tonykipkemboi/ollama_pdf_rag

A full-stack demo showcasing a local RAG (Retrieval Augmented Generation) pipeline to chat with your PDFs.

What it solves

It allows users to chat with their PDF documents entirely locally, ensuring that sensitive data never leaves the machine. It solves the problem of needing expensive or privacy-invasive cloud services to perform Retrieval Augmented Generation (RAG) on personal or corporate documents.

How it works

The application uses a pipeline powered by LangChain and ChromaDB to process PDFs into vector embeddings. It integrates with Ollama to run large language models (LLMs) and embedding models locally. Users can interact with this system through a Next.js web interface, a Streamlit app, or a FastAPI REST API, which handles the document uploading, indexing, and querying processes.

Who it’s for

This tool is designed for users who want a private, local AI assistant for document analysis, as well as developers looking for a reference implementation of a local RAG pipeline using Ollama and LangChain.

Highlights

  • 100% Local Processing: No data is sent to external servers.
  • Multiple Interfaces: Offers a modern Next.js frontend, a classic Streamlit UI, and a programmatic REST API.
  • Multi-PDF Support: Ability to upload and query across multiple documents simultaneously.
  • Advanced Retrieval: Features multi-query RAG with source citations and visibility into the AI's reasoning steps.