Dashscope Thinking Agent

Enable thinking on DashScope’s QVQ Max to reason through an image problem.

thinking_agent.py

"""
Dashscope Thinking Agent
========================

Cookbook example for `dashscope/thinking_agent.py`.
"""

from agno.agent import Agent
from agno.media import Image
from agno.models.dashscope import DashScope

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------

agent = Agent(
    model=DashScope(id="qvq-max", enable_thinking=True),
)

image_url = "https://img.alicdn.com/imgextra/i1/O1CN01gDEY8M1W114Hi3XcN_!!6000000002727-0-tps-1024-406.jpg"

agent.print_response(
    "How do I solve this problem? Please think through each step carefully.",
    images=[Image(url=image_url)],
    stream=True,
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    pass

Run the Example

1. Set up your virtual environment

   Mac

   uv venv --python 3.12
   source .venv/bin/activate
   

   uv venv --python 3.12
   .venv\Scripts\activate
   
2. Install dependencies

   uv pip install -U agno openai
   
3. Export your DashScope API key

   Mac/Linux

   export DASHSCOPE_API_KEY="your_dashscope_api_key_here"
   

   $Env:DASHSCOPE_API_KEY="your_dashscope_api_key_here"
   
4. Run the example

   Save the code above as thinking_agent.py, then run:

   python thinking_agent.py
   

Full source: cookbook/90_models/dashscope/thinking_agent.py