Document Extraction

Overview

The "Document Extraction" API is a universal identification interface that allows you to initiate model calls based on the model ID. You can specify whether the interface returns the recognition results synchronously or asynchronously by the parameter "synchronously".

Request

POST https://api.docai.pro/api/identify/file/v2/identify

Request body

Name	Type	Mandatory	Description
modelId	string	true	The unique identifier of the model
file	file	true	Documents that need to be identified
legalPageNumbers	string	false	Page numbers to be identified, if not specified, the entire document will be recognized.
workspaceCode	string	false	The workspace name within the model.if empty, defaults to 'Default Workspace'.
isAsynchronous	string	false	Whether to return the recognition results asynchronously,Default: 0,1: Asynchronously return,0: Synchronously return

Examples of the legalPageNumbers:

1-1: only need to recognize the first page;

2-3: only need to recognize the second page and the third page;

1-1, 3-4: only need to recognize the first page, the third page, and the fourth page.

Response body

Name	Type	Mandatory	Description
fileId	string	true	Unique identifier for uploading files
recognizeStatus	string	true	Upload file recognition status (0 - failed, 1 - successful, 2 - Identifying)
result	object	true	Identification field

result Message Format

Name	Type	Mandatory	Description
fieldList	array	false	List of extracted fields from the document
pageNumber	int	false	The page number within the document for this field
key	string	false	The name of the extracted field
value	string	false	The value of the extracted field
itemList	array	false	Extracted line information from the document
pageNumber	integer	false	The page number within the document for this item
key	string	false	The name of the extracted item
value	string	false	The value of the extracted item

Example request

curl -i -X POST https://api.docai.pro/api/identify/file/v2/identify \
-H "Content-Type: multipart/form-data" \
-H "Authorization: Bearer $DOCAI_API_KEY" \
-F 'modelId=@MODEL_ID' \
-F 'file=@REPLACE_IMAGE_PATH.jpg'

Example of synchronous response

{
    "code": 200,
    "message": null,
    "costTime": null,
    "data": {
        "fileId": "2310091711378393918074800",
        "recognizeStatus": "1",
        "result": {
            "fieldList": [
                {
                    "pageNumber": 1,
                    "key": "paymentTerms",
                    "value": "Payment is due within 15 days"
                },
                {
                    "pageNumber": 1,
                    "key": "invoiceDate",
                    "value": "2019-02-11"
                },
                {
                    "pageNumber": 1,
                    "key": "documentType",
                    "value": "invoice"
                },
                {
                    "pageNumber": 1,
                    "key": "invoiceNumber",
                    "value": "US-001"
                },
                {
                    "pageNumber": 1,
                    "key": "grossAmount",
                    "value": "154.06"
                },
                {
                    "pageNumber": 1,
                    "key": "totalTax",
                    "value": "9.06"
                },
                {
                    "pageNumber": 1,
                    "key": "dueDate",
                    "value": "2019-02-26"
                }
            ],
            "taxList": [
                [
                    {
                        "pageNumber": 1,
                        "key": "taxValue",
                        "value": "9.06"
                    },
                    {
                        "pageNumber": 1,
                        "key": "taxPercentage",
                        "value": "6.25"
                    }
                ]
            ],
            "itemList": [
                [
                    {
                        "pageNumber": 1,
                        "key": "totalPriceInclTax",
                        "value": "100.00"
                    },
                    {
                        "pageNumber": 1,
                        "key": "unitPrice",
                        "value": "100.00"
                    },
                    {
                        "pageNumber": 1,
                        "key": "quantity",
                        "value": "1"
                    },
                    {
                        "pageNumber": 1,
                        "key": "description",
                        "value": "Front and rear brake cables"
                    },
                    {
                        "pageNumber": 1,
                        "key": "totalPriceExclTax",
                        "value": "100.00"
                    }
                ],
                [
                    {
                        "pageNumber": 1,
                        "key": "totalPriceInclTax",
                        "value": "30.00"
                    },
                    {
                        "pageNumber": 1,
                        "key": "unitPrice",
                        "value": "15.00"
                    },
                    {
                        "pageNumber": 1,
                        "key": "quantity",
                        "value": "2"
                    },
                    {
                        "pageNumber": 1,
                        "key": "description",
                        "value": "New set of pedal arms"
                    },
                    {
                        "pageNumber": 1,
                        "key": "totalPriceExclTax",
                        "value": "30.00"
                    }
                ],
                [
                    {
                        "pageNumber": 1,
                        "key": "totalPriceInclTax",
                        "value": "15.00"
                    },
                    {
                        "pageNumber": 1,
                        "key": "unitPrice",
                        "value": "5.00"
                    },
                    {
                        "pageNumber": 1,
                        "key": "quantity",
                        "value": "3"
                    },
                    {
                        "pageNumber": 1,
                        "key": "description",
                        "value": "Labor 3hrs"
                    },
                    {
                        "pageNumber": 1,
                        "key": "totalPriceExclTax",
                        "value": "15.00"
                    }
                ]
            ]
        }
    },
    "requestId": "da69edd3cb1d47b4a68db9303d280000",
    "currentTimeMillis": 1696859401185
}

Example of asynchronous response

{
    "code": 200,
    "message": null,
    "costTime": null,
    "data": {
        "fileId": "2310091711378393918074800",
        "recognizeStatus": "1"
    },
    "requestId": "da69edd3cb1d47b4a68db9303d280000",
    "currentTimeMillis": 1696859401185
}