VisionOutputFormat

Structured JSON with elements sorted by reading order (default). Contains paragraph text, tables, key-value regions, word-level coordinates, and per-page metadata.

Markdown text optimized for human reading and LLM consumption. Uses standard markdown primitives (headings, paragraphs, tables, blockquotes for footnotes). Loses structural information like coordinates.

IR Lite intermediate representation optimized for LLM position retrieval. Preserves spatial coordinates with a compact token-efficient format.

Returns the enum constant of this type with the specified name. The string must match exactly an identifier used to declare an enum constant in this type. (Extraneous whitespace characters are not permitted.)

Returns an array containing the constants of this enum type, in the order they're declared. This method may be used to iterate over the constants.