Build Your Own RAG for Unstructured PDF, Website via chatgpt & LangChain
Advanced RAG 101 - build agentic RAG
Learn how to build a RAG (Retrieval Augmented Generation) app in Python that can let you query/chat with your website using generative AI.
This project contains some more advanced topics, like how to run RAG apps locally (with Ollama), how to update a vector DB with new items, how to use RAG with PDFs (or any other files), and how to test the quality of AI generated responses.
80% of enterprise data exists in difficult-to-use formats like HTML, PDF, CSV, PNG, PPTX, and more. Unstructured effortlessly extracts and transforms complex data for use with every major vector database and LLM framework.
Here we will extract the infromation from the pdf, website and sql database.
⏱️ Timestamps
0:00 Intro
0:16 Steps to RAG
1:28 Problem with simple RAG
2:26 Better Chunking
6:09 Searching
10:23 Rerank
11:12 Code Walkthrough
15:54 Demo.
#unstructureddata #unstructuredio #rag #langchain #llm #datasciencebasics