Doc Chat: A Document-Based Chatbot using Streamlit and OpenAI

Overview

Doc Chat is a document-based chat bot that allows users to upload PDF documents, query related information, and get responses generated by GPT models (GPT-4 Turbo or GPT-5). It uses Streamlit for the frontend, LangChain, and ChromaDB for storing vector embeddings of the documents.

Installation

1. Create a virtual environment to manage dependencies:

     python -m venv doc_chat_env
     source doc_chat_env/bin/activate

2. Clone the repository:

     git clone [https://github.com/your_username/doc-chat.git](https://github.com/AIOnGraph/docChatBot.git)https://github.com/AIOnGraph/docChatBot.git
     cd docChatBot
     ```

3. Install dependencies: bash pip install -r requirements.txt

4. Run the application: bash streamlit run main.py

5. Usage:

   • Open the provided URL in your browser to access the application.
     • (https://health-report-analysis.streamlit.app/)

Usage

1. **Enter OpenApiKey in sidebar**
2. **Upload PDF document**
3. **Select GPT model(GPT-4 Turbo or GPT-5)**
4. **Ask Query:**

Support and Feedback

If you encounter any issues, have feedback, or suggestions, please open an issue on GitHub