Fix Docker postgres build #45
Workflow file for this run
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Build Docker Image | |
| on: | |
| pull_request | |
| permissions: | |
| contents: read | |
| jobs: | |
| docker-build: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - name: Checkout repository | |
| uses: actions/checkout@v4 | |
| - name: Free up 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 | |
| sudo docker image prune --all --force | |
| sudo docker builder prune -a --force | |
| df -h | |
| - name: Set up Docker Buildx | |
| uses: docker/setup-buildx-action@v3 | |
| - name: Extract metadata | |
| id: meta | |
| uses: docker/metadata-action@v5 | |
| with: | |
| images: ghcr.io/${{ github.repository_owner }}/morphik-core | |
| tags: | | |
| type=ref,event=pr | |
| type=sha,prefix=pr-{{branch}}- | |
| - name: Build Docker image | |
| uses: docker/build-push-action@v5 | |
| with: | |
| context: . | |
| file: ./dockerfile | |
| push: false | |
| load: true | |
| tags: | | |
| ${{ steps.meta.outputs.tags }} | |
| morphik-core:test | |
| labels: ${{ steps.meta.outputs.labels }} | |
| cache-from: type=gha | |
| # Remove cache-to for PR builds to save disk space | |
| - name: Test Docker container | |
| run: | | |
| # Use the local test tag instead of the registry tag | |
| IMAGE_TAG="morphik-core:test" | |
| echo "Testing image: $IMAGE_TAG" | |
| # Create a minimal config file for testing | |
| cat > morphik.toml.test << 'EOF' | |
| [api] | |
| host = "0.0.0.0" | |
| port = 8000 | |
| reload = true | |
| [auth] | |
| jwt_algorithm = "HS256" | |
| dev_mode = true # Enabled by default for easier local development | |
| dev_entity_id = "dev_user" # Default dev user ID | |
| dev_entity_type = "developer" # Default dev entity type | |
| dev_permissions = ["read", "write", "admin"] # Default dev permissions | |
| #### Registered models | |
| [registered_models] | |
| # OpenAI models | |
| openai_gpt4 = { model_name = "gpt-4" } | |
| openai_gpt4-1 = { model_name = "gpt-4.1" } | |
| openai_gpt4o = { model_name = "gpt-4o" } | |
| # Embedding models | |
| openai_embedding = { model_name = "text-embedding-3-small" } | |
| openai_embedding_large = { model_name = "text-embedding-3-large" } | |
| #### Component configurations #### | |
| [agent] | |
| model = "openai_gpt4-1" | |
| [completion] | |
| model = "openai_gpt4o" | |
| default_max_tokens = "1000" | |
| default_temperature = 0.5 | |
| [document_analysis] | |
| model = "openai_gpt4-1" | |
| [database] | |
| provider = "postgres" | |
| # Connection pool settings | |
| pool_size = 10 # Maximum number of connections in the pool | |
| max_overflow = 15 # Maximum number of connections that can be created beyond pool_size | |
| pool_recycle = 3600 # Time in seconds after which a connection is recycled (1 hour) | |
| pool_timeout = 10 # Seconds to wait for a connection from the pool | |
| pool_pre_ping = true # Check connection viability before using it from the pool | |
| max_retries = 3 # Number of retries for database operations | |
| retry_delay = 1.0 # Initial delay between retries in seconds | |
| [embedding] | |
| model = "openai_embedding" # Reference to registered model | |
| dimensions = 1536 | |
| similarity_metric = "cosine" | |
| [parser] | |
| chunk_size = 6000 | |
| chunk_overlap = 300 | |
| use_unstructured_api = false | |
| use_contextual_chunking = false | |
| contextual_chunking_model = "openai_gpt4-1" # Reference to a key in registered_models | |
| [parser.vision] | |
| model = "openai_gpt4-1" # Reference to a key in registered_models | |
| frame_sample_rate = -1 # Set to -1 to disable frame captioning | |
| [reranker] | |
| use_reranker = true | |
| provider = "flag" | |
| model_name = "BAAI/bge-reranker-large" | |
| query_max_length = 256 | |
| passage_max_length = 512 | |
| use_fp16 = true | |
| device = "cpu" # use "cpu" if on docker and using a mac, "cuda" if cuda enabled device | |
| [storage] | |
| provider = "local" | |
| storage_path = "./storage" | |
| # [storage] | |
| # provider = "aws-s3" | |
| # region = "us-east-2" | |
| # bucket_name = "morphik-s3-storage" | |
| [vector_store] | |
| provider = "pgvector" | |
| [rules] | |
| model = "openai_gpt4-1" | |
| batch_size = 4096 | |
| [morphik] | |
| enable_colpali = true | |
| mode = "self_hosted" # "cloud" or "self_hosted" | |
| api_domain = "api.morphik.ai" # API domain for cloud URIs | |
| [redis] | |
| host = "redis" # use "redis" for docker | |
| port = 6379 | |
| [graph] | |
| model = "openai_gpt4-1" | |
| enable_entity_resolution = true | |
| # Start container in detached mode with config mounted | |
| CONTAINER_ID=$(docker run -d -p 8000:8000 \ | |
| -e POSTGRES_URI="postgresql://morphik:morphik@localhost:5432/morphik" \ | |
| -v "$(pwd)/morphik.toml.test:/app/morphik.toml" \ | |
| "$IMAGE_TAG") | |
| echo "Started container: $CONTAINER_ID" | |
| # Wait for server to be ready with 60 second timeout | |
| timeout=60 | |
| interval=2 | |
| elapsed=0 | |
| echo "Waiting for server to be ready..." | |
| while [ $elapsed -lt $timeout ]; do | |
| if curl -f -s http://localhost:8000/ping > /dev/null 2>&1; then | |
| echo "✅ Server is responding to /ping endpoint" | |
| break | |
| fi | |
| echo "⏳ Waiting for server... (${elapsed}s/${timeout}s)" | |
| sleep $interval | |
| elapsed=$((elapsed + interval)) | |
| done | |
| # Check if we timed out | |
| if [ $elapsed -ge $timeout ]; then | |
| echo "❌ Server failed to respond within ${timeout} seconds" | |
| echo "Container logs:" | |
| docker logs "$CONTAINER_ID" | |
| docker stop "$CONTAINER_ID" | |
| docker rm "$CONTAINER_ID" | |
| exit 1 | |
| fi | |
| # Verify the response is actually 200 | |
| HTTP_CODE=$(curl -s -o /dev/null -w "%{http_code}" http://localhost:8000/ping) | |
| if [ "$HTTP_CODE" = "200" ]; then | |
| echo "✅ Health check passed - /ping returned HTTP $HTTP_CODE" | |
| else | |
| echo "❌ Health check failed - /ping returned HTTP $HTTP_CODE" | |
| docker logs "$CONTAINER_ID" | |
| docker stop "$CONTAINER_ID" | |
| docker rm "$CONTAINER_ID" | |
| exit 1 | |
| fi | |
| # Clean up | |
| echo "🧹 Cleaning up container" | |
| docker stop "$CONTAINER_ID" | |
| docker rm "$CONTAINER_ID" | |
| echo "✅ Test completed successfully" |