Skip to main content

Configuration Options

When creating a new Extraction Agent, the schema is the most important part. However, there are a few other options that can significantly impact the extraction process.

  • Extraction Mode (str): The mode of extraction to use. Can be either FAST, BALANCED or MULTIMODAL. The default is BALANCED. You can start here and switch to FAST once you have finalized your schema to see whether the speed/accuracy tradeoff is worth it for your use case. FAST mode is suitable for simpler documents with no OCR and limited tabular extraction. On the other hand, MULTIMODAL mode is suitable for visually rich documents with a mix of text, tables, and images.
  • System Prompt (str): Any additional system level instructions for the extraction agent. Note that you should use the schema descriptions to pass field-level instructions.
  • Extraction Target (str): Whether to use the schema on a per-page basis or on the entire document. For the per-page mode, the schema is applied to each page of the document and an array of results is returned.