An ultrafast, high-performance AI chatbot built with Streamlit and powered by the Groq LPU™ Inference Engine. Experience sub-second tokens-per-second responses with state-of-the-art LLMs like Llama 3.3 and Mixtral.
- 🏎️ Extreme Speed: Powered by Groq's LPU for near-instantaneous inference.
- 💬 Full Conversation Memory: Maintains context throughout the chat session.
- 🌊 Real-time Streaming: Watch the AI "think" and "type" with smooth streaming delta updates.
- 🛠️ Configurable Settings: Toggle between models (Llama 3.3, Mixtral, Gemma) and adjust temperature/max tokens on the fly.
- 🌑 Premium Dark UI: A refined, modern aesthetic designed for readability and focus.
git clone https://github.com/uday-codes69/Chatbot-project.git
cd Chatbot-projectCreate a .env file in the root directory and add your Groq API Key:
GROQ_API_KEY=your_api_key_herepip install -r requirements.txtstreamlit run app.py- Frontend: Streamlit
- LLM API: Groq Cloud SDK
- Environment Management:
python-dotenv - Logic: Python 3.x
app.py: The main Streamlit interface and UI logic.llm.py: Backend wrapper for the Groq API handling streaming and logic.requirements.txt: List of necessary Python packages..env: (Private) Storage for your API credentials.
Contributions are welcome! Feel free to open an issue or submit a pull request if you have ideas for new features or improvements.
This project is licensed under the MIT License - see the LICENSE file for details.
Built with ❤️ by uday-codes69