Retrieve - Amazon Kendra API Reference
Request SyntaxRequest ParametersResponse SyntaxResponse ElementsErrorsSee Also

Retrieve

Retrieves relevant passages or text excerpts given an input query.

This API is similar to the Query API. However, by default, the Query API only returns excerpt passages of up to 100 token words. With the Retrieve API, you can retrieve longer passages of up to 200 token words and up to 100 semantically relevant passages. This doesn't include question-answer or FAQ type responses from your index. The passages are text excerpts that can be semantically extracted from multiple documents and multiple parts of the same document. If in extreme cases your documents produce zero passages using the Retrieve API, you can alternatively use the Query API and its types of responses.

You can also do the following:

  • Override boosting at the index level

  • Filter based on document fields or attributes

  • Filter based on the user or their group access to documents

  • View the confidence score bucket for a retrieved passage result. The confidence bucket provides a relative ranking that indicates how confident Amazon Kendra is that the response is relevant to the query.

    Note

    Confidence score buckets are currently available only for English.

You can also include certain fields in the response that might provide useful additional information.

The Retrieve API shares the number of query capacity units that you set for your index. For more information on what's included in a single capacity unit and the default base capacity for an index, see Adjusting capacity.

Request Syntax

{
   "AttributeFilter": { 
      "AndAllFilters": [ 
         "AttributeFilter"
      ],
      "ContainsAll": { 
         "Key": "string",
         "Value": { 
            "DateValue": number,
            "LongValue": number,
            "StringListValue": [ "string" ],
            "StringValue": "string"
         }
      },
      "ContainsAny": { 
         "Key": "string",
         "Value": { 
            "DateValue": number,
            "LongValue": number,
            "StringListValue": [ "string" ],
            "StringValue": "string"
         }
      },
      "EqualsTo": { 
         "Key": "string",
         "Value": { 
            "DateValue": number,
            "LongValue": number,
            "StringListValue": [ "string" ],
            "StringValue": "string"
         }
      },
      "GreaterThan": { 
         "Key": "string",
         "Value": { 
            "DateValue": number,
            "LongValue": number,
            "StringListValue": [ "string" ],
            "StringValue": "string"
         }
      },
      "GreaterThanOrEquals": { 
         "Key": "string",
         "Value": { 
            "DateValue": number,
            "LongValue": number,
            "StringListValue": [ "string" ],
            "StringValue": "string"
         }
      },
      "LessThan": { 
         "Key": "string",
         "Value": { 
            "DateValue": number,
            "LongValue": number,
            "StringListValue": [ "string" ],
            "StringValue": "string"
         }
      },
      "LessThanOrEquals": { 
         "Key": "string",
         "Value": { 
            "DateValue": number,
            "LongValue": number,
            "StringListValue": [ "string" ],
            "StringValue": "string"
         }
      },
      "NotFilter": "AttributeFilter",
      "OrAllFilters": [ 
         "AttributeFilter"
      ]
   },
   "DocumentRelevanceOverrideConfigurations": [ 
      { 
         "Name": "string",
         "Relevance": { 
            "Duration": "string",
            "Freshness": boolean,
            "Importance": number,
            "RankOrder": "string",
            "ValueImportanceMap": { 
               "string" : number 
            }
         }
      }
   ],
   "IndexId": "string",
   "PageNumber": number,
   "PageSize": number,
   "QueryText": "string",
   "RequestedDocumentAttributes": [ "string" ],
   "UserContext": { 
      "DataSourceGroups": [ 
         { 
            "DataSourceId": "string",
            "GroupId": "string"
         }
      ],
      "Groups": [ "string" ],
      "Token": "string",
      "UserId": "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.

AttributeFilter

Filters search results by document fields/attributes. You can only provide one attribute filter; however, the AndAllFilters, NotFilter, and OrAllFilters parameters contain a list of other filters.

The AttributeFilter parameter means you can create a set of filtering rules that a document must satisfy to be included in the query results.

Type: AttributeFilter object

Required: No

DocumentRelevanceOverrideConfigurations

Overrides relevance tuning configurations of fields/attributes set at the index level.

If you use this API to override the relevance tuning configured at the index level, but there is no relevance tuning configured at the index level, then Amazon Kendra does not apply any relevance tuning.

If there is relevance tuning configured for fields at the index level, and you use this API to override only some of these fields, then for the fields you did not override, the importance is set to 1.

Type: Array of DocumentRelevanceConfiguration objects

Array Members: Minimum number of 0 items. Maximum number of 500 items.

Required: No

IndexId

The identifier of the index to retrieve relevant passages for the search.

Type: String

Length Constraints: Fixed length of 36.

Pattern: [a-zA-Z0-9][a-zA-Z0-9-]*

Required: Yes

PageNumber

Retrieved relevant passages are returned in pages the size of the PageSize parameter. By default, Amazon Kendra returns the first page of results. Use this parameter to get result pages after the first one.

Type: Integer

Required: No

PageSize

Sets the number of retrieved relevant passages that are returned in each page of results. The default page size is 10. The maximum number of results returned is 100. If you ask for more than 100 results, only 100 are returned.

Type: Integer

Required: No

QueryText

The input query text to retrieve relevant passages for the search. Amazon Kendra truncates queries at 30 token words, which excludes punctuation and stop words. Truncation still applies if you use Boolean or more advanced, complex queries. For example, Timeoff AND October AND Category:HR is counted as 3 tokens: timeoff, october, hr. For more information, see Searching with advanced query syntax in the Amazon Kendra Developer Guide.

Type: String

Required: Yes

RequestedDocumentAttributes

A list of document fields/attributes to include in the response. You can limit the response to include certain document fields. By default, all document fields are included in the response.

Type: Array of strings

Array Members: Minimum number of 1 item. Maximum number of 100 items.

Length Constraints: Minimum length of 1. Maximum length of 200.

Pattern: [a-zA-Z0-9_][a-zA-Z0-9_-]*

Required: No

UserContext

The user context token or user and group information.

Type: UserContext object

Required: No

Response Syntax

{
   "QueryId": "string",
   "ResultItems": [ 
      { 
         "Content": "string",
         "DocumentAttributes": [ 
            { 
               "Key": "string",
               "Value": { 
                  "DateValue": number,
                  "LongValue": number,
                  "StringListValue": [ "string" ],
                  "StringValue": "string"
               }
            }
         ],
         "DocumentId": "string",
         "DocumentTitle": "string",
         "DocumentURI": "string",
         "Id": "string",
         "ScoreAttributes": { 
            "ScoreConfidence": "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.

QueryId

The identifier of query used for the search. You also use QueryId to identify the search when using the Submitfeedback API.

Type: String

Length Constraints: Minimum length of 1. Maximum length of 36.

Pattern: [a-zA-Z0-9][a-zA-Z0-9-]*

ResultItems

The results of the retrieved relevant passages for the search.

Type: Array of RetrieveResultItem objects

Errors

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

AccessDeniedException

You don't have sufficient access to perform this action. Please ensure you have the required permission policies and user accounts and try again.

HTTP Status Code: 400

ConflictException

A conflict occurred with the request. Please fix any inconsistences with your resources and try again.

HTTP Status Code: 400

InternalServerException

An issue occurred with the internal server used for your Amazon Kendra service. Please wait a few minutes and try again, or contact Support for help.

HTTP Status Code: 500

ResourceNotFoundException

The resource you want to use doesn’t exist. Please check you have provided the correct resource and try again.

HTTP Status Code: 400

ServiceQuotaExceededException

You have exceeded the set limits for your Amazon Kendra service. Please see Quotas for more information, or contact Support to inquire about an increase of limits.

HTTP Status Code: 400

ThrottlingException

The request was denied due to request throttling. Please reduce the number of requests and try again.

HTTP Status Code: 400

ValidationException

The input fails to satisfy the constraints set by the Amazon Kendra service. Please provide the correct input and try again.

HTTP Status Code: 400

See Also

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