Skip to content
TechIndexSubmit
Back to directory

Evidence-Grounded-Medical-RAG

This project is a medical chatbot built using a RAG pipeline, grounded in The GALE ENCYCLOPEDIA of MEDICINE SECOND EDITION. It retrieves relevant medical information using pritamdeka/S-PubMedBert-MS-MARCO embeddings and generates accurate, context-based responses with meta-llama/Llama-3-8B-Instruct.

Similar tools

  • This project implements a production-ready Conversational (RAG) chatbot using LangChain, Groq’s LLaMA 3 model, ChromaDB, and HuggingFace embeddings. It supports persistent chat history across sessions using RunnableWithMessageHistory, and integrates modular prompting, document loading, and retriever-aware chains to handle context-aware multi-chats.

    Models
  • A GenAI-powered Website Q&A system built using RAG (Retrieval-Augmented Generation). Users can input any URL and ask questions about its content. The system uses web scraping, embeddings, vector search (ChromaDB), and Groq Llama 3 models to generate context-aware answers.

    AI Apps
  • A Graph RAG System for Evidenced-based Medical Information Retrieval [ACL 2025]

    Models
  • In this project, we leverage Weaviate, a vector database, to power our retrieval-augmented generation (RAG) application. Weaviate enables efficient vector similarity search, which is crucial for building effective RAG systems. Additionally, we use local language model (LLM) and embedding models.

    Models
  • RAG chatbot for answering questions about PDF reports using FAISS and Sentence Transformers

    AI Apps
  • A PDF question-answering system using Retrieval-Augmented Generation (RAG) with DeepSeek-R1, Streamlit, and LangChain.

    Models