vantadb 0.1.4

name: VantaDB Performance Benchmarks

on:
  push:
    branches: [ "main" ]
    paths:
      - 'src/**'
      - 'vantadb-python/**'
      - 'benchmarks/**'
      - 'Cargo.toml'
      - 'Cargo.lock'
  pull_request:
    branches: [ "main" ]
    paths:
      - 'src/**'
      - 'vantadb-python/**'
      - 'benchmarks/**'
  workflow_dispatch:
    inputs:
      size:
        description: 'Number of vectors to ingest'
        required: true
        default: '10000'
      queries:
        description: 'Number of queries to run'
        required: true
        default: '1000'
      dim:
        description: 'Dimensionality of vectors'
        required: true
        default: '128'

env:
  CARGO_TERM_COLOR: always
  CARGO_INCREMENTAL: 0
  RUST_BACKTRACE: 1

permissions:
  contents: write

jobs:
  benchmark:
    runs-on: ubuntu-latest
    timeout-minutes: 30

    steps:
    - name: Free Disk Space
      run: |

        sudo rm -rf /usr/share/dotnet
        sudo rm -rf /usr/local/lib/android
        sudo rm -rf /opt/ghc
        sudo rm -rf /opt/hostedtoolcache/CodeQL

    - uses: actions/checkout@v6

    - name: Set up Rust
      uses: dtolnay/rust-toolchain@stable

    - name: Rust Cache
      uses: Swatinem/rust-cache@v2
      with:
        cache-bin: "false"

    - name: Install system dependencies (RocksDB + Clang)
      run: |

        sudo apt-get update
        sudo apt-get install -y libclang-dev clang librocksdb-dev

    - name: Set up Python
      uses: actions/setup-python@v6
      with:
        python-version: '3.11'
        cache: 'pip'

    - name: Build & install Python wheel
      run: |

        python -m venv .venv
        .venv/bin/python -m pip install --upgrade pip
        .venv/bin/python -m pip install maturin
        .venv/bin/maturin build --manifest-path vantadb-python/Cargo.toml --release --out vantadb-python/dist
        .venv/bin/pip install $(ls -t vantadb-python/dist/vantadb_py-*.whl | head -n 1) --force-reinstall
        .venv/bin/python -c "import vantadb_py; print('Import OK:', vantadb_py.__version__)"

    - name: Run Standard Ingestion & Search Benchmark
      run: |

        # Use inputs if triggered manually, otherwise fall back to a lightweight 1K size for automated push runs
        SIZE="${{ github.event.inputs && github.event.inputs.size || '1000' }}"
        QUERIES="${{ github.event.inputs && github.event.inputs.queries || '100' }}"
        DIM="${{ github.event.inputs && github.event.inputs.dim || '128' }}"
        .venv/bin/python benchmarks/vantadb_local_bench.py --size $SIZE --dim $DIM --queries $QUERIES --output benchmark_results.json

    - name: Update BENCHMARKS.md dynamically
      run: |

        .venv/bin/python benchmarks/update_markdown.py

    - name: Commit and Push Benchmark Metrics
      if: github.event_name == 'push' && github.ref == 'refs/heads/main'
      env:
        GITHUB_TOKEN: ${{ github.token }}
      run: |

        git config --global user.name "github-actions[bot]"
        git config --global user.email "github-actions[bot]@users.noreply.github.com"
        git remote set-url origin "https://x-access-token:${GITHUB_TOKEN}@github.com/${{ github.repository }}.git"
        git add docs/operations/BENCHMARKS.md
        if ! git diff-index --quiet HEAD; then
          git commit -m "docs: update dynamic performance metrics [skip ci]"
          git push origin HEAD:main || echo "::warning::Unable to push benchmark metrics (branch protection may be enabled); benchmark artifacts were still uploaded."
        fi

    - name: Upload Benchmark Results Artifact
      uses: actions/upload-artifact@v4
      with:
        name: vanta-benchmark-results
        path: benchmark_results.json
        retention-days: 14