Fetching metadata from the HF Docker repository...
-
feat: add MedGemma readiness gate to prevent cold-start pipeline failures
bshepp
-
fix: add retry logic, error handling, and startup diagnostics for deployed pipeline
bshepp
- Add startup config logging in main.py (masked secrets, warnings if empty)
- Add retry with exponential backoff in MedGemma API (3 retries, handles 503 cold-start)
- Broaden patient_parser exception handler (catch all, not just ValueError)
- Stop pipeline on critical step failure (skip remaining instead of cascading errors)
- Add /api/health/config diagnostic endpoint -
Implement validation pipeline fixes (P1-P7) and experimental track system
bshepp
Pipeline fixes:
- P1: Question type classifier (question_classifier.py) - 9 types via heuristic regex
- P3: Preserve question stem - _extract_vignette -> _split_question returning (vignette, stem)
- P4: Type-aware scoring - score_case() dispatcher with per-type scorers (diagnostic, treatment, mechanism, lab_finding, generic)
- P5: Improved fuzzy matching - recall-based with medical stopwords, 3-strategy approach
- P6: MCQ answer selection - select_mcq_answer() uses MedGemma to pick A/B/C/D given CDS report
- P7: Stratified reporting - per-type breakdown table + pipeline-appropriate subset metrics
Experimental track system:
- CLAUDE.md, TRACKS.md, EXPERIMENT_PLAN.md - project intelligence and track registry
- Track A: Baseline pipeline tagged (all app/ files)
- Track B: RAG variants (10 configs, chunking/embedding experiments)
- Track C: Iterative refinement (4 configs, serial refinement rounds)
- Track D: Arbitrated parallel (4 configs, specialist + arbiter pattern)
- Shared utilities…
-
MedGemma validation: 50-case MedQA run, TGI endpoint config, prompt improvements
bshepp
- Fixed TGI token limits (MAX_INPUT_TOKENS=12288, MAX_TOTAL_TOKENS=16384)
- Reduced per-step max_tokens for faster generation
- Improved clinical reasoning prompt (disease-level dx, not symptoms)
- Fixed Unicode encoding issues for Windows console
- Fixed error masking in orchestrator (failed steps now surface errors)
- Fixed endpoint URL in .env
- Added analyze_results.py for question-type categorization
- Results: 94% pipeline success, 38% top3 accuracy, 14% dx-only accuracy
- Paused endpoint to save costs
-
Initial commit: CDS Agent - Clinical Decision Support System
bshepp
- 5-step agentic pipeline: parse reason drug check RAG guidelines synthesize
- Backend: FastAPI + Python 3.10, Gemma 3 27B IT via Google AI Studio
- Frontend: Next.js 14 + React 18 + TypeScript + Tailwind CSS
- RAG: ChromaDB with 62 clinical guidelines across 14 specialties
- Drug APIs: OpenFDA + RxNorm/NLM
- Tests: E2E pipeline, 30 RAG quality queries (100% pass), 22 clinical scenarios
- Full documentation: architecture, test results, development log, writeup
