Spaces:
Runtime error
Runtime error
Commit History
-
docs: Add deployment summary
MediGuard AIc40e4c4 -
feat: Initial release of MediGuard AI v2.0
MediGuard AIc4f5f25
-
chore: implement true multi-stage docker build to reduce image size
7d110d0 -
refactor: resolve pylint errors and warnings across api and src routers
- Enforced explicit exception chaining (raise from exc) in ask/search/analyze routes - Fixed dynamic method call references pointing to llm_config missing members - Patched missing explicit utf-8 encodings in file handlers via BiomarkerValidator7caf4dc -
chore: codebase audit and fixes (ruff, mypy, pytest)
- Fixed pytest collection hang by adding root conftest.py and testpaths in pytest.ini - Fixed mypy missing keys for GuildState TypedDict definitions - Fixed ruff whitespace formatting and unhandled B904 exceptions - Added skip markers for unmocked LLM API calls in integration tests - Removed redundant debug script logging and trace files9659593
-
Fix HF Docker build: auto-generate requirements.txt from pyproject.toml
Nikhil Pravin Pise2ac1524 -
Fix codebase issues: linting, types, tests, and security.
Nikhil Pravin Pise- Resolved over 3,000 ruff linting violations - Enforced strict type checking with mypy - Fixed infinite loop in pytest suite by migrating obsolete tests - Remediated security warnings flagged by Bandit696f787
-
fix: all 15 bugs + full agentic RAG pipeline in HF Space
Nikhil Pravin PiseCritical fixes: - OpenSearch client param names aligned (query_text/query_vector) - _execute_search preserves _source as nested dict - health.py: SQLAlchemy text() wrapper + FAISS import path - llm_config: module-level get_synthesizer() function - Redis cache: simplified get(key)/set(key,value) API High priority: - Infinite rewrite loop prevented via retrieval_attempts counter - analyze.py: handles both dict and object results HF Space full pipeline integration: - retrieve_node: retriever-agnostic (FAISS/OpenSearch/BM25) - AgenticContext: retriever field added - grade_documents_node + generate_answer_node: unified doc format - app.py: full guardrail->retrieve->grade->rewrite->generate pipeline - asyncio.get_event_loop() -> get_running_loop()fd5543a -
Fix HF bugs: HTML rendering, Q&A validation, add separate Q&A tab
Nikhil Pravin Pise- Fixed format_summary: Added missing severity_config tuple with color/bg_color - Changed summary header text to dark color (#1e293b) instead of white - Rewrote answer_medical_question() to use retriever+LLM directly (not PatientInput) - Rewrote streaming_answer() to use retriever+LLM directly (not PatientInput) - Added top-level tabs: Biomarker Analysis | Medical Q&A - Improved Q&A UX with dedicated tab for easy accessca20dc7 -
Production Upgrade v2.0: SSE streaming, HIPAA compliance, Gradio Q&A UI
Nikhil Pravin Pise## Features Added - SSE streaming endpoint (/ask/stream) for real-time responses - HIPAA-compliant audit middleware with PHI redaction - Security headers middleware (CSP, X-Frame-Options) - Medical Q&A chat interface in Gradio HF app - PostgreSQL and FAISS health checks - Comprehensive medical safety test suite (19 tests) ## Files Modified - src/routers/ask.py: Added SSE streaming with AsyncGenerator - src/routers/health.py: PostgreSQL + FAISS health probes - src/main.py: Integrated HIPAA/security middlewares - huggingface/app.py: Added streaming Q&A section ## Files Added - src/middlewares.py: HIPAAAuditMiddleware, SecurityHeadersMiddleware - tests/test_medical_safety.py: Critical biomarker, guardrail, citation tests ## Test Results - 129 tests passing, 6 skipped - All production features validated3ca1d38
-
feat: Enable 100% HF Space capability with dynamic environment variables
Nikhil Pravin Pise- Add env helper functions for both naming conventions (simple and nested) - Support all embeddings providers: Jina, Google, HuggingFace - Enable Langfuse observability configuration - Make LLM models configurable via environment - Remove hardcoded values - everything is now dynamic - Update HF README with complete secrets reference - Add .env.huggingface template with all options - Update deployment guide with secrets configuration - Enhance startup logging to show all enabled features - Tests passing: 4/4 llm_config, 3/3 settingsd495234 -
Fix: Improve UI formatting and handle missing biomarker data gracefully
Nikhil Pravin Pise- Better biomarker name extraction with fallback options - Skip unknown/generic biomarker names - Add default recommendations when none provided - Improve grid layout for biomarker cards - Better handling of missing/sparse data - More robust type checking for recommendations - Improved visual consistency and spacingf55411e -
Security: Replace API keys with placeholders in .env.example
Nikhil Pravin Pise3b8e1fe -
Merge feature/production-upgrade: HF Spaces deployment with modern UI
Nikhil Pravin Pise9794258 -
Overhaul Gradio UI with modern medical design
Nikhil Pravin Pise- Complete redesign with professional medical theme - Gradient backgrounds and styled cards - Beautiful biomarker status indicators - Enhanced HTML output for analysis results - Agent cards with hover effects - Responsive grid layouts - Better visual hierarchy - Custom CSS for all components - Improved error and status messages193fabd -
Fix: Dynamic API key loading - secrets now work properly on HuggingFace Spaces
Nikhil Pravin Pise150e705 -
Fix HF deployment: add langchain-text-splitters, langchain-huggingface, simplify env
Nikhil Pravin Pise9f32f16 -
Deploy to HuggingFace Spaces - Medical RAG with vector store
Nikhil Pravin Pise9699bea -
feat: production upgrade — agentic RAG, OpenSearch, Redis, Langfuse, Docker, Gradio, Telegram
Nikhil Pravin PisePhase 1: Project structure & dev tooling - pyproject.toml with Ruff/MyPy/pytest config and optional deps - Makefile with dev/test/docker/lint targets - Multi-stage Dockerfile + docker-compose.yml (12 services) - .env.example, .pre-commit-config.yaml Phase 2: Core infrastructure - src/settings.py: hierarchical Pydantic Settings (env-driven) - src/exceptions.py: domain exception hierarchy (15+ classes) - src/database.py: SQLAlchemy engine/session factory - src/models/analysis.py: ORM models (PatientAnalysis, MedicalDocument, SOPVersion) - src/repositories/: data access layer Phase 3: Production services - OpenSearch client with BM25, KNN vector, and hybrid RRF search - Medical synonym analyzer + KNN index mapping (1024d, HNSW) - Multi-provider embedding service (Jina/Google/HuggingFace) with fallback - Redis cache with graceful degradation (NullCache) - Langfuse v3 observability tracer (NullSpan for no-ops) - Ollama REST client with streaming + LangChain integration - Medical-aware tex…1e732dd -
Refactor: Improve code quality, security, and configuration
Nikhil Pravin Pise- Remove redundant sys.path manipulation in agents and services - Enhance CORS configuration with environment-based origin handling - Improve error handling (no internal detail leakage) - Fix environment variable handling in setup scripts (remove extra quotes) - Update gitignore for external tools and course materials - Correct clinical biomarker reference ranges - Add comprehensive production upgrade plan - Improve test configuration (HuggingFace deprecation filters) - Add optional dependencies for evaluation tools - Consolidate path initialization patternsad2e847 -
docs: update all documentation to reflect current codebase state
Nikhil Pravin Pise- Update README.md: correct test count (83 -> 30), fix test commands - Rewrite START_HERE.md as proper onboarding guide - Update QUICKSTART.md and CONTRIBUTING.md test commands - Update api/ docs: Groq/Gemini as default providers (not Ollama) - Update api/ARCHITECTURE.md: multi-provider LLM diagram - Update api/GETTING_STARTED.md: Groq/Gemini prerequisites - Update api/QUICK_REFERENCE.md: fix troubleshooting, commands - Update docs/DEVELOPMENT.md: fix code examples, test commands - Update docs/DEEP_REVIEW.md: add RESOLVED/OPEN status to all findings - Update scripts/README.md: use .venv python paths - Archive stale root-level docs to docs/archive/ - All 30 tests passingaefac4f
-
Remove GITHUB_READY.md from repository
Nikhil Pravin Pise92981df -
refactor: major repository cleanup and bug fixes
Nikhil Pravin PiseCleanup & Organization: - Removed clutter: deleted archive/ and setup.py - Reorganized scripts: moved PowerShell startup scripts to scripts/ - Created examples/ folder with HTML/JS integration examples - Consolidated docs: archived 13 old implementation notes to docs/archive/ - Rewrote root README.md for clarity and professional appearance Core Bug Fixes: - Fixed Google Gemini embedding API 404 error by switching to HuggingFace local embeddings - Upgraded torch/torchvision to resolve PyTorch compatibility issues - Fixed HuggingFaceEmbeddings import and configuration in pdf_processor.py - Successfully rebuilt FAISS vector store with compatible embeddings (2,609 chunks) Documentation: - Created docs/ARCHITECTURE.md: system design, components, data flow - Created docs/API.md: complete REST API reference with examples - Created docs/DEVELOPMENT.md: extension guide for developers - Created scripts/README.md: utility scripts reference - Created examples/README.md: integration patterns for …6dc9d46
-
The Context is Here
Nikhil Pravin Pisea8c922b -
Initial commit
Nikhil Pravin Pise68e2687