For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
GuidesAPI ReferenceChangelogModel Versioning
GuidesAPI ReferenceChangelogModel Versioning
    • Getting Started
        • Quick Start
        • Configuration Options
        • Recipes
        • Response Format
        • Best Practices
        • Error Codes
      • Batch Processing
LogoLogo
On this page
  • Recipe 1: Optimized for RAG Pipeline
  • Recipe 2: High-Volume Processing (Performance-Optimized)
  • Recipe 3: Complex Legal Documents
  • Recipe 4: Handwritten Forms
Core Document ProcessingParsing

Recipes

Was this page helpful?
Previous

Response Format

Next
Built with

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:

1{
2  "config": {
3    "target": "markdown",
4    "chunkingStrategy": {
5      "type": "section",
6      "options": {
7        "minCharacters": 500,
8        "maxCharacters": 10000
9      }
10    },
11    "blockOptions": {
12      "figures": {
13        "enabled": true,
14        "figureImageClippingEnabled": false
15      },
16      "tables": {
17        "targetFormat": "html"
18      }
19    },
20    "advancedOptions": {
21      "pageRotationEnabled": true
22    }
23  }
24}

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

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

1{
2  "config": {
3    "target": "markdown",
4    "chunkingStrategy": {
5      "type": "page"
6    },
7    "blockOptions": {
8      "figures": {
9        "enabled": false
10      },
11      "tables": {
12        "targetFormat": "markdown"
13      },
14      "text": {
15        "signatureDetectionEnabled": false,
16        "agentic": {
17          "enabled": false
18        }
19      }
20    },
21    "advancedOptions": {
22      "pageRotationEnabled": false
23    }
24  }
25}

Recipe 3: Complex Legal Documents

Maximum accuracy with signature detection and header continuation:

1{
2  "config": {
3    "target": "markdown",
4    "chunkingStrategy": {
5      "type": "section"
6    },
7    "blockOptions": {
8      "figures": {
9        "enabled": true,
10        "figureImageClippingEnabled": true
11      },
12      "tables": {
13        "targetFormat": "html",
14        "tableHeaderContinuationEnabled": true
15      },
16      "text": {
17        "signatureDetectionEnabled": true,
18        "agentic": {
19          "enabled": true
20        }
21      }
22    },
23    "advancedOptions": {
24      "pageRotationEnabled": true
25    }
26  }
27}

Recipe 4: Handwritten Forms

Optimized for handwritten or degraded documents:

1{
2  "config": {
3    "target": "spatial",
4    "chunkingStrategy": {
5      "type": "page"
6    },
7    "blockOptions": {
8      "figures": {
9        "enabled": false
10      },
11      "tables": {
12        "agentic": {
13          "enabled": true
14        }
15      },
16      "text": {
17        "signatureDetectionEnabled": true,
18        "agentic": {
19          "enabled": true
20        }
21      }
22    },
23    "advancedOptions": {
24      "pageRotationEnabled": true
25    }
26  }
27}