Query

kendra_query

R Documentation

Searches an index given an input query

Description

Searches an index given an input query.

If you are working with large language models (LLMs) or implementing retrieval augmented generation (RAG) systems, you can use Amazon Kendra's retrieve API, which can return longer semantically relevant passages. We recommend using the retrieve API instead of filing a service limit increase to increase the query API document excerpt length.

You can configure boosting or relevance tuning at the query level to override boosting at the index level, filter based on document fields/attributes and faceted search, and filter based on the user or their group access to documents. You can also include certain fields in the response that might provide useful additional information.

A query response contains three types of results.

• Relevant suggested answers. The answers can be either a text excerpt or table excerpt. The answer can be highlighted in the excerpt.

• Matching FAQs or questions-answer from your FAQ file.

• Relevant documents. This result type includes an excerpt of the document with the document title. The searched terms can be highlighted in the excerpt.

You can specify that the query return only one type of result using the QueryResultTypeFilter parameter. Each query returns the 100 most relevant results. If you filter result type to only question-answers, a maximum of four results are returned. If you filter result type to only answers, a maximum of three results are returned.

Usage

kendra_query(IndexId, QueryText, AttributeFilter, Facets,
  RequestedDocumentAttributes, QueryResultTypeFilter,
  DocumentRelevanceOverrideConfigurations, PageNumber, PageSize,
  SortingConfiguration, SortingConfigurations, UserContext, VisitorId,
  SpellCorrectionConfiguration, CollapseConfiguration)

Arguments

IndexId

[required] The identifier of the index for the search.

QueryText

The input query text 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.

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.

Facets

An array of documents fields/attributes for faceted search. Amazon Kendra returns a count for each field key specified. This helps your users narrow their search.

RequestedDocumentAttributes

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

QueryResultTypeFilter

Sets the type of query result or response. Only results for the specified type are returned.

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.

PageNumber

Query results 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.

PageSize

Sets the number of results 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.

SortingConfiguration

Provides information that determines how the results of the query are sorted. You can set the field that Amazon Kendra should sort the results on, and specify whether the results should be sorted in ascending or descending order. In the case of ties in sorting the results, the results are sorted by relevance.

If you don't provide sorting configuration, the results are sorted by the relevance that Amazon Kendra determines for the result.

SortingConfigurations

Provides configuration information to determine how the results of a query are sorted.

You can set upto 3 fields that Amazon Kendra should sort the results on, and specify whether the results should be sorted in ascending or descending order. The sort field quota can be increased.

If you don't provide a sorting configuration, the results are sorted by the relevance that Amazon Kendra determines for the result. In the case of ties in sorting the results, the results are sorted by relevance.

UserContext

The user context token or user and group information.

VisitorId

Provides an identifier for a specific user. The VisitorId should be a unique identifier, such as a GUID. Don't use personally identifiable information, such as the user's email address, as the VisitorId.

SpellCorrectionConfiguration

Enables suggested spell corrections for queries.

CollapseConfiguration

Provides configuration to determine how to group results by document attribute value, and how to display them (collapsed or expanded) under a designated primary document for each group.

Value

A list with the following syntax:

list(
  QueryId = "string",
  ResultItems = list(
    list(
      Id = "string",
      Type = "DOCUMENT"|"QUESTION_ANSWER"|"ANSWER",
      Format = "TABLE"|"TEXT",
      AdditionalAttributes = list(
        list(
          Key = "string",
          ValueType = "TEXT_WITH_HIGHLIGHTS_VALUE",
          Value = list(
            TextWithHighlightsValue = list(
              Text = "string",
              Highlights = list(
                list(
                  BeginOffset = 123,
                  EndOffset = 123,
                  TopAnswer = TRUE|FALSE,
                  Type = "STANDARD"|"THESAURUS_SYNONYM"
                )
              )
            )
          )
        )
      ),
      DocumentId = "string",
      DocumentTitle = list(
        Text = "string",
        Highlights = list(
          list(
            BeginOffset = 123,
            EndOffset = 123,
            TopAnswer = TRUE|FALSE,
            Type = "STANDARD"|"THESAURUS_SYNONYM"
          )
        )
      ),
      DocumentExcerpt = list(
        Text = "string",
        Highlights = list(
          list(
            BeginOffset = 123,
            EndOffset = 123,
            TopAnswer = TRUE|FALSE,
            Type = "STANDARD"|"THESAURUS_SYNONYM"
          )
        )
      ),
      DocumentURI = "string",
      DocumentAttributes = list(
        list(
          Key = "string",
          Value = list(
            StringValue = "string",
            StringListValue = list(
              "string"
            ),
            LongValue = 123,
            DateValue = as.POSIXct(
              "2015-01-01"
            )
          )
        )
      ),
      ScoreAttributes = list(
        ScoreConfidence = "VERY_HIGH"|"HIGH"|"MEDIUM"|"LOW"|"NOT_AVAILABLE"
      ),
      FeedbackToken = "string",
      TableExcerpt = list(
        Rows = list(
          list(
            Cells = list(
              list(
                Value = "string",
                TopAnswer = TRUE|FALSE,
                Highlighted = TRUE|FALSE,
                Header = TRUE|FALSE
              )
            )
          )
        ),
        TotalNumberOfRows = 123
      ),
      CollapsedResultDetail = list(
        DocumentAttribute = list(
          Key = "string",
          Value = list(
            StringValue = "string",
            StringListValue = list(
              "string"
            ),
            LongValue = 123,
            DateValue = as.POSIXct(
              "2015-01-01"
            )
          )
        ),
        ExpandedResults = list(
          list(
            Id = "string",
            DocumentId = "string",
            DocumentTitle = list(
              Text = "string",
              Highlights = list(
                list(
                  BeginOffset = 123,
                  EndOffset = 123,
                  TopAnswer = TRUE|FALSE,
                  Type = "STANDARD"|"THESAURUS_SYNONYM"
                )
              )
            ),
            DocumentExcerpt = list(
              Text = "string",
              Highlights = list(
                list(
                  BeginOffset = 123,
                  EndOffset = 123,
                  TopAnswer = TRUE|FALSE,
                  Type = "STANDARD"|"THESAURUS_SYNONYM"
                )
              )
            ),
            DocumentURI = "string",
            DocumentAttributes = list(
              list(
                Key = "string",
                Value = list(
                  StringValue = "string",
                  StringListValue = list(
                    "string"
                  ),
                  LongValue = 123,
                  DateValue = as.POSIXct(
                    "2015-01-01"
                  )
                )
              )
            )
          )
        )
      )
    )
  ),
  FacetResults = list(
    list(
      DocumentAttributeKey = "string",
      DocumentAttributeValueType = "STRING_VALUE"|"STRING_LIST_VALUE"|"LONG_VALUE"|"DATE_VALUE",
      DocumentAttributeValueCountPairs = list(
        list(
          DocumentAttributeValue = list(
            StringValue = "string",
            StringListValue = list(
              "string"
            ),
            LongValue = 123,
            DateValue = as.POSIXct(
              "2015-01-01"
            )
          ),
          Count = 123,
          FacetResults = list()
        )
      )
    )
  ),
  TotalNumberOfResults = 123,
  Warnings = list(
    list(
      Message = "string",
      Code = "QUERY_LANGUAGE_INVALID_SYNTAX"
    )
  ),
  SpellCorrectedQueries = list(
    list(
      SuggestedQueryText = "string",
      Corrections = list(
        list(
          BeginOffset = 123,
          EndOffset = 123,
          Term = "string",
          CorrectedTerm = "string"
        )
      )
    )
  ),
  FeaturedResultsItems = list(
    list(
      Id = "string",
      Type = "DOCUMENT"|"QUESTION_ANSWER"|"ANSWER",
      AdditionalAttributes = list(
        list(
          Key = "string",
          ValueType = "TEXT_WITH_HIGHLIGHTS_VALUE",
          Value = list(
            TextWithHighlightsValue = list(
              Text = "string",
              Highlights = list(
                list(
                  BeginOffset = 123,
                  EndOffset = 123,
                  TopAnswer = TRUE|FALSE,
                  Type = "STANDARD"|"THESAURUS_SYNONYM"
                )
              )
            )
          )
        )
      ),
      DocumentId = "string",
      DocumentTitle = list(
        Text = "string",
        Highlights = list(
          list(
            BeginOffset = 123,
            EndOffset = 123,
            TopAnswer = TRUE|FALSE,
            Type = "STANDARD"|"THESAURUS_SYNONYM"
          )
        )
      ),
      DocumentExcerpt = list(
        Text = "string",
        Highlights = list(
          list(
            BeginOffset = 123,
            EndOffset = 123,
            TopAnswer = TRUE|FALSE,
            Type = "STANDARD"|"THESAURUS_SYNONYM"
          )
        )
      ),
      DocumentURI = "string",
      DocumentAttributes = list(
        list(
          Key = "string",
          Value = list(
            StringValue = "string",
            StringListValue = list(
              "string"
            ),
            LongValue = 123,
            DateValue = as.POSIXct(
              "2015-01-01"
            )
          )
        )
      ),
      FeedbackToken = "string"
    )
  )
)

Request syntax

svc$query(
  IndexId = "string",
  QueryText = "string",
  AttributeFilter = list(
    AndAllFilters = list(
      list()
    ),
    OrAllFilters = list(
      list()
    ),
    NotFilter = list(),
    EqualsTo = list(
      Key = "string",
      Value = list(
        StringValue = "string",
        StringListValue = list(
          "string"
        ),
        LongValue = 123,
        DateValue = as.POSIXct(
          "2015-01-01"
        )
      )
    ),
    ContainsAll = list(
      Key = "string",
      Value = list(
        StringValue = "string",
        StringListValue = list(
          "string"
        ),
        LongValue = 123,
        DateValue = as.POSIXct(
          "2015-01-01"
        )
      )
    ),
    ContainsAny = list(
      Key = "string",
      Value = list(
        StringValue = "string",
        StringListValue = list(
          "string"
        ),
        LongValue = 123,
        DateValue = as.POSIXct(
          "2015-01-01"
        )
      )
    ),
    GreaterThan = list(
      Key = "string",
      Value = list(
        StringValue = "string",
        StringListValue = list(
          "string"
        ),
        LongValue = 123,
        DateValue = as.POSIXct(
          "2015-01-01"
        )
      )
    ),
    GreaterThanOrEquals = list(
      Key = "string",
      Value = list(
        StringValue = "string",
        StringListValue = list(
          "string"
        ),
        LongValue = 123,
        DateValue = as.POSIXct(
          "2015-01-01"
        )
      )
    ),
    LessThan = list(
      Key = "string",
      Value = list(
        StringValue = "string",
        StringListValue = list(
          "string"
        ),
        LongValue = 123,
        DateValue = as.POSIXct(
          "2015-01-01"
        )
      )
    ),
    LessThanOrEquals = list(
      Key = "string",
      Value = list(
        StringValue = "string",
        StringListValue = list(
          "string"
        ),
        LongValue = 123,
        DateValue = as.POSIXct(
          "2015-01-01"
        )
      )
    )
  ),
  Facets = list(
    list(
      DocumentAttributeKey = "string",
      Facets = list(),
      MaxResults = 123
    )
  ),
  RequestedDocumentAttributes = list(
    "string"
  ),
  QueryResultTypeFilter = "DOCUMENT"|"QUESTION_ANSWER"|"ANSWER",
  DocumentRelevanceOverrideConfigurations = list(
    list(
      Name = "string",
      Relevance = list(
        Freshness = TRUE|FALSE,
        Importance = 123,
        Duration = "string",
        RankOrder = "ASCENDING"|"DESCENDING",
        ValueImportanceMap = list(
          123
        )
      )
    )
  ),
  PageNumber = 123,
  PageSize = 123,
  SortingConfiguration = list(
    DocumentAttributeKey = "string",
    SortOrder = "DESC"|"ASC"
  ),
  SortingConfigurations = list(
    list(
      DocumentAttributeKey = "string",
      SortOrder = "DESC"|"ASC"
    )
  ),
  UserContext = list(
    Token = "string",
    UserId = "string",
    Groups = list(
      "string"
    ),
    DataSourceGroups = list(
      list(
        GroupId = "string",
        DataSourceId = "string"
      )
    )
  ),
  VisitorId = "string",
  SpellCorrectionConfiguration = list(
    IncludeQuerySpellCheckSuggestions = TRUE|FALSE
  ),
  CollapseConfiguration = list(
    DocumentAttributeKey = "string",
    SortingConfigurations = list(
      list(
        DocumentAttributeKey = "string",
        SortOrder = "DESC"|"ASC"
      )
    ),
    MissingAttributeKeyStrategy = "IGNORE"|"COLLAPSE"|"EXPAND",
    Expand = TRUE|FALSE,
    ExpandConfiguration = list(
      MaxResultItemsToExpand = 123,
      MaxExpandedResultsPerItem = 123
    )
  )
)