Praison AI

Multimodal Content • AI Agent SDK

multimodal_content: Convenience factory for building a multimodal ToolResult.

multimodal_content

Function

</div>

This function is defined in the base module.

Convenience factory for building a multimodal ToolResult.

Example::

python
from praisonaiagents.tools import multimodal_content, image_part, text_part

def screenshot() -> ToolResult:
    png_bytes = capture()
    return multimodal_content(
        text_part("Here is the current screen:"),
        image_part(png_bytes, mime="image/png", name="screen.png"),
    )

Signature

python
def multimodal_content() -> 'ToolResult'

Returns

ResponseField 'ToolResult'

The result of the operation.

Uses

  • ToolResult

Source

View on GitHub

praisonaiagents/tools/base.py at line 130