Add comprehensive E2E testing infrastructure with PostgreSQL performance tuning,
Gunicorn multi-worker support, and evaluation scripts for RAGAS-based quality
assessment. Introduces 4 new evaluation utilities: compare_results.py for A/B test
analysis, download_wikipedia.py for reproducible test datasets, e2e_test_harness.py
for automated evaluation pipelines, and ingest_test_docs.py for batch document
ingestion. Updates docker-compose.test.yml with aggressive async settings, memory
limits, and optimized chunking parameters. Parallelize entity summarization in
operate.py for improved extraction performance. Fix typos in merge node/edge logs.
Implement automatic orphan entity connection system that identifies entities with
no relationships and creates meaningful connections via vector similarity + LLM
validation. This improves knowledge graph connectivity and retrieval quality.
Changes:
- Add orphan connection configuration parameters (thresholds, cross-connect settings)
- Implement aconnect_orphan_entities() method with 4-step validation pipeline
- Add SQL templates for efficient orphan and candidate entity queries
- Create POST /graph/orphans/connect API endpoint with configurable parameters
- Add orphan connection validation prompt for LLM-based relationship verification
- Include relationship density requirement in extraction prompts to prevent orphans
- Update docker-compose.test.yml with optimized extraction parameters
- Add quality validation test suite (run_quality_tests.py) for retrieval evaluation
- Add unit test framework (test_orphan_connection_quality.py) with test cases
- Enable auto-run of orphan connection after document processing
- Extract PostgreSQL storage check into named variable for clarity
- Move APIRouter initialization into create_table_routes function scope
- Add robust type handling for database query results
- Add input validation for table names and pagination parameters
- Add regex-based SQL injection prevention for table name sanitization
- Improve clipboard copy fallback logic and error handling
- Add memoization for JSON serialization to prevent unnecessary recalculations
- Hide meta column from table explorer UI display
- Sort table columns alphabetically for consistent ordering
- Add keyboard accessibility to status filter buttons
- Add preprocessed status filter to document manager
- Update @tanstack/react-query from 5.60.0 to 5.87.1
- Extract dev storage config into constant to reduce duplication
- Update documentation comments for clarity
- Implemented Table Explorer component to allow users to select and view database tables.
- Added API calls for fetching table list, schema, and paginated data.
- Introduced row detail modal for displaying and copying row data.
- Enhanced DataTable component to support row click events.
- Updated UI components for better user experience and accessibility.
- Added mock data for development mode to facilitate testing.
- Updated localization files to include new terms related to tables.
- Modified settings store to include storage configuration for conditional UI rendering.
- Improved styling and layout for various components to align with new design standards.
- Change build check from error to warning
- Redirect to /docs when WebUI unavailable
- Add webui_available to health endpoint
- Only mount /webui if assets exist
- Return status tuple from build check
Added support for structured output (JSON mode) from the OpenAI API in `openai.py` and `azure_openai.py`.
When `response_format` is used to request structured data, the new logic checks for the `message.parsed` attribute. If it exists, it's serialized into a JSON string as the final content. If not, the code falls back to the existing `message.content` handling, ensuring backward compatibility.
