Note:

You are viewing the documentation for an older major version of the AWS CLI (version 1).

AWS CLI version 2, the latest major version of AWS CLI, is now stable and recommended for general use. To view this page for the AWS CLI version 2, click here. For more information see the AWS CLI version 2 installation instructions and migration guide.

[ aws . qbusiness ]

create-retriever¶

Description¶

Adds a retriever to your Amazon Q Business application.

Synopsis¶

  create-retriever
--application-id <value>
--type <value>
--display-name <value>
--configuration <value>
[--role-arn <value>]
[--client-token <value>]
[--tags <value>]
[--cli-input-json <value>]
[--generate-cli-skeleton <value>]
[--debug]
[--endpoint-url <value>]
[--no-verify-ssl]
[--no-paginate]
[--output <value>]
[--query <value>]
[--profile <value>]
[--region <value>]
[--version <value>]
[--color <value>]
[--no-sign-request]
[--ca-bundle <value>]
[--cli-read-timeout <value>]
[--cli-connect-timeout <value>]

Options¶

--application-id (string)

The identifier of your Amazon Q Business application.

--type (string)

The type of retriever you are using.

Possible values:

NATIVE_INDEX

KENDRA_INDEX

--display-name (string)

The name of your retriever.

--configuration (tagged union structure)

Provides information on how the retriever used for your Amazon Q Business application is configured.

Note
This is a Tagged Union structure. Only one of the following top level keys can be set: nativeIndexConfiguration, kendraIndexConfiguration.

nativeIndexConfiguration -> (structure)

Provides information on how a Amazon Q Business index used as a retriever for your Amazon Q Business application is configured.

indexId -> (string)

The identifier for the Amazon Q Business index.

version -> (long)

A read-only field that specifies the version of the NativeIndexConfiguration .

Amazon Q Business introduces enhanced document retrieval capabilities in version 2 of NativeIndexConfiguration , focusing on streamlined metadata boosting that prioritizes recency and source relevance to deliver more accurate responses to your queries. Version 2 has the following differences from version 1:

Version 2 supports a single Date field (created_at OR last_updated_at) for recency boosting

Version 2 supports a single String field with an ordered list of up to 5 values

Version 2 introduces number-based boost levels (ONE, TWO) alongside the text-based levels

Version 2 allows specifying prioritization between Date and String fields

Version 2 maintains backward compatibility with existing configurations

boostingOverride -> (map)

Overrides the default boosts applied by Amazon Q Business to supported document attribute data types.

key -> (string)

value -> (tagged union structure)

Provides information on boosting supported Amazon Q Business document attribute types. When an end user chat query matches document attributes that have been boosted, Amazon Q Business prioritizes generating responses from content that matches the boosted document attributes.

In version 2, boosting uses numeric values (ONE, TWO) to indicate priority tiers that establish clear hierarchical relationships between boosted attributes. This allows for more precise control over how different attributes influence search results.

Note
For STRING and STRING_LIST type document attributes to be used for boosting on the console and the API, they must be enabled for search using the DocumentAttributeConfiguration object of the UpdateIndex API. If you haven’t enabled searching on these attributes, you can’t boost attributes of these data types on either the console or the API.

For more information on how boosting document attributes work in Amazon Q Business, see Boosting using document attributes .

Note
This is a Tagged Union structure. Only one of the following top level keys can be set: numberConfiguration, stringConfiguration, dateConfiguration, stringListConfiguration.

numberConfiguration -> (structure)

Provides information on boosting NUMBER type document attributes.

NUMBER attributes are not supported when using NativeIndexConfiguration version 2, which focuses on DATE attributes for recency and STRING attributes for source prioritization.

boostingLevel -> (string)

Specifies the priority of boosted document attributes in relation to other boosted attributes. This parameter determines how strongly the attribute influences document ranking in search results. NUMBER attributes can serve as additional boosting factors when needed, but are not supported when using NativeIndexConfiguration version 2.

boostingType -> (string)

Specifies whether higher or lower numeric values should be prioritized when boosting. Valid values are ASCENDING (higher numbers are more important) and DESCENDING (lower numbers are more important).

stringConfiguration -> (structure)

Provides information on boosting STRING type document attributes.

Version 2 assigns priority tiers to STRING attributes, establishing clear hierarchical relationships with other boosted attributes.

boostingLevel -> (string)

Specifies the priority tier ranking of boosting applied to document attributes. For version 2, this parameter indicates the relative ranking between boosted fields (ONE being highest priority, TWO being second highest, etc.) and determines the order in which attributes influence document ranking in search results. For version 1, this parameter specifies the boosting intensity. For version 2, boosting intensity (VERY HIGH, HIGH, MEDIUM, LOW, NONE) are not supported. Note that in version 2, you are not allowed to boost on only one field and make this value TWO.

attributeValueBoosting -> (map)

Specifies specific values of a STRING type document attribute being boosted. When using NativeIndexConfiguration version 2, you can specify up to five values in order of priority.

key -> (string)

value -> (string)

dateConfiguration -> (structure)

Provides information on boosting DATE type document attributes.

Version 2 assigns priority tiers to DATE attributes, establishing clear hierarchical relationships with other boosted attributes.

boostingLevel -> (string)

Specifies the priority tier ranking of boosting applied to document attributes. For version 2, this parameter indicates the relative ranking between boosted fields (ONE being highest priority, TWO being second highest, etc.) and determines the order in which attributes influence document ranking in search results. For version 1, this parameter specifies the boosting intensity. For version 2, boosting intensity (VERY HIGH, HIGH, MEDIUM, LOW, NONE) are not supported. Note that in version 2, you are not allowed to boost on only one field and make this value TWO.

boostingDurationInSeconds -> (long)

Specifies the duration, in seconds, of a boost applies to a DATE type document attribute.

stringListConfiguration -> (structure)

Provides information on boosting STRING_LIST type document attributes.

STRING_LIST attributes are not supported when using NativeIndexConfiguration version 2, which focuses on DATE attributes for recency and STRING attributes for source prioritization.

boostingLevel -> (string)

Specifies the priority of boosted document attributes in relation to other boosted attributes. This parameter determines how strongly the attribute influences document ranking in search results. STRING_LIST attributes can serve as additional boosting factors when needed, but are not supported when using NativeIndexConfiguration version 2.

kendraIndexConfiguration -> (structure)

Provides information on how the Amazon Kendra index used as a retriever for your Amazon Q Business application is configured.

indexId -> (string)

The identifier of the Amazon Kendra index.

JSON Syntax:

{
  "nativeIndexConfiguration": {
    "indexId": "string",
    "version": long,
    "boostingOverride": {"string": {
          "numberConfiguration": {
            "boostingLevel": "NONE"|"LOW"|"MEDIUM"|"HIGH"|"VERY_HIGH"|"ONE"|"TWO",
            "boostingType": "PRIORITIZE_LARGER_VALUES"|"PRIORITIZE_SMALLER_VALUES"
          },
          "stringConfiguration": {
            "boostingLevel": "NONE"|"LOW"|"MEDIUM"|"HIGH"|"VERY_HIGH"|"ONE"|"TWO",
            "attributeValueBoosting": {"string": "LOW"|"MEDIUM"|"HIGH"|"VERY_HIGH"|"ONE"|"TWO"|"THREE"|"FOUR"|"FIVE"
              ...}
          },
          "dateConfiguration": {
            "boostingLevel": "NONE"|"LOW"|"MEDIUM"|"HIGH"|"VERY_HIGH"|"ONE"|"TWO",
            "boostingDurationInSeconds": long
          },
          "stringListConfiguration": {
            "boostingLevel": "NONE"|"LOW"|"MEDIUM"|"HIGH"|"VERY_HIGH"|"ONE"|"TWO"
          }
        }
      ...}
  },
  "kendraIndexConfiguration": {
    "indexId": "string"
  }
}

--role-arn (string)

The ARN of an IAM role used by Amazon Q Business to access the basic authentication credentials stored in a Secrets Manager secret.

--client-token (string)

A token that you provide to identify the request to create your Amazon Q Business application retriever.

--tags (list)

A list of key-value pairs that identify or categorize the retriever. You can also use tags to help control access to the retriever. Tag keys and values can consist of Unicode letters, digits, white space, and any of the following symbols: _ . : / = + - @.

(structure)

A list of key/value pairs that identify an index, FAQ, or data source. Tag keys and values can consist of Unicode letters, digits, white space, and any of the following symbols: _ . : / = + - @.

key -> (string)

The key for the tag. Keys are not case sensitive and must be unique for the Amazon Q Business application or data source.

value -> (string)

The value associated with the tag. The value may be an empty string but it can’t be null.

Shorthand Syntax:

key=string,value=string ...

JSON Syntax:

[
  {
    "key": "string",
    "value": "string"
  }
  ...
]

--cli-input-json (string) Performs service operation based on the JSON string provided. The JSON string follows the format provided by --generate-cli-skeleton. If other arguments are provided on the command line, the CLI values will override the JSON-provided values. It is not possible to pass arbitrary binary values using a JSON-provided value as the string will be taken literally.

--generate-cli-skeleton (string) Prints a JSON skeleton to standard output without sending an API request. If provided with no value or the value input, prints a sample input JSON that can be used as an argument for --cli-input-json. If provided with the value output, it validates the command inputs and returns a sample output JSON for that command.

Global Options¶

--debug (boolean)

Turn on debug logging.

--endpoint-url (string)

Override command’s default URL with the given URL.

--no-verify-ssl (boolean)

By default, the AWS CLI uses SSL when communicating with AWS services. For each SSL connection, the AWS CLI will verify SSL certificates. This option overrides the default behavior of verifying SSL certificates.

--no-paginate (boolean)

Disable automatic pagination. If automatic pagination is disabled, the AWS CLI will only make one call, for the first page of results.

--output (string)

The formatting style for command output.

json
text
table

--query (string)

A JMESPath query to use in filtering the response data.

--profile (string)

Use a specific profile from your credential file.

--region (string)

The region to use. Overrides config/env settings.

--version (string)

Display the version of this tool.

--color (string)

Turn on/off color output.

on
off
auto

--no-sign-request (boolean)

Do not sign requests. Credentials will not be loaded if this argument is provided.

--ca-bundle (string)

The CA certificate bundle to use when verifying SSL certificates. Overrides config/env settings.

--cli-read-timeout (int)

The maximum socket read time in seconds. If the value is set to 0, the socket read will be blocking and not timeout. The default value is 60 seconds.

--cli-connect-timeout (int)

The maximum socket connect time in seconds. If the value is set to 0, the socket connect will be blocking and not timeout. The default value is 60 seconds.

Output¶

retrieverId -> (string)

The identifier of the retriever you are using.

retrieverArn -> (string)

The Amazon Resource Name (ARN) of an IAM role associated with a retriever.

Table of Contents

Feedback

User Guide

Note:

create-retriever¶

Description¶

Synopsis¶

Options¶

Note

Note

Note

Global Options¶

Output¶