Skip to content

Latest commit

 

History

History
45 lines (39 loc) · 1.13 KB

README.md

File metadata and controls

45 lines (39 loc) · 1.13 KB

PrivateGPT Chatbot

Overview

PrivateGPT is a chatbot designed to answer questions based on your documents. It ensures privacy by processing everything locally.

Features

  • Document ingestion and vector storage using Weaviate.
  • Retrieval-based Q&A with LangChain and HuggingFace.
  • Simple frontend using Streamlit.
  • Backend powered by FastAPI.

Workflow

ChatBot Workflow

Setup Instructions

  1. Clone the Repository
git clone https://github.com/your_username/privateGPT.git
cd privateGPT
  1. Install Dependencies
conda create -n privategpt_env python=3.10 -y
conda activate privategpt_env
pip install -r requirements.txt
  1. Prepare and process Documents Place your .pdf and .txt documents in the source_documents/ directory. Then run:
python ingest.py

This creates a local FAISS vectorstore for your documents.

  1. Rub Chatbot Start the chatbot by running:
python app.py
  1. Use the Web Interface Run the Streamlit UI:
streamlit run app_ui.py

Open the displayed URL in your browser to interact with the chatbot.