Spaces:
Sleeping
Sleeping
Commit History
-
feat: Add V4 NDJSON patch-based structured summarization
ming- Refactor StructuredSummarizer with new NDJSON streaming protocol - Add summarize_structured_stream_ndjson() method for patch-based streaming - Implement state management with _empty_state() and _apply_patch() - Update system prompt to instruct model to output NDJSON patches - Add new /api/v4/scrape-and-summarize/stream-ndjson endpoint - Support incremental state updates via delta/state events - Use deterministic decoding (greedy) for consistent results - Maintain backwards compatibility with existing stream endpoint Event structure: - delta: JSON patch object (set/append/done operations) - state: Current accumulated state - done: Completion flag - tokens_used: Token count - latency_ms: Final latency metric Test suite: - test_v4_ndjson_mock.py: Protocol logic validation (PASSED ✅) - test_v4_ndjson_http.py: HTTP endpoint test - test_v4_ndjson_url.py: URL scraping test (PASSED ✅) - test_v4_ndjson.py: Direct service test Documentation: - NDJSON_REFACTOR_SUMMARY.md:…93c9664
-
Improve start-server.sh script robustness
ming- Add multiple process killing methods for better reliability - Force kill processes using the port if needed - Add verification that port is actually free - Improve error handling and user feedback - Prevent 'Address already in use' errors The script now handles edge cases where processes don't match expected patterns and ensures clean server restarts.046ad45 -
feat: Add comprehensive configuration management and startup automation
ming- Add .env file with correct default configurations - Create automated startup scripts (start-server.sh, start-server.bat) - Add Ollama connectivity validation on server startup - Update README with improved setup instructions and troubleshooting - Prevent common configuration issues (wrong host, model mismatch, port conflicts) - Add cross-platform support for macOS/Linux and Windows Fixes issues with: - Ollama host resolution (ollama:11434 -> 127.0.0.1:11434) - Model availability (llama3.1:8b -> llama3.2:latest) - Port conflicts and startup automation035a845