DocuChat

DocuChat is an advanced chatbot that empowers you to explore and understand your data effortlessly. It integrates Langchain, Langsmith, Unstructured Loader, ChromaDB, and Streamlit to offer dynamic, context-aware interactions for deeper insights into your PDF data.

Medium Blog:

• part-1
• part-2

Features

• Extracts and analyzes text, tables, and images from PDF documents.
• Uses sophisticated LLMs to provide context-aware responses.
• Supports dynamic interactions through a Streamlit web interface.

Prerequisites

• Python 3.7 or higher
• pip

Installation

1. Clone the repository:

   git clone https://github.com/dcprakash/DocuChat.git
   cd docuchat

2. Create and activate a virtual environment:

   python3 -m venv venv
   source venv/bin/activate

3. Install the required dependencies:

   pip install -r requirements.txt

4. Create a .env file in the project directory and add your OpenAI API key:

   OPENAI_API_KEY=your_openai_api_key

Running the Application

To run the application, execute the provided shell script:

./setup_and_run.sh

The application will start, and you can access it in your web browser at http://localhost:8501.

Contributing

Contributions are welcome! Please read the CONTRIBUTING.md file for guidelines.

License

This project is licensed under the MIT License. See the LICENSE file for details.

Contact

Created by Darshan Chinvar. Reach out at chinvarpd@gmail.com.