DetectKeyPhrases - Amazon Comprehend API Reference


Detects the key noun phrases found in the text.

Request Syntax

{ "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.


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.

Type: String

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

Required: Yes


A UTF-8 text string. The string must contain less than 100 KB of UTF-8 encoded characters.

Type: String

Length Constraints: Minimum length of 1.

Required: Yes

Response Syntax

{ "KeyPhrases": [ { "BeginOffset": number, "EndOffset": number, "Score": number, "Text": "string" } ] }

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.


A collection of key phrases that Amazon Comprehend identified in the input text. For each key phrase, the response provides the text of the key phrase, where the key phrase begins and ends, and the level of confidence that Amazon Comprehend has in the accuracy of the detection.

Type: Array of KeyPhrase objects


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


An internal server error occurred. Retry your request.

HTTP Status Code: 500


The request is invalid.

HTTP Status Code: 400


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

HTTP Status Code: 400


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


Detect phrases

If the input text is "Bob lives in Seattle. He is a software engineer at Amazon.", the API returns the following:

{ "KeyPhrases": [ { "Text": "Bob", "Score": 1.0, "BeginOffset": 0, "EndOffset": 3 }, { "Text": "Seattle", "Score": 1.0, "BeginOffset": 13, "EndOffset": 20 }, { "Text": "a software engineer", "Score": 1.0, "BeginOffset": 28, "EndOffset": 39 }, { "Text": "Amazon", "Score": 1.0, "BeginOffset": 43, "EndOffset": 49 } ] }}

See Also

For more information about using this API in one of the language-specific AWS SDKs, see the following: