Code
image_agent_bytes.py
TOGETHER_MODEL_ID to a current model that accepts image input. See the Together vision guide and serverless catalog.
Usage
1
Set up your virtual environment
2
Set your API key
3
Install dependencies
4
Add sample image
Place a sample image named
sample.jpg in the same directory as the script.5
Run Agent
Save the code above as
image_agent_bytes.py, then run: