Build a Retrieval Augmented Generation (RAG) application in Python to query and chat with PDF documents using generative AI. Explore advanced topics including local RAG implementation with Ollama, vector database updates, PDF integration, and AI response quality testing. Follow along with code examples and learn how to load PDF data, generate embeddings, store and update information, run RAG locally, and implement unit tests for AI output. Access the GitHub repository for the complete project and dive into additional resources on document loaders, PDF handling, and Ollama integration.
Overview
Syllabus
Introduction
RAG Recap
Loading PDF Data
Generate Embeddings
How To Store and Update Data
Updating Database
Running RAG Locally
Unit Testing AI Output
Wrapping Up
Taught by
pixegami
Related Courses
-
Project: Generative AI Applications with RAG and LangChain
-
LangChain Chat with Your Data
-
Retrieval Augmented Generation (RAG) with LangChain
-
Vector Databases: from Embeddings to Applications
-
Fundamentals of AI Agents Using RAG and LangChain
-
Vector Embeddings Tutorial – Create an AI Assistant with GPT-4 & Natural Language Processing
4.5
