Commands

The DocLD CLI provides three main commands: parse, extract, and edit. Global options: --help, --version.

Parse

Convert documents into structured markdown output. See the Parse API and Document Parsing for API and format details.


# Parse a single file
docld parse document.pdf
 
# Parse an entire folder
docld parse ./documents
 
# Parse with AI enhancement (more accurate but slower)
docld parse document.pdf --agentic
 
# Include document metadata
docld parse document.pdf --hyperlinks --comments --highlights

Output: Creates <filename>.parse.md files with YAML frontmatter (job ID, page count, studio link) and structured markdown content.

Parse options

Flag	Description
`--agentic`	Enable AI enhancement for text, tables, and figures
`--change-tracking`	Enable change tracking for document revisions
`--hyperlinks`	Include hyperlinks in output
`--comments`	Include document comments in output
`--highlights`	Include highlighted text in output
`-o, --output <dir>`	Output directory (default: same as input)

Extract

Extract structured data from documents using JSON schemas. See the Extract API, Data Extraction, and Custom Extraction for schemas and field types.


# Extract with a schema file
docld extract invoice.pdf -s schemas/invoice.json
 
# Extract from multiple files
docld extract ./invoices -s schemas/invoice.json
 
# Include source citations
docld extract invoice.pdf -s schema.json --citations

Output: Creates <filename>.extract.json files. Extraction reuses existing .parse.md files when available to speed up processing.

Extract options

Flag	Description
`-s, --schema <path>`	Path to JSON schema file (required)
`--citations`	Include source citations in output
`-o, --output <dir>`	Output directory

Schema format

Schemas must be valid JSON Schema with type: "object":


{
  "type": "object",
  "properties": {
    "invoice_number": { "type": "string" },
    "total_amount": { "type": "number" },
    "line_items": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "description": { "type": "string" },
          "quantity": { "type": "number" },
          "price": { "type": "number" }
        }
      }
    }
  },
  "required": ["invoice_number", "total_amount"]
}

Edit

Modify documents with natural language instructions. Supports .pdf and .docx only. See the Edit API and Edit feature for programmatic access and concepts.


# Fill a form
docld edit form.pdf -i "Fill the client name as 'Acme Corp' and date as 'January 15, 2024'"
 
# Edit multiple documents
docld edit ./contracts -i "Replace 'OLD COMPANY' with 'NEW COMPANY' throughout"

Output: Creates <filename>.edited.<ext> files with the modifications applied.

Edit options

Flag	Description
`-i, --instructions <text>`	Natural language editing instructions (required)
`-o, --output <dir>`	Output directory

Examples

Invoice processing pipeline


docld parse ./invoices --agentic
docld extract ./invoices -s schemas/invoice.json
# Results in .extract.json files

Contract editing


docld edit ./contracts -i "Replace 'Old Corp' with 'New Corp' throughout the document"

Batch processing


docld parse ./documents -o ./parsed
docld extract ./documents -s schema.json -o ./extracted

Commands

The DocLD CLI provides three main commands: parse, extract, and edit. Global options: --help, --version.

Parse

Convert documents into structured markdown output. See the Parse API and Document Parsing for API and format details.


# Parse a single file
docld parse document.pdf
 
# Parse an entire folder
docld parse ./documents
 
# Parse with AI enhancement (more accurate but slower)
docld parse document.pdf --agentic
 
# Include document metadata
docld parse document.pdf --hyperlinks --comments --highlights

Output: Creates <filename>.parse.md files with YAML frontmatter (job ID, page count, studio link) and structured markdown content.

Parse options

Flag	Description
`--agentic`	Enable AI enhancement for text, tables, and figures
`--change-tracking`	Enable change tracking for document revisions
`--hyperlinks`	Include hyperlinks in output
`--comments`	Include document comments in output
`--highlights`	Include highlighted text in output
`-o, --output <dir>`	Output directory (default: same as input)

Extract

Extract structured data from documents using JSON schemas. See the Extract API, Data Extraction, and Custom Extraction for schemas and field types.


# Extract with a schema file
docld extract invoice.pdf -s schemas/invoice.json
 
# Extract from multiple files
docld extract ./invoices -s schemas/invoice.json
 
# Include source citations
docld extract invoice.pdf -s schema.json --citations

Output: Creates <filename>.extract.json files. Extraction reuses existing .parse.md files when available to speed up processing.

Extract options

Flag	Description
`-s, --schema <path>`	Path to JSON schema file (required)
`--citations`	Include source citations in output
`-o, --output <dir>`	Output directory

Schema format

Schemas must be valid JSON Schema with type: "object":


{
  "type": "object",
  "properties": {
    "invoice_number": { "type": "string" },
    "total_amount": { "type": "number" },
    "line_items": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "description": { "type": "string" },
          "quantity": { "type": "number" },
          "price": { "type": "number" }
        }
      }
    }
  },
  "required": ["invoice_number", "total_amount"]
}

Edit

Modify documents with natural language instructions. Supports .pdf and .docx only. See the Edit API and Edit feature for programmatic access and concepts.


# Fill a form
docld edit form.pdf -i "Fill the client name as 'Acme Corp' and date as 'January 15, 2024'"
 
# Edit multiple documents
docld edit ./contracts -i "Replace 'OLD COMPANY' with 'NEW COMPANY' throughout"

Output: Creates <filename>.edited.<ext> files with the modifications applied.

Edit options

Flag	Description
`-i, --instructions <text>`	Natural language editing instructions (required)
`-o, --output <dir>`	Output directory

Examples

Invoice processing pipeline


docld parse ./invoices --agentic
docld extract ./invoices -s schemas/invoice.json
# Results in .extract.json files

Contract editing


docld edit ./contracts -i "Replace 'Old Corp' with 'New Corp' throughout the document"

Batch processing


docld parse ./documents -o ./parsed
docld extract ./documents -s schema.json -o ./extracted

Commands

Parse

Parse options

Extract

Extract options

Schema format

Edit

Edit options

Examples

Invoice processing pipeline

Contract editing

Batch processing

See also

Commands

Parse

Parse options

Extract

Extract options

Schema format

Edit

Edit options

Examples

Invoice processing pipeline

Contract editing

Batch processing

See also