Building an AI RAG Application with LangChain and Next.js
Offered By: Dave Gray via YouTube
Course Description
Overview
Learn how to build an AI RAG (Retrieval Augmented Generation) application using LangChain and Next.js in this comprehensive 34-minute tutorial. Explore the fundamentals of RAG and LangChain, set up your development environment with necessary dependencies, and progress through a series of practical examples. Start with a simple chat implementation, then advance to more complex scenarios including chat with history, personality-driven conversations, and RAG pattern chats using JSON objects and files. Gain hands-on experience with OpenAI API integration, frontend chat component development, and the implementation of various LangChain features to enhance your AI application's capabilities.
Syllabus
Intro
Welcome
Lesson Goal
What is RAG?
What is LangChain?
Source Code
OpenAI API Key
Dependencies
Frontend Chat Component
Simple Chat Example
Ex. 1: LangChain Chat
Ex. 2: Chat with History
Ex. 3: Chat with Personality
Ex. 4a: RAG Pattern Chat with JSON Object
Ex. 4b: RAG Pattern Chat with JSON file
Wrap-up
Taught by
Dave Gray
Related Courses
Better Llama with Retrieval Augmented Generation - RAGJames Briggs via YouTube Live Code Review - Pinecone Vercel Starter Template and Retrieval Augmented Generation
Pinecone via YouTube Nvidia's NeMo Guardrails - Full Walkthrough for Chatbots - AI
James Briggs via YouTube Hugging Face LLMs with SageMaker - RAG with Pinecone
James Briggs via YouTube Supercharge Your LLM Applications with RAG
Data Science Dojo via YouTube