For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /max/get-started.md).

Python class

VideoContentPart

`VideoContentPart`

class max.pipelines.modeling.types.pipeline_variants.VideoContentPart(*, type='video', fps=None, max_frames=None, detail=None, max_long_side_pixel=None)

source

Bases: _MessageContentPart

A video content part of a message.

Parameters:

type (Literal['video'])
fps (float | None)
max_frames (int | None)
detail (str | None)
max_long_side_pixel (int | None)

`detail`

detail: str | None

source

`fps`

fps: float | None

source

`max_frames`

max_frames: int | None

source

`max_long_side_pixel`

max_long_side_pixel: int | None

source

`model_config`

model_config: ClassVar[ConfigDict] = {'frozen': True}

source

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

`type`

type: Literal['video']

source

VideoContentPart​

detail​

fps​

max_frames​

max_long_side_pixel​

model_config​

type​

`VideoContentPart`

`detail`

`fps`

`max_frames`

`max_long_side_pixel`

`model_config`

`type`