Ultra-fast AI assistant powered by Groq's LPUs
Chat with Llama 3, Mixtral, or Gemma models in real-time with customizable parameters
- Multiple LLMs: llama3-8b/70b, mixtral-8x7b, gemma-7b
- Customizable: Adjust temperature (0-1) and max tokens (50-4000)
- Persistent Chat: Maintains conversation history during session
- Secure: API keys encrypted in session state
- Responsive: Works on desktop and mobile
git clone https://github.com/yourusername/nexusthink-ai.git
cd nexusthink-ai
python -m venv venv
source venv/bin/activate # Linux/Mac
venv\Scripts\activate # Windows
pip install -r requirements.txt
# Required
GROQ_API_KEY=your_key_here_from_groq.com
# Optional (for LangSmith)
LANGCHAIN_API_KEY=your_key
LANGCHAIN_TRACING_V2=true
#Launch
streamlit run app.py