|
|
--- |
|
|
title: Template Final Assignment |
|
|
emoji: 🕵🏻♂️ |
|
|
colorFrom: indigo |
|
|
colorTo: indigo |
|
|
sdk: gradio |
|
|
sdk_version: 5.25.2 |
|
|
app_file: app.py |
|
|
pinned: false |
|
|
hf_oauth: true |
|
|
|
|
|
hf_oauth_expiration_minutes: 480 |
|
|
--- |
|
|
|
|
|
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference |
|
|
|
|
|
# Modular Agent Evaluation Template |
|
|
|
|
|
This project provides a modular, production-ready template for evaluating agents using the Hugging Face Unit 4 Evaluation API. |
|
|
|
|
|
## Architecture |
|
|
|
|
|
- `app.py`: Gradio UI and orchestration |
|
|
- `agent.py`: Agent logic (extend `BaseAgent`) |
|
|
- `api.py`: API interaction and error handling |
|
|
- `requirements.txt`: Dependencies |
|
|
|
|
|
## Setup |
|
|
|
|
|
```bash |
|
|
pip install -r requirements.txt |
|
|
python app.py |
|
|
``` |
|
|
|
|
|
## Usage |
|
|
|
|
|
1. Log in with your Hugging Face account in the UI. |
|
|
2. Click "Run Evaluation & Submit All Answers" to evaluate and submit. |
|
|
3. Extend `agent.py` to implement your own agent logic. |
|
|
|
|
|
## Extending the Agent |
|
|
|
|
|
- Edit `agent.py` and subclass `BaseAgent`. |
|
|
- Implement the `__call__` method to generate answers for questions. |
|
|
|
|
|
## Troubleshooting |
|
|
|
|
|
- Ensure all dependencies are installed. |
|
|
- Check API availability and network connection. |
|
|
- Review error messages in the UI for guidance. |
