https://github.com/git-vish/docqa

DocQA is a tool that enables users to interact with their documents by extracting and summarizing relevant information.
https://github.com/git-vish/docqa

faiss google-gemini langchain python streamlit

Last synced: about 2 months ago
JSON representation

DocQA is a tool that enables users to interact with their documents by extracting and summarizing relevant information.

• Host: GitHub
• URL: https://github.com/git-vish/docqa
• Owner: git-vish
• Created: 2024-09-01T10:02:31.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2024-09-08T14:06:31.000Z (almost 2 years ago)
• Last Synced: 2025-02-05T21:53:25.275Z (over 1 year ago)
• Topics: faiss, google-gemini, langchain, python, streamlit
• Language: Python
• Homepage: https://docqa.vishwajeet.xyz
• Size: 185 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# DocQA

---

This project implements a document-based knowledge base and Q&A system using Streamlit, LangChain, Google GenAI, and FAISS.

![DocQA Screenshot](images/screenshot.png)

## Features

- Text extraction and chunking

- In-memory vector storage using FAISS

- Question answering using LangChain and Google GenAI

## Setup

1. Clone the repository

2. Install dependencies: `uv install` or `pip install -r requirements.txt`

3. Set up environment variables in `.env` file

4. Run the application: `streamlit run src/main.py`

## References

- [uv](https://docs.astral.sh/uv/): Python package manager

- [RAG](https://python.langchain.com/v0.2/docs/tutorials/rag/#built-in-chains)

- [Chat History](https://python.langchain.com/v0.2/docs/tutorials/qa_chat_history/#adding-chat-history)

- [FAISS](https://python.langchain.com/v0.2/docs/integrations/vectorstores/faiss/#saving-and-loading)