Spaces:
Running on Zero
Running on Zero
|
Download README.md from batgre/Final_Assignment_Template: direct link, hf CLI and curl.
- Browser
- Download file 1.11 kB
-
https://huggingface.co/spaces/batgre/Final_Assignment_Template/resolve/main/README.md
- Command line
-
hf download hf://spaces/batgre/Final_Assignment_Template/README.md
-
curl -L -o README.md https://huggingface.co/spaces/batgre/Final_Assignment_Template/resolve/main/README.md
1.11 kB
| 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 | |
| # optional, default duration is 8 hours/480 minutes. Max duration is 30 days/43200 minutes. | |
| hf_oauth_expiration_minutes: 480 | |
| Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference | |
| ## Agent architecture | |
| - The manager uses `GROQ_MANAGER_MODEL` (default: `openai/gpt-oss-120b`). | |
| - Web research is one direct, bounded Tavily request; it does not start a | |
| second LLM agent. | |
| - Document and media tasks keep dedicated agents because they may need to | |
| download and inspect an attachment in multiple steps. | |
| - Calculations use `python_exec` or `calculator` directly. | |
| - Final answer formatting uses `GROQ_NORMALIZER_MODEL` (default: | |
| `openai/gpt-oss-20b`). | |
| Required Space secrets are `GROQ_API_KEY` and `TAVILY_API_KEY`. Set | |
| `GROQ_VLM_MODEL` as well to enable image and video analysis. | |
| Run the offline web-search regression tests with: | |
| ```bash | |
| python -m unittest -v test_web_search.py | |
| ``` | |