> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# IBM Image Agent Bytes

> Pass an image as raw bytes to Llama 3.2 Vision on watsonx for analysis.

```python image_agent_bytes.py theme={null}
"""
Ibm Image Agent Bytes
=====================

Cookbook example for `ibm/watsonx/image_agent_bytes.py`.
"""

from pathlib import Path

from agno.agent import Agent
from agno.media import Image
from agno.models.ibm import WatsonX

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

agent = Agent(
    model=WatsonX(id="meta-llama/llama-3-2-11b-vision-instruct"),
    markdown=True,
)

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

# 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,
)

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

if __name__ == "__main__":
    pass
```

## Run the Example

<Snippet file="create-venv-step.mdx" />

**1. Install dependencies**

```bash theme={null}
uv pip install -U agno ibm-watsonx-ai
```

**2. Export environment variables**

```bash Mac/Linux theme={null}
export IBM_WATSONX_API_KEY="your_ibm_watsonx_api_key_here"
export IBM_WATSONX_PROJECT_ID="your_ibm_watsonx_project_id_here"
```

```bash Windows theme={null}
$Env:IBM_WATSONX_API_KEY="your_ibm_watsonx_api_key_here"
$Env:IBM_WATSONX_PROJECT_ID="your_ibm_watsonx_project_id_here"
```

**3. Add a sample image**

Place a JPEG named `sample.jpg` in the same directory as `image_agent_bytes.py`.

**4. Run the example**

Save the code above as `image_agent_bytes.py`, then run:

```bash theme={null}
python image_agent_bytes.py
```

Full source: [cookbook/90\_models/ibm/watsonx/image\_agent\_bytes.py](https://github.com/agno-agi/agno/blob/v3.0.4/cookbook/90_models/ibm/watsonx/image_agent_bytes.py)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.