ImageContent#

Choose message roles and distinguish model input from stored history. See the guide.

class zett_agent.messages.ImageContent(source, detail=ImageDetail.AUTO, alt_text=None)[源代码]#

One image block in an ordered multimodal message.

参数:
source: ImageSource#

Remote URL or local in-memory encoded image bytes.

detail: ImageDetail#

Requested fidelity, mapped according to provider capabilities.

alt_text: str | None#

Optional textual description of the image.