Spaces:
Running on Zero
Running on Zero
|
Download README.md from gouatm/Final_Assignment_Template: direct link, hf CLI and curl.
- Browser
- Download file 1.12 kB
-
https://huggingface.co/spaces/gouatm/Final_Assignment_Template/resolve/main/README.md
- Command line
-
hf download hf://spaces/gouatm/Final_Assignment_Template/README.md
-
curl -L -o README.md https://huggingface.co/spaces/gouatm/Final_Assignment_Template/resolve/main/README.md
1.12 kB
A newer version of the Gradio SDK is available: 6.30.0
metadata
title: GAIA Agent – 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
GAIA Level‑1 agent (HF Agents Course, Unit 4)
A smolagents CodeAgent with tools for web search, page reading, Wikipedia,
YouTube transcripts, audio transcription, spreadsheets, running attached Python
files, image description and chess analysis.
Configuration (Space → Settings → Variables & secrets)
| Variable | Purpose |
|---|---|
MODEL_ID |
LiteLLM model id, e.g. anthropic/claude-sonnet-4-5, gpt-4o, gemini/gemini-2.0-flash |
ANTHROPIC_API_KEY / OPENAI_API_KEY / GEMINI_API_KEY |
key for the provider above (secret) |
OPENAI_API_KEY |
also enables Whisper API transcription (otherwise local faster-whisper is used) |
HF_MODEL_ID, HF_TOKEN |
alternative: HF Inference API model (default Qwen/Qwen2.5-Coder-32B-Instruct) |
VISION_MODEL_ID |
optional separate vision model for image questions |
Then: log in → Run agent → Submit answers.