May 18
Loading video player...
🚀 In this video, I’ll show you how to build and deploy a complete End-to-End Modular RAG Medical AI Assistant using modern AI engineering tools like LangChain, Pinecone, FastAPI, Groq LLaMA 3, and Google Embeddings. This project demonstrates how to create a domain-specific Medical AI Chatbot capable of answering medical queries using Retrieval-Augmented Generation (RAG) with real medical PDF documents. 🔍 What You’ll Learn: ✅ Medical PDF ingestion & processing ✅ Text chunking with LangChain ✅ Semantic search using Pinecone Vector DB ✅ Google Generative AI Embeddings ✅ Response generation using Groq LLaMA3-70B ✅ Modular backend architecture with FastAPI ✅ End-to-end RAG workflow ✅ Deployment on Render ✅ Production-style AI engineering practices 🛠️ Tech Stack Used: • LangChain • Pinecone Vector Database • FastAPI • Groq LLaMA3-70B • Google Generative AI Embeddings • Render • Python 📂 Project Source Code: 🔗 GitHub: https://github.com/snsupratim/medicalAssistant ⏱️ Chapters: 00:00 - Intro 00:32 - Demo 03:24 - RAG Concepts Explained 06:21 - Technical Architecture & Core Modules 08:48 - Setup & Installation 14:20 - Backend Development with FastAPI 01:34:50 - Frontend / Client-side Integration 02:01:35 - Deployment on Render 🎓 This tutorial is perfect for: • AI Engineers • GenAI Developers • LangChain Developers • Students learning RAG Systems • Developers building AI chatbots • Anyone interested in Medical AI applications 🔥 If you enjoy hands-on AI engineering tutorials, subscribe to "sn dev" for more advanced projects on: • RAG Systems • Agentic AI • LangChain • FastAPI • LLM Applications • Generative AI Projects • Production AI Systems 👍 Like • Share • Subscribe #LangChain #RAG #MedicalAI #FastAPI #Pinecone #Groq #LLaMA3 #AIChatbot #GenAI #HealthcareAI #LLM #VectorDatabase #AIEngineering #Python #MachineLearning