Vision
Specifies which vision processing pipeline to use for content extraction. ICR (Intelligent Content Recognition) refers to intelligent document understanding that goes beyond traditional OCR. While OCR simply converts images of text into machine-readable characters, ICR analyzes the full document structure.
Entries
VLM-enhanced ICR extraction pipeline combining ICR with Vision Language Models. Requires a VLM provider to be configured via with appropriate API credentials (if required). The VLM enhances extraction quality by providing contextual understanding with AI.
Local ICR extraction pipeline using only ONNX models (no VLM required). Provides full document layout analysis and content extraction using local inference only. This mode runs entirely offline without requiring external API calls, making it suitable for air-gapped environments or when VLM setup/costs/latency are a concern.
Functions
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.