Skip to content

Akshay-hub-007/multi-modal-rag

Repository files navigation

Multi-Modal RAG

An AI-powered pipeline for extracting, chunking, and summarizing content from PDF documents using advanced chunking strategies and generative models. Supports text, tables, and images, with vector search and retrieval via ChromaDB.

Features

  • PDF partitioning and intelligent chunking
  • Handles text, tables, and images
  • AI-generated summaries for mixed content
  • Embedding and vector search with ChromaDB

Quick Start

  1. Clone the repository
  2. Install dependencies
  3. Run the notebook to process your PDF and create a searchable vector store

Technologies

  • Python
  • LangChain
  • Unstructured
  • ChromaDB
  • Google Generative AI

License

MIT

About

Multi-Modal RAG: An AI-powered pipeline for extracting, chunking, and summarizing content from PDF documents using advanced chunking strategies and generative models. Includes support for text, tables, and images, with vector search and retrieval via ChromaDB.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors