Merge remote-tracking branch 'milli/main' into import-milli

.github/workflows/enforce-label.yml

@@ -0,0 +1,14 @@
+name: Enforce PR labels
+
+on:
+  pull_request:
+    types: [labeled, unlabeled, opened, edited, synchronize]
+
+jobs:
+  enforce-label:
+    name: Specify breaking
+    runs-on: ubuntu-latest
+    steps:
+    - uses: yogevbd/enforce-label-action@2.2.2
+      with:
+        REQUIRED_LABELS_ANY: 'no breaking,DB breaking,API breaking,skip changelog'

.github/workflows/manual_benchmarks.yml

@@ -0,0 +1,77 @@
+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)'
+        required: false
+        default: 'search_songs'
+
+env:
+  BENCH_NAME: ${{ github.event.inputs.dataset_name }}
+
+jobs:
+  benchmarks:
+    name: Run and upload benchmarks
+    runs-on: benchmarks
+    timeout-minutes: 4320 # 72h
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions-rs/toolchain@v1
+        with:
+          profile: minimal
+          toolchain: stable
+          override: true
+
+      # Set variables
+      - name: Set current branch name
+        shell: bash
+        run: echo "name=$(echo ${GITHUB_REF#refs/heads/})" >> $GITHUB_OUTPUT
+        id: current_branch
+      - name: Set normalized current branch name # Replace `/` by `_` in branch name to avoid issues when pushing to S3
+        shell: bash
+        run: echo "name=$(echo ${GITHUB_REF#refs/heads/} | 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 ${BENCH_NAME}_${{ steps.normalized_current_branch.outputs.name }}_${{ steps.commit_sha.outputs.short }})" >> $GITHUB_OUTPUT
+        id: file
+
+      # Run benchmarks
+      - name: Run benchmarks - Dataset ${BENCH_NAME} - Branch ${{ steps.current_branch.outputs.name }} - Commit ${{ steps.commit_sha.outputs.short }}
+        run: |
+          cd benchmarks
+          cargo bench --bench ${BENCH_NAME} -- --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: ${{ steps.file.outputs.basename }}.json
+          out_dir: critcmp_results
+
+      # Helper
+      - name: 'README: compare with another benchmark'
+        run: |
+          echo "${{ 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/scipts/compare.sh <file-to-compare-with> ${{ steps.file.outputs.basename }}.json"

.github/workflows/push_benchmarks_indexing.yml

@@ -0,0 +1,79 @@
+name: Benchmarks indexing (push)
+
+on:
+  push:
+    branches:
+      - main
+
+env:
+  INFLUX_TOKEN: ${{ secrets.INFLUX_TOKEN }}
+  BENCH_NAME: "indexing"
+
+jobs:
+  benchmarks:
+    name: Run and upload benchmarks
+    runs-on: benchmarks
+    timeout-minutes: 4320 # 72h
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions-rs/toolchain@v1
+        with:
+          profile: minimal
+          toolchain: stable
+          override: true
+
+      # Set variables
+      - name: Set current branch name
+        shell: bash
+        run: echo "name=$(echo ${GITHUB_REF#refs/heads/})" >> $GITHUB_OUTPUT
+        id: current_branch
+      - name: Set normalized current branch name # Replace `/` by `_` in branch name to avoid issues when pushing to S3
+        shell: bash
+        run: echo "name=$(echo ${GITHUB_REF#refs/heads/} | 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 ${BENCH_NAME}_${{ steps.normalized_current_branch.outputs.name }}_${{ steps.commit_sha.outputs.short }})" >> $GITHUB_OUTPUT
+        id: file
+
+      # Run benchmarks
+      - name: Run benchmarks - Dataset ${BENCH_NAME} - Branch ${{ steps.current_branch.outputs.name }} - Commit ${{ steps.commit_sha.outputs.short }}
+        run: |
+          cd benchmarks
+          cargo bench --bench ${BENCH_NAME} -- --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
+
+      # Upload benchmarks to influxdb
+      - name: Upload ${{ steps.file.outputs.basename }}.json to influxDB
+        run: telegraf --config https://eu-central-1-1.aws.cloud2.influxdata.com/api/v2/telegrafs/08b52e34a370b000 --once --debug
+
+      # Helper
+      - name: 'README: compare with another benchmark'
+        run: |
+          echo "${{ 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/scipts/compare.sh <file-to-compare-with> ${{ steps.file.outputs.basename }}.json"

.github/workflows/push_benchmarks_search_geo.yml

@@ -0,0 +1,78 @@
+name: Benchmarks search geo (push)
+
+on:
+  push:
+    branches:
+      - main
+
+env:
+  BENCH_NAME: "search_geo"
+  INFLUX_TOKEN: ${{ secrets.INFLUX_TOKEN }}
+
+jobs:
+  benchmarks:
+    name: Run and upload benchmarks
+    runs-on: benchmarks
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions-rs/toolchain@v1
+        with:
+          profile: minimal
+          toolchain: stable
+          override: true
+
+      # Set variables
+      - name: Set current branch name
+        shell: bash
+        run: echo "name=$(echo ${GITHUB_REF#refs/heads/})" >> $GITHUB_OUTPUT
+        id: current_branch
+      - name: Set normalized current branch name # Replace `/` by `_` in branch name to avoid issues when pushing to S3
+        shell: bash
+        run: echo "name=$(echo ${GITHUB_REF#refs/heads/} | 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 ${BENCH_NAME}_${{ steps.normalized_current_branch.outputs.name }}_${{ steps.commit_sha.outputs.short }})" >> $GITHUB_OUTPUT
+        id: file
+
+      # Run benchmarks
+      - name: Run benchmarks - Dataset ${BENCH_NAME} - Branch ${{ steps.current_branch.outputs.name }} - Commit ${{ steps.commit_sha.outputs.short }}
+        run: |
+          cd benchmarks
+          cargo bench --bench ${BENCH_NAME} -- --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
+
+      # Upload benchmarks to influxdb
+      - name: Upload ${{ steps.file.outputs.basename }}.json to influxDB
+        run: telegraf --config https://eu-central-1-1.aws.cloud2.influxdata.com/api/v2/telegrafs/08b52e34a370b000 --once --debug
+
+      # Helper
+      - name: 'README: compare with another benchmark'
+        run: |
+          echo "${{ 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/scipts/compare.sh <file-to-compare-with> ${{ steps.file.outputs.basename }}.json"

.github/workflows/push_benchmarks_search_songs.yml

@@ -0,0 +1,78 @@
+name: Benchmarks search songs (push)
+
+on:
+  push:
+    branches:
+      - main
+
+env:
+  BENCH_NAME: "search_songs"
+  INFLUX_TOKEN: ${{ secrets.INFLUX_TOKEN }}
+
+jobs:
+  benchmarks:
+    name: Run and upload benchmarks
+    runs-on: benchmarks
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions-rs/toolchain@v1
+        with:
+          profile: minimal
+          toolchain: stable
+          override: true
+
+      # Set variables
+      - name: Set current branch name
+        shell: bash
+        run: echo "name=$(echo ${GITHUB_REF#refs/heads/})" >> $GITHUB_OUTPUT
+        id: current_branch
+      - name: Set normalized current branch name # Replace `/` by `_` in branch name to avoid issues when pushing to S3
+        shell: bash
+        run: echo "name=$(echo ${GITHUB_REF#refs/heads/} | 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 ${BENCH_NAME}_${{ steps.normalized_current_branch.outputs.name }}_${{ steps.commit_sha.outputs.short }})" >> $GITHUB_OUTPUT
+        id: file
+
+      # Run benchmarks
+      - name: Run benchmarks - Dataset ${BENCH_NAME} - Branch ${{ steps.current_branch.outputs.name }} - Commit ${{ steps.commit_sha.outputs.short }}
+        run: |
+          cd benchmarks
+          cargo bench --bench ${BENCH_NAME} -- --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
+
+      # Upload benchmarks to influxdb
+      - name: Upload ${{ steps.file.outputs.basename }}.json to influxDB
+        run: telegraf --config https://eu-central-1-1.aws.cloud2.influxdata.com/api/v2/telegrafs/08b52e34a370b000 --once --debug
+
+      # Helper
+      - name: 'README: compare with another benchmark'
+        run: |
+          echo "${{ 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/scipts/compare.sh <file-to-compare-with> ${{ steps.file.outputs.basename }}.json"

.github/workflows/push_benchmarks_search_wiki.yml

@@ -0,0 +1,78 @@
+name: Benchmarks search wikipedia articles (push)
+
+on:
+  push:
+    branches:
+      - main
+
+env:
+  BENCH_NAME: "search_wiki"
+  INFLUX_TOKEN: ${{ secrets.INFLUX_TOKEN }}
+
+jobs:
+  benchmarks:
+    name: Run and upload benchmarks
+    runs-on: benchmarks
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions-rs/toolchain@v1
+        with:
+          profile: minimal
+          toolchain: stable
+          override: true
+
+      # Set variables
+      - name: Set current branch name
+        shell: bash
+        run: echo "name=$(echo ${GITHUB_REF#refs/heads/})" >> $GITHUB_OUTPUT
+        id: current_branch
+      - name: Set normalized current branch name # Replace `/` by `_` in branch name to avoid issues when pushing to S3
+        shell: bash
+        run: echo "name=$(echo ${GITHUB_REF#refs/heads/} | 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 ${BENCH_NAME}_${{ steps.normalized_current_branch.outputs.name }}_${{ steps.commit_sha.outputs.short }})" >> $GITHUB_OUTPUT
+        id: file
+
+      # Run benchmarks
+      - name: Run benchmarks - Dataset ${BENCH_NAME} - Branch ${{ steps.current_branch.outputs.name }} - Commit ${{ steps.commit_sha.outputs.short }}
+        run: |
+          cd benchmarks
+          cargo bench --bench ${BENCH_NAME} -- --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
+
+      # Upload benchmarks to influxdb
+      - name: Upload ${{ steps.file.outputs.basename }}.json to influxDB
+        run: telegraf --config https://eu-central-1-1.aws.cloud2.influxdata.com/api/v2/telegrafs/08b52e34a370b000 --once --debug
+
+      # Helper
+      - name: 'README: compare with another benchmark'
+        run: |
+          echo "${{ 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/scipts/compare.sh <file-to-compare-with> ${{ steps.file.outputs.basename }}.json"

.github/workflows/release-drafter.yml

@@ -0,0 +1,16 @@
+name: Release Drafter
+
+on:
+  push:
+    branches:
+      - main
+
+jobs:
+  update_release_draft:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: release-drafter/release-drafter@v5
+        with:
+          config-name: release-draft-template.yml
+        env:
+          GITHUB_TOKEN: ${{ secrets.RELEASE_DRAFTER_TOKEN }}

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

@@ -13,7 +13,6 @@ env:
   GH_TOKEN: ${{ secrets.MEILI_BOT_GH_PAT }}
 
 jobs:
-
   update-version-cargo-toml:
     name: Update version in Cargo.toml files
     runs-on: ubuntu-latest