{
"type": "object",
"properties": {
"PCID": {
"type": "string",
"description": "Pink Connect ID for the authenticated connection"
},
"async": {
"type": "object",
"description": "The async value",
"properties": {
"metadata": {
"description": "JSON metadata included in webhook request body. Defaults to None."
},
"priority": {
"type": "boolean",
"description": "If True, attempts to process the job with priority if the user has priority processing budget available; by default, sync jobs are prioritized above async jobs."
},
"webhook": {
"description": "The webhook configuration for the asynchronous processing."
}
}
},
"enhance": {
"type": "object",
"description": "The enhance value",
"properties": {
"agentic": {
"type": "array",
"description": "Agentic uses vision language models to enhance the accuracy of the output of different types of extraction. This will incur a cost and latency increase."
},
"summarize_figures": {
"type": "boolean",
"description": "If True, summarize figures using a small vision language model. Defaults to True."
},
"intelligent_ordering": {
"type": "boolean",
"description": "If True, use an advanced vision language model to improve reading order accuracy, with a small increase in latency. Defaults to False."
}
}
},
"formatting": {
"type": "object",
"description": "The formatting value",
"properties": {
"add_page_markers": {
"type": "boolean",
"description": "If True, add page markers to the output. Defaults to False. Useful for extracting data with page specific information."
},
"table_output_format": {
"type": "string",
"description": "The mode to use for table output. Defaults to dynamic, which returns md for simpler tables and html for more complex tables.",
"enum": [
"html",
"json",
"md",
"jsonbbox",
"dynamic",
"csv"
]
},
"merge_tables": {
"type": "boolean",
"description": "A flag to indicate if consecutive tables with the same number of columns should be merged. Defaults to False."
},
"include": {
"type": "array",
"items": {
"type": "string",
"enum": [
"change_tracking",
"highlight",
"comments",
"hyperlinks",
"signatures",
"ignore_watermarks"
]
},
"description": "A list of formatting to include in the output."
}
}
},
"input": {
"description": "For parse/split/extract pipelines, the URL of the document to be processed. You can provide one of the following: 1. A publicly available URL 2. A presigned S3 URL 3. A reducto:// prefixed URL obtained from the /upload endpoint after directly uploading a document 4. A jobid:// prefixed URL obtained from a previous /parse invocation 5. A list of URLs (for multi-document pipelines, V3 API only) For edit pipelines, this should be a string containing the edit instructions"
},
"queue_priority": {
"type": "string",
"description": "Customer-facing queue priority for parse jobs.",
"enum": [
"auto",
"batch"
]
},
"retrieval": {
"type": "object",
"description": "The retrieval value",
"properties": {
"chunking": {
"type": "object",
"description": "The chunking value"
},
"filter_blocks": {
"type": "array",
"items": {
"type": "string",
"enum": [
"Header",
"Footer",
"Title",
"Section Header",
"Page Number",
"List Item",
"Figure",
"Table",
"Key Value",
"Text",
"Comment",
"Signature"
]
},
"description": "A list of block types to filter out from 'content' and 'embed' fields. By default, no blocks are filtered."
},
"embedding_optimized": {
"type": "boolean",
"description": "If True, use embedding optimized mode. Defaults to False."
}
}
},
"settings": {
"type": "object",
"description": "The settings value",
"properties": {
"ocr_system": {
"type": "string",
"description": "Standard is our best multilingual OCR system. Legacy only supports germanic languages and is available for backwards compatibility.",
"enum": [
"standard",
"legacy"
]
},
"extraction_mode": {
"type": "string",
"description": "The mode to use for text extraction from PDFs. OCR mode uses optical character recognition only. Hybrid mode combines OCR with embedded PDF text for best accuracy (default).",
"enum": [
"ocr",
"hybrid"
]
},
"force_url_result": {
"type": "boolean",
"description": "Force the result to be returned in URL form."
},
"force_file_extension": {
"type": "string",
"description": "Force the URL to be downloaded as a specific file extension (e.g. `.png`)."
},
"return_ocr_data": {
"type": "boolean",
"description": "If True, return OCR data in the result. Defaults to False."
},
"return_images": {
"type": "array",
"items": {
"type": "string",
"enum": [
"figure",
"table",
"page"
]
},
"description": "Whether to return images for the specified block types. 'page' returns full page images. By default, no images are returned."
},
"embed_pdf_metadata": {
"type": "boolean",
"description": "If True, embed OCR metadata into the returned PDF. Defaults to False."
},
"persist_results": {
"type": "boolean",
"description": "If True, persist the results indefinitely. Defaults to False."
},
"timeout": {
"type": "number",
"description": "The timeout for the job in seconds."
},
"page_range": {
"description": "The page range to process (1-indexed). By default, the entire document is processed. For spreadsheets, you can also provide a list of sheet names."
},
"document_password": {
"type": "string",
"description": "Password to decrypt password-protected documents."
}
}
},
"spreadsheet": {
"type": "object",
"description": "The spreadsheet value",
"properties": {
"split_large_tables": {
"type": "object",
"description": "Split Large Tables"
},
"include": {
"type": "array",
"items": {
"type": "string",
"enum": [
"cell_colors",
"formula",
"dropdowns"
]
},
"description": "Whether to include cell color, formula, and dropdown information in the output."
},
"clustering": {
"type": "string",
"description": "In a spreadsheet with different tables inside, we enable splitting up the tables by default. Accurate mode applies more powerful models for superior accuracy, at 5× the default per-cell rate. Disabling will register as one large table.",
"enum": [
"accurate",
"fast",
"disabled"
]
},
"exclude": {
"type": "array",
"items": {
"type": "string",
"enum": [
"hidden_sheets",
"hidden_rows",
"hidden_cols",
"styling",
"spreadsheet_images"
]
},
"description": "Whether to exclude hidden sheets, rows, or columns in the output."
}
}
}
},
"required": [
"PCID",
"input"
]
}
