Spaces:
Sleeping
Sleeping
| title: GAIA Agent Submission | |
| emoji: π | |
| colorFrom: indigo | |
| colorTo: blue | |
| sdk: docker | |
| app_port: 7860 | |
| app_file: eval.py | |
| pinned: false | |
| # π€ GAIA Agent Submission Runner | |
| This Space is configured to run the **GAIA Benchmark Evaluation & Submission**. | |
| ## π How to Submit | |
| 1. **Login**: Click the "Login using Hugging Face" button in the app. | |
| 2. **Submit**: Click "Run Evaluation & Submit All Answers". | |
| * The agent will fetch questions, solve them, and auto-submit the results to the leaderboard. | |
| ## βοΈ Configuration | |
| This agent uses a generic OpenAI-compatible provider (configured for SambaNova by default) via `agent.json`. | |
| **Required Secrets:** | |
| Ensure these are set in your Space Settings: | |
| * `SAMBANOVA_API_KEY`: Your SambaNova API key (or equivalent for your chosen provider). | |
| * `HF_TOKEN`: (Optional but recommended) For accessing private datasets if needed. | |
| ## π οΈ Local Development | |
| * **Chat Demo**: Run `python app.py` locally to use the interactive chat interface. | |
| * **Evaluation**: Run `python eval.py` locally to test the submission logic. | |