Back to Projects
Generative AIadvanced

End to End Medical Chatbot

This project involves building a Medical Chatbot capable of answering medical-related queries by leveraging Retrieval-Augmented Generation (RAG). The system uses a knowledge base created from medical PDF documents, stores them as vector embeddings in Pinecone, and retrieves relevant information to generate accurate responses using LLM via LangChain. The application is served using Flask and is designed for deployment on AWS using Docker and GitHub Actions.

10 lectures

What You Will Learn

Master building a Generative AI-powered Medical Chatbot from scratch.
Implement Retrieval-Augmented Generation (RAG) using LangChain for factual accuracy.
Understand the integration and management of Pinecone Vector Database.
Gain experience integrating LLMs for natural language understanding and generation.
Learn how to process medical knowledge from unstructured PDF documents.
Develop a production-ready application with Docker and AWS CI/CD.

System Architecture

End to End Medical Chatbot Architecture Diagram

High-level architecture overview of the End to End Medical Chatbot .

What You'll Build

  • An "End-to-End Medical Chatbot" that provides answers to medical queries based on specialized data.
  • A data ingestion pipeline that transforms PDF documents into searchable vector embeddings.
  • A RAG-based backend that retrieves relevant medical context and generates responses using LLMs.
  • A web-based chat application with a responsive interface for user interaction.
  • A CI/CD pipeline for automated deployment to AWS using GitHub Actions and Docker.
Premium
One Subscription. 40+ Projects. Unlimited Access.
AccessMobile & Web