Format of content returned by and .

from nutrient_sdk import VisionOutputFormat

Values

NameValueDescription
VisionOutputFormat.JSON0Structured JSON with elements sorted by reading order (default). Contains paragraph text, tables, key-value regions, word-level coordinates, and per-page metadata.
VisionOutputFormat.MARKDOWN1Markdown text optimized for human reading and LLM consumption. Uses standard markdown primitives (headings, paragraphs, tables, blockquotes for footnotes). Loses structural information like coordinates.
VisionOutputFormat.IR_LITE2IR Lite intermediate representation optimized for LLM position retrieval. Preserves spatial coordinates with a compact token-efficient format.

Usage Example

from nutrient_sdk import VisionOutputFormat
# Access enum values
value = VisionOutputFormat.JSON
print(f"Value: {value}") # Output: Value: VisionOutputFormat.JSON
print(f"Integer value: {value.value}") # Output: Integer value: 0