Taming medical hallucinations: A RAG assistant for querying clinical papers with strict source attribution and confidence scoring.
ControlMind: MinerU-powered scientific document intelligence — 500-question cross-modal benchmark, 15-intent data agent, and local-first medical RAG
Evidence-grounded medical RAG system that retrieves FDA and NICE drug guidelines, generates cited answers, and safely refuses unsupported queries to minimize hallucinations.
A research-grade clinical decision-support RAG system that synthesizes recommendations across 4 major AAA guidelines (USPSTF, NICE, ESVS, SVS). Built for trust and safety, it delivers verifiable cited answers, surfaces guideline conflicts, abstains when evidence is insufficient, and enforces multi-tier safety guardrails.
Somnus — Evidence-grounded Clinical Decision Support & Live Voice Assistant for Insomnia & Sleep Disorders (AASM & VA/DoD Guidelines, Hybrid Dense-Sparse RAG, BGE Cross-Encoder, Next.js 14 & FastAPI).
Advanced medical RAG intelligence platform with open corpus ingestion, hybrid retrieval, citations, safety guardrails, evaluation, and dashboard
Medical RAG Chatbot is a Retrieval-Augmented Generation chatbot that answers medical questions using PDF knowledge sources, Groq LLM, Hugging Face embeddings, FAISS vector search, and LangChain orchestration. Includes Flask APIs, HTML/CSS UI, Dockerized deployment, Jenkins CI/CD, and Trivy image scanning on AWS.
A production-style Medical RAG chatbot built with FastAPI, LangChain, Pinecone, and Google Gemini. Uses document ingestion and vector search to provide grounded, context-aware medical responses with strict safety constraints.
MedRAG is a multi-modal medical retrieval and generation system that combines research literature and radiological images to deliver evidence-grounded, context-aware medical insights. The system integrates semantic search, citation-aware ranking, and controlled language generation to support exploratory medical research and decision support.
Privacy-first medical AI. Quote-gated RAG transforms scattered medical records (lab reports and clinic notes) into a searchable longitudinal health history with verifiable citations, semantic search, deterministic extraction, hybrid SQL+RAG retrieval, and local-first architecture.
A local full-stack medical research assistant combining semantic vector search and keyword queries with Ollama Qwen3 to answer clinical literature questions with cited references.
To associate your repository with the medical-rag topic, visit your repo's landing page and select "manage topics."