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 function
validate_vision_position_ids
validate_vision_position_ids()
max.pipelines.context.validate_vision_position_ids(context)
Validates that vision_position_ids is present when vision encoding is needed.
-
Parameters:
-
context (TextContext | TextAndVisionContext | PixelContext) – The context to validate.
-
Raises:
-
InputError – If vision_position_ids is missing from extra_model_args when vision encoding is needed.
-
Return type:
-
None
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!