Provides a relative ranking that indicates how confident Amazon Kendra is that the * response is relevant to the query.
* @public */ export interface ScoreAttributes { /** *A relative ranking for how relevant the response is to the query.
* @public */ ScoreConfidence?: ScoreConfidence | undefined; } /** *Provides information about a table cell in a table excerpt.
* @public */ export interface TableCell { /** *The actual value or content within a table cell. A table cell could contain a date * value of a year, or a string value of text, for example.
* @public */ Value?: string | undefined; /** *
* TRUE if the response of the table cell is the top answer. This is the
* cell value or content with the highest confidence score or is the most relevant to the
* query.
* TRUE means that the table cell has a high enough confidence and is
* relevant to the query, so the value or content should be highlighted.
* TRUE means that the table cell should be treated as a header.
Information about a row in a table excerpt.
* @public */ export interface TableRow { /** *A list of table cells in a row.
* @public */ Cells?: TableCell[] | undefined; } /** *An excerpt from a table within a document. The table excerpt displays up to five * columns and three rows, depending on how many table cells are relevant to the query and * how many columns are available in the original table. The top most relevant cell is * displayed in the table excerpt, along with the next most relevant cells.
* @public */ export interface TableExcerpt { /** *A list of rows in the table excerpt.
* @public */ Rows?: TableRow[] | undefined; /** *A count of the number of rows in the original table within the document.
* @public */ TotalNumberOfRows?: number | undefined; } /** *A single query result.
*A query result contains information about a document returned by the query. This * includes the original location of the document, a list of attributes assigned to the * document, and relevant text from the document that satisfies the query.
* @public */ export interface QueryResultItem { /** *The unique identifier for the query result item id (Id) and the query
* result item document id (DocumentId) combined. The value of this field changes
* with every request, even when you have the same documents.
The type of document within the response. For example, a response could include a * question-answer that's relevant to the query.
* @public */ Type?: QueryResultType | undefined; /** *If the Type of document within the response is ANSWER, then it
* is either a TABLE answer or TEXT answer. If it's a table answer,
* a table excerpt is returned in TableExcerpt. If it's a text answer, a text
* excerpt is returned in DocumentExcerpt.
One or more additional fields/attributes associated with the query result.
* @public */ AdditionalAttributes?: AdditionalResultAttribute[] | undefined; /** *The identifier for the document.
* @public */ DocumentId?: string | undefined; /** *The title of the document. Contains the text of the title and information for * highlighting the relevant terms in the title.
* @public */ DocumentTitle?: TextWithHighlights | undefined; /** *An extract of the text in the document. Contains information about highlighting the * relevant terms in the excerpt.
* @public */ DocumentExcerpt?: TextWithHighlights | undefined; /** *The URI of the original location of the document.
* @public */ DocumentURI?: string | undefined; /** *An array of document fields/attributes assigned to a document in the search results. For
* example, the document author (_author) or the source URI
* (_source_uri) of the document.
Indicates the confidence level of Amazon Kendra providing a relevant result for the
* query. Each result is placed into a bin that indicates the confidence,
* VERY_HIGH, HIGH, MEDIUM and LOW. You
* can use the score to determine if a response meets the confidence needed for your
* application.
The field is only set to LOW when the Type field is set to
* DOCUMENT and Amazon Kendra is not confident that the result is
* relevant to the query.
A token that identifies a particular result from a particular query. Use this token to * provide click-through feedback for the result. For more information, see Submitting * feedback.
* @public */ FeedbackToken?: string | undefined; /** *An excerpt from a table within a document.
* @public */ TableExcerpt?: TableExcerpt | undefined; /** *Provides details about a collapsed group of search results.
* @public */ CollapsedResultDetail?: CollapsedResultDetail | undefined; } /** *A corrected misspelled word in a query.
* @public */ export interface Correction { /** *The zero-based location in the response string or text where * the corrected word starts.
* @public */ BeginOffset?: number | undefined; /** *The zero-based location in the response string or text where * the corrected word ends.
* @public */ EndOffset?: number | undefined; /** *The string or text of a misspelled word in a query.
* @public */ Term?: string | undefined; /** *The string or text of a corrected misspelled word in a query.
* @public */ CorrectedTerm?: string | undefined; } /** *A query with suggested spell corrections.
* @public */ export interface SpellCorrectedQuery { /** *The query with the suggested spell corrections.
* @public */ SuggestedQueryText?: string | undefined; /** *The corrected misspelled word or words in a query.
* @public */ Corrections?: Correction[] | undefined; } /** * @public * @enum */ export declare const WarningCode: { readonly QUERY_LANGUAGE_INVALID_SYNTAX: "QUERY_LANGUAGE_INVALID_SYNTAX"; }; /** * @public */ export type WarningCode = (typeof WarningCode)[keyof typeof WarningCode]; /** *The warning code and message that explains a problem with a query.
* @public */ export interface Warning { /** *The message that explains the problem with the query.
* @public */ Message?: string | undefined; /** *The code used to show the type of warning for the query.
* @public */ Code?: WarningCode | undefined; } /** *A single retrieved relevant passage result.
* @public */ export interface RetrieveResultItem { /** *The identifier of the relevant passage result.
* @public */ Id?: string | undefined; /** *The identifier of the document.
* @public */ DocumentId?: string | undefined; /** *The title of the document.
* @public */ DocumentTitle?: string | undefined; /** *The contents of the relevant passage.
* @public */ Content?: string | undefined; /** *The URI of the original location of the document.
* @public */ DocumentURI?: string | undefined; /** *An array of document fields/attributes assigned to a document in the search results.
* For example, the document author (_author) or the source URI
* (_source_uri) of the document.
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.
* @public */ ScoreAttributes?: ScoreAttributes | undefined; } /** * @public */ export interface RetrieveResult { /** *The identifier of query used for the search. You also use QueryId to
* identify the search when using the Submitfeedback
* API.
The results of the retrieved relevant passages for the search.
* @public */ ResultItems?: RetrieveResultItem[] | undefined; } /** *The resource you want to use is currently in use. Please check you have provided the * correct resource and try again.
* @public */ export declare class ResourceInUseException extends __BaseException { readonly name: "ResourceInUseException"; readonly $fault: "client"; Message?: string | undefined; /** * @internal */ constructor(opts: __ExceptionOptionTypeThe identifier of the data source connector to synchronize.
* @public */ Id: string | undefined; /** *The identifier of the index used with the data source connector.
* @public */ IndexId: string | undefined; } /** * @public */ export interface StartDataSourceSyncJobResponse { /** *Identifies a particular synchronization job.
* @public */ ExecutionId?: string | undefined; } /** * @public */ export interface StopDataSourceSyncJobRequest { /** *The identifier of the data source connector for which to stop the synchronization * jobs.
* @public */ Id: string | undefined; /** *The identifier of the index used with the data source connector.
* @public */ IndexId: string | undefined; } /** *Gathers information about when a particular result was clicked by a user. Your
* application uses the SubmitFeedback API to provide click
* information.
The identifier of the search result that was clicked.
* @public */ ResultId: string | undefined; /** *The Unix timestamp when the result was clicked.
* @public */ ClickTime: Date | undefined; } /** * @public * @enum */ export declare const RelevanceType: { readonly NOT_RELEVANT: "NOT_RELEVANT"; readonly RELEVANT: "RELEVANT"; }; /** * @public */ export type RelevanceType = (typeof RelevanceType)[keyof typeof RelevanceType]; /** *Provides feedback on how relevant a document is to a search. Your application uses the
* SubmitFeedback API to provide relevance information.
The identifier of the search result that the user provided relevance feedback * for.
* @public */ ResultId: string | undefined; /** *Whether the document was relevant or not relevant to the search.
* @public */ RelevanceValue: RelevanceType | undefined; } /** * @public */ export interface SubmitFeedbackRequest { /** *The identifier of the index that was queried.
* @public */ IndexId: string | undefined; /** *The identifier of the specific query for which you are submitting
* feedback. The query ID is returned in the response to the
* Query API.
Tells Amazon Kendra that a particular search result link was chosen * by the user.
* @public */ ClickFeedbackItems?: ClickFeedback[] | undefined; /** *Provides Amazon Kendra with relevant or not relevant feedback for * whether a particular item was relevant to the search.
* @public */ RelevanceFeedbackItems?: RelevanceFeedback[] | undefined; } /** * @public */ export interface TagResourceRequest { /** *The Amazon Resource Name (ARN) of the index, FAQ, data source, or other resource to add a tag. * For example, the ARN of an index is constructed as follows: * arn:aws:kendra:your-region:your-account-id:index/index-id * For information on how to construct an ARN for all types of Amazon Kendra resources, see * Resource * types.
* @public */ ResourceARN: string | undefined; /** *A list of tag keys to add to the index, FAQ, data source, or other resource. If a tag already * exists, the existing value is replaced with the new value.
* @public */ Tags: Tag[] | undefined; } /** * @public */ export interface TagResourceResponse { } /** * @public */ export interface UntagResourceRequest { /** *The Amazon Resource Name (ARN) of the index, FAQ, data source, or other resource to remove a tag. * For example, the ARN of an index is constructed as follows: * arn:aws:kendra:your-region:your-account-id:index/index-id * For information on how to construct an ARN for all types of Amazon Kendra resources, see * Resource * types.
* @public */ ResourceARN: string | undefined; /** *A list of tag keys to remove from the index, FAQ, data source, or other resource. If a tag * key doesn't exist for the resource, it is ignored.
* @public */ TagKeys: string[] | undefined; } /** * @public */ export interface UntagResourceResponse { } /** * @public */ export interface UpdateAccessControlConfigurationRequest { /** *The identifier of the index for an access control configuration.
* @public */ IndexId: string | undefined; /** *The identifier of the access control configuration you want to update.
* @public */ Id: string | undefined; /** *A new name for the access control configuration.
* @public */ Name?: string | undefined; /** *A new description for the access control configuration.
* @public */ Description?: string | undefined; /** *Information you want to update on principals (users and/or groups) and which documents * they should have access to. This is useful for user context filtering, where search * results are filtered based on the user or their group access to documents.
* @public */ AccessControlList?: Principal[] | undefined; /** *The updated list of principal lists that define the * hierarchy for which documents users should have access to.
* @public */ HierarchicalAccessControlList?: HierarchicalPrincipal[] | undefined; } /** * @public */ export interface UpdateAccessControlConfigurationResponse { } /** * @public */ export interface UpdateDataSourceRequest { /** *The identifier of the data source connector you want to update.
* @public */ Id: string | undefined; /** *A new name for the data source connector.
* @public */ Name?: string | undefined; /** *The identifier of the index used with the data source connector.
* @public */ IndexId: string | undefined; /** *Configuration information you want to update for the data source connector.
* @public */ Configuration?: DataSourceConfiguration | undefined; /** *Configuration information for an Amazon Virtual Private Cloud to connect to your data source. * For more information, see Configuring a VPC.
* @public */ VpcConfiguration?: DataSourceVpcConfiguration | undefined; /** *A new description for the data source connector.
* @public */ Description?: string | undefined; /** *The sync schedule you want to update for the data source connector.
* @public */ Schedule?: string | undefined; /** *The Amazon Resource Name (ARN) of an IAM role with permission to access * the data source and required resources. For more information, see IAM roles for Amazon Kendra.
* @public */ RoleArn?: string | undefined; /** *The code for a language you want to update for the data source connector. * This allows you to support a language for all * documents when updating the data source. English is supported * by default. For more information on supported languages, including their codes, * see Adding * documents in languages other than English.
* @public */ LanguageCode?: string | undefined; /** *Configuration information you want to update for altering document metadata and * content during the document ingestion process.
*For more information on how to create, modify and delete document metadata, or make * other content alterations when you ingest documents into Amazon Kendra, see Customizing document metadata during the ingestion process.
* @public */ CustomDocumentEnrichmentConfiguration?: CustomDocumentEnrichmentConfiguration | undefined; } /** * @public */ export interface UpdateExperienceRequest { /** *The identifier of your Amazon Kendra experience you want to update.
* @public */ Id: string | undefined; /** *A new name for your Amazon Kendra experience.
* @public */ Name?: string | undefined; /** *The identifier of the index for your Amazon Kendra experience.
* @public */ IndexId: string | undefined; /** *The Amazon Resource Name (ARN) of an IAM role with permission to access
* the Query API, QuerySuggestions API, SubmitFeedback
* API, and IAM Identity Center that stores your users and groups information.
* For more information, see IAM roles for Amazon Kendra.
Configuration information you want to update for your Amazon Kendra experience.
* @public */ Configuration?: ExperienceConfiguration | undefined; /** *A new description for your Amazon Kendra experience.
* @public */ Description?: string | undefined; } /** * @public */ export interface UpdateFeaturedResultsSetRequest { /** *The identifier of the index used for featuring results.
* @public */ IndexId: string | undefined; /** *The identifier of the set of featured results that you want to update.
* @public */ FeaturedResultsSetId: string | undefined; /** *A new name for the set of featured results.
* @public */ FeaturedResultsSetName?: string | undefined; /** *A new description for the set of featured results.
* @public */ Description?: string | undefined; /** *You can set the status to ACTIVE or INACTIVE.
* When the value is ACTIVE, featured results are ready for
* use. You can still configure your settings before setting the status
* to ACTIVE. The queries you specify for featured results
* must be unique per featured results set for each index, whether the
* status is ACTIVE or INACTIVE.
A list of queries for featuring results. For more information on the * list of queries, see FeaturedResultsSet.
* @public */ QueryTexts?: string[] | undefined; /** *A list of document IDs for the documents you want to feature at the * top of the search results page. For more information on the list of * featured documents, see FeaturedResultsSet.
* @public */ FeaturedDocuments?: FeaturedDocument[] | undefined; } /** * @public */ export interface UpdateFeaturedResultsSetResponse { /** *Information on the set of featured results. This includes the identifier * of the featured results set, whether the featured results set is active * or inactive, when the featured results set was last updated, and more.
* @public */ FeaturedResultsSet?: FeaturedResultsSet | undefined; } /** * @public */ export interface UpdateIndexRequest { /** *The identifier of the index you want to update.
* @public */ Id: string | undefined; /** *A new name for the index.
* @public */ Name?: string | undefined; /** *An Identity and Access Management (IAM) role that gives Amazon Kendra * permission to access Amazon CloudWatch logs and metrics.
* @public */ RoleArn?: string | undefined; /** *A new description for the index.
* @public */ Description?: string | undefined; /** *The document metadata configuration you want to update for the index. Document metadata * are fields or attributes associated with your documents. For example, the company department * name associated with each document.
* @public */ DocumentMetadataConfigurationUpdates?: DocumentMetadataConfiguration[] | undefined; /** *Sets the number of additional document storage and query capacity units that should be * used by the index. You can change the capacity of the index up to 5 times per day, or make 5 * API calls.
*If you are using extra storage units, you can't reduce the storage capacity below what is * required to meet the storage needs for your index.
* @public */ CapacityUnits?: CapacityUnitsConfiguration | undefined; /** *The user token configuration.
*If you're using an Amazon Kendra Gen AI Enterprise Edition index and you try to use
* UserTokenConfigurations to configure user context policy, Amazon Kendra returns
* a ValidationException error.
The user context policy.
*If you're using an Amazon Kendra Gen AI Enterprise Edition index, you can only use
* ATTRIBUTE_FILTER to filter search results by user context. If you're
* using an Amazon Kendra Gen AI Enterprise Edition index and you try to use
* USER_TOKEN to configure user context policy, Amazon Kendra returns a
* ValidationException error.
Gets users and groups from IAM Identity Center identity source. To configure this, * see UserGroupResolutionConfiguration. This is useful for user context filtering, * where search results are filtered based on the user or their group access to * documents.
*If you're using an Amazon Kendra Gen AI Enterprise Edition index,
* UserGroupResolutionConfiguration isn't supported.
The identifier of the index for the block list.
* @public */ IndexId: string | undefined; /** *The identifier of the block list you want to update.
* @public */ Id: string | undefined; /** *A new name for the block list.
* @public */ Name?: string | undefined; /** *A new description for the block list.
* @public */ Description?: string | undefined; /** *The S3 path where your block list text file sits in S3.
*If you update your block list and provide the same path to the
* block list text file in S3, then Amazon Kendra reloads the file to refresh
* the block list. Amazon Kendra does not automatically refresh your block list.
* You need to call the UpdateQuerySuggestionsBlockList API
* to refresh you block list.
If you update your block list, then Amazon Kendra asynchronously refreshes * all query suggestions with the latest content in the S3 file. This * means changes might not take effect immediately.
* @public */ SourceS3Path?: S3Path | undefined; /** *The IAM (Identity and Access Management) role used to access the * block list text file in S3.
* @public */ RoleArn?: string | undefined; } /** * @public */ export interface UpdateQuerySuggestionsConfigRequest { /** *The identifier of the index with query suggestions you want to update.
* @public */ IndexId: string | undefined; /** *Set the mode to ENABLED or LEARN_ONLY.
By default, Amazon Kendra enables query suggestions.
* LEARN_ONLY mode allows you to turn off query suggestions.
* You can to update this at any time.
In LEARN_ONLY mode, Amazon Kendra continues to learn from new
* queries to keep suggestions up to date for when you are ready to
* switch to ENABLED mode again.
How recent your queries are in your query log time window.
*The time window is the number of days from current day to past days.
*By default, Amazon Kendra sets this to 180.
* @public */ QueryLogLookBackWindowInDays?: number | undefined; /** *
* TRUE to include queries without user information (i.e. all queries,
* irrespective of the user), otherwise FALSE to only include queries
* with user information.
If you pass user information to Amazon Kendra along with the queries, you can set this
* flag to FALSE and instruct Amazon Kendra to only consider queries with user
* information.
If you set to FALSE, Amazon Kendra only considers queries searched at least
* MinimumQueryCount times across MinimumNumberOfQueryingUsers
* unique users for suggestions.
If you set to TRUE, Amazon Kendra ignores all user information and learns
* from all queries.
The minimum number of unique users who must search a query in order for the query * to be eligible to suggest to your users.
*Increasing this number might decrease the number of suggestions. However, this * ensures a query is searched by many users and is truly popular to suggest to users.
*How you tune this setting depends on your specific needs.
* @public */ MinimumNumberOfQueryingUsers?: number | undefined; /** *The the minimum number of times a query must be searched in order to be * eligible to suggest to your users.
*Decreasing this number increases the number of suggestions. However, this * affects the quality of suggestions as it sets a low bar for a query to be * considered popular to suggest to users.
*How you tune this setting depends on your specific needs.
* @public */ MinimumQueryCount?: number | undefined; /** *Configuration information for the document fields/attributes that you want to base * query suggestions on.
* @public */ AttributeSuggestionsConfig?: AttributeSuggestionsUpdateConfig | undefined; } /** * @public */ export interface UpdateThesaurusRequest { /** *The identifier of the thesaurus you want to update.
* @public */ Id: string | undefined; /** *A new name for the thesaurus.
* @public */ Name?: string | undefined; /** *The identifier of the index for the thesaurus.
* @public */ IndexId: string | undefined; /** *A new description for the thesaurus.
* @public */ Description?: string | undefined; /** *An IAM role that gives Amazon Kendra permissions to
* access thesaurus file specified in SourceS3Path.
Information required to find a specific file in an Amazon S3 bucket.
* @public */ SourceS3Path?: S3Path | undefined; } /** *Information about a document attribute or field. You can use document attributes as * facets.
*For example, the document attribute or facet "Department" includes the values "HR", * "Engineering", and "Accounting". You can display these values in the search results so that * documents can be searched by department.
*You can display up to 10 facet values per facet for a query. If you want to increase * this limit, contact Support.
* @public */ export interface Facet { /** *The unique key for the document attribute.
* @public */ DocumentAttributeKey?: string | undefined; /** *An array of document attributes that are nested facets within a facet.
*For example, the document attribute or facet "Department" includes a value called * "Engineering". In addition, the document attribute or facet "SubDepartment" includes the * values "Frontend" and "Backend" for documents assigned to "Engineering". You can display * nested facets in the search results so that documents can be searched not only by * department but also by a sub department within a department. This helps your users further * narrow their search.
*You can only have one nested facet within a facet. If you want to increase this limit, * contact Support.
* @public */ Facets?: Facet[] | undefined; /** *Maximum number of facet values per facet. The default is 10. You can use this to limit * the number of facet values to less than 10. If you want to increase the default, contact * Support.
* @public */ MaxResults?: number | undefined; } /** *Provides the count of documents that match a particular document attribute or field when * doing a faceted search.
* @public */ export interface DocumentAttributeValueCountPair { /** *The value of the attribute/field. For example, "HR".
* @public */ DocumentAttributeValue?: DocumentAttributeValue | undefined; /** *The number of documents in the response that have the attribute/field value for the * key.
* @public */ Count?: number | undefined; /** *Contains the results of a document attribute/field that is a nested facet. A
* FacetResult contains the counts for each facet nested within a
* facet.
For example, the document attribute or facet "Department" includes a value called * "Engineering". In addition, the document attribute or facet "SubDepartment" includes the * values "Frontend" and "Backend" for documents assigned to "Engineering". You can display * nested facets in the search results so that documents can be searched not only by * department but also by a sub department within a department. The counts for documents that * belong to "Frontend" and "Backend" within "Engineering" are returned for a query.
* * * @public */ FacetResults?: FacetResult[] | undefined; } /** *The facet values for the documents in the response.
* @public */ export interface FacetResult { /** *The key for the facet values. This is the same as the DocumentAttributeKey
* provided in the query.
The data type of the facet value. This is the same as the type defined for the index * field when it was created.
* @public */ DocumentAttributeValueType?: DocumentAttributeValueType | undefined; /** *An array of key/value pairs, where the key is the value of the attribute and the count * is the number of documents that share the key value.
* @public */ DocumentAttributeValueCountPairs?: DocumentAttributeValueCountPair[] | undefined; } /** *Filters the search results based on document attributes or fields.
*You can filter results using attributes for your particular documents. The attributes
* must exist in your index. For example, if your documents include the custom attribute
* "Department", you can filter documents that belong to the "HR" department. You would use
* the EqualsTo operation to filter results or documents with "Department" equals
* to "HR".
You can use AndAllFilters and OrAllFilters in combination with
* each other or with other operations such as EqualsTo. For example:
* AndAllFilters
*
* EqualsTo: "Department", "HR"
* OrAllFilters
*
* ContainsAny: "Project Name", ["new hires", "new hiring"]
This example filters results or documents that belong to the HR department
* AND belong to projects that contain "new hires"
* OR "new hiring" in the project name (must use
* ContainAny with StringListValue). This example is filtering
* with a depth of 2.
You cannot filter more than a depth of 2, otherwise you receive a
* ValidationException exception with the message "AttributeFilter cannot have
* a depth of more than 2." Also, if you use more than 10 attribute filters in a given list
* for AndAllFilters or OrAllFilters, you receive a
* ValidationException with the message "AttributeFilter cannot have a length
* of more than 10".
For examples of using AttributeFilter, see Using document attributes to
* filter search results.
Performs a logical AND operation on all filters that you specify.
Performs a logical OR operation on all filters that you specify.
Performs a logical NOT operation on all filters that you specify.
Performs an equals operation on document attributes/fields and their values.
* @public */ EqualsTo?: DocumentAttribute | undefined; /** *Returns true when a document contains all of the specified document attributes/fields. * This filter is only applicable to StringListValue.
* @public */ ContainsAll?: DocumentAttribute | undefined; /** *Returns true when a document contains any of the specified document attributes/fields. * This filter is only applicable to StringListValue.
* @public */ ContainsAny?: DocumentAttribute | undefined; /** *Performs a greater than operation on document attributes/fields and their values. Use
* with the document attribute
* type
* Date or Long.
Performs a greater or equals than operation on document attributes/fields and their
* values. Use with the document attribute
* type
* Date or Long.
Performs a less than operation on document attributes/fields and their values. Use with
* the document attribute
* type
* Date or Long.
Performs a less than or equals operation on document attributes/fields and their values.
* Use with the document attribute
* type
* Date or Long.
The identifier for the search. You also use QueryId to identify the search
* when using the SubmitFeedback
* API.
The results of the search.
* @public */ ResultItems?: QueryResultItem[] | undefined; /** *Contains the facet results. A FacetResult contains the counts for each
* field/attribute key that was specified in the Facets input parameter.
The total number of items found by the search. However, you can only retrieve up to 100 * items. For example, if the search found 192 items, you can only retrieve the first 100 of * the items.
* @public */ TotalNumberOfResults?: number | undefined; /** *A list of warning codes and their messages on problems with your query.
*Amazon Kendra currently only supports one type of warning, which is a warning on * invalid syntax used in the query. For examples of invalid query syntax, see Searching * with advanced query syntax.
* @public */ Warnings?: Warning[] | undefined; /** *A list of information related to suggested spell corrections for a query.
* @public */ SpellCorrectedQueries?: SpellCorrectedQuery[] | undefined; /** *The list of featured result items. Featured results are displayed at the top of the * search results page, placed above all other results for certain queries. If there's an * exact match of a query, then certain documents are featured in the search results.
* @public */ FeaturedResultsItems?: FeaturedResultsItem[] | undefined; } /** *Provides the configuration information for the document fields/attributes that you want * to base query suggestions on.
* @public */ export interface AttributeSuggestionsGetConfig { /** *The list of document field/attribute keys or field names to use for query suggestions. * If the content within any of the fields match what your user starts typing as their query, * then the field content is returned as a query suggestion.
* @public */ SuggestionAttributes?: string[] | undefined; /** *The list of additional document field/attribute keys or field names to include in the * response. You can use additional fields to provide extra information in the response. * Additional fields are not used to based suggestions on.
* @public */ AdditionalResponseAttributes?: string[] | undefined; /** *Filters the search results based on document fields/attributes.
* @public */ AttributeFilter?: AttributeFilter | undefined; /** *Applies user context filtering so that only users who are given access to certain * documents see these document in their search results.
* @public */ UserContext?: UserContext | undefined; } /** * @public */ export interface RetrieveRequest { /** *The identifier of the index to retrieve relevant passages for the search.
* @public */ IndexId: string | undefined; /** *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.
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.
For Amazon Kendra Gen AI Enterprise Edition indices use AttributeFilter to
* enable document filtering for end users using _email_id or include
* public documents (_email_id=null).
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.
* @public */ RequestedDocumentAttributes?: string[] | undefined; /** *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.
* @public */ DocumentRelevanceOverrideConfigurations?: DocumentRelevanceConfiguration[] | undefined; /** *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.
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.
* @public */ PageSize?: number | undefined; /** *The user context token or user and group information.
* @public */ UserContext?: UserContext | undefined; } /** * @public */ export interface GetQuerySuggestionsRequest { /** *The identifier of the index you want to get query suggestions from.
* @public */ IndexId: string | undefined; /** *The text of a user's query to generate query suggestions.
*A query is suggested if the query prefix matches * what a user starts to type as their query.
*Amazon Kendra does not show any suggestions if a user * types fewer than two characters or more than 60 characters. * A query must also have at least one search result and contain * at least one word of more than four characters.
* @public */ QueryText: string | undefined; /** *The maximum number of query suggestions you want to show * to your users.
* @public */ MaxSuggestionsCount?: number | undefined; /** *The suggestions type to base query suggestions on. The suggestion * types are query history or document fields/attributes. You can set * one type or the other.
*If you set query history as your suggestions type, Amazon Kendra * suggests queries relevant to your users based on popular queries in * the query history.
*If you set document fields/attributes as your suggestions type, * Amazon Kendra suggests queries relevant to your users based on the * contents of document fields.
* @public */ SuggestionTypes?: SuggestionType[] | undefined; /** *Configuration information for the document fields/attributes that you * want to base query suggestions on.
* @public */ AttributeSuggestionsConfig?: AttributeSuggestionsGetConfig | undefined; } /** * @public */ export interface QueryRequest { /** *The identifier of the index for the search.
* @public */ IndexId: string | undefined; /** *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.
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.
For Amazon Kendra Gen AI Enterprise Edition indices use AttributeFilter to
* enable document filtering for end users using _email_id or include public
* documents (_email_id=null).
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.
* @public */ Facets?: Facet[] | undefined; /** *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.
* @public */ RequestedDocumentAttributes?: string[] | undefined; /** *Sets the type of query result or response. Only results for the specified type are * returned.
* @public */ QueryResultTypeFilter?: QueryResultType | undefined; /** *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.
* @public */ DocumentRelevanceOverrideConfigurations?: DocumentRelevanceConfiguration[] | undefined; /** *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.
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.
* @public */ PageSize?: number | undefined; /** *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.
* @public */ SortingConfiguration?: SortingConfiguration | undefined; /** *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.
* @public */ SortingConfigurations?: SortingConfiguration[] | undefined; /** *The user context token or user and group information.
* @public */ UserContext?: UserContext | undefined; /** *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.
Enables suggested spell corrections for queries.
* @public */ SpellCorrectionConfiguration?: SpellCorrectionConfiguration | undefined; /** *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.
* @public */ CollapseConfiguration?: CollapseConfiguration | undefined; }