topoteretes--cognee/.github/workflows/vector_db_tests.yml

name: Reusable Vector DB Tests

on:
  workflow_call:
    inputs:
      databases:
        required: false
        type: string
        default: "all"
        description: "Which vector databases to test (comma-separated list or 'all')"
      ci-image:
        required: false
        type: string
        default: ''
    secrets:

      POSTGRES_PASSWORD:
        required: false

env:
  COGNEE_SKIP_CONNECTION_TEST: 'true'

jobs:
  run-postgres-tests:
    name: PostgreSQL Tests
    runs-on: ubuntu-22.04
    container: ${{ inputs.ci-image != '' && fromJSON(format('{{"image":"{0}","credentials":{{"username":"{1}","password":"{2}"}}}}', inputs.ci-image, github.actor, github.token)) || null }}
    if: ${{ inputs.databases == 'all' || contains(inputs.databases, 'postgres') }}
    services:
      postgres:
        image: ghcr.io/topoteretes/pgvector:pg17
        credentials:
          username: ${{ github.actor }}
          password: ${{ secrets.GITHUB_TOKEN }}
        env:
          POSTGRES_USER: cognee
          POSTGRES_PASSWORD: ${{ secrets.POSTGRES_PASSWORD }}
          POSTGRES_DB: cognee_db
        options: >-
          --health-cmd pg_isready
          --health-interval 10s
          --health-timeout 5s
          --health-retries 5
        ports:
          - 5432:5432
    steps:
      - name: Check out
        uses: actions/checkout@v6
        with:
          fetch-depth: 0

      - name: Cognee Setup
        uses: ./.github/actions/cognee_setup
        with:
          python-version: ${{ inputs.python-version }}
          extra-dependencies: "postgres"

      - name: Run PGVector Tests
        env:
          ENV: 'dev'
          ENABLE_BACKEND_ACCESS_CONTROL: 'false'
          LLM_MODEL: ${{ secrets.LLM_MODEL }}
          LLM_ENDPOINT: ${{ secrets.LLM_ENDPOINT }}
          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
          LLM_ARGS: ${{ secrets.LLM_ARGS }}
          LLM_API_VERSION: ${{ secrets.LLM_API_VERSION }}
          EMBEDDING_DIMENSIONS: 300
          EMBEDDING_MODEL: ${{ secrets.EMBEDDING_MODEL }}
          EMBEDDING_API_KEY: ${{ secrets.EMBEDDING_API_KEY }}
          DB_HOST: ${{ inputs.ci-image != '' && 'postgres' || '127.0.0.1' }}
        run: uv run python ./cognee/tests/test_pgvector.py

  run-pgvector-multi-user-tests:
    name: PGVector Multi-User Tests
    runs-on: ubuntu-22.04
    container: ${{ inputs.ci-image != '' && fromJSON(format('{{"image":"{0}","credentials":{{"username":"{1}","password":"{2}"}}}}', inputs.ci-image, github.actor, github.token)) || null }}
    if: ${{ inputs.databases == 'all' || contains(inputs.databases, 'postgres') }}
    services:
      postgres:
        image: ghcr.io/topoteretes/pgvector:pg17
        credentials:
          username: ${{ github.actor }}
          password: ${{ secrets.GITHUB_TOKEN }}
        env:
          POSTGRES_USER: cognee
          POSTGRES_PASSWORD: ${{ secrets.POSTGRES_PASSWORD }}
          POSTGRES_DB: cognee_db
        options: >-
          --health-cmd pg_isready
          --health-interval 10s
          --health-timeout 5s
          --health-retries 5
        ports:
          - 5432:5432
    steps:
      - name: Check out
        uses: actions/checkout@v6
        with:
          fetch-depth: 0

      - name: Cognee Setup
        uses: ./.github/actions/cognee_setup
        with:
          python-version: ${{ inputs.python-version }}
          extra-dependencies: "postgres"

      - name: Run PGVector Permissions Tests
        env:
          ENV: 'dev'
          ENABLE_BACKEND_ACCESS_CONTROL: 'true'
          LLM_MODEL: ${{ secrets.LLM_MODEL }}
          LLM_ENDPOINT: ${{ secrets.LLM_ENDPOINT }}
          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
          LLM_ARGS: ${{ secrets.LLM_ARGS }}
          LLM_API_VERSION: ${{ secrets.LLM_API_VERSION }}
          EMBEDDING_MODEL: ${{ secrets.EMBEDDING_MODEL }}
          EMBEDDING_API_KEY: ${{ secrets.EMBEDDING_API_KEY }}
          VECTOR_DB_HOST: ${{ inputs.ci-image != '' && 'postgres' || '127.0.0.1' }}
          VECTOR_DB_PORT: 5432
          VECTOR_DB_USERNAME: cognee
          VECTOR_DB_PASSWORD: ${{ secrets.POSTGRES_PASSWORD }}
          VECTOR_DATASET_DATABASE_HANDLER: pgvector
        run: uv run python ./cognee/tests/test_permissions.py

  run-lancedb-tests:
    name: LanceDB Tests
    runs-on: ubuntu-22.04
    container: ${{ inputs.ci-image != '' && fromJSON(format('{{"image":"{0}","credentials":{{"username":"{1}","password":"{2}"}}}}', inputs.ci-image, github.actor, github.token)) || null }}
    steps:
      - name: Check out
        uses: actions/checkout@v6
        with:
          fetch-depth: 0

      - name: Cognee Setup
        uses: ./.github/actions/cognee_setup
        with:
          python-version: ${{ inputs.python-version }}

      - name: Run LanceDB Tests
        env:
          ENV: 'dev'
          # Cap cached DB adapters
          DATABASE_MAX_LRU_CACHE_SIZE: 1
          LLM_MODEL: ${{ secrets.LLM_MODEL }}
          LLM_ENDPOINT: ${{ secrets.LLM_ENDPOINT }}
          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
          LLM_ARGS: ${{ secrets.LLM_ARGS }}
          LLM_API_VERSION: ${{ secrets.LLM_API_VERSION }}
          EMBEDDING_DIMENSIONS: 300
          EMBEDDING_MODEL: ${{ secrets.EMBEDDING_MODEL }}
          EMBEDDING_API_KEY: ${{ secrets.EMBEDDING_API_KEY }}
        run: uv run python ./cognee/tests/test_lancedb.py