Represents media data (image or audio) for multimodal LLM processing. Corresponds to the AILIALLMMediaData C structure.
Raw media data (currently unsupported, reserved for future use)
Size of the raw data
Path to the media file (UTF-8)
Height for images (pixels), unused for audio (set to 0)
Media type: "image" or "audio" (audio is reserved for future use)
Width for images (pixels), sample count for audio