AgentPick is an agentic system that helps users find the right language model for their specific needs. Rather than manually searching through thousands of models on Hugging Face, AgentPick understands your task requirements and recommends the most suitable models.
It takes RAG one step further and employs multiple agents to answer user questions more precisely and accurately.
The system operates in three stages:
- Interpretation
- Retrieval & Filtering
- Recommendation
- Backend: Flask
- Frontend: React
- Database: Qdrant, MySQL
cd backend
pip install -r requirements.txt
flask runcd frontend
npm install
npm startThe application will be available at http://localhost:3000 with the backend running on http://localhost:5000.
The project is fully open source. For any contributions or questions, feel free to open a pull request or contact the owner.