Spaces:
Paused
Paused
| title: Groq-LLaMA3.x | |
| emoji: 📚 | |
| colorFrom: yellow | |
| colorTo: blue | |
| sdk: streamlit | |
| sdk_version: 1.41.1 | |
| app_file: app.py | |
| pinned: false | |
| license: mit | |
| short_description: Groq & Llama3.x updated | |
| # Groq Chat with LLaMA3x | |
| A Streamlit-based chat application that leverages Groq's API to interact with LLaMA3x models. | |
| ## Features | |
| ### Model Integration | |
| - Seamless integration with Groq's LLaMA3x model family | |
| - Dynamic model selection from available LLaMA variants | |
| - Automatic model metadata fetching and display | |
| - Model-specific token limit handling | |
| ### Chat Interface | |
| - Real-time streaming responses with character-by-character display | |
| - Non-streaming mode for batch responses | |
| - Persistent chat history with session management | |
| - Clear chat functionality | |
| - User-friendly message input system | |
| - Distinct avatars for user (🧑💻) and assistant (🔋) messages | |
| - Basic image support for vision models (11b and 70b) | |
| ### Performance Controls | |
| - Adjustable token limit slider with model-specific maximums | |
| - Toggle between streaming and non-streaming modes | |
| - Automatic session state management | |
| - Error handling with user-friendly error messages | |
| ### Usage Analytics | |
| - Real-time token usage tracking | |
| - Prompt tokens | |
| - Response tokens | |
| - Total tokens used | |
| - Performance timing metrics | |
| - Prompt processing time | |
| - Response generation time | |
| - Total interaction time | |
| ### UI/UX Features | |
| - Responsive wide-layout design | |
| - Sidebar with model controls and settings | |
| - Groq branding integration | |
| - Important disclaimer for AI-generated content | |
| - Clear visual hierarchy with markdown formatting | |
| ## Prerequisites | |
| - Python 3.7+ | |
| - Groq API key | |
| - Required Python packages: | |
| - streamlit | |
| - groq | |
| - python-dotenv | |
| ## Installation | |
| 1. Clone the repository | |
| 2. Install dependencies: | |
| ```bash | |
| pip install streamlit groq python-dotenv | |
| ``` | |
| 3. Create a `.env` file and add your Groq API key: | |
| ``` | |
| GROQ_API_KEY=your_api_key_here | |
| ``` | |
| ## Usage | |
| Run the application: | |
| ```bash | |
| streamlit run app.py | |
| ``` | |
| The app will open in your default browser, featuring: | |
| - Model selection dropdown | |
| - Adjustable token limit slider | |
| - Streaming mode toggle | |
| - Clear chat functionality | |
| - Real-time usage statistics | |
| ## Security Note | |
| Always keep your API key secure and never commit it to version control. The application uses environment variables for sensitive data management. | |
| ## License | |
| MIT |