Image/audio data for multimodal processing. Audio requires an audio-capable projector. Images can be loaded from file path, encoded buffer (JPG, PNG, etc.), or raw RGB data. Supported encoded buffer formats are JPG, PNG, TGA, BMP, PSD, GIF, HDR, and PIC. More...

#include <ailia_llm.h>

Public Attributes
const char *	media_type
	Media type (image, audio). Audio requires an audio-capable mmproj. More...

const char *	file_path
	Path to the media file (UTF-8). Ignored if data is provided. More...

const unsigned char *	data
	Optional: Media data from buffer (alternative to file_path). If width/height are 0, treated as encoded file buffer (JPG, PNG, etc.). If width/height are specified, treated as raw RGB data (width * height * 3 bytes). For audio, use an encoded WAV/MP3/FLAC buffer with width/height=0. Raw PCM is unsupported. More...

unsigned int	data_size
	Size of the buffer (used with data parameter) More...

unsigned int	width
	Width for images (pixels). Only specify for raw RGB data. Set to 0 for encoded buffer. More...

unsigned int	height
	Height for images (pixels). Only specify for raw RGB data. Set to 0 for encoded buffer. More...

Detailed Description

Image/audio data for multimodal processing. Audio requires an audio-capable projector. Images can be loaded from file path, encoded buffer (JPG, PNG, etc.), or raw RGB data. Supported encoded buffer formats are JPG, PNG, TGA, BMP, PSD, GIF, HDR, and PIC.

Member Data Documentation

◆ data

const unsigned char* _AILIALLMMediaData::data

Optional: Media data from buffer (alternative to file_path). If width/height are 0, treated as encoded file buffer (JPG, PNG, etc.). If width/height are specified, treated as raw RGB data (width * height * 3 bytes). For audio, use an encoded WAV/MP3/FLAC buffer with width/height=0. Raw PCM is unsupported.

◆ data_size

unsigned int _AILIALLMMediaData::data_size

Size of the buffer (used with data parameter)

◆ file_path

const char* _AILIALLMMediaData::file_path

Path to the media file (UTF-8). Ignored if data is provided.

◆ height

unsigned int _AILIALLMMediaData::height

Height for images (pixels). Only specify for raw RGB data. Set to 0 for encoded buffer.

◆ media_type

const char* _AILIALLMMediaData::media_type

Media type (image, audio). Audio requires an audio-capable mmproj.

◆ width

unsigned int _AILIALLMMediaData::width

Width for images (pixels). Only specify for raw RGB data. Set to 0 for encoded buffer.

The documentation for this struct was generated from the following file:

ailia_llm.h

Public Attributes