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

name: Reusable Adapter Caching Tests

permissions:
  contents: read
  packages: read

on:
  workflow_call:
    inputs:
      databases:
        required: false
        type: string
        default: "all"
        description: "Which provider combos to test (comma-separated list or 'all')"
      python-version:
        required: false
        type: string
        default: '3.11.x'
        description: "Python version to test"
      ci-image:
        required: false
        type: string
        default: ''
        description: "Container image for CI (empty string means no container)"
    secrets:
      LLM_MODEL:
        required: true
      LLM_ENDPOINT:
        required: true
      LLM_API_KEY:
        required: true
      LLM_ARGS:
        required: false
      LLM_API_VERSION:
        required: true
      EMBEDDING_MODEL:
        required: true
      EMBEDDING_API_KEY:
        required: true

jobs:
  run-ladybug-lance-sqlite-caching:
    name: Adapter caching — Ladybug + LanceDB + Sqlite
    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, 'ladybug/lance/sqlite') }}
    steps:
      - name: Check out
        uses: actions/checkout@v6

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

      - name: Run adapter caching test
        env:
          ENV: 'dev'
          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 }}
          GRAPH_DATABASE_PROVIDER: 'ladybug'
          VECTOR_DB_PROVIDER: 'lancedb'
          DB_PROVIDER: 'sqlite'
        run: uv run python ./cognee/tests/test_adapter_object_caching.py

  run-neo4j-lance-sqlite-caching:
    name: Adapter caching — Neo4j + LanceDB + Sqlite
    runs-on: ubuntu-22.04
    if: ${{ inputs.databases == 'all' || contains(inputs.databases, 'neo4j/lance/sqlite') }}
    steps:
      - name: Check out
        uses: actions/checkout@v6

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

      - name: Setup Neo4j with GDS
        uses: ./.github/actions/setup_neo4j
        id: neo4j

      - name: Run adapter caching test
        env:
          ENV: 'dev'
          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 }}
          GRAPH_DATABASE_PROVIDER: 'neo4j'
          VECTOR_DB_PROVIDER: 'lancedb'
          DB_PROVIDER: 'sqlite'
          ENABLE_BACKEND_ACCESS_CONTROL: 'false'
          GRAPH_DATABASE_URL: ${{ steps.neo4j.outputs.neo4j-url }}
          GRAPH_DATABASE_USERNAME: ${{ steps.neo4j.outputs.neo4j-username }}
          GRAPH_DATABASE_PASSWORD: ${{ steps.neo4j.outputs.neo4j-password }}
        run: uv run python ./cognee/tests/test_adapter_object_caching.py

  run-ladybug-pgvector-postgres-caching:
    name: Adapter caching — Ladybug + PGVector + Postgres
    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, 'ladybug/pgvector/postgres') }}
    services:
      postgres:
        image: ghcr.io/topoteretes/pgvector:pg17
        credentials:
          username: ${{ github.actor }}
          password: ${{ secrets.GITHUB_TOKEN }}
        env:
          POSTGRES_USER: cognee
          POSTGRES_PASSWORD: cognee
          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

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

      - name: Run adapter caching test
        env:
          ENV: 'dev'
          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 }}
          GRAPH_DATABASE_PROVIDER: 'ladybug'
          VECTOR_DB_PROVIDER: 'pgvector'
          ENABLE_BACKEND_ACCESS_CONTROL: 'false'
          DB_PROVIDER: 'postgres'
          DB_NAME: 'cognee_db'
          DB_HOST: ${{ inputs.ci-image != '' && 'postgres' || '127.0.0.1' }}
          DB_PORT: 5432
          DB_USERNAME: cognee
          DB_PASSWORD: cognee
        run: uv run python ./cognee/tests/test_adapter_object_caching.py

  run-neo4j-pgvector-postgres-caching:
    name: Adapter caching — Neo4j + PGVector + Postgres
    runs-on: ubuntu-22.04
    if: ${{ inputs.databases == 'all' || contains(inputs.databases, 'neo4j/pgvector/postgres') }}
    services:
      postgres:
        image: ghcr.io/topoteretes/pgvector:pg17
        credentials:
          username: ${{ github.actor }}
          password: ${{ secrets.GITHUB_TOKEN }}
        env:
          POSTGRES_USER: cognee
          POSTGRES_PASSWORD: cognee
          POSTGRES_DB: cognee_db
        ports:
          - 5432:5432
        options: >-
          --health-cmd pg_isready
          --health-interval 10s
          --health-timeout 5s
          --health-retries=5
    steps:
      - name: Check out
        uses: actions/checkout@v6

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

      - name: Setup Neo4j with GDS
        uses: ./.github/actions/setup_neo4j
        id: neo4j

      - name: Run adapter caching test
        env:
          ENV: 'dev'
          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 }}
          GRAPH_DATABASE_PROVIDER: 'neo4j'
          VECTOR_DB_PROVIDER: 'pgvector'
          DB_PROVIDER: 'postgres'
          ENABLE_BACKEND_ACCESS_CONTROL: 'false'
          GRAPH_DATABASE_URL: ${{ steps.neo4j.outputs.neo4j-url }}
          GRAPH_DATABASE_USERNAME: ${{ steps.neo4j.outputs.neo4j-username }}
          GRAPH_DATABASE_PASSWORD: ${{ steps.neo4j.outputs.neo4j-password }}
          DB_NAME: cognee_db
          DB_HOST: 127.0.0.1
          DB_PORT: 5432
          DB_USERNAME: cognee
          DB_PASSWORD: cognee
        run: uv run python ./cognee/tests/test_adapter_object_caching.py

  run-postgres-pgvector-postgres-caching:
    name: Adapter caching — Postgres graph + PGVector + Postgres (access control)
    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/pgvector/postgres') }}
    services:
      postgres:
        image: ghcr.io/topoteretes/pgvector:pg17
        credentials:
          username: ${{ github.actor }}
          password: ${{ secrets.GITHUB_TOKEN }}
        env:
          POSTGRES_USER: cognee
          POSTGRES_PASSWORD: cognee
          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

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

      - name: Run adapter caching test
        env:
          ENV: 'dev'
          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 }}
          # Access control mode: every dataset gets its own physical Postgres
          # database (named after the deterministic dataset id) that is created
          # on add and dropped on delete — the engine-cache lifecycle across
          # that drop/recreate boundary is what this job guards.
          ENABLE_BACKEND_ACCESS_CONTROL: 'true'
          DB_PROVIDER: 'postgres'
          DB_NAME: 'cognee_db'
          DB_HOST: ${{ inputs.ci-image != '' && 'postgres' || '127.0.0.1' }}
          DB_PORT: 5432
          DB_USERNAME: cognee
          DB_PASSWORD: cognee
          VECTOR_DB_PROVIDER: 'pgvector'
          VECTOR_DB_NAME: 'cognee_db'
          VECTOR_DB_HOST: ${{ inputs.ci-image != '' && 'postgres' || '127.0.0.1' }}
          VECTOR_DB_PORT: 5432
          VECTOR_DB_USERNAME: cognee
          VECTOR_DB_PASSWORD: cognee
          VECTOR_DATASET_DATABASE_HANDLER: 'pgvector'
          GRAPH_DATABASE_PROVIDER: 'postgres'
          GRAPH_DATABASE_NAME: 'cognee_db'
          GRAPH_DATABASE_HOST: ${{ inputs.ci-image != '' && 'postgres' || '127.0.0.1' }}
          GRAPH_DATABASE_PORT: 5432
          GRAPH_DATABASE_USERNAME: cognee
          GRAPH_DATABASE_PASSWORD: cognee
          GRAPH_DATASET_DATABASE_HANDLER: 'postgres_graph'
        run: uv run python ./cognee/tests/test_adapter_object_caching.py