Amazon Comprehend

{'EndpointArn': 'string'}

Inspects text for named entities, and returns information about them. For more information, about named entities, see how-entities.

See also: AWS API Documentation

Request Syntax

client.detect_entities(
    Text='string',
    LanguageCode='en'|'es'|'fr'|'de'|'it'|'pt'|'ar'|'hi'|'ja'|'ko'|'zh'|'zh-TW',
    EndpointArn='string'
)

type Text

string

param Text

[REQUIRED]

A UTF-8 text string. Each string must contain fewer that 5,000 bytes of UTF-8 encoded characters.

type LanguageCode

string

param LanguageCode

The language of the input documents. You can specify any of the primary languages supported by Amazon Comprehend. All documents must be in the same language.

If your request includes the endpoint for a custom entity recognition model, Amazon Comprehend uses the language of your custom model, and it ignores any language code that you specify here.

type EndpointArn

string

param EndpointArn

The Amazon Resource Name of an endpoint that is associated with a custom entity recognition model. Provide an endpoint if you want to detect entities by using your own custom model instead of the default model that is used by Amazon Comprehend.

If you specify an endpoint, Amazon Comprehend uses the language of your custom model, and it ignores any language code that you provide in your request.

rtype

dict

returns

Response Syntax

{
    'Entities': [
        {
            'Score': ...,
            'Type': 'PERSON'|'LOCATION'|'ORGANIZATION'|'COMMERCIAL_ITEM'|'EVENT'|'DATE'|'QUANTITY'|'TITLE'|'OTHER',
            'Text': 'string',
            'BeginOffset': 123,
            'EndOffset': 123
        },
    ]
}

Response Structure

• (dict) --

  • Entities (list) --

    A collection of entities identified in the input text. For each entity, the response provides the entity text, entity type, where the entity text begins and ends, and the level of confidence that Amazon Comprehend has in the detection.

    If your request uses a custom entity recognition model, Amazon Comprehend detects the entities that the model is trained to recognize. Otherwise, it detects the default entity types. For a list of default entity types, see how-entities.

    • (dict) --

      Provides information about an entity.

      • Score (float) --

        The level of confidence that Amazon Comprehend has in the accuracy of the detection.

      • Type (string) --

        The entity's type.

      • Text (string) --

        The text of the entity.

      • BeginOffset (integer) --

        A character offset in the input text that shows where the entity begins (the first character is at position 0). The offset returns the position of each UTF-8 code point in the string. A code point is the abstract character from a particular graphical representation. For example, a multi-byte UTF-8 character maps to a single code point.

      • EndOffset (integer) --

        A character offset in the input text that shows where the entity ends. The offset returns the position of each UTF-8 code point in the string. A code point is the abstract character from a particular graphical representation. For example, a multi-byte UTF-8 character maps to a single code point.