Multi-Agent-Medical-Assistant

Dependency freshness

Declared = lowest version the kit's dependency file (package.json, pyproject.toml or requirements.txt) allows. Latest = the npm "latest" tag or the newest PyPI release. TypeScript, the Stripe SDK, FastAPI and other 0.x packages are shown but not counted in the verdict.

What's in the stack

Framework

FastAPI, Flask

Database / ORM

SQLAlchemy

AI

OpenAI SDK, LangChain, LangGraph

API layer

Pydantic, Uvicorn

Testing

pytest

Detected from declared dependencies. A listed package means it's installed, not necessarily fully wired up.

What the README says you get

• Admin
  Human-in-the-loop verificationHuman-in-the-loop verification by medical professionals before finalizing outputs
• AI
  Multi-agent architectureSpecialized agents working in harmony to handle diagnosis, information retrieval, reasoning, and more
• AI
  Docling PDF parsingDocling based parsing to extract text, tables, and images from PDFs
• AI
  Semantic chunkingLLM based semantic chunking with structural boundary awareness
• AI
  Query expansionLLM based query expansion with related medical domain terms
• AI
  Cross-encoder rerankingHuggingFace Cross-Encoder based reranking of retrieved document chunks for accurate LLM reponses
• AI
  Input-output guardrailsInput-output guardrails to ensure safe and relevant responses
• AI
  Source document linksLinks to source documents and images present in reference document chunks provided with reponse
• AI
  Confidence-based handoffConfidence-based agent-to-agent handoff between RAG and Web Search to prevent hallucinations
• AI
  Chest X-ray classificationChest X-ray Disease Classification
• AI
  Skin lesion segmentationSkin Lesion Segmentation
• AI
  Real-time web searchWeb search agent that retrieves the latest medical research papers and findings
• Data
  Qdrant hybrid searchQdrant hybrid search combining BM25 sparse keyword search along with dense embedding vector search

Extracted from the kit's README by a local AI model (deepseek-flash) on Sep 29, 2026. Every item is checked against an exact README quote; 1 unverifiable item was discarded. A README claim is the maker's description, not something we tested.