README.md

metadata

title: GPT-Style Chat Assistant
emoji: 🤖
colorFrom: blue
colorTo: green
sdk: streamlit
sdk_version: 1.42.2
app_file: app.py
pinned: false

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

GPT-Style Chat Assistant

A sophisticated Streamlit app that mimics the ChatGPT interface, using OpenAI's GPT models for advanced reasoning capabilities.

Features

• ChatGPT-like interface with conversation sidebar
• Multiple conversation management:
  • Create new chats
  • Switch between conversations
  • Delete old conversations
• Model selection - choose between different OpenAI models:
  • Standard Models:
    • GPT-3.5-Turbo (default)
    • GPT-4
    • GPT-3.5-Turbo-16k (for longer conversations)
    • GPT-4-Turbo
    • GPT-4o (latest GPT-4 Omni model)
    • GPT-4o-Mini (efficient version of GPT-4o)
  • Reasoning Models:
    • o1-mini (Mini reasoning model)
    • o1 (Standard reasoning model)
    • o1-pro (Professional reasoning model)
    • o3-mini (Advanced reasoning - Mini)
    • o3-mini-high (Advanced reasoning - Enhanced)
• Conversation history preserved between sessions
• Demo mode that works without an API key
• Responsive design that adapts to different screen sizes

Setup

1. Clone this repository
2. Install the required packages:

   pip install -r requirements.txt
   

3. (Required for full functionality) Get an OpenAI API key:
   • Create an account at OpenAI
   • Go to API Keys
   • Create a new API key
   • Add it to a .env file in the root directory:

     OPENAI_API_KEY=your_api_key_here
     

Running Locally

Run the app with the following command:

streamlit run app.py

If you're having trouble with the streamlit command not being found, you can use the full path to the executable:

python -m streamlit run app.py

Or use the provided runner script:

python run_app.py

This will start the app and open it in your default browser.

Demo Mode

The app includes a demo mode that works without an API key. In this mode:

• The assistant will provide pre-defined responses to common questions
• You'll see a text field in the sidebar where you can optionally enter an OpenAI API key
• For a full chatbot experience with reasoning capabilities, it's recommended to add your OpenAI API key

Deploying to Hugging Face Spaces

1. Create a new Space on Hugging Face Spaces (https://huggingface.co/spaces)
2. Choose Streamlit as the SDK
3. Link your GitHub repository or upload the files directly
4. Add your OpenAI API key as a secret:
   • Go to Settings > Repository Secrets
   • Add a secret named OPENAI_API_KEY with your key

The app will automatically deploy and be available at your Hugging Face Spaces URL.

About the Models

This app lets you select from multiple OpenAI models:

Standard Models

• GPT-3.5-Turbo: Fast and cost-effective, suitable for most tasks
• GPT-4: More capable but slower and more expensive
• GPT-3.5-Turbo-16k: Supports longer conversations with extended context window
• GPT-4-Turbo: OpenAI's advanced model with larger context window
• GPT-4o: Latest GPT-4 Omni model, OpenAI's most advanced offering
• GPT-4o-Mini: More efficient version of GPT-4o with excellent capabilities

Reasoning Models

OpenAI's specialized models for enhanced logical reasoning and problem-solving:

O1 Series

• o1-mini: Compact reasoning model for efficient problem-solving
• o1: Standard reasoning model with balanced capabilities
• o1-pro: Professional-grade reasoning with enhanced analytical abilities

O3 Series

• o3-mini: Advanced reasoning model optimized for efficiency
• o3-mini-high: Enhanced version with superior reasoning capabilities

All models are accessible using your OpenAI API key. Model availability depends on your API key permissions and subscription tier.

Customization

You can easily customize the app by:

• Changing the model parameters in the AVAILABLE_MODELS dictionary
• Adjusting the styling in the CSS section
• Adding more features to the sidebar
• Creating additional response templates for the demo mode