Skip to main content

Code

cookbook/models/vertexai/claude/image_input_bytes.py
from pathlib import Path

from agno.agent import Agent
from agno.media import Image
from agno.models.vertexai.claude import Claude
from agno.tools.duckduckgo import DuckDuckGoTools
from agno.utils.media import download_image

agent = Agent(
    model=Claude(id="claude-sonnet-4@20250514"),
    tools=[DuckDuckGoTools()],
    markdown=True,
)

image_path = Path(__file__).parent.joinpath("sample.jpg")

download_image(
    url="https://upload.wikimedia.org/wikipedia/commons/0/0c/GoldenGateBridge-001.jpg",
    output_path=str(image_path),
)

# Read the image file content as bytes
image_bytes = image_path.read_bytes()

agent.print_response(
    "Tell me about this image and give me the latest news about it.",
    images=[
        Image(content=image_bytes),
    ],
    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 environment variables

export CLOUD_ML_REGION=xxx
export GOOGLE_CLOUD_PROJECT=xxx
3

Authenticate your CLI session

gcloud auth application-default login
You dont need to authenticate your CLI every time.
4

Install libraries

pip install -U anthropic agno
5

Run Agent

python cookbook/models/vertexai/claude/image_input_bytes.py 
I