Extraction settings

Extraction unit

Page by page Sliding window of pages

Window size

Number of consecutive pages processed together as a unit.

Window overlap

Number of pages shared between units to preserve context.

The window overlap should be lower than window size. The overlap will be automatically set to window size - 1

Customize extraction prompt

Use a custom prompt rather than the default one (can be useful to extract specific information)

Extraction unit

Try to split by sections Full document

Max section depth

Maximum depth of sections to extract - deeper sections will be considered as plain text.

Image handling mode

OCR Engine

Languages

Language tags separated by commas. BCP47 tag or ISO639 code can be added

Outputs structure

Embed

Prompt output (chunked if applicable) Extracted text (chunked if applicable)

Store for retrieval

Extracted text (chunked if applicable) This output can later be used to augment LLMs in the generated Knowledge Bank

Store images in

An output folder is required to store images extracted from documents with this strategy. Select it from the Input / Output tab.

Force reprocessing

Rule edits don't trigger reprocessing on unmodified documents by default. Check to force reprocessing.