Request Syntax Request Parameters Response Syntax Response Elements Errors Examples See Also

DetectEntities

Detects named entities in input text when you use the pre-trained model. Detects custom entities if you have a custom entity recognition model.

When detecting named entities using the pre-trained model, use plain text as the input. For more information about named entities, see Entities in the Comprehend Developer Guide.

When you use a custom entity recognition model, you can input plain text or you can upload a single-page input document (text, PDF, Word, or image).

If the system detects errors while processing a page in the input document, the API response includes an entry in Errors for each error.

If the system detects a document-level error in your input document, the API returns an InvalidRequestException error response. For details about this exception, see Errors in semi-structured documents in the Comprehend Developer Guide.

Request Syntax


{
   "Bytes": blob,
   "DocumentReaderConfig": { 
      "DocumentReadAction": "string",
      "DocumentReadMode": "string",
      "FeatureTypes": [ "string" ]
   },
   "EndpointArn": "string",
   "LanguageCode": "string",
   "Text": "string"
}

Request Parameters

For information about the parameters that are common to all actions, see Common Parameters.

The request accepts the following data in JSON format.

Bytes

This field applies only when you use a custom entity recognition model that was trained with PDF annotations. For other cases, enter your text input in the Text field.

Use the Bytes parameter to input a text, PDF, Word or image file. Using a plain-text file in the Bytes parameter is equivelent to using the Text parameter (the Entities field in the response is identical).

You can also use the Bytes parameter to input an Amazon Textract DetectDocumentText or AnalyzeDocument output file.

Provide the input document as a sequence of base64-encoded bytes. If your code uses an AWS SDK to detect entities, the SDK may encode the document file bytes for you.

The maximum length of this field depends on the input document type. For details, see Inputs for real-time custom analysis in the Comprehend Developer Guide.

If you use the Bytes parameter, do not use the Text parameter.

Type: Base64-encoded binary data object

Length Constraints: Minimum length of 1.

Required: No

DocumentReaderConfig

Provides configuration parameters to override the default actions for extracting text from PDF documents and image files.

Type: DocumentReaderConfig object

Required: No

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.

For information about endpoints, see Managing endpoints.

Type: String

Length Constraints: Maximum length of 256.

Pattern: arn:aws(-[^:]+)?:comprehend:[a-zA-Z0-9-]*:[0-9]{12}:entity-recognizer-endpoint/[a-zA-Z0-9](-*[a-zA-Z0-9])*

Required: No

LanguageCode

The language of the input documents. You can specify any of the primary languages supported by Amazon Comprehend. 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.

All input documents must be in the same language.

Type: String

Valid Values: en | es | fr | de | it | pt | ar | hi | ja | ko | zh | zh-TW

Required: No

Text

A UTF-8 text string. The maximum string size is 100 KB. If you enter text using this parameter, do not use the Bytes parameter.

Type: String

Length Constraints: Minimum length of 1.

Required: No

Response Syntax


{
   "Blocks": [ 
      { 
         "BlockType": "string",
         "Geometry": { 
            "BoundingBox": { 
               "Height": number,
               "Left": number,
               "Top": number,
               "Width": number
            },
            "Polygon": [ 
               { 
                  "X": number,
                  "Y": number
               }
            ]
         },
         "Id": "string",
         "Page": number,
         "Relationships": [ 
            { 
               "Ids": [ "string" ],
               "Type": "string"
            }
         ],
         "Text": "string"
      }
   ],
   "DocumentMetadata": { 
      "ExtractedCharacters": [ 
         { 
            "Count": number,
            "Page": number
         }
      ],
      "Pages": number
   },
   "DocumentType": [ 
      { 
         "Page": number,
         "Type": "string"
      }
   ],
   "Entities": [ 
      { 
         "BeginOffset": number,
         "BlockReferences": [ 
            { 
               "BeginOffset": number,
               "BlockId": "string",
               "ChildBlocks": [ 
                  { 
                     "BeginOffset": number,
                     "ChildBlockId": "string",
                     "EndOffset": number
                  }
               ],
               "EndOffset": number
            }
         ],
         "EndOffset": number,
         "Score": number,
         "Text": "string",
         "Type": "string"
      }
   ],
   "Errors": [ 
      { 
         "ErrorCode": "string",
         "ErrorMessage": "string",
         "Page": number
      }
   ]
}

Response Elements

If the action is successful, the service sends back an HTTP 200 response.

The following data is returned in JSON format by the service.

Blocks

Information about each block of text in the input document. Blocks are nested. A page block contains a block for each line of text, which contains a block for each word.

The Block content for a Word input document does not include a Geometry field.

The Block field is not present in the response for plain-text inputs.

Type: Array of Block objects

DocumentMetadata

Information about the document, discovered during text extraction. This field is present in the response only if your request used the Byte parameter.

Type: DocumentMetadata object

DocumentType

The document type for each page in the input document. This field is present in the response only if your request used the Byte parameter.

Type: Array of DocumentTypeListItem objects

Entities

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 Entities in the Comprehend Developer Guide.

Type: Array of Entity objects

Errors

Page-level errors that the system detected while processing the input document. The field is empty if the system encountered no errors.

Type: Array of ErrorsListItem objects

Errors

For information about the errors that are common to all actions, see Common Errors.

InternalServerException

An internal server error occurred. Retry your request.

HTTP Status Code: 500

InvalidRequestException

The request is invalid.

HTTP Status Code: 400

ResourceUnavailableException

The specified resource is not available. Check the resource and try your request again.

HTTP Status Code: 400

TextSizeLimitExceededException

The size of the input text exceeds the limit. Use a smaller document.

HTTP Status Code: 400

UnsupportedLanguageException

Amazon Comprehend can't process the language of the input text. For a list of supported languages, Supported languages in the Comprehend Developer Guide.

HTTP Status Code: 400

Examples

Detect entities

If the input text is "Bob ordered two sandwiches and three ice cream cones today from a store in Seattle.", the operation returns the following:



    {
    "Entities": [
        {
            "Text": "Bob",
            "Score": 1.0,
            "Type": "PERSON",
            "BeginOffset": 0,
            "EndOffset": 3
        },
        {
            "Text": "two",
            "Score": 1.0,
            "Type": "QUANTITY",
            "BeginOffset": 12,
            "EndOffset": 15
        },
        {
            "Text": "three",
            "Score": 1.0,
            "Type": "QUANTITY",
            "BeginOffset": 32,
            "EndOffset": 37
        },
        {
            "Text": "Today",
            "Score": 1.0,
            "Type": "DATE",
            "BeginOffset": 54,
            "EndOffset": 59
        },
        {
            "Text": "Seattle",
            "Score": 1.0,
            "Type": "LOCATION",
            "BeginOffset": 76,
            "EndOffset": 83
        }
    ],
}