How to Build PDF RAG Chatbot with LangChain, OpenAI, Streamlit & PGVector
This video is a tutorial on building RAG pipeline PDF chatbots using LangChain, OpenAI and Streamlit.
This tutorial explains how you can build a RAG (Retrieval-Augmented Generation) pipeline with a persistent storage using RedisStore and PGVector for PDF documents.
🔍What You’ll Learn:
• How to extract text & tables from PDFs using the Unstructured library.
• How to use PGVector for Vector Embeddings
• How to use RedisStore for Raw Storage
• Step-by-step instructions to connect your RAG pipeline to an LLM and to Streamlit
0:00 - Intro
03:51 - Set up & Installation
06:43 - RAG pipeline
24:10 - Integration with Streamlit
🔴 Subscribe for more tips just like this: / @codetops
----------------------------------------------------------------
Github Repository
https://github.com/Mercytopsy/pdf-rag...
----------------------------------------------------------------
OpenAI API
https://platform.openai.com/
----------------------------------------------------------------
Download Poppler
https://github.com/oschwartz10612/pop...
----------------------------------------------------------------
Download Tesseract
https://github.com/UB-Mannheim/tesser...
#RAG #Multimodal RAG #LangChain #AI #MachineLearning #LangChainTutorial #Python #Chatbot #LLMs #OpenAI #GPT4 #AIApps #PGVector #Streamlit