Skip to main content

​
Code

cookbook/models/anthropic/image_input_url.py
from agno.agent import Agent
from agno.media import Image
from agno.models.anthropic import Claude
from agno.tools.duckduckgo import DuckDuckGoTools

agent = Agent(
    model=Claude(id="claude-3-5-sonnet-20241022"),
    tools=[DuckDuckGoTools()],
    markdown=True,
)

agent.print_response(
    "Tell me about this image and search the web for more information.",
    images=[
        Image(
            url="https://upload.wikimedia.org/wikipedia/commons/a/a7/Camponotus_flavomarginatus_ant.jpg"
        ),
    ],
    stream=True,
)

​
Usage

1

Create a virtual environment

Open the Terminal and create a python virtual environment.
python3 -m venv .venv
source .venv/bin/activate
2

Set your API key

export ANTHROPIC_API_KEY=xxx
3

Install libraries

pip install -U anthropic agno duckduckgo-search
4

Run Agent

python cookbook/models/anthropic/image_input_url.py