affinda-documents

Server path: /affinda-documents | Type: Application | PCID required: Yes

Tools

Tool	Description
`affinda_documents_batch_create_annotations`	Batch create annotations
`affinda_documents_batch_create_validation_results`	Batch create validation results
`affinda_documents_batch_delete_annotations`	Batch delete annotations
`affinda_documents_batch_delete_validation_results`	Batch delete validation results
`affinda_documents_batch_update_annotations`	Batch update annotations
`affinda_documents_create_annotation`	Create a annotation
`affinda_documents_create_document`	Upload a document for parsing
`affinda_documents_create_document_type`	Create a document type
`affinda_documents_create_validation_result`	Create a validation result
`affinda_documents_delete_annotation`	Delete an annotation
`affinda_documents_delete_document`	Delete a document
`affinda_documents_delete_document_type`	Delete a document type
`affinda_documents_delete_validation_result`	Delete a validation result
`affinda_documents_get_all_annotations`	Get list of all annotations
`affinda_documents_get_all_documents`	Get list of all documents
`affinda_documents_get_all_validation_results`	Get list of all validation results
`affinda_documents_get_annotation`	Get specific annotation
`affinda_documents_get_document`	Get specific document
`affinda_documents_get_document_type`	Get a document type
`affinda_documents_get_document_types`	List document types
`affinda_documents_get_redacted_document`	Get redacted document
`affinda_documents_get_validation_result`	Get specific validation result
`affinda_documents_json_schema_from_document_type`	Generate JSON schema from a document type
`affinda_documents_pydantic_models_from_document_type`	Generate Pydantic models from a document type
`affinda_documents_update_annotation`	Update an annotation
`affinda_documents_update_document`	Update a document
`affinda_documents_update_document_type`	Update a document type
`affinda_documents_update_validation_result`	Update a validation result

affinda_documents_batch_create_annotations

Batch create annotations Parameters:

Parameter	Type	Required	Default	Description
`body`	object[]	Yes	—	Request body

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "body": {
      "type": "array",
      "items": {
        "type": "object"
      },
      "description": "Request body"
    }
  },
  "required": [
    "PCID",
    "body"
  ]
}

affinda_documents_batch_create_validation_results

Batch create validation results Parameters:

Parameter	Type	Required	Default	Description
`body`	object[]	Yes	—	Request body

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "body": {
      "type": "array",
      "items": {
        "type": "object"
      },
      "description": "Request body"
    }
  },
  "required": [
    "PCID",
    "body"
  ]
}

affinda_documents_batch_delete_annotations

Batch delete annotations Parameters:

Parameter	Type	Required	Default	Description
`body`	integer[]	Yes	—	Array of annotation IDs to be deleted

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "body": {
      "type": "array",
      "items": {
        "type": "integer"
      },
      "description": "Array of annotation IDs to be deleted"
    }
  },
  "required": [
    "PCID",
    "body"
  ]
}

affinda_documents_batch_delete_validation_results

Batch delete validation results Parameters:

Parameter	Type	Required	Default	Description
`ids`	integer[]	Yes	—	List of validation result IDs to delete.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "ids": {
      "type": "array",
      "items": {
        "type": "integer"
      },
      "description": "List of validation result IDs to delete."
    }
  },
  "required": [
    "PCID",
    "ids"
  ]
}

affinda_documents_batch_update_annotations

Batch update annotations Parameters:

Parameter	Type	Required	Default	Description
`body`	object[]	Yes	—	Request body

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "body": {
      "type": "array",
      "items": {
        "type": "object"
      },
      "description": "Request body"
    }
  },
  "required": [
    "PCID",
    "body"
  ]
}

affinda_documents_create_annotation

Create a annotation Parameters:

Parameter	Type	Required	Default	Description
`dataPoint`	string	No	—	Data point’s identifier
`document`	string	Yes	—	Unique identifier for the document
`field`	string	No	—	Field’s identifier
`isClientVerified`	boolean	No	—	Indicates whether the data has been validated by a human
`pageIndex`	integer	Yes	—	The page number within the document, starting from 0.
`parent`	integer	No	—	The parent annotation’s ID
`parsed`	object	No	—	The parsed value
`raw`	string	No	—	Raw data extracted from the before any post-processing
`rectangles`	object[]	No	—	x/y coordinates for the rectangles containing the data. An annotation can be contained within multiple rectangles.
`validationResults`	object[]	No	—	The validation results created, changed or deleted as a result of creating the annotation.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "dataPoint": {
      "type": "string",
      "description": "Data point's identifier"
    },
    "document": {
      "type": "string",
      "description": "Unique identifier for the document"
    },
    "field": {
      "type": "string",
      "description": "Field's identifier"
    },
    "isClientVerified": {
      "type": "boolean",
      "description": "Indicates whether the data has been validated by a human"
    },
    "pageIndex": {
      "type": "integer",
      "description": "The page number within the document, starting from 0."
    },
    "parent": {
      "type": "integer",
      "description": "The parent annotation's ID"
    },
    "parsed": {
      "description": "The parsed value"
    },
    "raw": {
      "type": "string",
      "description": "Raw data extracted from the before any post-processing"
    },
    "rectangles": {
      "type": "array",
      "items": {
        "type": "object"
      },
      "description": "x/y coordinates for the rectangles containing the data. An annotation can be contained within multiple rectangles."
    },
    "validationResults": {
      "type": "array",
      "items": {
        "type": "object"
      },
      "description": "The validation results created, changed or deleted as a result of creating the annotation."
    }
  },
  "required": [
    "PCID",
    "document",
    "pageIndex"
  ]
}

affinda_documents_create_document

Upload a document for parsing Parameters:

Parameter	Type	Required	Default	Description
`snake_case`	boolean	No	—	Whether to return the response in snake_case instead of camelCase. Default is false.
`collection`	string	No	—	Uniquely identify a collection.
`compact`	boolean	No	—	If true, the returned parse result (assuming `wait` is also true) will be a compact version of the full result.
`customIdentifier`	string	No	—	Specify a custom identifier for the document if you need one, not required to be unique.
`deleteAfterParse`	boolean	No	—	If true, no data will be stored after parsing. Only compatible with requests where wait: True.
`documentType`	string	No	—	The document type’s identifier. Provide if you already know the document type.
`enableValidationTool`	boolean	No	—	If true, the document will be viewable in the Affinda Validation Tool. Set to False to optimize parsing speed.
`expiryTime`	string	No	—	The date/time in ISO-8601 format when the document will be automatically deleted. Defaults to no expiry.
`file`	string	No	—	File as binary data blob. Supported formats: PDF, DOC, DOCX, TXT, RTF, HTML, PNG, JPG, TIFF, ODT, XLS, XLSX
`fileName`	string	No	—	Optional filename of the file
`identifier`	string	No	—	Deprecated in favor of `customIdentifier`.
`language`	string	No	—	Language code in ISO 639-1 format. Must specify zh-cn or zh-tw for Chinese.
`limitToExamples`	string[]	No	—	Restrict LLM example selection to the specified document identifiers.
`llmHint`	string	No	—	Optional hint inserted into the LLM prompt when processing this document.
`lowPriority`	boolean	No	—	Explicitly mark this document as low priority.
`regionBias`	string	No	—	A JSON representation of the RegionBias object.
`rejectDuplicates`	boolean	No	—	If “true”, parsing will fail when the uploaded document is duplicate of an existing document, no credits will be consumed. If “false”, will parse the document normally whether its a duplicate or not. If not provided, will fallback to the workspace settings.
`url`	string	No	—	URL to download the document.
`useOcr`	boolean	No	—	If true, the document will be treated like an image, and the text will be extracted using OCR. If false, the document will be treated like a PDF, and the text will be extracted using the parser. If not set, we will determine whether to use OCR based on whether words are found in the document.
`wait`	boolean	No	—	If “true” (default), will return a response only after processing has completed. If “false”, will return an empty data object which can be polled at the GET endpoint until processing is complete.
`warningMessages`	object[]	No	—	Warning Messages
`workspace`	string	No	—	Uniquely identify a workspace.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "snake_case": {
      "type": "boolean",
      "description": "Whether to return the response in snake_case instead of camelCase. Default is false."
    },
    "collection": {
      "type": "string",
      "description": "Uniquely identify a collection."
    },
    "compact": {
      "type": "boolean",
      "description": "If true, the returned parse result (assuming `wait` is also true) will be a compact version of the full result."
    },
    "customIdentifier": {
      "type": "string",
      "description": "Specify a custom identifier for the document if you need one, not required to be unique."
    },
    "deleteAfterParse": {
      "type": "boolean",
      "description": "If true, no data will be stored after parsing. Only compatible with requests where wait: True."
    },
    "documentType": {
      "type": "string",
      "description": "The document type's identifier.  Provide if you already know the document type."
    },
    "enableValidationTool": {
      "type": "boolean",
      "description": "If true, the document will be viewable in the Affinda Validation Tool. Set to False to optimize parsing speed."
    },
    "expiryTime": {
      "type": "string",
      "description": "The date/time in ISO-8601 format when the document will be automatically deleted.  Defaults to no expiry."
    },
    "file": {
      "type": "string",
      "description": "File as binary data blob. Supported formats: PDF, DOC, DOCX, TXT, RTF, HTML, PNG, JPG, TIFF, ODT, XLS, XLSX"
    },
    "fileName": {
      "type": "string",
      "description": "Optional filename of the file"
    },
    "identifier": {
      "type": "string",
      "description": "Deprecated in favor of `customIdentifier`."
    },
    "language": {
      "type": "string",
      "description": "Language code in ISO 639-1 format. Must specify zh-cn or zh-tw for Chinese."
    },
    "limitToExamples": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Restrict LLM example selection to the specified document identifiers."
    },
    "llmHint": {
      "type": "string",
      "description": "Optional hint inserted into the LLM prompt when processing this document."
    },
    "lowPriority": {
      "type": "boolean",
      "description": "Explicitly mark this document as low priority."
    },
    "regionBias": {
      "type": "string",
      "description": "A JSON representation of the RegionBias object."
    },
    "rejectDuplicates": {
      "type": "boolean",
      "description": "If \"true\", parsing will fail when the uploaded document is duplicate of an existing document, no credits will be consumed. If \"false\", will parse the document normally whether its a duplicate or not. If not provided, will fallback to the workspace settings."
    },
    "url": {
      "type": "string",
      "description": "URL to download the document."
    },
    "useOcr": {
      "type": "boolean",
      "description": "If true, the document will be treated like an image, and the text will be extracted using OCR. If false, the document will be treated like a PDF, and the text will be extracted using the parser. If not set, we will determine whether to use OCR based on whether words are found in the document."
    },
    "wait": {
      "type": "boolean",
      "description": "If \"true\" (default), will return a response only after processing has completed. If \"false\", will return an empty data object which can be polled at the GET endpoint until processing is complete."
    },
    "warningMessages": {
      "type": "array",
      "items": {
        "type": "object"
      },
      "description": "Warning Messages"
    },
    "workspace": {
      "type": "string",
      "description": "Uniquely identify a workspace."
    }
  },
  "required": [
    "PCID"
  ]
}

affinda_documents_create_document_type

Create a document type Parameters:

Parameter	Type	Required	Default	Description
`description`	string	No	—	A description of the document type.
`name`	string	Yes	—	The name of the document type.
`organization`	string	Yes	—	The identifier of the organization this document type belongs to.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "description": {
      "type": "string",
      "description": "A description of the document type."
    },
    "name": {
      "type": "string",
      "description": "The name of the document type."
    },
    "organization": {
      "type": "string",
      "description": "The identifier of the organization this document type belongs to."
    }
  },
  "required": [
    "PCID",
    "name",
    "organization"
  ]
}

affinda_documents_create_validation_result

Create a validation result Parameters:

Parameter	Type	Required	Default	Description
`annotations`	integer[]	Yes	—	List of annotation ids that were validated
`document`	string	Yes	—	Unique identifier for the document
`message`	string	Yes	—	Message explaining why the validation failed
`passed`	boolean	No	—	Whether the validation passed or not, null if the validation was not applicable
`ruleSlug`	string	Yes	—	The kebab-case slug of the validation rule that was applied

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "annotations": {
      "type": "array",
      "items": {
        "type": "integer"
      },
      "description": "List of annotation ids that were validated"
    },
    "document": {
      "type": "string",
      "description": "Unique identifier for the document"
    },
    "message": {
      "type": "string",
      "description": "Message explaining why the validation failed"
    },
    "passed": {
      "type": "boolean",
      "description": "Whether the validation passed or not, null if the validation was not applicable"
    },
    "ruleSlug": {
      "type": "string",
      "description": "The kebab-case slug of the validation rule that was applied"
    }
  },
  "required": [
    "PCID",
    "annotations",
    "document",
    "message",
    "ruleSlug"
  ]
}

affinda_documents_delete_annotation

Delete an annotation Parameters:

Parameter	Type	Required	Default	Description
`id`	integer	Yes	—	Annotation’s ID

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "id": {
      "type": "integer",
      "description": "Annotation's ID"
    }
  },
  "required": [
    "PCID",
    "id"
  ]
}

affinda_documents_delete_document

Delete a document Parameters:

Parameter	Type	Required	Default	Description
`identifier`	string	Yes	—	Document’s identifier

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "identifier": {
      "type": "string",
      "description": "Document's identifier"
    }
  },
  "required": [
    "PCID",
    "identifier"
  ]
}

affinda_documents_delete_document_type

Delete a document type Parameters:

Parameter	Type	Required	Default	Description
`identifier`	string	Yes	—	Document type identifier

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "identifier": {
      "type": "string",
      "description": "Document type identifier"
    }
  },
  "required": [
    "PCID",
    "identifier"
  ]
}

affinda_documents_delete_validation_result

Delete a validation result Parameters:

Parameter	Type	Required	Default	Description
`id`	integer	Yes	—	Validation result’s ID.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "id": {
      "type": "integer",
      "description": "Validation result's ID."
    }
  },
  "required": [
    "PCID",
    "id"
  ]
}

affinda_documents_get_all_annotations

Get list of all annotations Parameters:

Parameter	Type	Required	Default	Description
`document`	string	Yes	—	Filter by document.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "document": {
      "type": "string",
      "description": "Filter by document."
    }
  },
  "required": [
    "PCID",
    "document"
  ]
}

affinda_documents_get_all_documents

Get list of all documents Parameters:

Parameter	Type	Required	Default	Description
`offset`	integer	No	—	The number of documents to skip before starting to collect the result set.
`limit`	integer	No	—	The numbers of results to return.
`workspace`	string	No	—	Filter by workspace.
`collection`	string	No	—	Filter by collection.
`state`	string	No	—	Filter by the document’s state.
`tags`	integer[]	No	—	Filter by tag’s IDs.
`created_dt`	string	No	—	Filter by created datetime.
`search`	string	No	—	Partial, case-insensitive match with file name or tag name.
`ordering`	string[]	No	—	Sort the result set. A ”-” at the beginning denotes DESC sort, e.g. -created_dt. Sort by multiple fields is supported. Supported values include: ‘file_name’, ‘extractor’, ‘created_dt’, ‘validated_dt’, ‘archived_dt’ and ‘parsed__<dataPointSlug>’.
`include_data`	boolean	No	—	By default, this endpoint returns only the meta data of the documents. Set this to `true` will return a summary of the data that was parsed. If you want to retrieve the full set of data for a document, use the `GET /documents/{identifier}` endpoint.
`exclude`	string[]	No	—	Exclude some documents from the result.
`in_review`	boolean	No	—	Exclude documents that are currently being reviewed.
`failed`	boolean	No	—	Filter by failed status.
`ready`	boolean	No	—	Filter by ready status.
`validatable`	boolean	No	—	Filter for validatable documents.
`has_challenges`	boolean	No	—	Filter for documents with challenges.
`custom_identifier`	string	No	—	Filter for documents with this custom identifier.
`compact`	boolean	No	—	If “true”, the response is compacted to annotations’ parsed data. Annotations’ meta data are excluded. Default is “false”.
`count`	boolean	No	—	If “false”, the documents count is not computed, thus saving time for large collections. Default is “true”.
`snake_case`	boolean	No	—	Whether to return the response in snake_case instead of camelCase. Default is false.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "offset": {
      "type": "integer",
      "description": "The number of documents to skip before starting to collect the result set."
    },
    "limit": {
      "type": "integer",
      "description": "The numbers of results to return."
    },
    "workspace": {
      "type": "string",
      "description": "Filter by workspace."
    },
    "collection": {
      "type": "string",
      "description": "Filter by collection."
    },
    "state": {
      "type": "string",
      "description": "Filter by the document's state.",
      "enum": [
        "uploaded",
        "review",
        "validated",
        "archived",
        "rejected"
      ]
    },
    "tags": {
      "type": "array",
      "items": {
        "type": "integer"
      },
      "description": "Filter by tag's IDs."
    },
    "created_dt": {
      "type": "string",
      "description": "Filter by created datetime.",
      "enum": [
        "today",
        "yesterday",
        "week",
        "month",
        "year"
      ]
    },
    "search": {
      "type": "string",
      "description": "Partial, case-insensitive match with file name or tag name."
    },
    "ordering": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Sort the result set. A \"-\" at the beginning denotes DESC sort, e.g. -created_dt. Sort by multiple fields is supported. Supported values include: 'file_name', 'extractor', 'created_dt', 'validated_dt', 'archived_dt' and 'parsed__<dataPointSlug>'."
    },
    "include_data": {
      "type": "boolean",
      "description": "By default, this endpoint returns only the meta data of the documents. Set this to `true` will return a summary of the data that was parsed. If you want to retrieve the full set of data for a document, use the `GET /documents/{identifier}` endpoint."
    },
    "exclude": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Exclude some documents from the result."
    },
    "in_review": {
      "type": "boolean",
      "description": "Exclude documents that are currently being reviewed."
    },
    "failed": {
      "type": "boolean",
      "description": "Filter by failed status."
    },
    "ready": {
      "type": "boolean",
      "description": "Filter by ready status."
    },
    "validatable": {
      "type": "boolean",
      "description": "Filter for validatable documents."
    },
    "has_challenges": {
      "type": "boolean",
      "description": "Filter for documents with challenges."
    },
    "custom_identifier": {
      "type": "string",
      "description": "Filter for documents with this custom identifier."
    },
    "compact": {
      "type": "boolean",
      "description": "If \"true\", the response is compacted to annotations' parsed data. Annotations' meta data are excluded. Default is \"false\"."
    },
    "count": {
      "type": "boolean",
      "description": "If \"false\", the documents count is not computed, thus saving time for large collections. Default is \"true\"."
    },
    "snake_case": {
      "type": "boolean",
      "description": "Whether to return the response in snake_case instead of camelCase. Default is false."
    }
  },
  "required": [
    "PCID"
  ]
}

affinda_documents_get_all_validation_results

Get list of all validation results Parameters:

Parameter	Type	Required	Default	Description
`offset`	integer	No	—	The number of documents to skip before starting to collect the result set.
`limit`	integer	No	—	The numbers of results to return.
`document`	string	Yes	—	Filter by document.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "offset": {
      "type": "integer",
      "description": "The number of documents to skip before starting to collect the result set."
    },
    "limit": {
      "type": "integer",
      "description": "The numbers of results to return."
    },
    "document": {
      "type": "string",
      "description": "Filter by document."
    }
  },
  "required": [
    "PCID",
    "document"
  ]
}

affinda_documents_get_annotation

Get specific annotation Parameters:

Parameter	Type	Required	Default	Description
`id`	integer	Yes	—	Annotation’s ID

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "id": {
      "type": "integer",
      "description": "Annotation's ID"
    }
  },
  "required": [
    "PCID",
    "id"
  ]
}

affinda_documents_get_document

Get specific document Parameters:

Parameter	Type	Required	Default	Description
`identifier`	string	Yes	—	Document’s identifier
`format`	string	No	—	Specify which format you want the response to be. Default is “json”
`compact`	boolean	No	—	If “true”, the response is compacted to annotations’ parsed data. Annotations’ meta data are excluded. Default is “false”.
`snake_case`	boolean	No	—	Whether to return the response in snake_case instead of camelCase. Default is false.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "identifier": {
      "type": "string",
      "description": "Document's identifier"
    },
    "format": {
      "type": "string",
      "description": "Specify which format you want the response to be. Default is \"json\"",
      "enum": [
        "json",
        "xml",
        "hr-xml"
      ]
    },
    "compact": {
      "type": "boolean",
      "description": "If \"true\", the response is compacted to annotations' parsed data. Annotations' meta data are excluded. Default is \"false\"."
    },
    "snake_case": {
      "type": "boolean",
      "description": "Whether to return the response in snake_case instead of camelCase. Default is false."
    }
  },
  "required": [
    "PCID",
    "identifier"
  ]
}

affinda_documents_get_document_type

Get a document type Parameters:

Parameter	Type	Required	Default	Description
`identifier`	string	Yes	—	Document type identifier

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "identifier": {
      "type": "string",
      "description": "Document type identifier"
    }
  },
  "required": [
    "PCID",
    "identifier"
  ]
}

affinda_documents_get_document_types

List document types Parameters:

Parameter	Type	Required	Default	Description
`organization`	string	No	—	Filter by organization identifier
`workspace`	string	No	—	Filter by workspace identifier

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "organization": {
      "type": "string",
      "description": "Filter by organization identifier"
    },
    "workspace": {
      "type": "string",
      "description": "Filter by workspace identifier"
    }
  },
  "required": [
    "PCID"
  ]
}

affinda_documents_get_redacted_document

Get redacted document Parameters:

Parameter	Type	Required	Default	Description
`identifier`	string	Yes	—	Document identifier

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "identifier": {
      "type": "string",
      "description": "Document identifier"
    }
  },
  "required": [
    "PCID",
    "identifier"
  ]
}

affinda_documents_get_validation_result

Get specific validation result Parameters:

Parameter	Type	Required	Default	Description
`id`	integer	Yes	—	Validation result’s ID.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "id": {
      "type": "integer",
      "description": "Validation result's ID."
    }
  },
  "required": [
    "PCID",
    "id"
  ]
}

affinda_documents_json_schema_from_document_type

Generate JSON schema from a document type Parameters:

Parameter	Type	Required	Default	Description
`identifier`	string	Yes	—	Document type’s identifier
`title`	string	No	—	Title for the JSON schema

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "identifier": {
      "type": "string",
      "description": "Document type's identifier"
    },
    "title": {
      "type": "string",
      "description": "Title for the JSON schema"
    }
  },
  "required": [
    "PCID",
    "identifier"
  ]
}

affinda_documents_pydantic_models_from_document_type

Generate Pydantic models from a document type Parameters:

Parameter	Type	Required	Default	Description
`identifier`	string	Yes	—	Document type’s identifier
`model_name`	string	No	—	Name for the Pydantic model

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "identifier": {
      "type": "string",
      "description": "Document type's identifier"
    },
    "model_name": {
      "type": "string",
      "description": "Name for the Pydantic model"
    }
  },
  "required": [
    "PCID",
    "identifier"
  ]
}

affinda_documents_update_annotation

Update an annotation Parameters:

Parameter	Type	Required	Default	Description
`id`	integer	Yes	—	Annotation’s ID
`dataPoint`	string	No	—	Data point’s identifier
`document`	string	No	—	Unique identifier for the document
`field`	string	No	—	Field’s identifier
`isClientVerified`	boolean	No	—	Indicates whether the data has been validated by a human
`pageIndex`	integer	No	—	The page number within the document, starting from 0.
`parent`	integer	No	—	The parent annotation’s ID
`parsed`	object	No	—	The parsed value
`raw`	string	No	—	Raw data extracted from the before any post-processing
`rectangles`	object[]	No	—	x/y coordinates for the rectangles containing the data. An annotation can be contained within multiple rectangles.
`validationResults`	object[]	No	—	The validation results created, changed or deleted as a result of updating the annotation.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "id": {
      "type": "integer",
      "description": "Annotation's ID"
    },
    "dataPoint": {
      "type": "string",
      "description": "Data point's identifier"
    },
    "document": {
      "type": "string",
      "description": "Unique identifier for the document"
    },
    "field": {
      "type": "string",
      "description": "Field's identifier"
    },
    "isClientVerified": {
      "type": "boolean",
      "description": "Indicates whether the data has been validated by a human"
    },
    "pageIndex": {
      "type": "integer",
      "description": "The page number within the document, starting from 0."
    },
    "parent": {
      "type": "integer",
      "description": "The parent annotation's ID"
    },
    "parsed": {
      "description": "The parsed value"
    },
    "raw": {
      "type": "string",
      "description": "Raw data extracted from the before any post-processing"
    },
    "rectangles": {
      "type": "array",
      "items": {
        "type": "object"
      },
      "description": "x/y coordinates for the rectangles containing the data. An annotation can be contained within multiple rectangles."
    },
    "validationResults": {
      "type": "array",
      "items": {
        "type": "object"
      },
      "description": "The validation results created, changed or deleted as a result of updating the annotation."
    }
  },
  "required": [
    "PCID",
    "id"
  ]
}

affinda_documents_update_document

Update a document Parameters:

Parameter	Type	Required	Default	Description
`identifier`	string	Yes	—	Document’s identifier
`compact`	boolean	No	—	If “true”, the response is compacted to annotations’ parsed data. Annotations’ meta data are excluded. Default is “false”.
`snake_case`	boolean	No	—	Whether to return the response in snake_case instead of camelCase. Default is false.
`collection`	string	No	—	Uniquely identify a collection.
`customIdentifier`	string	No	—	Specify a custom identifier for the document if you need one, not required to be unique.
`documentType`	string	No	—	The document type’s identifier. Provide if you already know the document type.
`expiryTime`	string	No	—	The date/time in ISO-8601 format when the document will be automatically deleted. Defaults to no expiry.
`fileName`	string	No	—	Optional filename of the file
`isArchived`	boolean	No	—	Is Archived
`isConfirmed`	boolean	No	—	Is Confirmed
`isRejected`	boolean	No	—	Is Rejected
`language`	string	No	—	Language code in ISO 639-1 format. Must specify zh-cn or zh-tw for Chinese.
`llmHint`	string	No	—	Optional hint inserted into the LLM prompt when processing this document.
`skipParse`	boolean	No	—	Skip Parse
`warningMessages`	object[]	No	—	Warning Messages
`workspace`	string	No	—	Uniquely identify a workspace.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "identifier": {
      "type": "string",
      "description": "Document's identifier"
    },
    "compact": {
      "type": "boolean",
      "description": "If \"true\", the response is compacted to annotations' parsed data. Annotations' meta data are excluded. Default is \"false\"."
    },
    "snake_case": {
      "type": "boolean",
      "description": "Whether to return the response in snake_case instead of camelCase. Default is false."
    },
    "collection": {
      "type": "string",
      "description": "Uniquely identify a collection."
    },
    "customIdentifier": {
      "type": "string",
      "description": "Specify a custom identifier for the document if you need one, not required to be unique."
    },
    "documentType": {
      "type": "string",
      "description": "The document type's identifier.  Provide if you already know the document type."
    },
    "expiryTime": {
      "type": "string",
      "description": "The date/time in ISO-8601 format when the document will be automatically deleted.  Defaults to no expiry."
    },
    "fileName": {
      "type": "string",
      "description": "Optional filename of the file"
    },
    "isArchived": {
      "type": "boolean",
      "description": "Is Archived"
    },
    "isConfirmed": {
      "type": "boolean",
      "description": "Is Confirmed"
    },
    "isRejected": {
      "type": "boolean",
      "description": "Is Rejected"
    },
    "language": {
      "type": "string",
      "description": "Language code in ISO 639-1 format. Must specify zh-cn or zh-tw for Chinese."
    },
    "llmHint": {
      "type": "string",
      "description": "Optional hint inserted into the LLM prompt when processing this document."
    },
    "skipParse": {
      "type": "boolean",
      "description": "Skip Parse"
    },
    "warningMessages": {
      "type": "array",
      "items": {
        "type": "object"
      },
      "description": "Warning Messages"
    },
    "workspace": {
      "type": "string",
      "description": "Uniquely identify a workspace."
    }
  },
  "required": [
    "PCID",
    "identifier"
  ]
}

affinda_documents_update_document_type

Update a document type Parameters:

Parameter	Type	Required	Default	Description
`identifier`	string	Yes	—	Document type identifier
`description`	string	No	—	A new description of the document type.
`name`	string	No	—	The new name of the document type.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "identifier": {
      "type": "string",
      "description": "Document type identifier"
    },
    "description": {
      "type": "string",
      "description": "A new description of the document type."
    },
    "name": {
      "type": "string",
      "description": "The new name of the document type."
    }
  },
  "required": [
    "PCID",
    "identifier"
  ]
}

affinda_documents_update_validation_result

Update a validation result Parameters:

Parameter	Type	Required	Default	Description
`id`	integer	Yes	—	Validation result’s ID.
`annotations`	integer[]	No	—	List of annotation ids that were validated
`document`	string	No	—	Unique identifier for the document
`message`	string	No	—	Message explaining why the validation failed
`passed`	boolean	No	—	Whether the validation passed or not, null if the validation was not applicable
`ruleSlug`	string	No	—	The kebab-case slug of the validation rule that was applied

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "id": {
      "type": "integer",
      "description": "Validation result's ID."
    },
    "annotations": {
      "type": "array",
      "items": {
        "type": "integer"
      },
      "description": "List of annotation ids that were validated"
    },
    "document": {
      "type": "string",
      "description": "Unique identifier for the document"
    },
    "message": {
      "type": "string",
      "description": "Message explaining why the validation failed"
    },
    "passed": {
      "type": "boolean",
      "description": "Whether the validation passed or not, null if the validation was not applicable"
    },
    "ruleSlug": {
      "type": "string",
      "description": "The kebab-case slug of the validation rule that was applied"
    }
  },
  "required": [
    "PCID",
    "id"
  ]
}

Triggers API

Platform API

Embedded MCP Servers

Application MCP Servers

Skills Guides

Tools

affinda_documents_batch_create_annotations

affinda_documents_batch_create_validation_results

affinda_documents_batch_delete_annotations

affinda_documents_batch_delete_validation_results

affinda_documents_batch_update_annotations

affinda_documents_create_annotation

affinda_documents_create_document

affinda_documents_create_document_type

affinda_documents_create_validation_result

affinda_documents_delete_annotation

affinda_documents_delete_document

affinda_documents_delete_document_type

affinda_documents_delete_validation_result

affinda_documents_get_all_annotations

affinda_documents_get_all_documents

affinda_documents_get_all_validation_results

affinda_documents_get_annotation

affinda_documents_get_document

affinda_documents_get_document_type

affinda_documents_get_document_types

affinda_documents_get_redacted_document

affinda_documents_get_validation_result

affinda_documents_json_schema_from_document_type

affinda_documents_pydantic_models_from_document_type

affinda_documents_update_annotation

affinda_documents_update_document

affinda_documents_update_document_type

affinda_documents_update_validation_result

Triggers API

Platform API

Embedded MCP Servers

Application MCP Servers

Skills Guides

​Tools

​affinda_documents_batch_create_annotations

​affinda_documents_batch_create_validation_results

​affinda_documents_batch_delete_annotations

​affinda_documents_batch_delete_validation_results

​affinda_documents_batch_update_annotations

​affinda_documents_create_annotation

​affinda_documents_create_document

​affinda_documents_create_document_type

​affinda_documents_create_validation_result

​affinda_documents_delete_annotation

​affinda_documents_delete_document

​affinda_documents_delete_document_type

​affinda_documents_delete_validation_result

​affinda_documents_get_all_annotations

​affinda_documents_get_all_documents

​affinda_documents_get_all_validation_results

​affinda_documents_get_annotation

​affinda_documents_get_document

​affinda_documents_get_document_type

​affinda_documents_get_document_types

​affinda_documents_get_redacted_document

​affinda_documents_get_validation_result

​affinda_documents_json_schema_from_document_type

​affinda_documents_pydantic_models_from_document_type

​affinda_documents_update_annotation

​affinda_documents_update_document

​affinda_documents_update_document_type

​affinda_documents_update_validation_result

Tools

affinda_documents_batch_create_annotations

affinda_documents_batch_create_validation_results

affinda_documents_batch_delete_annotations

affinda_documents_batch_delete_validation_results

affinda_documents_batch_update_annotations

affinda_documents_create_annotation

affinda_documents_create_document

affinda_documents_create_document_type

affinda_documents_create_validation_result

affinda_documents_delete_annotation

affinda_documents_delete_document

affinda_documents_delete_document_type

affinda_documents_delete_validation_result

affinda_documents_get_all_annotations

affinda_documents_get_all_documents

affinda_documents_get_all_validation_results

affinda_documents_get_annotation

affinda_documents_get_document

affinda_documents_get_document_type

affinda_documents_get_document_types

affinda_documents_get_redacted_document

affinda_documents_get_validation_result

affinda_documents_json_schema_from_document_type

affinda_documents_pydantic_models_from_document_type

affinda_documents_update_annotation

affinda_documents_update_document

affinda_documents_update_document_type

affinda_documents_update_validation_result