How the model processes this part's media for understanding. Only meaningful for video parts (inline_data or file_data with video mime). Non-video parts ignore this field.
inline_data
file_data
Model-driven dynamic navigation. Recommended for most use cases.
Defaults to model-specific processing.
Fixed-rate frame extraction. All frames placed in context.
How the model processes this part's media for understanding. Only meaningful for video parts (
inline_dataorfile_datawith video mime). Non-video parts ignore this field.