DashScope Image Agent

Analyze image URLs with a tool-capable Qwen3-VL model and enrich answers with web search.

Analyze two image URLs with a tool-capable Qwen3-VL model and enrich both responses with web search.

The source combines WebSearchTools with qwen-vl-plus, while Alibaba documents function calling for the Qwen3-VL families. Its second Wikimedia thumbnail URL also returns HTTP 400. Apply both migrations before running. See Alibaba’s function-calling model list.

image_agent.py

"""
Dashscope Image Agent
=====================

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

import asyncio

from agno.agent import Agent
from agno.media import Image
from agno.models.dashscope import DashScope
from agno.tools.websearch import WebSearchTools

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

agent = Agent(
    model=DashScope(id="qwen-vl-plus"),
    tools=[WebSearchTools()],
    markdown=True,
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    # --- Sync + Streaming ---
    agent.print_response(
        "Analyze this image in detail and tell me what you see. Also search for more information about the subject.",
        images=[
            Image(
                url="https://upload.wikimedia.org/wikipedia/commons/0/0c/GoldenGateBridge-001.jpg"
            )
        ],
        stream=True,
    )

    # --- Async + Streaming ---
    async def main():
        await agent.aprint_response(
            "What do you see in this image? Provide a detailed description and search for related information.",
            images=[
                Image(
                    url="https://upload.wikimedia.org/wikipedia/commons/thumb/3/3a/Cat03.jpg/1200px-Cat03.jpg"
                )
            ],
            stream=True,
        )

    asyncio.run(main())

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 ddgs 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. Use a tool-capable vision model

   Replace DashScope(id="qwen-vl-plus") with DashScope(id="qwen3-vl-plus") in the saved file.

5. Replace the unavailable image

   Replace https://upload.wikimedia.org/wikipedia/commons/thumb/3/3a/Cat03.jpg/1200px-Cat03.jpg with https://agno-public.s3.amazonaws.com/images/krakow_mariacki.jpg in the saved file.

6. Run the example

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

   python image_agent.py
   

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