Skip to content

Image, Audio & Document Input

Some LLMs are now capable of understanding both audio, image and document content.

Image Input

Info

Some models do not support image input. Please check the model's documentation to confirm whether it supports image input.

If you have a direct URL for the image, you can use ImageUrl:

main.py
from pydantic_ai import Agent, ImageUrl

agent = Agent(model='openai:gpt-4o')
result = agent.run_sync(
    [
        'What company is this logo from?',
        ImageUrl(url='https://iili.io/3Hs4FMg.png'),
    ]
)
print(result.data)
#> This is the logo for Pydantic, a data validation and settings management library in Python.

If you have the image locally, you can also use BinaryContent:

main.py
import httpx

from pydantic_ai import Agent, BinaryContent

image_response = httpx.get('https://iili.io/3Hs4FMg.png')  # Pydantic logo

agent = Agent(model='openai:gpt-4o')
result = agent.run_sync(
    [
        'What company is this logo from?',
        BinaryContent(data=image_response.content, media_type='image/png'),  # (1)!
    ]
)
print(result.data)
#> This is the logo for Pydantic, a data validation and settings management library in Python.
  1. To ensure the example is runnable we download this image from the web, but you can also use Path().read_bytes() to read a local file's contents.

Audio Input

Info

Some models do not support audio input. Please check the model's documentation to confirm whether it supports audio input.

You can provide audio input using either AudioUrl or BinaryContent. The process is analogous to the examples above.

Document Input

Info

Some models do not support document input. Please check the model's documentation to confirm whether it supports document input.

Warning

When using Gemini models, the document content will always be sent as binary data, regardless of whether you use DocumentUrl or BinaryContent. This is due to differences in how Vertex AI and Google AI handle document inputs.

For more details, see this discussion.

If you are unsatisfied with this behavior, please let us know by opening an issue on GitHub.

You can provide document input using either DocumentUrl or BinaryContent. The process is similar to the examples above.

If you have a direct URL for the document, you can use DocumentUrl:

main.py
from pydantic_ai import Agent, DocumentUrl

agent = Agent(model='anthropic:claude-3-sonnet')
result = agent.run_sync(
    [
        'What is the main content of this document?',
        DocumentUrl(url='https://storage.googleapis.com/cloud-samples-data/generative-ai/pdf/2403.05530.pdf'),
    ]
)
print(result.data)
#> This document is the technical report introducing Gemini 1.5, Google's latest large language model...

The supported document formats vary by model.

You can also use BinaryContent to pass document data directly:

main.py
from pathlib import Path
from pydantic_ai import Agent, BinaryContent

pdf_path = Path('document.pdf')
agent = Agent(model='anthropic:claude-3-sonnet')
result = agent.run_sync(
    [
        'What is the main content of this document?',
        BinaryContent(data=pdf_path.read_bytes(), media_type='application/pdf'),
    ]
)
print(result.data)
#> The document discusses...