", features = [
-    "serde-well-known",
-    "formatting",
-    "parsing",
-    "macros",
-] }
-tracing = "0.1.41"
-ureq = "2.12.1"
-uuid = { version = "1.17.0", features = ["serde", "v4"] }
-backoff = "0.4.0"
-
-[dev-dependencies]
-big_s = "1.0.2"
-crossbeam-channel = "0.5.15"
-# fixed version due to format breakages in v1.40
-insta = { version = "=1.39.0", features = ["json", "redactions"] }
-maplit = "1.0.2"
-meili-snap = { path = "../meili-snap" }

crates/index-scheduler/src/dump.rs

@@ -1,326 +0,0 @@
-#![allow(clippy::result_large_err)]
-
-use std::collections::HashMap;
-use std::io;
-
-use dump::{KindDump, TaskDump, UpdateFile};
-use meilisearch_types::batches::{Batch, BatchId};
-use meilisearch_types::heed::RwTxn;
-use meilisearch_types::index_uid_pattern::IndexUidPattern;
-use meilisearch_types::milli;
-use meilisearch_types::tasks::{Kind, KindWithContent, Status, Task};
-use roaring::RoaringBitmap;
-use uuid::Uuid;
-
-use crate::{utils, Error, IndexScheduler, Result};
-
-pub struct Dump<'a> {
-    index_scheduler: &'a IndexScheduler,
-    wtxn: RwTxn<'a>,
-
-    batch_to_task_mapping: HashMap<BatchId, RoaringBitmap>,
-
-    indexes: HashMap<String, RoaringBitmap>,
-    statuses: HashMap<Status, RoaringBitmap>,
-    kinds: HashMap<Kind, RoaringBitmap>,
-
-    batch_indexes: HashMap<String, RoaringBitmap>,
-    batch_statuses: HashMap<Status, RoaringBitmap>,
-    batch_kinds: HashMap<Kind, RoaringBitmap>,
-}
-
-impl<'a> Dump<'a> {
-    pub(crate) fn new(index_scheduler: &'a mut IndexScheduler) -> Result<Self> {
-        // While loading a dump no one should be able to access the scheduler thus I can block everything.
-        let wtxn = index_scheduler.env.write_txn()?;
-
-        Ok(Dump {
-            index_scheduler,
-            wtxn,
-            batch_to_task_mapping: HashMap::new(),
-            indexes: HashMap::new(),
-            statuses: HashMap::new(),
-            kinds: HashMap::new(),
-            batch_indexes: HashMap::new(),
-            batch_statuses: HashMap::new(),
-            batch_kinds: HashMap::new(),
-        })
-    }
-
-    /// Register a new batch coming from a dump in the scheduler.
-    /// By taking a mutable ref we're pretty sure no one will ever import a dump while actix is running.
-    pub fn register_dumped_batch(&mut self, batch: Batch) -> Result<()> {
-        self.index_scheduler.queue.batches.all_batches.put(&mut self.wtxn, &batch.uid, &batch)?;
-        if let Some(enqueued_at) = batch.enqueued_at {
-            utils::insert_task_datetime(
-                &mut self.wtxn,
-                self.index_scheduler.queue.batches.enqueued_at,
-                enqueued_at.earliest,
-                batch.uid,
-            )?;
-            utils::insert_task_datetime(
-                &mut self.wtxn,
-                self.index_scheduler.queue.batches.enqueued_at,
-                enqueued_at.oldest,
-                batch.uid,
-            )?;
-        }
-        utils::insert_task_datetime(
-            &mut self.wtxn,
-            self.index_scheduler.queue.batches.started_at,
-            batch.started_at,
-            batch.uid,
-        )?;
-        if let Some(finished_at) = batch.finished_at {
-            utils::insert_task_datetime(
-                &mut self.wtxn,
-                self.index_scheduler.queue.batches.finished_at,
-                finished_at,
-                batch.uid,
-            )?;
-        }
-
-        for index in batch.stats.index_uids.keys() {
-            match self.batch_indexes.get_mut(index) {
-                Some(bitmap) => {
-                    bitmap.insert(batch.uid);
-                }
-                None => {
-                    let mut bitmap = RoaringBitmap::new();
-                    bitmap.insert(batch.uid);
-                    self.batch_indexes.insert(index.to_string(), bitmap);
-                }
-            };
-        }
-
-        for status in batch.stats.status.keys() {
-            self.batch_statuses.entry(*status).or_default().insert(batch.uid);
-        }
-        for kind in batch.stats.types.keys() {
-            self.batch_kinds.entry(*kind).or_default().insert(batch.uid);
-        }
-
-        Ok(())
-    }
-
-    /// Register a new task coming from a dump in the scheduler.
-    /// By taking a mutable ref we're pretty sure no one will ever import a dump while actix is running.
-    pub fn register_dumped_task(
-        &mut self,
-        task: TaskDump,
-        content_file: Option<Box<UpdateFile>>,
-    ) -> Result<Task> {
-        let task_has_no_docs = matches!(task.kind, KindDump::DocumentImport { documents_count, .. } if documents_count == 0);
-
-        let content_uuid = match content_file {
-            Some(content_file) if task.status == Status::Enqueued => {
-                let (uuid, file) = self.index_scheduler.queue.create_update_file(false)?;
-                let mut writer = io::BufWriter::new(file);
-                for doc in content_file {
-                    let doc = doc?;
-                    serde_json::to_writer(&mut writer, &doc).map_err(|e| {
-                        Error::from_milli(milli::InternalError::SerdeJson(e).into(), None)
-                    })?;
-                }
-                let file = writer.into_inner().map_err(|e| e.into_error())?;
-                file.persist()?;
-
-                Some(uuid)
-            }
-            // If the task isn't `Enqueued` then just generate a recognisable `Uuid`
-            // in case we try to open it later.
-            _ if task.status != Status::Enqueued => Some(Uuid::nil()),
-            None if task.status == Status::Enqueued && task_has_no_docs => {
-                let (uuid, file) = self.index_scheduler.queue.create_update_file(false)?;
-                file.persist()?;
-
-                Some(uuid)
-            }
-            _ => None,
-        };
-
-        let task = Task {
-            uid: task.uid,
-            batch_uid: task.batch_uid,
-            enqueued_at: task.enqueued_at,
-            started_at: task.started_at,
-            finished_at: task.finished_at,
-            error: task.error,
-            canceled_by: task.canceled_by,
-            details: task.details,
-            status: task.status,
-            network: task.network,
-            kind: match task.kind {
-                KindDump::DocumentImport {
-                    primary_key,
-                    method,
-                    documents_count,
-                    allow_index_creation,
-                } => KindWithContent::DocumentAdditionOrUpdate {
-                    index_uid: task.index_uid.ok_or(Error::CorruptedDump)?,
-                    primary_key,
-                    method,
-                    content_file: content_uuid.ok_or(Error::CorruptedDump)?,
-                    documents_count,
-                    allow_index_creation,
-                },
-                KindDump::DocumentDeletion { documents_ids } => KindWithContent::DocumentDeletion {
-                    documents_ids,
-                    index_uid: task.index_uid.ok_or(Error::CorruptedDump)?,
-                },
-                KindDump::DocumentDeletionByFilter { filter } => {
-                    KindWithContent::DocumentDeletionByFilter {
-                        filter_expr: filter,
-                        index_uid: task.index_uid.ok_or(Error::CorruptedDump)?,
-                    }
-                }
-                KindDump::DocumentEdition { filter, context, function } => {
-                    KindWithContent::DocumentEdition {
-                        index_uid: task.index_uid.ok_or(Error::CorruptedDump)?,
-                        filter_expr: filter,
-                        context,
-                        function,
-                    }
-                }
-                KindDump::DocumentClear => KindWithContent::DocumentClear {
-                    index_uid: task.index_uid.ok_or(Error::CorruptedDump)?,
-                },
-                KindDump::Settings { settings, is_deletion, allow_index_creation } => {
-                    KindWithContent::SettingsUpdate {
-                        index_uid: task.index_uid.ok_or(Error::CorruptedDump)?,
-                        new_settings: settings,
-                        is_deletion,
-                        allow_index_creation,
-                    }
-                }
-                KindDump::IndexDeletion => KindWithContent::IndexDeletion {
-                    index_uid: task.index_uid.ok_or(Error::CorruptedDump)?,
-                },
-                KindDump::IndexCreation { primary_key } => KindWithContent::IndexCreation {
-                    index_uid: task.index_uid.ok_or(Error::CorruptedDump)?,
-                    primary_key,
-                },
-                KindDump::IndexUpdate { primary_key, uid } => KindWithContent::IndexUpdate {
-                    index_uid: task.index_uid.ok_or(Error::CorruptedDump)?,
-                    primary_key,
-                    new_index_uid: uid,
-                },
-                KindDump::IndexSwap { swaps } => KindWithContent::IndexSwap { swaps },
-                KindDump::TaskCancelation { query, tasks } => {
-                    KindWithContent::TaskCancelation { query, tasks }
-                }
-                KindDump::TasksDeletion { query, tasks } => {
-                    KindWithContent::TaskDeletion { query, tasks }
-                }
-                KindDump::DumpCreation { keys, instance_uid } => {
-                    KindWithContent::DumpCreation { keys, instance_uid }
-                }
-                KindDump::SnapshotCreation => KindWithContent::SnapshotCreation,
-                KindDump::Export { url, api_key, payload_size, indexes } => {
-                    KindWithContent::Export {
-                        url,
-                        api_key,
-                        payload_size,
-                        indexes: indexes
-                            .into_iter()
-                            .map(|(pattern, settings)| {
-                                Ok((
-                                    IndexUidPattern::try_from(pattern)
-                                        .map_err(|_| Error::CorruptedDump)?,
-                                    settings,
-                                ))
-                            })
-                            .collect::<Result<_, Error>>()?,
-                    }
-                }
-                KindDump::UpgradeDatabase { from } => KindWithContent::UpgradeDatabase { from },
-            },
-        };
-
-        self.index_scheduler.queue.tasks.all_tasks.put(&mut self.wtxn, &task.uid, &task)?;
-        if let Some(batch_id) = task.batch_uid {
-            self.batch_to_task_mapping.entry(batch_id).or_default().insert(task.uid);
-        }
-
-        for index in task.indexes() {
-            match self.indexes.get_mut(index) {
-                Some(bitmap) => {
-                    bitmap.insert(task.uid);
-                }
-                None => {
-                    let mut bitmap = RoaringBitmap::new();
-                    bitmap.insert(task.uid);
-                    self.indexes.insert(index.to_string(), bitmap);
-                }
-            };
-        }
-
-        utils::insert_task_datetime(
-            &mut self.wtxn,
-            self.index_scheduler.queue.tasks.enqueued_at,
-            task.enqueued_at,
-            task.uid,
-        )?;
-
-        // we can't override the started_at & finished_at, so we must only set it if the tasks is finished and won't change
-        if matches!(task.status, Status::Succeeded | Status::Failed | Status::Canceled) {
-            if let Some(started_at) = task.started_at {
-                utils::insert_task_datetime(
-                    &mut self.wtxn,
-                    self.index_scheduler.queue.tasks.started_at,
-                    started_at,
-                    task.uid,
-                )?;
-            }
-            if let Some(finished_at) = task.finished_at {
-                utils::insert_task_datetime(
-                    &mut self.wtxn,
-                    self.index_scheduler.queue.tasks.finished_at,
-                    finished_at,
-                    task.uid,
-                )?;
-            }
-        }
-
-        self.statuses.entry(task.status).or_default().insert(task.uid);
-        self.kinds.entry(task.kind.as_kind()).or_default().insert(task.uid);
-
-        Ok(task)
-    }
-
-    /// Commit all the changes and exit the importing dump state
-    pub fn finish(mut self) -> Result<()> {
-        for (batch_id, task_ids) in self.batch_to_task_mapping {
-            self.index_scheduler.queue.batch_to_tasks_mapping.put(
-                &mut self.wtxn,
-                &batch_id,
-                &task_ids,
-            )?;
-        }
-
-        for (index, bitmap) in self.indexes {
-            self.index_scheduler.queue.tasks.index_tasks.put(&mut self.wtxn, &index, &bitmap)?;
-        }
-        for (status, bitmap) in self.statuses {
-            self.index_scheduler.queue.tasks.put_status(&mut self.wtxn, status, &bitmap)?;
-        }
-        for (kind, bitmap) in self.kinds {
-            self.index_scheduler.queue.tasks.put_kind(&mut self.wtxn, kind, &bitmap)?;
-        }
-
-        for (index, bitmap) in self.batch_indexes {
-            self.index_scheduler.queue.batches.index_tasks.put(&mut self.wtxn, &index, &bitmap)?;
-        }
-        for (status, bitmap) in self.batch_statuses {
-            self.index_scheduler.queue.batches.put_status(&mut self.wtxn, status, &bitmap)?;
-        }
-        for (kind, bitmap) in self.batch_kinds {
-            self.index_scheduler.queue.batches.put_kind(&mut self.wtxn, kind, &bitmap)?;
-        }
-
-        self.wtxn.commit()?;
-        self.index_scheduler.scheduler.wake_up.signal();
-
-        Ok(())
-    }
-}

crates/index-scheduler/src/error.rs

@@ -1,328 +0,0 @@
-use std::fmt::Display;
-
-use meilisearch_types::batches::BatchId;
-use meilisearch_types::error::{Code, ErrorCode};
-use meilisearch_types::milli::index::RollbackOutcome;
-use meilisearch_types::tasks::{Kind, Status};
-use meilisearch_types::{heed, milli};
-use thiserror::Error;
-
-use crate::TaskId;
-
-#[derive(Copy, Clone, Debug, PartialEq, Eq)]
-pub enum DateField {
-    BeforeEnqueuedAt,
-    AfterEnqueuedAt,
-    BeforeStartedAt,
-    AfterStartedAt,
-    BeforeFinishedAt,
-    AfterFinishedAt,
-}
-
-impl Display for DateField {
-    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
-        match self {
-            DateField::BeforeEnqueuedAt => write!(f, "beforeEnqueuedAt"),
-            DateField::AfterEnqueuedAt => write!(f, "afterEnqueuedAt"),
-            DateField::BeforeStartedAt => write!(f, "beforeStartedAt"),
-            DateField::AfterStartedAt => write!(f, "afterStartedAt"),
-            DateField::BeforeFinishedAt => write!(f, "beforeFinishedAt"),
-            DateField::AfterFinishedAt => write!(f, "afterFinishedAt"),
-        }
-    }
-}
-
-impl From<DateField> for Code {
-    fn from(date: DateField) -> Self {
-        match date {
-            DateField::BeforeEnqueuedAt => Code::InvalidTaskBeforeEnqueuedAt,
-            DateField::AfterEnqueuedAt => Code::InvalidTaskAfterEnqueuedAt,
-            DateField::BeforeStartedAt => Code::InvalidTaskBeforeStartedAt,
-            DateField::AfterStartedAt => Code::InvalidTaskAfterStartedAt,
-            DateField::BeforeFinishedAt => Code::InvalidTaskBeforeFinishedAt,
-            DateField::AfterFinishedAt => Code::InvalidTaskAfterFinishedAt,
-        }
-    }
-}
-
-#[allow(clippy::large_enum_variant)]
-#[derive(Error, Debug)]
-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.")]
-    IndexAlreadyExists(String),
-    #[error(
-        "Indexes must be declared only once during a swap. `{0}` was specified several times."
-    )]
-    SwapDuplicateIndexFound(String),
-    #[error(
-        "Indexes must be declared only once during a swap. {} were specified several times.",
-        .0.iter().map(|s| format!("`{}`", s)).collect::<Vec<_>>().join(", ")
-    )]
-    SwapDuplicateIndexesFound(Vec<String>),
-    #[error("Index `{0}` not found.")]
-    SwapIndexNotFound(String),
-    #[error("Cannot rename `{0}` to `{1}` as the index already exists. Hint: You can remove `{1}` first and then do your remove.")]
-    SwapIndexFoundDuringRename(String, String),
-    #[error("Meilisearch cannot receive write operations because the limit of the task database has been reached. Please delete tasks to continue performing write operations.")]
-    NoSpaceLeftInTaskQueue,
-    #[error(
-        "Indexes {} not found.",
-        .0.iter().map(|s| format!("`{}`", s)).collect::<Vec<_>>().join(", ")
-    )]
-    SwapIndexesNotFound(Vec<String>),
-    #[error("The following indexes are being renamed but cannot because their new name conflicts with an already existing index: {}. Renaming doesn't overwrite the other index name.",
-        .0.iter().map(|s| format!("`{}`", s)).collect::<Vec<_>>().join(", ")
-    )]
-    SwapIndexesFoundDuringRename(Vec<String>),
-    #[error("Corrupted dump.")]
-    CorruptedDump,
-    #[error(
-        "Task `{field}` `{date}` is invalid. It should follow the YYYY-MM-DD or RFC 3339 date-time format."
-    )]
-    InvalidTaskDate { field: DateField, date: String },
-    #[error("Task uid `{task_uid}` is invalid. It should only contain numeric characters.")]
-    InvalidTaskUid { task_uid: String },
-    #[error("Batch uid `{batch_uid}` is invalid. It should only contain numeric characters.")]
-    InvalidBatchUid { batch_uid: String },
-    #[error(
-        "Task status `{status}` is invalid. Available task statuses are {}.",
-            enum_iterator::all::<Status>()
-                .map(|s| format!("`{s}`"))
-                .collect::<Vec<String>>()
-                .join(", ")
-    )]
-    InvalidTaskStatuses { status: String },
-    #[error(
-        "Task type `{type_}` is invalid. Available task types are {}",
-            enum_iterator::all::<Kind>()
-                .map(|s| format!("`{s}`"))
-                .collect::<Vec<String>>()
-                .join(", ")
-    )]
-    InvalidTaskTypes { type_: String },
-    #[error(
-        "Task canceledBy `{canceled_by}` is invalid. It should only contains numeric characters separated by `,` character."
-    )]
-    InvalidTaskCanceledBy { canceled_by: String },
-    #[error(
-        "{index_uid} is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_), and can not be more than 400 bytes."
-    )]
-    InvalidIndexUid { index_uid: String },
-    #[error("Task `{0}` not found.")]
-    TaskNotFound(TaskId),
-    #[error("Task `{0}` does not contain any documents. Only `documentAdditionOrUpdate` tasks with the statuses `enqueued` or `processing` contain documents")]
-    TaskFileNotFound(TaskId),
-    #[error("Batch `{0}` not found.")]
-    BatchNotFound(BatchId),
-    #[error("Query parameters to filter the tasks to delete are missing. Available query parameters are: `uids`, `indexUids`, `statuses`, `types`, `canceledBy`, `beforeEnqueuedAt`, `afterEnqueuedAt`, `beforeStartedAt`, `afterStartedAt`, `beforeFinishedAt`, `afterFinishedAt`.")]
-    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),
-    #[error(transparent)]
-    Heed(#[from] heed::Error),
-    #[error("{}", match .index_uid {
-        Some(uid) if !uid.is_empty() => format!("Index `{}`: {error}", uid),
-        _ => format!("{error}")
-    })]
-    Milli { error: milli::Error, index_uid: Option<String> },
-    #[error("An unexpected crash occurred when processing the task: {0}")]
-    ProcessBatchPanicked(String),
-    #[error(transparent)]
-    FileStore(#[from] file_store::Error),
-    #[error(transparent)]
-    IoError(#[from] std::io::Error),
-    #[error(transparent)]
-    Persist(#[from] tempfile::PersistError),
-    #[error(transparent)]
-    FeatureNotEnabled(#[from] FeatureNotEnabledError),
-
-    #[error(transparent)]
-    Anyhow(#[from] anyhow::Error),
-
-    // Irrecoverable errors:
-    #[error(transparent)]
-    CreateBatch(Box<Self>),
-    #[error("Corrupted task queue.")]
-    CorruptedTaskQueue,
-    #[error(transparent)]
-    DatabaseUpgrade(Box<Self>),
-    #[error(transparent)]
-    Export(Box<Self>),
-    #[error("Failed to export documents to remote server {code} ({type}): {message} <{link}>")]
-    FromRemoteWhenExporting { message: String, code: String, r#type: String, link: String },
-    #[error("Failed to rollback for index `{index}`: {rollback_outcome} ")]
-    RollbackFailed { index: String, rollback_outcome: RollbackOutcome },
-    #[error(transparent)]
-    UnrecoverableError(Box<Self>),
-    #[error("The index scheduler is in version v{}.{}.{}, but Meilisearch is in version v{}.{}.{}.\n  - hint: start the correct version of Meilisearch, or consider updating your database. See also <https://www.meilisearch.com/docs/learn/update_and_migration/updating>",
-    index_scheduler_version.0, index_scheduler_version.1, index_scheduler_version.2,
-    package_version.0, package_version.1, package_version.2)]
-    IndexSchedulerVersionMismatch {
-        index_scheduler_version: (u32, u32, u32),
-        package_version: (u32, u32, u32),
-    },
-    #[error("Index `{index}` is in version v{}.{}.{}, but Meilisearch is in version v{}.{}.{}.\n  - note: this is an internal error, please consider filing a bug report: <https://github.com/meilisearch/meilisearch/issues/new?template=bug_report.md>",
-    index_version.0, index_version.1, index_version.2, package_version.0, package_version.1, package_version.2)]
-    IndexVersionMismatch {
-        index: String,
-        index_version: (u32, u32, u32),
-        package_version: (u32, u32, u32),
-    },
-    #[error(transparent)]
-    HeedTransaction(heed::Error),
-
-    #[cfg(test)]
-    #[error("Planned failure for tests.")]
-    PlannedFailure,
-}
-
-#[derive(Debug, thiserror::Error)]
-#[error(
-    "{disabled_action} requires enabling the `{feature}` experimental feature. See {issue_link}"
-)]
-pub struct FeatureNotEnabledError {
-    pub disabled_action: &'static str,
-    pub feature: &'static str,
-    pub issue_link: &'static str,
-}
-
-impl Error {
-    pub fn is_recoverable(&self) -> bool {
-        match self {
-            Error::IndexNotFound(_)
-            | Error::WithCustomErrorCode(_, _)
-            | Error::BadTaskId { .. }
-            | Error::IndexAlreadyExists(_)
-            | Error::SwapDuplicateIndexFound(_)
-            | Error::SwapDuplicateIndexesFound(_)
-            | Error::SwapIndexNotFound(_)
-            | Error::NoSpaceLeftInTaskQueue
-            | Error::SwapIndexesNotFound(_)
-            | Error::SwapIndexFoundDuringRename(_, _)
-            | Error::SwapIndexesFoundDuringRename(_)
-            | Error::CorruptedDump
-            | Error::InvalidTaskDate { .. }
-            | Error::InvalidTaskUid { .. }
-            | Error::InvalidBatchUid { .. }
-            | Error::InvalidTaskStatuses { .. }
-            | Error::InvalidTaskTypes { .. }
-            | Error::InvalidTaskCanceledBy { .. }
-            | Error::InvalidIndexUid { .. }
-            | Error::TaskNotFound(_)
-            | Error::TaskFileNotFound(_)
-            | Error::BatchNotFound(_)
-            | Error::TaskDeletionWithEmptyQuery
-            | Error::TaskCancelationWithEmptyQuery
-            | Error::FromRemoteWhenExporting { .. }
-            | Error::AbortedTask
-            | Error::Dump(_)
-            | Error::Heed(_)
-            | Error::Milli { .. }
-            | Error::ProcessBatchPanicked(_)
-            | Error::FileStore(_)
-            | Error::IoError(_)
-            | Error::Persist(_)
-            | Error::FeatureNotEnabled(_)
-            | Error::Export(_)
-            | Error::Anyhow(_) => true,
-            Error::CreateBatch(_)
-            | Error::CorruptedTaskQueue
-            | Error::DatabaseUpgrade(_)
-            | Error::UnrecoverableError(_)
-            | Error::IndexSchedulerVersionMismatch { .. }
-            | Error::IndexVersionMismatch { .. }
-            | Error::RollbackFailed { .. }
-            | Error::HeedTransaction(_) => false,
-            #[cfg(test)]
-            Error::PlannedFailure => false,
-        }
-    }
-
-    pub fn with_custom_error_code(self, code: Code) -> Self {
-        Self::WithCustomErrorCode(code, Box::new(self))
-    }
-
-    pub fn from_milli(err: milli::Error, index_uid: Option<String>) -> Self {
-        match err {
-            milli::Error::UserError(milli::UserError::InvalidFilter(_)) => {
-                Self::Milli { error: err, index_uid }
-                    .with_custom_error_code(Code::InvalidDocumentFilter)
-            }
-            milli::Error::UserError(milli::UserError::InvalidFilterExpression { .. }) => {
-                Self::Milli { error: err, index_uid }
-                    .with_custom_error_code(Code::InvalidDocumentFilter)
-            }
-            _ => Self::Milli { error: err, index_uid },
-        }
-    }
-}
-
-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,
-            Error::SwapDuplicateIndexFound(_) => Code::InvalidSwapDuplicateIndexFound,
-            Error::SwapIndexNotFound(_) => Code::IndexNotFound,
-            Error::SwapIndexesNotFound(_) => Code::IndexNotFound,
-            Error::SwapIndexFoundDuringRename(_, _) => Code::IndexAlreadyExists,
-            Error::SwapIndexesFoundDuringRename(_) => Code::IndexAlreadyExists,
-            Error::InvalidTaskDate { field, .. } => (*field).into(),
-            Error::InvalidTaskUid { .. } => Code::InvalidTaskUids,
-            Error::InvalidBatchUid { .. } => Code::InvalidBatchUids,
-            Error::InvalidTaskStatuses { .. } => Code::InvalidTaskStatuses,
-            Error::InvalidTaskTypes { .. } => Code::InvalidTaskTypes,
-            Error::InvalidTaskCanceledBy { .. } => Code::InvalidTaskCanceledBy,
-            Error::InvalidIndexUid { .. } => Code::InvalidIndexUid,
-            Error::TaskNotFound(_) => Code::TaskNotFound,
-            Error::TaskFileNotFound(_) => Code::TaskFileNotFound,
-            Error::BatchNotFound(_) => Code::BatchNotFound,
-            Error::TaskDeletionWithEmptyQuery => Code::MissingTaskFilters,
-            Error::TaskCancelationWithEmptyQuery => Code::MissingTaskFilters,
-            // TODO: not sure of the Code to use
-            Error::NoSpaceLeftInTaskQueue => Code::NoSpaceLeftOnDevice,
-            Error::Dump(e) => e.error_code(),
-            Error::Milli { error, .. } => error.error_code(),
-            Error::ProcessBatchPanicked(_) => Code::Internal,
-            Error::FromRemoteWhenExporting { .. } => Code::Internal,
-            Error::Heed(e) => e.error_code(),
-            Error::HeedTransaction(e) => e.error_code(),
-            Error::FileStore(e) => e.error_code(),
-            Error::IoError(e) => e.error_code(),
-            Error::Persist(e) => e.error_code(),
-            Error::FeatureNotEnabled(_) => Code::FeatureNotEnabled,
-
-            // Irrecoverable errors
-            Error::Anyhow(_) => Code::Internal,
-            Error::CorruptedTaskQueue => Code::Internal,
-            Error::CorruptedDump => Code::Internal,
-            Error::DatabaseUpgrade(_) => Code::Internal,
-            Error::Export(_) => Code::Internal,
-            Error::RollbackFailed { .. } => Code::Internal,
-            Error::UnrecoverableError(_) => Code::Internal,
-            Error::IndexSchedulerVersionMismatch { .. } => Code::Internal,
-            Error::IndexVersionMismatch { .. } => 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,
-        }
-    }
-}

crates/index-scheduler/src/features.rs

@@ -1,253 +0,0 @@
-use std::sync::{Arc, RwLock};
-
-use meilisearch_types::enterprise_edition::network::Network;
-use meilisearch_types::features::{InstanceTogglableFeatures, RuntimeTogglableFeatures};
-use meilisearch_types::heed::types::{SerdeJson, Str};
-use meilisearch_types::heed::{Database, Env, RwTxn, WithoutTls};
-
-use crate::error::FeatureNotEnabledError;
-use crate::Result;
-
-/// The number of database used by features
-const NUMBER_OF_DATABASES: u32 = 1;
-/// Database const names for the `FeatureData`.
-mod db_name {
-    pub const EXPERIMENTAL_FEATURES: &str = "experimental-features";
-}
-
-mod db_keys {
-    pub const EXPERIMENTAL_FEATURES: &str = "experimental-features";
-    pub const NETWORK: &str = "network";
-}
-
-#[derive(Clone)]
-pub(crate) struct FeatureData {
-    persisted: Database<Str, SerdeJson<RuntimeTogglableFeatures>>,
-    runtime: Arc<RwLock<RuntimeTogglableFeatures>>,
-    network: Arc<RwLock<Network>>,
-}
-
-#[derive(Debug, Clone, Copy)]
-pub struct RoFeatures {
-    runtime: RuntimeTogglableFeatures,
-}
-
-impl RoFeatures {
-    fn new(data: &FeatureData) -> Self {
-        let runtime = data.runtime_features();
-        Self { runtime }
-    }
-
-    pub fn runtime_features(&self) -> RuntimeTogglableFeatures {
-        self.runtime
-    }
-
-    pub fn check_metrics(&self) -> Result<()> {
-        if self.runtime.metrics {
-            Ok(())
-        } else {
-            Err(FeatureNotEnabledError {
-                disabled_action: "Getting metrics",
-                feature: "metrics",
-                issue_link: "https://github.com/meilisearch/product/discussions/625",
-            }
-            .into())
-        }
-    }
-
-    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_edit_documents_by_function(&self, disabled_action: &'static str) -> Result<()> {
-        if self.runtime.edit_documents_by_function {
-            Ok(())
-        } else {
-            Err(FeatureNotEnabledError {
-                disabled_action,
-                feature: "edit documents by function",
-                issue_link: "https://github.com/orgs/meilisearch/discussions/762",
-            }
-            .into())
-        }
-    }
-
-    pub fn check_contains_filter(&self) -> Result<()> {
-        if self.runtime.contains_filter {
-            Ok(())
-        } else {
-            Err(FeatureNotEnabledError {
-                disabled_action: "Using `CONTAINS` in a filter",
-                feature: "contains filter",
-                issue_link: "https://github.com/orgs/meilisearch/discussions/763",
-            }
-            .into())
-        }
-    }
-
-    pub fn check_network(&self, disabled_action: &'static str) -> Result<()> {
-        if self.runtime.network {
-            Ok(())
-        } else {
-            Err(FeatureNotEnabledError {
-                disabled_action,
-                feature: "network",
-                issue_link: "https://github.com/orgs/meilisearch/discussions/805",
-            }
-            .into())
-        }
-    }
-
-    pub fn check_get_task_documents_route(&self) -> Result<()> {
-        if self.runtime.get_task_documents_route {
-            Ok(())
-        } else {
-            Err(FeatureNotEnabledError {
-                disabled_action: "Getting the documents of an enqueued task",
-                feature: "get task documents route",
-                issue_link: "https://github.com/orgs/meilisearch/discussions/808",
-            }
-            .into())
-        }
-    }
-
-    pub fn check_composite_embedders(&self, disabled_action: &'static str) -> Result<()> {
-        if self.runtime.composite_embedders {
-            Ok(())
-        } else {
-            Err(FeatureNotEnabledError {
-                disabled_action,
-                feature: "composite embedders",
-                issue_link: "https://github.com/orgs/meilisearch/discussions/816",
-            }
-            .into())
-        }
-    }
-
-    pub fn check_chat_completions(&self, disabled_action: &'static str) -> Result<()> {
-        if self.runtime.chat_completions {
-            Ok(())
-        } else {
-            Err(FeatureNotEnabledError {
-                disabled_action,
-                feature: "chat completions",
-                issue_link: "https://github.com/orgs/meilisearch/discussions/835",
-            }
-            .into())
-        }
-    }
-
-    pub fn check_multimodal(&self, disabled_action: &'static str) -> Result<()> {
-        if self.runtime.multimodal {
-            Ok(())
-        } else {
-            Err(FeatureNotEnabledError {
-                disabled_action,
-                feature: "multimodal",
-                issue_link: "https://github.com/orgs/meilisearch/discussions/846",
-            }
-            .into())
-        }
-    }
-
-    pub fn check_vector_store_setting(&self, disabled_action: &'static str) -> Result<()> {
-        if self.runtime.vector_store_setting {
-            Ok(())
-        } else {
-            Err(FeatureNotEnabledError {
-                disabled_action,
-                feature: "vector_store_setting",
-                issue_link: "https://github.com/orgs/meilisearch/discussions/860",
-            }
-            .into())
-        }
-    }
-}
-
-impl FeatureData {
-    pub(crate) const fn nb_db() -> u32 {
-        NUMBER_OF_DATABASES
-    }
-
-    pub fn new(
-        env: &Env<WithoutTls>,
-        wtxn: &mut RwTxn,
-        instance_features: InstanceTogglableFeatures,
-    ) -> Result<Self> {
-        let runtime_features_db =
-            env.create_database(wtxn, Some(db_name::EXPERIMENTAL_FEATURES))?;
-
-        let persisted_features: RuntimeTogglableFeatures =
-            runtime_features_db.get(wtxn, db_keys::EXPERIMENTAL_FEATURES)?.unwrap_or_default();
-        let InstanceTogglableFeatures { metrics, logs_route, contains_filter } = instance_features;
-        let runtime = Arc::new(RwLock::new(RuntimeTogglableFeatures {
-            metrics: metrics || persisted_features.metrics,
-            logs_route: logs_route || persisted_features.logs_route,
-            contains_filter: contains_filter || persisted_features.contains_filter,
-            ..persisted_features
-        }));
-
-        // Once this is stabilized, network should be stored along with webhooks in index-scheduler's persisted database
-        let network_db = runtime_features_db.remap_data_type::<SerdeJson<Network>>();
-        let network: Network = network_db.get(wtxn, db_keys::NETWORK)?.unwrap_or_default();
-
-        Ok(Self {
-            persisted: runtime_features_db,
-            runtime,
-            network: Arc::new(RwLock::new(network)),
-        })
-    }
-
-    pub fn put_runtime_features(
-        &self,
-        mut wtxn: RwTxn,
-        features: RuntimeTogglableFeatures,
-    ) -> Result<()> {
-        self.persisted.put(&mut wtxn, db_keys::EXPERIMENTAL_FEATURES, &features)?;
-        wtxn.commit()?;
-
-        // safe to unwrap, the lock will only fail if:
-        // 1. requested by the same thread concurrently -> it is called and released in methods that don't call each other
-        // 2. there's a panic while the thread is held -> it is only used for an assignment here.
-        let mut toggled_features = self.runtime.write().unwrap();
-        *toggled_features = features;
-        Ok(())
-    }
-
-    fn runtime_features(&self) -> RuntimeTogglableFeatures {
-        // sound to unwrap, the lock will only fail if:
-        // 1. requested by the same thread concurrently -> it is called and released in methods that don't call each other
-        // 2. there's a panic while the thread is held -> it is only used for copying the data here
-        *self.runtime.read().unwrap()
-    }
-
-    pub fn features(&self) -> RoFeatures {
-        RoFeatures::new(self)
-    }
-
-    pub fn put_network(&self, mut wtxn: RwTxn, new_network: Network) -> Result<()> {
-        self.persisted.remap_data_type::<SerdeJson<Network>>().put(
-            &mut wtxn,
-            db_keys::NETWORK,
-            &new_network,
-        )?;
-        wtxn.commit()?;
-
-        let mut network = self.network.write().unwrap();
-        *network = new_network;
-        Ok(())
-    }
-
-    pub fn network(&self) -> Network {
-        Network::clone(&*self.network.read().unwrap())
-    }
-}

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

@@ -1,405 +0,0 @@
-use std::collections::BTreeMap;
-use std::env::VarError;
-use std::path::Path;
-use std::str::FromStr;
-use std::time::Duration;
-
-use meilisearch_types::heed::{EnvClosingEvent, EnvFlags, EnvOpenOptions};
-use meilisearch_types::milli::{Index, Result};
-use time::OffsetDateTime;
-use uuid::Uuid;
-
-use super::IndexStatus::{self, Available, BeingDeleted, Closing, Missing};
-use crate::clamp_to_page_size;
-use crate::lru::{InsertionOutcome, LruMap};
-/// Keep an internally consistent view of the open indexes in memory.
-///
-/// This view is made of an LRU cache that will evict the least frequently used indexes when new indexes are opened.
-/// Indexes that are being closed (for resizing or due to cache eviction) or deleted cannot be evicted from the cache and
-/// are stored separately.
-///
-/// This view provides operations to change the state of the index as it is known in memory:
-/// open an index (making it available for queries), close an index (specifying the new size it should be opened with),
-/// delete an index.
-///
-/// External consistency with the other bits of data of an index is provided by the `IndexMapper` parent structure.
-pub struct IndexMap {
-    /// A LRU map of indexes that are in the open state and available for queries.
-    available: LruMap<Uuid, Index>,
-    /// A map of indexes that are not available for queries, either because they are being deleted
-    /// or because they are being closed.
-    ///
-    /// If they are being deleted, the UUID points to `None`.
-    unavailable: BTreeMap<Uuid, Option<ClosingIndex>>,
-
-    /// A monotonically increasing generation number, used to differentiate between multiple successive index closing requests.
-    ///
-    /// Because multiple readers could be waiting on an index to close, the following could theoretically happen:
-    ///
-    /// 1. Multiple readers wait for the index closing to occur.
-    /// 2. One of them "wins the race", takes the lock and then removes the index that finished closing from the map.
-    /// 3. The index is reopened, but must be closed again (such as being resized again).
-    /// 4. One reader that "lost the race" in (2) wakes up and tries to take the lock and remove the index from the map.
-    ///
-    /// In that situation, the index may or may not have finished closing. The `generation` field allows to remember which
-    /// closing request was made, so the reader that "lost the race" has the old generation and will need to wait again for the index
-    /// to close.
-    generation: usize,
-}
-
-#[derive(Clone)]
-pub struct ClosingIndex {
-    uuid: Uuid,
-    closing_event: EnvClosingEvent,
-    enable_mdb_writemap: bool,
-    map_size: usize,
-    generation: usize,
-}
-
-impl ClosingIndex {
-    /// Waits for the index to be definitely closed.
-    ///
-    /// To avoid blocking, users should relinquish their locks to the IndexMap before calling this function.
-    ///
-    /// After the index is physically closed, the in memory map must still be updated to take this into account.
-    /// To do so, a `ReopenableIndex` is returned, that can be used to either definitely close or definitely open
-    /// the index without waiting anymore.
-    pub fn wait_timeout(self, timeout: Duration) -> Option<ReopenableIndex> {
-        self.closing_event.wait_timeout(timeout).then_some(ReopenableIndex {
-            uuid: self.uuid,
-            enable_mdb_writemap: self.enable_mdb_writemap,
-            map_size: self.map_size,
-            generation: self.generation,
-        })
-    }
-}
-
-pub struct ReopenableIndex {
-    uuid: Uuid,
-    enable_mdb_writemap: bool,
-    map_size: usize,
-    generation: usize,
-}
-
-impl ReopenableIndex {
-    /// Attempts to reopen the index, which can result in the index being reopened again or not
-    /// (e.g. if another thread already opened and closed the index again).
-    ///
-    /// Use get again on the IndexMap to get the updated status.
-    ///
-    /// Fails if the underlying index creation fails.
-    ///
-    /// # Status table
-    ///
-    /// | Previous Status | New Status                                   |
-    /// |-----------------|----------------------------------------------|
-    /// | Missing         | Missing                                      |
-    /// | BeingDeleted    | BeingDeleted                                 |
-    /// | Closing         | Available or Closing depending on generation |
-    /// | Available       | Available                                    |
-    ///
-    pub fn reopen(self, map: &mut IndexMap, path: &Path) -> Result<()> {
-        if let Closing(reopen) = map.get(&self.uuid) {
-            if reopen.generation != self.generation {
-                return Ok(());
-            }
-            map.unavailable.remove(&self.uuid);
-            map.create(&self.uuid, path, None, self.enable_mdb_writemap, self.map_size, false)?;
-        }
-        Ok(())
-    }
-
-    /// Attempts to close the index, which may or may not result in the index being closed
-    /// (e.g. if another thread already reopened the index again).
-    ///
-    /// Use get again on the IndexMap to get the updated status.
-    ///
-    /// # Status table
-    ///
-    /// | Previous Status | New Status                                 |
-    /// |-----------------|--------------------------------------------|
-    /// | Missing         | Missing                                    |
-    /// | BeingDeleted    | BeingDeleted                               |
-    /// | Closing         | Missing or Closing depending on generation |
-    /// | Available       | Available                                  |
-    pub fn close(self, map: &mut IndexMap) {
-        if let Closing(reopen) = map.get(&self.uuid) {
-            if reopen.generation != self.generation {
-                return;
-            }
-            map.unavailable.remove(&self.uuid);
-        }
-    }
-}
-
-impl IndexMap {
-    pub fn new(cap: usize) -> IndexMap {
-        Self { unavailable: Default::default(), available: LruMap::new(cap), generation: 0 }
-    }
-
-    /// Gets the current status of an index in the map.
-    ///
-    /// If the index is available it can be accessed from the returned status.
-    pub fn get(&self, uuid: &Uuid) -> IndexStatus {
-        self.available
-            .get(uuid)
-            .map(|index| Available(index.clone()))
-            .unwrap_or_else(|| self.get_unavailable(uuid))
-    }
-
-    fn get_unavailable(&self, uuid: &Uuid) -> IndexStatus {
-        match self.unavailable.get(uuid) {
-            Some(Some(reopen)) => Closing(reopen.clone()),
-            Some(None) => BeingDeleted,
-            None => Missing,
-        }
-    }
-
-    /// Attempts to create a new index that wasn't existing before.
-    ///
-    /// # Status table
-    ///
-    /// | Previous Status | New Status |
-    /// |-----------------|------------|
-    /// | Missing         | Available  |
-    /// | BeingDeleted    | panics     |
-    /// | Closing         | panics     |
-    /// | Available       | panics     |
-    ///
-    pub fn create(
-        &mut self,
-        uuid: &Uuid,
-        path: &Path,
-        date: Option<(OffsetDateTime, OffsetDateTime)>,
-        enable_mdb_writemap: bool,
-        map_size: usize,
-        creation: bool,
-    ) -> Result<Index> {
-        if !matches!(self.get_unavailable(uuid), Missing) {
-            panic!("Attempt to open an index that was unavailable");
-        }
-        let index = create_or_open_index(path, date, enable_mdb_writemap, map_size, creation)?;
-        match self.available.insert(*uuid, index.clone()) {
-            InsertionOutcome::InsertedNew => (),
-            InsertionOutcome::Evicted(evicted_uuid, evicted_index) => {
-                self.close(evicted_uuid, evicted_index, enable_mdb_writemap, 0);
-            }
-            InsertionOutcome::Replaced(_) => {
-                panic!("Attempt to open an index that was already opened")
-            }
-        }
-        Ok(index)
-    }
-
-    /// Increases the current generation. See documentation for this field.
-    ///
-    /// In the unlikely event that the 2^64 generations would have been exhausted, we simply wrap-around.
-    ///
-    /// For this to cause an issue, one should be able to stop a reader in time after it got a `ReopenableIndex` and before it takes the lock
-    /// to remove it from the unavailable map, and keep the reader in this frozen state for 2^64 closing of other indexes.
-    ///
-    /// This seems overwhelmingly impossible to achieve in practice.
-    fn next_generation(&mut self) -> usize {
-        self.generation = self.generation.wrapping_add(1);
-        self.generation
-    }
-
-    /// Attempts to close an index.
-    ///
-    /// # Status table
-    ///
-    /// | Previous Status | New Status    |
-    /// |-----------------|---------------|
-    /// | Missing         | Missing       |
-    /// | BeingDeleted    | BeingDeleted  |
-    /// | Closing         | Closing       |
-    /// | Available       | Closing       |
-    ///
-    pub fn close_for_resize(
-        &mut self,
-        uuid: &Uuid,
-        enable_mdb_writemap: bool,
-        map_size_growth: usize,
-    ) {
-        let Some(index) = self.available.remove(uuid) else {
-            return;
-        };
-        self.close(*uuid, index, enable_mdb_writemap, map_size_growth);
-    }
-
-    fn close(
-        &mut self,
-        uuid: Uuid,
-        index: Index,
-        enable_mdb_writemap: bool,
-        map_size_growth: usize,
-    ) {
-        let map_size = index.map_size() + map_size_growth;
-        let closing_event = index.prepare_for_closing();
-        let generation = self.next_generation();
-        self.unavailable.insert(
-            uuid,
-            Some(ClosingIndex { uuid, closing_event, enable_mdb_writemap, map_size, generation }),
-        );
-    }
-
-    /// Attempts to delete and index.
-    ///
-    ///  `end_deletion` must be called just after.
-    ///
-    /// # Status table
-    ///
-    /// | Previous Status | New Status   | Return value                |
-    /// |-----------------|--------------|-----------------------------|
-    /// | Missing         | BeingDeleted | Ok(None)                    |
-    /// | BeingDeleted    | BeingDeleted | Err(None)                   |
-    /// | Closing         | Closing      | Err(Some(reopen))           |
-    /// | Available       | BeingDeleted | Ok(Some(env_closing_event)) |
-    pub fn start_deletion(
-        &mut self,
-        uuid: &Uuid,
-    ) -> std::result::Result<Option<EnvClosingEvent>, Option<ClosingIndex>> {
-        if let Some(index) = self.available.remove(uuid) {
-            self.unavailable.insert(*uuid, None);
-            return Ok(Some(index.prepare_for_closing()));
-        }
-        match self.unavailable.remove(uuid) {
-            Some(Some(reopen)) => Err(Some(reopen)),
-            Some(None) => Err(None),
-            None => Ok(None),
-        }
-    }
-
-    /// Marks that an index deletion finished.
-    ///
-    /// Must be used after calling `start_deletion`.
-    ///
-    /// # Status table
-    ///
-    /// | Previous Status | New Status |
-    /// |-----------------|------------|
-    /// | Missing         | Missing    |
-    /// | BeingDeleted    | Missing    |
-    /// | Closing         | panics     |
-    /// | Available       | panics     |
-    pub fn end_deletion(&mut self, uuid: &Uuid) {
-        assert!(
-            self.available.get(uuid).is_none(),
-            "Attempt to finish deletion of an index that was not being deleted"
-        );
-        // Do not panic if the index was Missing or BeingDeleted
-        assert!(
-            !matches!(self.unavailable.remove(uuid), Some(Some(_))),
-            "Attempt to finish deletion of an index that was being closed"
-        );
-    }
-}
-
-/// Create or open an index in the specified path.
-/// The path *must* exist or an error will be thrown.
-fn create_or_open_index(
-    path: &Path,
-    date: Option<(OffsetDateTime, OffsetDateTime)>,
-    enable_mdb_writemap: bool,
-    map_size: usize,
-    creation: bool,
-) -> Result<Index> {
-    let options = EnvOpenOptions::new();
-    let mut options = options.read_txn_without_tls();
-    options.map_size(clamp_to_page_size(map_size));
-
-    // You can find more details about this experimental
-    // environment variable on the following GitHub discussion:
-    // <https://github.com/orgs/meilisearch/discussions/806>
-    let max_readers = match std::env::var("MEILI_EXPERIMENTAL_INDEX_MAX_READERS") {
-        Ok(value) => u32::from_str(&value).unwrap(),
-        Err(VarError::NotPresent) => 1024,
-        Err(VarError::NotUnicode(value)) => panic!(
-            "Invalid unicode for the `MEILI_EXPERIMENTAL_INDEX_MAX_READERS` env var: {value:?}"
-        ),
-    };
-    options.max_readers(max_readers);
-    if enable_mdb_writemap {
-        unsafe { options.flags(EnvFlags::WRITE_MAP) };
-    }
-
-    if let Some((created, updated)) = date {
-        Ok(Index::new_with_creation_dates(options, path, created, updated, creation)?)
-    } else {
-        Ok(Index::new(options, path, creation)?)
-    }
-}
-
-/// Putting the tests of the LRU down there so we have access to the cache's private members
-#[cfg(test)]
-mod tests {
-
-    use meilisearch_types::heed::{Env, WithoutTls};
-    use meilisearch_types::Index;
-    use uuid::Uuid;
-
-    use super::super::IndexMapper;
-    use crate::test_utils::IndexSchedulerHandle;
-    use crate::utils::clamp_to_page_size;
-    use crate::IndexScheduler;
-
-    impl IndexMapper {
-        fn test() -> (Self, Env<WithoutTls>, IndexSchedulerHandle) {
-            let (index_scheduler, handle) = IndexScheduler::test(true, vec![]);
-            (index_scheduler.index_mapper, index_scheduler.env, handle)
-        }
-    }
-
-    fn check_first_unavailable(mapper: &IndexMapper, expected_uuid: Uuid, is_closing: bool) {
-        let index_map = mapper.index_map.read().unwrap();
-        let (uuid, state) = index_map.unavailable.first_key_value().unwrap();
-        assert_eq!(uuid, &expected_uuid);
-        assert_eq!(state.is_some(), is_closing);
-    }
-
-    #[test]
-    fn evict_indexes() {
-        let (mapper, env, _handle) = IndexMapper::test();
-        let mut uuids = vec![];
-        // LRU cap + 1
-        for i in 0..(5 + 1) {
-            let index_name = format!("index-{i}");
-            let wtxn = env.write_txn().unwrap();
-            mapper.create_index(wtxn, &index_name, None).unwrap();
-            let txn = env.read_txn().unwrap();
-            uuids.push(mapper.index_mapping.get(&txn, &index_name).unwrap().unwrap());
-        }
-        // index-0 was evicted
-        check_first_unavailable(&mapper, uuids[0], true);
-
-        // get back the evicted index
-        let wtxn = env.write_txn().unwrap();
-        mapper.create_index(wtxn, "index-0", None).unwrap();
-
-        // Least recently used is now index-1
-        check_first_unavailable(&mapper, uuids[1], true);
-    }
-
-    #[test]
-    fn resize_index() {
-        let (mapper, env, _handle) = IndexMapper::test();
-        let index = mapper.create_index(env.write_txn().unwrap(), "index", None).unwrap();
-        assert_index_size(index, mapper.index_base_map_size);
-
-        mapper.resize_index(&env.read_txn().unwrap(), "index").unwrap();
-
-        let index = mapper.create_index(env.write_txn().unwrap(), "index", None).unwrap();
-        assert_index_size(index, mapper.index_base_map_size + mapper.index_growth_amount);
-
-        mapper.resize_index(&env.read_txn().unwrap(), "index").unwrap();
-
-        let index = mapper.create_index(env.write_txn().unwrap(), "index", None).unwrap();
-        assert_index_size(index, mapper.index_base_map_size + mapper.index_growth_amount * 2);
-    }
-
-    fn assert_index_size(index: Index, expected: usize) {
-        let expected = clamp_to_page_size(expected);
-        let index_map_size = index.map_size();
-        assert_eq!(index_map_size, expected);
-    }
-}

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

@@ -1,594 +0,0 @@
-use std::path::PathBuf;
-use std::sync::{Arc, RwLock};
-use std::time::Duration;
-use std::{fs, thread};
-
-use meilisearch_types::heed::types::{SerdeJson, Str};
-use meilisearch_types::heed::{Database, Env, RoTxn, RwTxn, WithoutTls};
-use meilisearch_types::milli;
-use meilisearch_types::milli::database_stats::DatabaseStats;
-use meilisearch_types::milli::index::RollbackOutcome;
-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;
-use self::IndexStatus::{Available, BeingDeleted, Closing, Missing};
-use crate::uuid_codec::UuidCodec;
-use crate::{Error, IndexBudget, IndexSchedulerOptions, Result};
-
-mod index_map;
-
-/// The number of database used by index mapper
-const NUMBER_OF_DATABASES: u32 = 2;
-/// Database const names for the `IndexMapper`.
-mod db_name {
-    pub const INDEX_MAPPING: &str = "index-mapping";
-    pub const INDEX_STATS: &str = "index-stats";
-}
-
-/// Structure managing meilisearch's indexes.
-///
-/// It is responsible for:
-/// 1. Creating new indexes
-/// 2. Opening indexes and storing references to these opened indexes
-/// 3. Accessing indexes through their uuid
-/// 4. Mapping a user-defined name to each index uuid.
-///
-/// # Implementation notes
-///
-/// An index exists as 3 bits of data:
-/// 1. The index data on disk, that can exist in 3 states: Missing, Present, or BeingDeleted.
-/// 2. The persistent database containing the association between the index' name and its UUID,
-///    that can exist in 2 states: Missing or Present.
-/// 3. The state of the index in the in-memory `IndexMap`, that can exist in multiple states:
-///   - Missing
-///   - Available
-///   - Closing (because an index needs resizing or was evicted from the cache)
-///   - BeingDeleted
-///
-/// All of this data should be kept consistent between index operations, which is achieved by the `IndexMapper`
-/// with the use of the following primitives:
-/// - A RwLock on the `IndexMap`.
-/// - Transactions on the association database.
-/// - ClosingEvent signals emitted when closing an environment.
-#[derive(Clone)]
-pub struct IndexMapper {
-    /// Keep track of the opened indexes. Used mainly by the index resolver.
-    index_map: Arc<RwLock<IndexMap>>,
-
-    /// Map an index name with an index uuid currently available on disk.
-    pub(crate) index_mapping: Database<Str, UuidCodec>,
-    /// Map an index UUID with the cached stats associated to the index.
-    ///
-    /// Using an UUID forces to use the index_mapping table to recover the index behind a name, ensuring
-    /// consistency wrt index swapping.
-    pub(crate) index_stats: Database<UuidCodec, SerdeJson<IndexStats>>,
-
-    /// Path to the folder where the LMDB environments of each index are.
-    base_path: PathBuf,
-    /// The map size an index is opened with on the first time.
-    pub(crate) index_base_map_size: usize,
-    /// The quantity by which the map size of an index is incremented upon reopening, in bytes.
-    index_growth_amount: usize,
-    /// 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
-#[allow(clippy::large_enum_variant)]
-#[derive(Clone)]
-pub enum IndexStatus {
-    /// Not currently in the index map.
-    Missing,
-    /// Do not insert it back in the index map as it is currently being deleted.
-    BeingDeleted,
-    /// Temporarily do not insert the index in the index map as it is currently being resized/evicted from the map.
-    Closing(index_map::ClosingIndex),
-    /// You can use the index without worrying about anything.
-    Available(Index),
-}
-
-/// The statistics that can be computed from an `Index` object.
-#[derive(Serialize, Deserialize, Debug)]
-pub struct IndexStats {
-    /// Stats of the documents database.
-    #[serde(default)]
-    pub documents_database_stats: DatabaseStats,
-
-    #[serde(default, skip_serializing)]
-    pub number_of_documents: Option<u64>,
-
-    /// Size taken up by the index' DB, in bytes.
-    ///
-    /// This includes the size taken by both the used and free pages of the DB, and as the free pages
-    /// are not returned to the disk after a deletion, this number is typically larger than
-    /// `used_database_size` that only includes the size of the used pages.
-    pub database_size: u64,
-    /// Number of embeddings in the index.
-    /// Option: retrocompatible with the stats of the pre-v1.13.0 versions of meilisearch
-    pub number_of_embeddings: Option<u64>,
-    /// Number of embedded documents in the index.
-    /// Option: retrocompatible with the stats of the pre-v1.13.0 versions of meilisearch
-    pub number_of_embedded_documents: Option<u64>,
-    /// Size taken by the used pages of the index' DB, in bytes.
-    ///
-    /// As the DB backend does not return to the disk the pages that are not currently used by the DB,
-    /// this value is typically smaller than `database_size`.
-    pub used_database_size: u64,
-    /// The primary key of the index
-    pub primary_key: Option<String>,
-    /// Association of every field name with the number of times it occurs in the documents.
-    pub field_distribution: FieldDistribution,
-    /// Creation date of the index.
-    #[serde(with = "time::serde::rfc3339")]
-    pub created_at: OffsetDateTime,
-    /// Date of the last update of the index.
-    #[serde(with = "time::serde::rfc3339")]
-    pub updated_at: OffsetDateTime,
-}
-
-impl IndexStats {
-    /// Compute the stats of an index
-    ///
-    /// # Parameters
-    ///
-    /// - rtxn: a RO transaction for the index, obtained from `Index::read_txn()`.
-    pub fn new(index: &Index, rtxn: &RoTxn) -> milli::Result<Self> {
-        let vector_store_stats = index.vector_store_stats(rtxn)?;
-        Ok(IndexStats {
-            number_of_embeddings: Some(vector_store_stats.number_of_embeddings),
-            number_of_embedded_documents: Some(vector_store_stats.documents.len()),
-            documents_database_stats: index.documents_stats(rtxn)?.unwrap_or_default(),
-            number_of_documents: None,
-            database_size: index.on_disk_size()?,
-            used_database_size: index.used_size()?,
-            primary_key: index.primary_key(rtxn)?.map(|s| s.to_string()),
-            field_distribution: index.field_distribution(rtxn)?,
-            created_at: index.created_at(rtxn)?,
-            updated_at: index.updated_at(rtxn)?,
-        })
-    }
-}
-
-impl IndexMapper {
-    pub(crate) const fn nb_db() -> u32 {
-        NUMBER_OF_DATABASES
-    }
-
-    pub fn new(
-        env: &Env<WithoutTls>,
-        wtxn: &mut RwTxn,
-        options: &IndexSchedulerOptions,
-        budget: IndexBudget,
-    ) -> Result<Self> {
-        Ok(Self {
-            index_map: Arc::new(RwLock::new(IndexMap::new(budget.index_count))),
-            index_mapping: env.create_database(wtxn, Some(db_name::INDEX_MAPPING))?,
-            index_stats: env.create_database(wtxn, Some(db_name::INDEX_STATS))?,
-            base_path: options.indexes_path.clone(),
-            index_base_map_size: budget.map_size,
-            index_growth_amount: options.index_growth_amount,
-            enable_mdb_writemap: options.enable_mdb_writemap,
-            indexer_config: options.indexer_config.clone(),
-            currently_updating_index: Default::default(),
-        })
-    }
-
-    /// Get or create the index.
-    pub fn create_index(
-        &self,
-        mut wtxn: RwTxn,
-        name: &str,
-        date: Option<(OffsetDateTime, OffsetDateTime)>,
-    ) -> Result<Index> {
-        match self.index(&wtxn, name) {
-            Ok(index) => {
-                wtxn.commit()?;
-                Ok(index)
-            }
-            Err(Error::IndexNotFound(_)) => {
-                let uuid = Uuid::new_v4();
-                self.index_mapping.put(&mut wtxn, name, &uuid)?;
-
-                let index_path = self.base_path.join(uuid.to_string());
-                fs::create_dir_all(&index_path)?;
-
-                // Error if the UUIDv4 somehow already exists in the map, since it should be fresh.
-                // This is very unlikely to happen in practice.
-                // TODO: it would be better to lazily create the index. But we need an Index::open function for milli.
-                let index = self
-                    .index_map
-                    .write()
-                    .unwrap()
-                    .create(
-                        &uuid,
-                        &index_path,
-                        date,
-                        self.enable_mdb_writemap,
-                        self.index_base_map_size,
-                        true,
-                    )
-                    .map_err(|e| Error::from_milli(e, Some(uuid.to_string())))?;
-                let index_rtxn = index.read_txn()?;
-                let stats = crate::index_mapper::IndexStats::new(&index, &index_rtxn)
-                    .map_err(|e| Error::from_milli(e, Some(name.to_string())))?;
-                self.store_stats_of(&mut wtxn, name, &stats)?;
-                drop(index_rtxn);
-
-                wtxn.commit()?;
-
-                Ok(index)
-            }
-            error => error,
-        }
-    }
-
-    /// Removes the index from the mapping table and the in-memory index map
-    /// but keeps the associated tasks.
-    pub fn delete_index(&self, mut wtxn: RwTxn, name: &str) -> Result<()> {
-        let uuid = self
-            .index_mapping
-            .get(&wtxn, name)?
-            .ok_or_else(|| Error::IndexNotFound(name.to_string()))?;
-
-        // Not an error if the index had no stats in cache.
-        self.index_stats.delete(&mut wtxn, &uuid)?;
-
-        // Once we retrieved the UUID of the index we remove it from the mapping table.
-        assert!(self.index_mapping.delete(&mut wtxn, name)?);
-
-        wtxn.commit()?;
-
-        let mut tries = 0;
-        // Attempts to remove the index from the in-memory index map in a loop.
-        //
-        // If the index is currently being closed, we will wait for it to be closed and retry getting it in a subsequent
-        // loop iteration.
-        //
-        // We make 100 attempts before giving up.
-        // This could happen in the following situations:
-        //
-        // 1. There is a bug preventing the index from being correctly closed, or us from detecting this.
-        // 2. A user of the index is keeping it open for more than 600 seconds. This could happen e.g. during a pathological search.
-        //    This can not be caused by indexation because deleting an index happens in the scheduler itself, so cannot be concurrent with indexation.
-        //
-        // In these situations, reporting the error through a panic is in order.
-        let closing_event = loop {
-            let mut lock = self.index_map.write().unwrap();
-            match lock.start_deletion(&uuid) {
-                Ok(env_closing) => break env_closing,
-                Err(Some(reopen)) => {
-                    // drop the lock here so that we don't synchronously wait for the index to close.
-                    drop(lock);
-                    tries += 1;
-                    if tries >= 100 {
-                        panic!("Too many attempts to close index {name} prior to deletion.")
-                    }
-                    let reopen = if let Some(reopen) = reopen.wait_timeout(Duration::from_secs(6)) {
-                        reopen
-                    } else {
-                        continue;
-                    };
-                    reopen.close(&mut self.index_map.write().unwrap());
-                    continue;
-                }
-                Err(None) => return Ok(()),
-            }
-        };
-
-        let index_map = self.index_map.clone();
-        let index_path = self.base_path.join(uuid.to_string());
-        let index_name = name.to_string();
-        thread::Builder::new()
-            .name(String::from("index_deleter"))
-            .spawn(move || {
-                // We first wait to be sure that the previously opened index is effectively closed.
-                // This can take a lot of time, this is why we do that in a separate thread.
-                if let Some(closing_event) = closing_event {
-                    closing_event.wait();
-                }
-
-                // Then we remove the content from disk.
-                if let Err(e) = fs::remove_dir_all(&index_path) {
-                    error!(
-                        "An error happened when deleting the index {} ({}): {}",
-                        index_name, uuid, e
-                    );
-                }
-
-                // Finally we remove the entry from the index map.
-                index_map.write().unwrap().end_deletion(&uuid);
-            })
-            .unwrap();
-
-        Ok(())
-    }
-
-    pub fn exists(&self, rtxn: &RoTxn, name: &str) -> Result<bool> {
-        Ok(self.index_mapping.get(rtxn, name)?.is_some())
-    }
-
-    /// Resizes the maximum size of the specified index to the double of its current maximum size.
-    ///
-    /// This operation involves closing the underlying environment and so can take a long time to complete.
-    ///
-    /// # Panics
-    ///
-    /// - If the Index corresponding to the passed name is concurrently being deleted/resized or cannot be found in the
-    ///   in memory hash map.
-    pub fn resize_index(&self, rtxn: &RoTxn, name: &str) -> Result<()> {
-        let uuid = self
-            .index_mapping
-            .get(rtxn, name)?
-            .ok_or_else(|| Error::IndexNotFound(name.to_string()))?;
-
-        // We remove the index from the in-memory index map.
-        self.index_map.write().unwrap().close_for_resize(
-            &uuid,
-            self.enable_mdb_writemap,
-            self.index_growth_amount,
-        );
-
-        Ok(())
-    }
-
-    /// Return an index, may open it if it wasn't already opened.
-    pub fn index(&self, rtxn: &RoTxn, name: &str) -> Result<Index> {
-        if let Some((current_name, current_index)) =
-            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)?
-            .ok_or_else(|| Error::IndexNotFound(name.to_string()))?;
-
-        let mut tries = 0;
-        // attempts to open the index in a loop.
-        //
-        // If the index is currently being closed, we will wait for it to be closed and retry getting it in a subsequent
-        // loop iteration.
-        //
-        // We make 100 attempts before giving up.
-        // This could happen in the following situations:
-        //
-        // 1. There is a bug preventing the index from being correctly closed, or us from detecting it was.
-        // 2. A user of the index is keeping it open for more than 600 seconds. This could happen e.g. during a long indexation,
-        //    a pathological search, and so on.
-        //
-        // In these situations, reporting the error through a panic is in order.
-        let index = loop {
-            tries += 1;
-            if tries > 100 {
-                panic!("Too many spurious wake ups while trying to open the index {name}");
-            }
-
-            // we get the index here to drop the lock before entering the match
-            let index = self.index_map.read().unwrap().get(&uuid);
-
-            match index {
-                Available(index) => break index,
-                Closing(reopen) => {
-                    // Avoiding deadlocks: no lock taken while doing this operation.
-                    let reopen = if let Some(reopen) = reopen.wait_timeout(Duration::from_secs(6)) {
-                        reopen
-                    } else {
-                        continue;
-                    };
-                    let index_path = self.base_path.join(uuid.to_string());
-                    // take the lock to reopen the environment.
-                    reopen
-                        .reopen(&mut self.index_map.write().unwrap(), &index_path)
-                        .map_err(|e| Error::from_milli(e, Some(uuid.to_string())))?;
-                    continue;
-                }
-                BeingDeleted => return Err(Error::IndexNotFound(name.to_string())),
-                // since we're lazy, it's possible that the index has not been opened yet.
-                Missing => {
-                    let mut index_map = self.index_map.write().unwrap();
-                    // between the read lock and the write lock it's not impossible
-                    // that someone already opened the index (eg if two searches happen
-                    // at the same time), thus before opening it we check a second time
-                    // if it's not already there.
-                    match index_map.get(&uuid) {
-                        Missing => {
-                            let index_path = self.base_path.join(uuid.to_string());
-
-                            break index_map
-                                .create(
-                                    &uuid,
-                                    &index_path,
-                                    None,
-                                    self.enable_mdb_writemap,
-                                    self.index_base_map_size,
-                                    false,
-                                )
-                                .map_err(|e| Error::from_milli(e, Some(uuid.to_string())))?;
-                        }
-                        Available(index) => break index,
-                        Closing(_) => {
-                            // the reopening will be handled in the next loop operation
-                            continue;
-                        }
-                        BeingDeleted => return Err(Error::IndexNotFound(name.to_string())),
-                    }
-                }
-            }
-        };
-
-        Ok(index)
-    }
-
-    pub fn rollback_index(
-        &self,
-        rtxn: &RoTxn,
-        name: &str,
-        to: (u32, u32, u32),
-    ) -> Result<RollbackOutcome> {
-        // remove any currently updating index to make sure that we aren't keeping a reference to the index somewhere
-        drop(self.currently_updating_index.write().unwrap().take());
-
-        let uuid = self
-            .index_mapping
-            .get(rtxn, name)?
-            .ok_or_else(|| Error::IndexNotFound(name.to_string()))?;
-
-        // take the lock to make sure noone is messing with the indexes while we rollback
-        // this will block any search or other operation, but we are rollbacking so this is probably acceptable.
-        let mut index_map = self.index_map.write().unwrap();
-
-        'close_index: loop {
-            match index_map.get(&uuid) {
-                Available(_) => {
-                    index_map.close_for_resize(&uuid, self.enable_mdb_writemap, 0);
-                    // index should now be `Closing`; try again
-                    continue;
-                }
-                // index already closed
-                Missing => break 'close_index,
-                // closing requested by this thread or another one; wait for closing to complete, then exit
-                Closing(closing_index) => {
-                    if closing_index.wait_timeout(Duration::from_secs(100)).is_none() {
-                        // release the lock so it doesn't get poisoned
-                        drop(index_map);
-                        panic!("cannot close index")
-                    }
-                    break;
-                }
-                BeingDeleted => return Err(Error::IndexNotFound(name.to_string())),
-            };
-        }
-
-        let index_path = self.base_path.join(uuid.to_string());
-        Index::rollback(milli::heed::EnvOpenOptions::new().read_txn_without_tls(), index_path, to)
-            .map_err(|err| crate::Error::from_milli(err, Some(name.to_string())))
-    }
-
-    /// Attempts `f` for each index that exists in the index mapper.
-    ///
-    /// It is preferable to use this function rather than a loop that opens all indexes, as a way to avoid having all indexes opened,
-    /// which is unsupported in general.
-    ///
-    /// Since `f` is allowed to return a result, and `Index` is cloneable, it is still possible to wrongly build e.g. a vector of
-    /// all the indexes, but this function makes it harder and so less likely to do accidentally.
-    pub fn try_for_each_index<U, V>(
-        &self,
-        rtxn: &RoTxn,
-        mut f: impl FnMut(&str, &Index) -> Result<U>,
-    ) -> Result<V>
-    where
-        V: FromIterator<U>,
-    {
-        self.index_mapping
-            .iter(rtxn)?
-            .map(|res| {
-                res.map_err(Error::from)
-                    .and_then(|(name, _)| self.index(rtxn, name).and_then(|index| f(name, &index)))
-            })
-            .collect()
-    }
-
-    /// Return the name of all indexes without opening them.
-    pub fn index_names(&self, rtxn: &RoTxn) -> Result<Vec<String>> {
-        self.index_mapping
-            .iter(rtxn)?
-            .map(|res| res.map_err(Error::from).map(|(name, _)| name.to_string()))
-            .collect()
-    }
-
-    /// Swap two index names.
-    pub fn swap(&self, wtxn: &mut RwTxn, lhs: &str, rhs: &str) -> Result<()> {
-        let lhs_uuid = self
-            .index_mapping
-            .get(wtxn, lhs)?
-            .ok_or_else(|| Error::IndexNotFound(lhs.to_string()))?;
-        let rhs_uuid = self
-            .index_mapping
-            .get(wtxn, rhs)?
-            .ok_or_else(|| Error::IndexNotFound(rhs.to_string()))?;
-
-        self.index_mapping.put(wtxn, lhs, &rhs_uuid)?;
-        self.index_mapping.put(wtxn, rhs, &lhs_uuid)?;
-
-        Ok(())
-    }
-
-    /// Rename an index.
-    pub fn rename(&self, wtxn: &mut RwTxn, current: &str, new: &str) -> Result<()> {
-        let uuid = self
-            .index_mapping
-            .get(wtxn, current)?
-            .ok_or_else(|| Error::IndexNotFound(current.to_string()))?;
-        if self.index_mapping.get(wtxn, new)?.is_some() {
-            return Err(Error::IndexAlreadyExists(new.to_string()));
-        }
-        self.index_mapping.delete(wtxn, current)?;
-        self.index_mapping.put(wtxn, new, &uuid)?;
-        Ok(())
-    }
-
-    /// The stats of an index.
-    ///
-    /// If available in the cache, they are directly returned.
-    /// Otherwise, the `Index` is opened to compute the stats on the fly (the result is not cached).
-    /// The stats for an index are cached after each `Index` update.
-    pub fn stats_of(&self, rtxn: &RoTxn, index_uid: &str) -> Result<IndexStats> {
-        let uuid = self
-            .index_mapping
-            .get(rtxn, index_uid)?
-            .ok_or_else(|| Error::IndexNotFound(index_uid.to_string()))?;
-
-        match self.index_stats.get(rtxn, &uuid)? {
-            Some(stats) => Ok(stats),
-            None => {
-                let index = self.index(rtxn, index_uid)?;
-                let index_rtxn = index.read_txn()?;
-                IndexStats::new(&index, &index_rtxn)
-                    .map_err(|e| Error::from_milli(e, Some(uuid.to_string())))
-            }
-        }
-    }
-
-    /// Stores the new stats for an index.
-    ///
-    /// Expected usage is to compute the stats the index using `IndexStats::new`, the pass it to this function.
-    pub fn store_stats_of(
-        &self,
-        wtxn: &mut RwTxn,
-        index_uid: &str,
-        stats: &IndexStats,
-    ) -> Result<()> {
-        let uuid = self
-            .index_mapping
-            .get(wtxn, index_uid)?
-            .ok_or_else(|| Error::IndexNotFound(index_uid.to_string()))?;
-
-        self.index_stats.put(wtxn, &uuid, stats)?;
-        Ok(())
-    }
-
-    pub fn index_exists(&self, rtxn: &RoTxn, name: &str) -> Result<bool> {
-        Ok(self.index_mapping.get(rtxn, name)?.is_some())
-    }
-
-    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;
-    }
-}

crates/index-scheduler/src/insta_snapshot.rs

@@ -1,422 +0,0 @@
-use std::collections::BTreeSet;
-use std::fmt::Write;
-
-use meilisearch_types::batches::{Batch, BatchEnqueuedAt, BatchStats};
-use meilisearch_types::heed::types::{SerdeBincode, SerdeJson, Str};
-use meilisearch_types::heed::{Database, RoTxn};
-use meilisearch_types::milli::{CboRoaringBitmapCodec, RoaringBitmapCodec, BEU32};
-use meilisearch_types::tasks::{Details, Kind, Status, Task};
-use meilisearch_types::versioning;
-use roaring::RoaringBitmap;
-
-use crate::index_mapper::IndexMapper;
-use crate::{IndexScheduler, BEI128};
-
-pub fn snapshot_index_scheduler(scheduler: &IndexScheduler) -> String {
-    // Since we'll snapshot the index right afterward, we don't need to ensure it's internally consistent for every run.
-    // We can only do it for the release run, where the function runs way faster.
-    #[cfg(not(debug_assertions))]
-    scheduler.assert_internally_consistent();
-
-    let IndexScheduler {
-        cleanup_enabled: _,
-        experimental_no_edition_2024_for_dumps: _,
-        processing_tasks,
-        env,
-        version,
-        queue,
-        scheduler,
-        persisted,
-
-        index_mapper,
-        features: _,
-        webhooks: _,
-        test_breakpoint_sdr: _,
-        planned_failures: _,
-        run_loop_iteration: _,
-        embedders: _,
-        chat_settings: _,
-    } = scheduler;
-
-    let rtxn = env.read_txn().unwrap();
-
-    let mut snap = String::new();
-
-    let indx_sched_version = version.get_version(&rtxn).unwrap();
-    let latest_version =
-        (versioning::VERSION_MAJOR, versioning::VERSION_MINOR, versioning::VERSION_PATCH);
-    if indx_sched_version != Some(latest_version) {
-        snap.push_str(&format!("index scheduler running on version {indx_sched_version:?}\n"));
-    }
-
-    let processing = processing_tasks.read().unwrap().clone();
-    snap.push_str(&format!("### Autobatching Enabled = {}\n", scheduler.autobatching_enabled));
-    snap.push_str(&format!(
-        "### Processing batch {:?}:\n",
-        processing.batch.as_ref().map(|batch| batch.uid)
-    ));
-    snap.push_str(&snapshot_bitmap(&processing.processing));
-    if let Some(ref batch) = processing.batch {
-        snap.push('\n');
-        snap.push_str(&snapshot_batch(&batch.to_batch()));
-    }
-    snap.push_str("\n----------------------------------------------------------------------\n");
-
-    let persisted_db_snapshot = snapshot_persisted_db(&rtxn, persisted);
-    if !persisted_db_snapshot.is_empty() {
-        snap.push_str("### Persisted:\n");
-        snap.push_str(&persisted_db_snapshot);
-        snap.push_str("----------------------------------------------------------------------\n");
-    }
-
-    snap.push_str("### All Tasks:\n");
-    snap.push_str(&snapshot_all_tasks(&rtxn, queue.tasks.all_tasks));
-    snap.push_str("----------------------------------------------------------------------\n");
-
-    snap.push_str("### Status:\n");
-    snap.push_str(&snapshot_status(&rtxn, queue.tasks.status));
-    snap.push_str("----------------------------------------------------------------------\n");
-
-    snap.push_str("### Kind:\n");
-    snap.push_str(&snapshot_kind(&rtxn, queue.tasks.kind));
-    snap.push_str("----------------------------------------------------------------------\n");
-
-    snap.push_str("### Index Tasks:\n");
-    snap.push_str(&snapshot_index_tasks(&rtxn, queue.tasks.index_tasks));
-    snap.push_str("----------------------------------------------------------------------\n");
-
-    snap.push_str("### Index Mapper:\n");
-    snap.push_str(&snapshot_index_mapper(&rtxn, index_mapper));
-    snap.push_str("\n----------------------------------------------------------------------\n");
-
-    snap.push_str("### Canceled By:\n");
-    snap.push_str(&snapshot_canceled_by(&rtxn, queue.tasks.canceled_by));
-    snap.push_str("\n----------------------------------------------------------------------\n");
-
-    snap.push_str("### Enqueued At:\n");
-    snap.push_str(&snapshot_date_db(&rtxn, queue.tasks.enqueued_at));
-    snap.push_str("----------------------------------------------------------------------\n");
-
-    snap.push_str("### Started At:\n");
-    snap.push_str(&snapshot_date_db(&rtxn, queue.tasks.started_at));
-    snap.push_str("----------------------------------------------------------------------\n");
-
-    snap.push_str("### Finished At:\n");
-    snap.push_str(&snapshot_date_db(&rtxn, queue.tasks.finished_at));
-    snap.push_str("----------------------------------------------------------------------\n");
-
-    snap.push_str("### All Batches:\n");
-    snap.push_str(&snapshot_all_batches(&rtxn, queue.batches.all_batches));
-    snap.push_str("----------------------------------------------------------------------\n");
-
-    snap.push_str("### Batch to tasks mapping:\n");
-    snap.push_str(&snapshot_batches_to_tasks_mappings(&rtxn, queue.batch_to_tasks_mapping));
-    snap.push_str("----------------------------------------------------------------------\n");
-
-    snap.push_str("### Batches Status:\n");
-    snap.push_str(&snapshot_status(&rtxn, queue.batches.status));
-    snap.push_str("----------------------------------------------------------------------\n");
-
-    snap.push_str("### Batches Kind:\n");
-    snap.push_str(&snapshot_kind(&rtxn, queue.batches.kind));
-    snap.push_str("----------------------------------------------------------------------\n");
-
-    snap.push_str("### Batches Index Tasks:\n");
-    snap.push_str(&snapshot_index_tasks(&rtxn, queue.batches.index_tasks));
-    snap.push_str("----------------------------------------------------------------------\n");
-
-    snap.push_str("### Batches Enqueued At:\n");
-    snap.push_str(&snapshot_date_db(&rtxn, queue.batches.enqueued_at));
-    snap.push_str("----------------------------------------------------------------------\n");
-
-    snap.push_str("### Batches Started At:\n");
-    snap.push_str(&snapshot_date_db(&rtxn, queue.batches.started_at));
-    snap.push_str("----------------------------------------------------------------------\n");
-
-    snap.push_str("### Batches Finished At:\n");
-    snap.push_str(&snapshot_date_db(&rtxn, queue.batches.finished_at));
-    snap.push_str("----------------------------------------------------------------------\n");
-
-    snap.push_str("### File Store:\n");
-    snap.push_str(&snapshot_file_store(&queue.file_store));
-    snap.push_str("\n----------------------------------------------------------------------\n");
-
-    snap
-}
-
-pub fn snapshot_file_store(file_store: &file_store::FileStore) -> String {
-    let mut snap = String::new();
-    // we store the uuid in a `BTreeSet` to keep them ordered.
-    let all_uuids = file_store.all_uuids().unwrap().collect::<Result<BTreeSet<_>, _>>().unwrap();
-    for uuid in all_uuids {
-        snap.push_str(&format!("{uuid}\n"));
-    }
-    snap
-}
-
-pub fn snapshot_bitmap(r: &RoaringBitmap) -> String {
-    let mut snap = String::new();
-    snap.push('[');
-    for x in r {
-        snap.push_str(&format!("{x},"));
-    }
-    snap.push(']');
-    snap
-}
-
-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 {
-        let (task_id, task) = next.unwrap();
-        snap.push_str(&format!("{task_id} {}\n", snapshot_task(&task)));
-    }
-    snap
-}
-
-pub fn snapshot_all_batches(rtxn: &RoTxn, db: Database<BEU32, SerdeJson<Batch>>) -> String {
-    let mut snap = String::new();
-    let iter = db.iter(rtxn).unwrap();
-    for next in iter {
-        let (batch_id, batch) = next.unwrap();
-        snap.push_str(&format!("{batch_id} {}\n", snapshot_batch(&batch)));
-    }
-    snap
-}
-
-pub fn snapshot_batches_to_tasks_mappings(
-    rtxn: &RoTxn,
-    db: Database<BEU32, CboRoaringBitmapCodec>,
-) -> String {
-    let mut snap = String::new();
-    let iter = db.iter(rtxn).unwrap();
-    for next in iter {
-        let (batch_id, tasks) = next.unwrap();
-        snap.push_str(&format!("{batch_id} {}\n", snapshot_bitmap(&tasks)));
-    }
-    snap
-}
-
-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 {
-        let (_timestamp, task_ids) = next.unwrap();
-        snap.push_str(&format!("[timestamp] {}\n", snapshot_bitmap(&task_ids)));
-    }
-    snap
-}
-
-pub fn snapshot_persisted_db(rtxn: &RoTxn, db: &Database<Str, Str>) -> String {
-    let mut snap = String::new();
-    let iter = db.iter(rtxn).unwrap();
-    for next in iter {
-        let (key, value) = next.unwrap();
-        snap.push_str(&format!("{key}: {value}\n"));
-    }
-    snap
-}
-
-pub fn snapshot_task(task: &Task) -> String {
-    let mut snap = String::new();
-    let Task {
-        uid,
-        batch_uid,
-        enqueued_at: _,
-        started_at: _,
-        finished_at: _,
-        error,
-        canceled_by,
-        details,
-        status,
-        kind,
-        network,
-    } = task;
-    snap.push('{');
-    snap.push_str(&format!("uid: {uid}, "));
-    if let Some(batch_uid) = batch_uid {
-        snap.push_str(&format!("batch_uid: {batch_uid}, "));
-    }
-    snap.push_str(&format!("status: {status}, "));
-    if let Some(canceled_by) = canceled_by {
-        snap.push_str(&format!("canceled_by: {canceled_by}, "));
-    }
-    if let Some(error) = error {
-        snap.push_str(&format!("error: {error:?}, "));
-    }
-    if let Some(details) = details {
-        snap.push_str(&format!("details: {}, ", &snapshot_details(details)));
-    }
-    snap.push_str(&format!("kind: {kind:?}"));
-    if let Some(network) = network {
-        snap.push_str(&format!("network: {network:?}, "))
-    }
-
-    snap.push('}');
-    snap
-}
-
-fn snapshot_details(d: &Details) -> String {
-    match d {
-        Details::DocumentAdditionOrUpdate {
-            received_documents,
-            indexed_documents,
-        } => {
-            format!("{{ received_documents: {received_documents}, indexed_documents: {indexed_documents:?} }}")
-        }
-        Details::DocumentEdition {
-            deleted_documents,
-            edited_documents,
-            original_filter,
-            context,
-            function,
-        } => {
-            format!(
-                "{{ deleted_documents: {deleted_documents:?}, edited_documents: {edited_documents:?}, context: {context:?}, function: {function:?}, original_filter: {original_filter:?} }}"
-            )
-        }
-        Details::SettingsUpdate { settings } => {
-            format!("{{ settings: {settings:?} }}")
-        }
-        Details::IndexInfo { primary_key, new_index_uid, old_index_uid } => {
-            format!("{{ primary_key: {primary_key:?}, old_new_uid: {old_index_uid:?}, new_index_uid: {new_index_uid:?} }}")
-        }
-        Details::DocumentDeletion {
-            provided_ids: received_document_ids,
-            deleted_documents,
-        } => format!("{{ received_document_ids: {received_document_ids}, deleted_documents: {deleted_documents:?} }}"),
-        Details::DocumentDeletionByFilter { original_filter, deleted_documents } => format!(
-           "{{ original_filter: {original_filter}, deleted_documents: {deleted_documents:?} }}"
-        ),
-        Details::ClearAll { deleted_documents } => {
-            format!("{{ deleted_documents: {deleted_documents:?} }}")
-        },
-        Details::TaskCancelation {
-            matched_tasks,
-            canceled_tasks,
-            original_filter,
-        } => {
-            format!("{{ matched_tasks: {matched_tasks:?}, canceled_tasks: {canceled_tasks:?}, original_filter: {original_filter:?} }}")
-        }
-        Details::TaskDeletion {
-            matched_tasks,
-            deleted_tasks,
-            original_filter,
-        } => {
-            format!("{{ matched_tasks: {matched_tasks:?}, deleted_tasks: {deleted_tasks:?}, original_filter: {original_filter:?} }}")
-        },
-        Details::Dump { dump_uid } => {
-            format!("{{ dump_uid: {dump_uid:?} }}")
-        },
-        Details::IndexSwap { swaps } => {
-            format!("{{ swaps: {swaps:?} }}")
-        }
-        Details::Export { url, api_key, payload_size, indexes } => {
-            format!("{{ url: {url:?}, api_key: {api_key:?}, payload_size: {payload_size:?}, indexes: {indexes:?} }}")
-        }
-        Details::UpgradeDatabase { from, to } => {
-            format!("{{ from: {from:?}, to: {to:?} }}")
-        }
-    }
-}
-
-pub fn snapshot_status(
-    rtxn: &RoTxn,
-    db: Database<SerdeBincode<Status>, RoaringBitmapCodec>,
-) -> String {
-    let mut snap = String::new();
-    let iter = db.iter(rtxn).unwrap();
-    for next in iter {
-        let (status, task_ids) = next.unwrap();
-        writeln!(snap, "{status} {}", snapshot_bitmap(&task_ids)).unwrap();
-    }
-    snap
-}
-
-pub fn snapshot_kind(rtxn: &RoTxn, db: Database<SerdeBincode<Kind>, RoaringBitmapCodec>) -> String {
-    let mut snap = String::new();
-    let iter = db.iter(rtxn).unwrap();
-    for next in iter {
-        let (kind, task_ids) = next.unwrap();
-        let kind = serde_json::to_string(&kind).unwrap();
-        writeln!(snap, "{kind} {}", snapshot_bitmap(&task_ids)).unwrap();
-    }
-    snap
-}
-
-pub fn snapshot_index_tasks(rtxn: &RoTxn, db: Database<Str, RoaringBitmapCodec>) -> String {
-    let mut snap = String::new();
-    let iter = db.iter(rtxn).unwrap();
-    for next in iter {
-        let (index, task_ids) = next.unwrap();
-        writeln!(snap, "{index} {}", snapshot_bitmap(&task_ids)).unwrap();
-    }
-    snap
-}
-
-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 {
-        let (kind, task_ids) = next.unwrap();
-        writeln!(snap, "{kind} {}", snapshot_bitmap(&task_ids)).unwrap();
-    }
-    snap
-}
-
-pub fn snapshot_batch(batch: &Batch) -> String {
-    let mut snap = String::new();
-    let Batch {
-        uid,
-        details,
-        stats,
-        embedder_stats,
-        started_at,
-        finished_at,
-        progress: _,
-        enqueued_at,
-        stop_reason,
-    } = batch;
-    let stats = BatchStats {
-        progress_trace: Default::default(),
-        internal_database_sizes: Default::default(),
-        write_channel_congestion: None,
-        ..stats.clone()
-    };
-    if let Some(finished_at) = finished_at {
-        assert!(finished_at > started_at);
-    }
-    let BatchEnqueuedAt { earliest, oldest } = enqueued_at.unwrap();
-    assert!(*started_at > earliest);
-    assert!(earliest >= oldest);
-
-    snap.push('{');
-    snap.push_str(&format!("uid: {uid}, "));
-    snap.push_str(&format!("details: {}, ", serde_json::to_string(details).unwrap()));
-    snap.push_str(&format!("stats: {}, ", serde_json::to_string(&stats).unwrap()));
-    if !embedder_stats.skip_serializing() {
-        snap.push_str(&format!(
-            "embedder stats: {}, ",
-            serde_json::to_string(&embedder_stats).unwrap()
-        ));
-    }
-    snap.push_str(&format!("stop reason: {}, ", serde_json::to_string(&stop_reason).unwrap()));
-    snap.push('}');
-    snap
-}
-
-pub fn snapshot_index_mapper(rtxn: &RoTxn, mapper: &IndexMapper) -> String {
-    let mut s = String::new();
-    let names = mapper.index_names(rtxn).unwrap();
-
-    for name in names {
-        let stats = mapper.stats_of(rtxn, &name).unwrap();
-        s.push_str(&format!(
-            "{name}: {{ number_of_documents: {}, field_distribution: {:?} }}\n",
-            stats.documents_database_stats.number_of_entries(),
-            stats.field_distribution
-        ));
-    }
-
-    s
-}