Articles in this section

Using Event Extraction Models in Production

Avatar
Jason Stevens
  • Updated
Follow

Note

If the model was trained with an instance of Rosette Server using a custom profile, the same profile must be used for event extraction.

The Event Training Server (ETS) supports both training and extraction. Rosette Server communicates with ETS to perform event extraction tasks. If the production instance is separate from the training instance, the trained event model must be moved to the production server by completing the following steps:

  1. Export the Event Extraction Model

  2. Upload the Model to the Production Server

Export the Event Extraction Model

Export the trained model from the Rosette Model Training Suite.

From the Rosette Adaptation Studio UI:

  1. Open the project that trained the model you are interested in.

  2. Select Manage from the project navigation bar.

  3. From the System Status block, select Export Model.

    The trained model will download to your machine.

The model can also be downloaded through the ETS API. This requires the workspace Id (wid) for the model you want to download.

The GET /workspaces method returns a list of all workspaces in the server:

curl -X 'GET' \
  'http://<ETSSERVER>/ets/workspaces' \
  -H 'accept: application/json'

The GET /workspace/{wid}/download-model method downloads the model specified by wid (workspace Id).

curl -X 'GET' \
  'http://<ETSSERVER>/ets/workspace/<wid>/download-model' \
  -H 'accept: application/octet-stream'

where <ETSSERVER> is the name of ETS in the training environment.

Upload the Model to the Production Server

Note

The Event Training Server must be installed on the production server.

Use the ETS API to upload the model to the production server. The workspaceID is the first token after ets-model. in the downloaded file name. For example:

  • filename: ets-model.613f53723a13b6a52938f9f8-20210917_10_09_61-LE.ets-model

  • workspaceID: 613f53723a13b6a52938f9f8

Use the ets-upload-model.sh script to upload the model to the production server. Execute this script from the /ets/scripts directory on the production server.

./ets-upload-model.sh -w <workspaceID> -m <filename>

If the model already exists in the workspace, the script will ask you whether to overwrite the existing model. When asked if the model should be overwritten, respond:

  • Y (default) to replace the model in the workspace with the newer version

  • N to make no change.

Example 6. Uploading a new version of an existing model

In this example, a version of the model already exists on the server and the user replaces it with a newer version.

$ ./ets-upload-model.sh -w testMe -m ~/Downloads/ets-model.6193e-LE.ets-model
Info: ETS reachable on http://localhost:9999/ets
Info: Uploading /Users/user/Downloads/ets-model.6193e-LE.ets-model to workspace testMe on http://localhost:9999
Error: Workspace testMe exists!
Should testMe be overwritten (y/n)? y
Info: Uploading /Users/user/Downloads/ets-model.6193e-LE.ets-model to workspace testMe on http://localhost:9999
Info: SUCCESS: Uploaded /Users/user/Downloads/ets-model.6193e-LE.ets-model to http://localhost:9999/ets/workspace/testMe got HTTP 201

Calling the /events Endpoint

https://<PRODSERVER>/rest/v1/events

An event is a dynamic situation that unfolds. Rosette event extraction analyzes unstructured text and extracts event mentions. An event model is trained to extract specific types of events. To use the endpoint, you must first train a model to extract the event types you are interested in. There is no standard or default model for event extraction.

An event mention consists of a key phrase and one or more role mentions.

  • A key phrase is a word or phrase in the text that evokes the given event type.

  • Roles are entity mentions. i.e. people, places, times, and other mentions, which add detail to the key phrase. Roles have a name indicating the type of role.

As an example, let's consider a trip event:

Bob flew from Boston to Los Angeles.

The key phrase is flew. Other lemmas of flew would also be identified as key phrases: flying and flies, for example.

The roles are:

  • Bob, traveler

  • Boston, origin

  • Los Angeses, destination

The key phrases (flew) and roles (traveler, origin, Los Angelses) were all defined in advance and a model trained to extract them. The event mention would identify the role mentions: Bob, Boston, Los Angeles.

The event type for flying could have other roles defined, such as when (a date or time). Not all roles must be extracted for all event mentions. The schema, which defines the key phrases and roles defines which roles are required. If a role is required, the event will not be extracted without a role mention.

Event Schema

The event schema defines the event types you are extracting. It includes key phrases, roles, role types, and extractors.

For each key phrase and role, there is a role-type. A role type is made up of one or more extractors. Extractors are reusable components which define the rules and techniques to identify roles and key phrases.

The supported extractor types are:

  • Entity: A list of REX entity types. You can use the standard, pre-defined REX entity types or train a custom model to extract other entity types. The custom model must be loaded in Rosette Server to define an entity extractor with custom entity types.

  • Exact: a list of words or phrases. Exact will match any words on the list, whether they are identified as entity types or not. For example, you could have a list of common modes of transportation, including armored personnel carrier and specific types of tanks.

  • Morphological: A list of words. When a word is added to this list, it is immediately converted to and stored as its lemma. Words with the same lemmatization will match. For example, a morphological extractor for go will match going, went, goes, gone.This is the only extractor type valid for key phrases.

  • Semantic: A list of words or phrases. Any word whose meaning is similar to one of these words will match. For example, an extractor of meeting will match assembly, gathering, conclave. Rosette uses word vector similarity to identify similar words. While a semantic extractor can be defined by a phrase, it will only identify single words as candidate roles.

You cannot modify the schema for a trained model. You can view it through the /events/info endpoint.

GET /events/info  Returns the list of all models currently installed in the system along with the schemas used to create the models.

GET /events/info?workspaceId={wid} Returns the schema used to create the model, where wid is the workspace identifier for the particular events model.

Extracting from Multiple Event Models

The events endpoint of Rosette Server can support event extraction from multiple event models in a single call.

  • Each event extraction model is for a single language. 

  • A model is identified by a workspaceId. 

  • A plan specifies a list of event models (identified by workspaceId) to be used to extract event mentions. The models are listed by language.

Through the plan options the user can specify a list of event extraction models to be used when extracting event mentions from a document. 

If no workspaceId or plan is specified, then all events models in the Rosette Server instance are used for extraction.

Only models matching the language of the content are called. This can be explicitly set by passing the language code in the call or Rosette will identify the language. Each model is called serially. The response time will increase as additional models are added to the search. It is still faster, however, than making multiple individual calls to each event model.

For each event mention extracted, the response will include the workspaceId of the model which extracted the event mention. Each entity extracted will include the customProfileId (if any) which the extracted entity came from.

Request

Name

Type

Description

Required?

content

string

Text to process

Required

language

string

Three-letter ISO 693-3 language code

Optional

Important

Input documents for event extraction should be no larger than 4K characters.

Do you know the language of your input?

If you know the language of your input, include the three-letter language code in your call. This will speed up the response time.

Otherwise, Rosette will identify the language automatically.

While Rosette will identify the language automatically, if the language is misidentified, the correct events model will not be used. We recommend you include the language code in your call, where possible.

If no language is provided, and Rosette is unable to auto-detect it, an endpoint may provide a “Language xxx is not supported” error, where xxx indicates the language was not determined.

Option

Type

Description

Required?

workspaceId

string

The id of a single events workspace.

Optional

plan

string

A list of languages and workspaces. Allows multiple event models to be used in a single call.

Optional

Either workspaceId or plan can be provided as an option. Both cannot be used in the same call. When using plan, the workspaceId is provided within the plan.

Example 7. Single event model request

Only a single event extraction model is called.

{
  "content": "string",
  "language": "string",
  "options": {
    "workspaceId": "string"
  }

Example 8. All event models request

All event extraction models that match the language of the content string are called. Multiple event mentions may be returned, from different event models.

{
  "content": "string",
  "language": "string",
}

Example 9. Multiple event model request

Multiple event extraction models are called in a single request. Only the models where the languageCode matches the language of the content string are called. Multiple event mentions may be returned, from different event models.

{
  "content": "string",
  "language": "string",
  "options": {
    "plan": {
       "languageCode": [
         "workspaceId": "string"
        ]
    }
  }

Response

{
  "events": [
    {
      "eventType": "string",
      "mentions": [
        {
          "startOffset": number,
          "endOffset": number,
          "roles": [
            {
              "startOffset": number,
              "endOffset": number,
              "name": "string",
              "id": "string",
              "dataSpan": "string",
              "obsolete": boolean,
              "roleType": "string",
              "extractorName": "string"
            },
          ]
        }
      ],
      "confidence": number,
      "workspaceId": "string"
    }
  ]
}

Examples

Example 10. Single Event Model

Example events request when using a single events model:

{"content": "I want flights from Boston to New York",
"language": "eng",
"options": {
   "workspaceId": "multi-1"
 }

Response:

{
    "events": [
        {
            "eventType": "flight_booking_schema.flight_booking",
            "mentions": [
                {
                    "startOffset": 7,
                    "endOffset": 38,
                    "roles": [
                        {
                            "startOffset": 7,
                            "endOffset": 14,
                            "name": "key",
                            "id": "E1",
                            "dataSpan": "flights",
                            "obsolete": false,
                            "roleType": "flight_booking_schema.flight_booking_key",
                            "extractorName": "flight_booking_schema.flight-key-morphological"
                        },
                        {
                            "startOffset": 20,
                            "endOffset": 26,
                            "name": "origin",
                            "id": "T0",
                            "dataSpan": "Boston",
                            "obsolete": false,
                            "roleType": "generic_schema.location",
                            "extractorName": "generic_schema.location-entity"
                        },
                        {
                            "startOffset": 30,
                            "endOffset": 38,
                            "name": "destination",
                            "id": "T1",
                            "dataSpan": "New York",
                            "obsolete": false,
                            "roleType": "generic_schema.location",
                            "extractorName": "generic_schema.location-entity"
                        }
                    ]
                }
            ],
            "confidence": 0.93891401,
            "workspaceId": "multi-1"
        }
    ]
}

Example 11. Multiple Event Models

Example events request when using multiple events models in a single call:

{content": "I want flights from Boston to New York",
  "language": "eng",
  "options": {
  "plan": {
      "eng": ["multi-1", "multi-2","multi-3"]}
  }

Response:

{
    "events": [
        {
            "eventType": "flight_booking_schema.flight_booking",
            "mentions": [
                {
                    "startOffset": 7,
                    "endOffset": 38,
                    "roles": [
                        {
                            "startOffset": 7,
                            "endOffset": 14,
                            "name": "key",
                            "id": "E1",
                            "dataSpan": "flights",
                            "obsolete": false,
                            "roleType": "flight_booking_schema.flight_booking_key",
                            "extractorName": "flight_booking_schema.flight-key-morphological"
                        },
                        {
                            "startOffset": 20,
                            "endOffset": 26,
                            "name": "origin",
                            "id": "T0",
                            "dataSpan": "Boston",
                            "obsolete": false,
                            "roleType": "generic_schema.location",
                            "extractorName": "generic_schema.location-entity"
                        },
                        {
                            "startOffset": 30,
                            "endOffset": 38,
                            "name": "destination",
                            "id": "T1",
                            "dataSpan": "New York",
                            "obsolete": false,
                            "roleType": "generic_schema.location",
                            "extractorName": "generic_schema.location-entity"
                        }
                    ]
                }
            ],
            "confidence": 0.93891401,
            "workspaceId": "multi-1"
        },
        {
            "eventType": "flight_booking_schema.flight_booking",
            "mentions": [
                {
                    "startOffset": 7,
                    "endOffset": 38,
                    "roles": [
                        {
                            "startOffset": 7,
                            "endOffset": 14,
                            "name": "key",
                            "id": "E2",
                            "dataSpan": "flights",
                            "obsolete": false,
                            "roleType": "flight_booking_schema.flight_booking_key",
                            "extractorName": "flight_booking_schema.flight-key-morphological"
                        },
                        {
                            "startOffset": 20,
                            "endOffset": 26,
                            "name": "origin",
                            "id": "T0",
                            "dataSpan": "Boston",
                            "obsolete": false,
                            "roleType": "generic_schema.location",
                            "extractorName": "generic_schema.location-entity"
                        },
                        {
                            "startOffset": 30,
                            "endOffset": 38,
                            "name": "destination",
                            "id": "T1",
                            "dataSpan": "New York",
                            "obsolete": false,
                            "roleType": "generic_schema.location",
                            "extractorName": "generic_schema.location-entity"
                        }
                    ]
                }
            ],
            "confidence": 0.93891401,
            "workspaceId": "multi-2"
        },
        {
            "eventType": "flight_booking_schema.flight_booking",
            "mentions": [
                {
                    "startOffset": 7,
                    "endOffset": 38,
                    "roles": [
                        {
                            "startOffset": 7,
                            "endOffset": 14,
                            "name": "key",
                            "id": "E3",
                            "dataSpan": "flights",
                            "obsolete": false,
                            "roleType": "flight_booking_schema.flight_booking_key",
                            "extractorName": "flight_booking_schema.flight-key-morphological"
                        },
                        {
                            "startOffset": 20,
                            "endOffset": 26,
                            "name": "origin",
                            "id": "T0",
                            "dataSpan": "Boston",
                            "obsolete": false,
                            "roleType": "generic_schema.location",
                            "extractorName": "generic_schema.location-entity"
                        },
                        {
                            "startOffset": 30,
                            "endOffset": 38,
                            "name": "destination",
                            "id": "T1",
                            "dataSpan": "New York",
                            "obsolete": false,
                            "roleType": "generic_schema.location",
                            "extractorName": "generic_schema.location-entity"
                        }
                    ]
                }
            ],
            "confidence": 0.93891401,
            "workspaceId": "multi-3"
        }
    ]
}

Example 12. All Event Models

This request queries all loaded event models in a single call. This call uses ?output=rosette to return the full ADM output, including entities:

https://<PRODSERVER>rest/v1/events?output=rosette

{content": "I need a flight from Boston to New York today. I don't want to get arrested here.",
  "language": "eng"
}

Response (without tokens section):

{
    "version": "1.1.0",
    "data": "I need a flight from Boston to New York today. I don't want to get arrested here.",
    "attributes": {
        "sentence": {
            "type": "list",
            "itemType": "sentence",
            "items": [
                {
                    "startOffset": 0,
                    "endOffset": 47
                },
                {
                    "startOffset": 47,
                    "endOffset": 81
                }
            ]
        },
        "languageDetection": {
            "type": "languageDetection",
            "startOffset": 0,
            "endOffset": 81,
            "detectionResults": [
                {
                    "language": "eng",
                    "encoding": "UTF-16BE",
                    "script": "Latn",
                    "confidence": 0.86757723
                }
            ]
        },
        "scriptRegion": {
            "type": "list",
            "itemType": "scriptRegion",
            "items": [
                {
                    "startOffset": 0,
                    "endOffset": 81,
                    "script": "Latn"
                }
            ]
        },
        "layoutRegion": {
            "type": "list",
            "itemType": "layoutRegion",
            "items": [
                {
                    "startOffset": 0,
                    "endOffset": 81,
                    "layout": "UNSTRUCTURED"
                }
            ]
        },
        "events": {
            "type": "list",
            "itemType": "event",
            "items": [
                {
                    "eventType": "flight_booking_schema.flight_booking",
                    "mentions": [
                        {
                            "startOffset": 9,
                            "endOffset": 39,
                            "roles": [
                                {
                                    "startOffset": 9,
                                    "endOffset": 15,
                                    "name": "key",
                                    "id": "E1",
                                    "dataSpan": "flight",
                                    "obsolete": false,
                                    "roleType": "flight_booking_schema.flight_booking_key",
                                    "extractorName": "flight_booking_schema.flight-key-morphological"
                                },
                                {
                                    "startOffset": 21,
                                    "endOffset": 27,
                                    "name": "origin",
                                    "id": "Q100",
                                    "dataSpan": "Boston",
                                    "confidence": 0.20862331,
                                    "obsolete": false,
                                    "roleType": "generic_schema.location",
                                    "extractorName": "generic_schema.location-entity"
                                },
                                {
                                    "startOffset": 31,
                                    "endOffset": 39,
                                    "name": "destination",
                                    "id": "T1",
                                    "dataSpan": "New York",
                                    "obsolete": false,
                                    "roleType": "generic_schema.location",
                                    "extractorName": "generic_schema.location-entity"
                                }
                            ]
                        }
                    ],
                    "confidence": 1.0,
                    "workspaceId": "flight_booking"
                },
                {
                    "eventType": "flight_booking_schema.flight_booking",
                    "mentions": [
                        {
                            "startOffset": 9,
                            "endOffset": 39,
                            "roles": [
                                {
                                    "startOffset": 9,
                                    "endOffset": 15,
                                    "name": "key",
                                    "id": "E2",
                                    "dataSpan": "flight",
                                    "obsolete": false,
                                    "roleType": "flight_booking_schema.flight_booking_key",
                                    "extractorName": "flight_booking_schema.flight-key-morphological"
                                },
                                {
                                    "startOffset": 21,
                                    "endOffset": 27,
                                    "name": "origin",
                                    "id": "T0",
                                    "dataSpan": "Boston",
                                    "obsolete": false,
                                    "roleType": "generic_schema.location",
                                    "extractorName": "generic_schema.location-entity"
                                },
                                {
                                    "startOffset": 31,
                                    "endOffset": 39,
                                    "name": "destination",
                                    "id": "T1",
                                    "dataSpan": "New York",
                                    "obsolete": false,
                                    "roleType": "generic_schema.location",
                                    "extractorName": "generic_schema.location-entity"
                                }
                            ]
                        }
                    ],
                    "confidence": 1.0,
                    "workspaceId": "starwars"
                },
                {
                    "eventType": "law_enforcement_schema.arrest",
                    "mentions": [
                        {
                            "startOffset": 67,
                            "endOffset": 75,
                            "roles": [
                                {
                                    "startOffset": 67,
                                    "endOffset": 75,
                                    "name": "key",
                                    "id": "E3",
                                    "dataSpan": "arrested",
                                    "obsolete": false,
                                    "roleType": "law_enforcement_schema.arrest_key",
                                    "extractorName": "law_enforcement_schema.arrest-key"
                                }
                            ]
                        }
                    ],
                    "confidence": 0.91264051,
                    "workspaceId": "law_enforcement"
                },
                {
                    "eventType": "flight_booking_schema.flight_booking",
                    "mentions": [
                        {
                            "startOffset": 9,
                            "endOffset": 39,
                            "roles": [
                                {
                                    "startOffset": 9,
                                    "endOffset": 15,
                                    "name": "key",
                                    "id": "E4",
                                    "dataSpan": "flight",
                                    "obsolete": false,
                                    "roleType": "flight_booking_schema.flight_booking_key",
                                    "extractorName": "flight_booking_schema.flight-key-morphological"
                                },
                                {
                                    "startOffset": 21,
                                    "endOffset": 27,
                                    "name": "origin",
                                    "id": "Q100",
                                    "dataSpan": "Boston",
                                    "confidence": 0.20862331,
                                    "obsolete": false,
                                    "roleType": "generic_schema.location",
                                    "extractorName": "generic_schema.location-entity"
                                },
                                {
                                    "startOffset": 31,
                                    "endOffset": 39,
                                    "name": "destination",
                                    "id": "T1",
                                    "dataSpan": "New York",
                                    "obsolete": false,
                                    "roleType": "generic_schema.location",
                                    "extractorName": "generic_schema.location-entity"
                                }
                            ]
                        }
                    ],
                    "confidence": 1.0,
                    "workspaceId": "flight_booking1"
                },
                {
                    "eventType": "flight_booking_schema.flight_booking",
                    "mentions": [
                        {
                            "startOffset": 9,
                            "endOffset": 39,
                            "roles": [
                                {
                                    "startOffset": 9,
                                    "endOffset": 15,
                                    "name": "key",
                                    "id": "E5",
                                    "dataSpan": "flight",
                                    "obsolete": false,
                                    "roleType": "flight_booking_schema.flight_booking_key",
                                    "extractorName": "flight_booking_schema.flight-key-morphological"
                                },
                                {
                                    "startOffset": 21,
                                    "endOffset": 27,
                                    "name": "origin",
                                    "id": "Q100",
                                    "dataSpan": "Boston",
                                    "confidence": 0.20862331,
                                    "obsolete": false,
                                    "roleType": "generic_schema.location",
                                    "extractorName": "generic_schema.location-entity"
                                },
                                {
                                    "startOffset": 31,
                                    "endOffset": 39,
                                    "name": "destination",
                                    "id": "T1",
                                    "dataSpan": "New York",
                                    "obsolete": false,
                                    "roleType": "generic_schema.location",
                                    "extractorName": "generic_schema.location-entity"
                                }
                            ]
                        }
                    ],
                    "confidence": 1.0,
                    "workspaceId": "kt2"
                },
                {
                    "eventType": "flight_booking_schema.flight_booking",
                    "mentions": [
                        {
                            "startOffset": 9,
                            "endOffset": 39,
                            "roles": [
                                {
                                    "startOffset": 9,
                                    "endOffset": 15,
                                    "name": "key",
                                    "id": "E6",
                                    "dataSpan": "flight",
                                    "obsolete": false,
                                    "roleType": "flight_booking_schema.flight_booking_key",
                                    "extractorName": "flight_booking_schema.flight-key-morphological"
                                },
                                {
                                    "startOffset": 21,
                                    "endOffset": 27,
                                    "name": "origin",
                                    "id": "Q100",
                                    "dataSpan": "Boston",
                                    "confidence": 0.20862331,
                                    "obsolete": false,
                                    "roleType": "generic_schema.location",
                                    "extractorName": "generic_schema.location-entity"
                                },
                                {
                                    "startOffset": 31,
                                    "endOffset": 39,
                                    "name": "destination",
                                    "id": "T1",
                                    "dataSpan": "New York",
                                    "obsolete": false,
                                    "roleType": "generic_schema.location",
                                    "extractorName": "generic_schema.location-entity"
                                }
                            ]
                        }
                    ],
                    "confidence": 1.0,
                    "workspaceId": "kt1"
                }
            ]
        },
        "token": {
            ...
           
        },
        "entities": {
            "type": "list",
            "itemType": "entities",
            "items": [
                {
                    "mentions": [
                        {
                            "startOffset": 21,
                            "endOffset": 27,
                            "source": "gazetteer",
                            "subsource": "/basis/roots//rex/7.51.1.c65.0/data/gazetteer/eng/accept/gaz-LE.bin",
                            "normalized": "Boston"
                        }
                    ],
                    "headMentionIndex": 0,
                    "type": "LOCATION",
                    "entityId": "T0",
                    "entitiesCustomProfile": "starwars"
                },
                {
                    "mentions": [
                        {
                            "startOffset": 31,
                            "endOffset": 39,
                            "source": "gazetteer",
                            "subsource": "/basis/roots//rex/7.51.1.c65.0/data/gazetteer/eng/accept/gaz-LE.bin",
                            "normalized": "New York"
                        }
                    ],
                    "headMentionIndex": 0,
                    "type": "LOCATION",
                    "entityId": "T1",
                    "entitiesCustomProfile": "starwars"
                },
                {
                    "mentions": [
                        {
                            "startOffset": 21,
                            "endOffset": 27,
                            "linkingConfidence": 0.20862331,
                            "source": "gazetteer",
                            "subsource": "/basis/roots//rex/7.51.1.c65.0/data/gazetteer/eng/accept/gaz-LE.bin",
                            "normalized": "Boston"
                        }
                    ],
                    "headMentionIndex": 0,
                    "type": "LOCATION",
                    "entityId": "Q100"
                },
                {
                    "mentions": [
                        {
                            "startOffset": 31,
                            "endOffset": 39,
                            "source": "gazetteer",
                            "subsource": "/basis/roots//rex/7.51.1.c65.0/data/gazetteer/eng/accept/gaz-LE.bin",
                            "normalized": "New York"
                        }
                    ],
                    "headMentionIndex": 0,
                    "type": "LOCATION",
                    "entityId": "T1"
                }
            ]
        }
    },
    "documentMetadata": {
        "eventsModelFingerprints": [
            "{\"v\": \"3ad91641b2b3cfd5a08f735f0ba3b709d9d533ec8ebae1bbf303564398f6cf9c\", \"t\": 1633468622.8697586}",
            "{\"v\": \"d25cf8b3ffa15f06c26e47970b4d1955f4c12619dbf710ff0221d45d8d29f0c7\", \"t\": 1633638752.92538}",
            "{\"v\": \"be886861e88855818de2b7e98148cc0f405fcc089da8ef3c997e21a1237ae61d\", \"t\": 1633468557.6076355}",
            "{\"v\": \"3ad91641b2b3cfd5a08f735f0ba3b709d9d533ec8ebae1bbf303564398f6cf9c\", \"t\": 1633468622.8697586}",
            "{\"v\": \"3ad91641b2b3cfd5a08f735f0ba3b709d9d533ec8ebae1bbf303564398f6cf9c\", \"t\": 1633468622.8697586}",
            "{\"v\": \"3ad91641b2b3cfd5a08f735f0ba3b709d9d533ec8ebae1bbf303564398f6cf9c\", \"t\": 1633468622.8697586}"
        ],
        "processedBy": [
            "language-identification@127.0.0.1",
            "event-extractor@127.0.0.1"
        ],
        "eventsModels": [
            "flight_booking",
            "starwars",
            "law_enforcement",
            "flight_booking1",
            "kt2",
            "kt1"
        ]
    }
}

Error Handling/Invalid Requests

  • The language parameter is optional. If not provided, Rosette Server will automatically identify the language of the content provided. If there is no model listed for the identified language, then a 400 Bad Request will be returned.

  • If no language is provided, and Rosette is unable to auto-detect it, the endpoint may provide a “Language xxx is not supported” error, where xxx indicates the language was not determined.

  • If the model identified by workspaceId does not exist on the Server, a 400 will be returned.

  • If any of the workspaceIds listed in the target plan do not exist on the servicing ETS, a 400 will be returned.

  • If any of the workspaces were trained with a custom entity model and any of the custom entity models are not deployed to Rosette Server, a 400 Bad Request will be returned.

  • If both workspaceId and plan options are provided in the same request, a 400 Bad Request will be returned.

Related articles

Comments

0 comments

Article is closed for comments.





Powered by Zendesk