Versions Compared

Old Version 1

changes.mady.by.user Technische Redaktion

Saved on

compared with

New Version Current

changes.mady.by.user Technische Redaktion

Saved on

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.


Page Properties
hiddentrue
idrLANGDONE

Product Version
Report Note
Assignee

Resources & Remarks


Modification History

NameDateProduct VersionAction
Antje15 JUL 20212021 Autumncreated
Antje25 NOV 20222022 Winterupdate endpoint url



As of Versionproduct version 2021 Autumn | component version 0.32022 Winter
Request MethodGET
Response FormatJSON
Description


Excerpt

To obtain Retrieves a metadata extraction predictions prediction for a single document, send the request with objectId in the path. identified by its the binary content file of a single object identified by its objectId.


The

Predict API will return a JSON structure indicating all classes the model is trained to recognize along with the probability

property IDs will be returned according to the inference schema along with their probability in percentage (level of confidence)

for each of those classes

in the properties section of the JSON response body. The properties page and boundingBox (coordinates on the page) describe the location within the binary content file where the decisive information was identified.

The response JSON further contains the predictionId that should be used for giving feedback to the

Predict

PREDICT-API on the quality of received predictions, as well as the system:objectId that was specified in the request URL.

Request Header

Content-Type: application/json

X-ID-TENANT-NAME: tenant_name

Request Example
/predict-api/predictapi/extraction/da20c2fb-8071-45e9-b4bf-2af376cdf9b6
Result Example


Code Block
languageymltitleresponse body
{
    "predictions": [{
        "properties": {
            "appAIInvoice:aiiCompanyName": [
                {
                    "value": "Lufthansa",
                    "probability": 99.24,
                    "boundingBox": [
                        403,
                        729,
                        61,
                        14
                    ],
                    "page": 0
                },
                {
                    "value": "AKG Thermotechnik International GmbH & Co.KG",
                    "probability": 93.24,
                    "boundingBox": [
                        413,
                        224,
                        93,
                        14
                    ],
                    "page": 1
                }
            ],
            "appAIInvoice:aiiIssueDateTime": [
                {
                    "value": "2018-01-26T15:21:170Z",
                    "probability": 85.12,
                    "boundingBox": [
                        213,
                        234,
                        76,
                        14
                    ],
                    "page": 1
                }
            ]
        },
        "system:objectId": "da20c2fb-8071-45e9-b4bf-2af376cdf9b6",
        "predictionId": 188
    }]
}

...