ImageChunk

class mint.types.ImageChunk ( StrictBase )

Fields:

• data ( bytes ) – Image data as bytes
• format ( Literal['png', 'jpeg'] ) – Image format
• expected_tokens ( int | None ) – Expected number of tokens this image represents. This is only advisory: the mindlab-toolkit backend will compute the number of tokens from the image, and we can fail requests quickly if the tokens does not match expected_tokens.
• type ( Literal['image'] )

validate_data ( value )

Deserialize base64 string to bytes if needed.

Parameters:

• value ( Union[bytes, str] )

Returns: bytes

serialize_data ( value )

Serialize bytes to base64 string for JSON.

Parameters:

• value ( bytes )

Returns: str