Skip to navigation
Core Document ProcessingParsing

Recipes

Use these recipes as ready-to-run config blocks. For field-level options and defaults, see Configuration Options.

Recipe 1: Optimized for RAG Pipeline

Section-based chunking with semantic boundaries:

{
  "config": {
    "target": "markdown",
    "chunkingStrategy": {
      "type": "section",
      "options": {
        "minCharacters": 500,
        "maxCharacters": 10000
      }
    },
    "blockOptions": {
      "figures": {
        "enabled": true,
        "figureImageClippingEnabled": false
      },
      "tables": {
        "targetFormat": "html"
      }
    },
    "advancedOptions": {
      "pageRotationEnabled": true
    }
  }
}

Recipe 2: High-Volume Processing (Performance-Optimized)

Performance-optimized configuration for fast, high-volume processing:

{
  "config": {
    "target": "markdown",
    "chunkingStrategy": {
      "type": "page"
    },
    "blockOptions": {
      "figures": {
        "enabled": false
      },
      "tables": {
        "targetFormat": "markdown"
      },
      "text": {
        "signatureDetectionEnabled": false,
        "agentic": {
          "enabled": false
        }
      }
    },
    "advancedOptions": {
      "pageRotationEnabled": false
    }
  }
}

Maximum accuracy with signature detection and header continuation:

{
  "config": {
    "target": "markdown",
    "chunkingStrategy": {
      "type": "section"
    },
    "blockOptions": {
      "figures": {
        "enabled": true,
        "figureImageClippingEnabled": true
      },
      "tables": {
        "targetFormat": "html",
        "tableHeaderContinuationEnabled": true
      },
      "text": {
        "signatureDetectionEnabled": true,
        "agentic": {
          "enabled": true
        }
      }
    },
    "advancedOptions": {
      "pageRotationEnabled": true
    }
  }
}

Recipe 4: Handwritten Forms

Optimized for handwritten or degraded documents:

{
  "config": {
    "target": "spatial",
    "chunkingStrategy": {
      "type": "page"
    },
    "blockOptions": {
      "figures": {
        "enabled": false
      },
      "tables": {
        "agentic": {
          "enabled": true
        }
      },
      "text": {
        "signatureDetectionEnabled": true,
        "agentic": {
          "enabled": true
        }
      }
    },
    "advancedOptions": {
      "pageRotationEnabled": true
    }
  }
}