SDK for PHP 3.x

Agents for Amazon Bedrock Runtime 2023-07-26

Client: Aws\BedrockAgentRuntime\BedrockAgentRuntimeClient
Service ID: bedrock-agent-runtime
Version: 2023-07-26

This page describes the parameters and results for the operations of the Agents for Amazon Bedrock Runtime (2023-07-26), and shows how to use the Aws\BedrockAgentRuntime\BedrockAgentRuntimeClient object to call the described operations. This documentation is specific to the 2023-07-26 API version of the service.

Operation Summary

Each of the following operations can be created from a client using $client->getCommand('CommandName'), where "CommandName" is the name of one of the following operations. Note: a command is a value that encapsulates an operation and the parameters used to create an HTTP request.

You can also create and send a command immediately using the magic methods available on a client object: $client->commandName(/* parameters */). You can send the command asynchronously (returning a promise) by appending the word "Async" to the operation name: $client->commandNameAsync(/* parameters */).

InvokeAgent ( array $params = [] )
The CLI doesn't support InvokeAgent.
Retrieve ( array $params = [] )
Queries a knowledge base and retrieves information from it.
RetrieveAndGenerate ( array $params = [] )
Queries a knowledge base and generates responses based on the retrieved results.

Paginators

Paginators handle automatically iterating over paginated API results. Paginators are associated with specific API operations, and they accept the parameters that the corresponding API operation accepts. You can get a paginator from a client class using getPaginator($paginatorName, $operationParameters). This client supports the following paginators:

Retrieve

Operations

InvokeAgent 

$result = $client->invokeAgent([/* ... */]);
$promise = $client->invokeAgentAsync([/* ... */]);

The CLI doesn't support InvokeAgent.

Sends a prompt for the agent to process and respond to. Note the following fields for the request:

  • To continue the same conversation with an agent, use the same sessionId value in the request.

  • To activate trace enablement, turn enableTrace to true. Trace enablement helps you follow the agent's reasoning process that led it to the information it processed, the actions it took, and the final result it yielded. For more information, see Trace enablement.

  • End a conversation by setting endSession to true.

  • In the sessionState object, you can include attributes for the session or prompt or, if you configured an action group to return control, results from invocation of the action group.

The response is returned in the bytes field of the chunk object.

  • The attribution object contains citations for parts of the response.

  • If you set enableTrace to true in the request, you can trace the agent's steps and reasoning process that led it to the response.

  • If the action predicted was configured to return control, the response returns parameters for the action, elicited from the user, in the returnControl field.

  • Errors are also surfaced in the response.

Parameter Syntax

$result = $client->invokeAgent([
    'agentAliasId' => '<string>', // REQUIRED
    'agentId' => '<string>', // REQUIRED
    'enableTrace' => true || false,
    'endSession' => true || false,
    'inputText' => '<string>',
    'sessionId' => '<string>', // REQUIRED
    'sessionState' => [
        'invocationId' => '<string>',
        'promptSessionAttributes' => ['<string>', ...],
        'returnControlInvocationResults' => [
            [
                'apiResult' => [
                    'actionGroup' => '<string>', // REQUIRED
                    'apiPath' => '<string>',
                    'httpMethod' => '<string>',
                    'httpStatusCode' => <integer>,
                    'responseBody' => [
                        '<String>' => [
                            'body' => '<string>',
                        ],
                        // ...
                    ],
                    'responseState' => 'FAILURE|REPROMPT',
                ],
                'functionResult' => [
                    'actionGroup' => '<string>', // REQUIRED
                    'function' => '<string>',
                    'responseBody' => [
                        '<String>' => [
                            'body' => '<string>',
                        ],
                        // ...
                    ],
                    'responseState' => 'FAILURE|REPROMPT',
                ],
            ],
            // ...
        ],
        'sessionAttributes' => ['<string>', ...],
    ],
]);

Parameter Details

Members
agentAliasId
Required: Yes
Type: string

The alias of the agent to use.

agentId
Required: Yes
Type: string

The unique identifier of the agent to use.

enableTrace
Type: boolean

Specifies whether to turn on the trace or not to track the agent's reasoning process. For more information, see Trace enablement.

endSession
Type: boolean

Specifies whether to end the session with the agent or not.

inputText
Type: string

The prompt text to send the agent.

If you include returnControlInvocationResults in the sessionState field, the inputText field will be ignored.

sessionId
Required: Yes
Type: string

The unique identifier of the session. Use the same value across requests to continue the same conversation.

sessionState
Type: SessionState structure

Contains parameters that specify various attributes of the session. For more information, see Control session context.

If you include returnControlInvocationResults in the sessionState field, the inputText field will be ignored.

Result Syntax

[
    'completion' => [ // EventParsingIterator
        'accessDeniedException' => [
            'message' => '<string>',
        ],
        'badGatewayException' => [
            'message' => '<string>',
            'resourceName' => '<string>',
        ],
        'chunk' => [
            'attribution' => [
                'citations' => [
                    [
                        'generatedResponsePart' => [
                            'textResponsePart' => [
                                'span' => [
                                    'end' => <integer>,
                                    'start' => <integer>,
                                ],
                                'text' => '<string>',
                            ],
                        ],
                        'retrievedReferences' => [
                            [
                                'content' => [
                                    'text' => '<string>',
                                ],
                                'location' => [
                                    's3Location' => [
                                        'uri' => '<string>',
                                    ],
                                    'type' => 'S3',
                                ],
                                'metadata' => [
                                    '<RetrievalResultMetadataKey>' => [
                                    ],
                                    // ...
                                ],
                            ],
                            // ...
                        ],
                    ],
                    // ...
                ],
            ],
            'bytes' => <string || resource || Psr\Http\Message\StreamInterface>,
        ],
        'conflictException' => [
            'message' => '<string>',
        ],
        'dependencyFailedException' => [
            'message' => '<string>',
            'resourceName' => '<string>',
        ],
        'internalServerException' => [
            'message' => '<string>',
        ],
        'resourceNotFoundException' => [
            'message' => '<string>',
        ],
        'returnControl' => [
            'invocationId' => '<string>',
            'invocationInputs' => [
                [
                    'apiInvocationInput' => [
                        'actionGroup' => '<string>',
                        'apiPath' => '<string>',
                        'httpMethod' => '<string>',
                        'parameters' => [
                            [
                                'name' => '<string>',
                                'type' => '<string>',
                                'value' => '<string>',
                            ],
                            // ...
                        ],
                        'requestBody' => [
                            'content' => [
                                '<String>' => [
                                    'properties' => [
                                        [
                                            'name' => '<string>',
                                            'type' => '<string>',
                                            'value' => '<string>',
                                        ],
                                        // ...
                                    ],
                                ],
                                // ...
                            ],
                        ],
                    ],
                    'functionInvocationInput' => [
                        'actionGroup' => '<string>',
                        'function' => '<string>',
                        'parameters' => [
                            [
                                'name' => '<string>',
                                'type' => '<string>',
                                'value' => '<string>',
                            ],
                            // ...
                        ],
                    ],
                ],
                // ...
            ],
        ],
        'serviceQuotaExceededException' => [
            'message' => '<string>',
        ],
        'throttlingException' => [
            'message' => '<string>',
        ],
        'trace' => [
            'agentAliasId' => '<string>',
            'agentId' => '<string>',
            'agentVersion' => '<string>',
            'sessionId' => '<string>',
            'trace' => [
                'failureTrace' => [
                    'failureReason' => '<string>',
                    'traceId' => '<string>',
                ],
                'guardrailTrace' => [
                    'action' => 'INTERVENED|NONE',
                    'inputAssessments' => [
                        [
                            'contentPolicy' => [
                                'filters' => [
                                    [
                                        'action' => 'BLOCKED',
                                        'confidence' => 'NONE|LOW|MEDIUM|HIGH',
                                        'type' => 'INSULTS|HATE|SEXUAL|VIOLENCE|MISCONDUCT|PROMPT_ATTACK',
                                    ],
                                    // ...
                                ],
                            ],
                            'sensitiveInformationPolicy' => [
                                'piiEntities' => [
                                    [
                                        'action' => 'BLOCKED|ANONYMIZED',
                                        'match' => '<string>',
                                        'type' => 'ADDRESS|AGE|AWS_ACCESS_KEY|AWS_SECRET_KEY|CA_HEALTH_NUMBER|CA_SOCIAL_INSURANCE_NUMBER|CREDIT_DEBIT_CARD_CVV|CREDIT_DEBIT_CARD_EXPIRY|CREDIT_DEBIT_CARD_NUMBER|DRIVER_ID|EMAIL|INTERNATIONAL_BANK_ACCOUNT_NUMBER|IP_ADDRESS|LICENSE_PLATE|MAC_ADDRESS|NAME|PASSWORD|PHONE|PIN|SWIFT_CODE|UK_NATIONAL_HEALTH_SERVICE_NUMBER|UK_NATIONAL_INSURANCE_NUMBER|UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER|URL|USERNAME|US_BANK_ACCOUNT_NUMBER|US_BANK_ROUTING_NUMBER|US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER|US_PASSPORT_NUMBER|US_SOCIAL_SECURITY_NUMBER|VEHICLE_IDENTIFICATION_NUMBER',
                                    ],
                                    // ...
                                ],
                                'regexes' => [
                                    [
                                        'action' => 'BLOCKED|ANONYMIZED',
                                        'match' => '<string>',
                                        'name' => '<string>',
                                        'regex' => '<string>',
                                    ],
                                    // ...
                                ],
                            ],
                            'topicPolicy' => [
                                'topics' => [
                                    [
                                        'action' => 'BLOCKED',
                                        'name' => '<string>',
                                        'type' => 'DENY',
                                    ],
                                    // ...
                                ],
                            ],
                            'wordPolicy' => [
                                'customWords' => [
                                    [
                                        'action' => 'BLOCKED',
                                        'match' => '<string>',
                                    ],
                                    // ...
                                ],
                                'managedWordLists' => [
                                    [
                                        'action' => 'BLOCKED',
                                        'match' => '<string>',
                                        'type' => 'PROFANITY',
                                    ],
                                    // ...
                                ],
                            ],
                        ],
                        // ...
                    ],
                    'outputAssessments' => [
                        [
                            'contentPolicy' => [
                                'filters' => [
                                    [
                                        'action' => 'BLOCKED',
                                        'confidence' => 'NONE|LOW|MEDIUM|HIGH',
                                        'type' => 'INSULTS|HATE|SEXUAL|VIOLENCE|MISCONDUCT|PROMPT_ATTACK',
                                    ],
                                    // ...
                                ],
                            ],
                            'sensitiveInformationPolicy' => [
                                'piiEntities' => [
                                    [
                                        'action' => 'BLOCKED|ANONYMIZED',
                                        'match' => '<string>',
                                        'type' => 'ADDRESS|AGE|AWS_ACCESS_KEY|AWS_SECRET_KEY|CA_HEALTH_NUMBER|CA_SOCIAL_INSURANCE_NUMBER|CREDIT_DEBIT_CARD_CVV|CREDIT_DEBIT_CARD_EXPIRY|CREDIT_DEBIT_CARD_NUMBER|DRIVER_ID|EMAIL|INTERNATIONAL_BANK_ACCOUNT_NUMBER|IP_ADDRESS|LICENSE_PLATE|MAC_ADDRESS|NAME|PASSWORD|PHONE|PIN|SWIFT_CODE|UK_NATIONAL_HEALTH_SERVICE_NUMBER|UK_NATIONAL_INSURANCE_NUMBER|UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER|URL|USERNAME|US_BANK_ACCOUNT_NUMBER|US_BANK_ROUTING_NUMBER|US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER|US_PASSPORT_NUMBER|US_SOCIAL_SECURITY_NUMBER|VEHICLE_IDENTIFICATION_NUMBER',
                                    ],
                                    // ...
                                ],
                                'regexes' => [
                                    [
                                        'action' => 'BLOCKED|ANONYMIZED',
                                        'match' => '<string>',
                                        'name' => '<string>',
                                        'regex' => '<string>',
                                    ],
                                    // ...
                                ],
                            ],
                            'topicPolicy' => [
                                'topics' => [
                                    [
                                        'action' => 'BLOCKED',
                                        'name' => '<string>',
                                        'type' => 'DENY',
                                    ],
                                    // ...
                                ],
                            ],
                            'wordPolicy' => [
                                'customWords' => [
                                    [
                                        'action' => 'BLOCKED',
                                        'match' => '<string>',
                                    ],
                                    // ...
                                ],
                                'managedWordLists' => [
                                    [
                                        'action' => 'BLOCKED',
                                        'match' => '<string>',
                                        'type' => 'PROFANITY',
                                    ],
                                    // ...
                                ],
                            ],
                        ],
                        // ...
                    ],
                    'traceId' => '<string>',
                ],
                'orchestrationTrace' => [
                    'invocationInput' => [
                        'actionGroupInvocationInput' => [
                            'actionGroupName' => '<string>',
                            'apiPath' => '<string>',
                            'function' => '<string>',
                            'parameters' => [
                                [
                                    'name' => '<string>',
                                    'type' => '<string>',
                                    'value' => '<string>',
                                ],
                                // ...
                            ],
                            'requestBody' => [
                                'content' => [
                                    '<String>' => [
                                        [
                                            'name' => '<string>',
                                            'type' => '<string>',
                                            'value' => '<string>',
                                        ],
                                        // ...
                                    ],
                                    // ...
                                ],
                            ],
                            'verb' => '<string>',
                        ],
                        'invocationType' => 'ACTION_GROUP|KNOWLEDGE_BASE|FINISH',
                        'knowledgeBaseLookupInput' => [
                            'knowledgeBaseId' => '<string>',
                            'text' => '<string>',
                        ],
                        'traceId' => '<string>',
                    ],
                    'modelInvocationInput' => [
                        'inferenceConfiguration' => [
                            'maximumLength' => <integer>,
                            'stopSequences' => ['<string>', ...],
                            'temperature' => <float>,
                            'topK' => <integer>,
                            'topP' => <float>,
                        ],
                        'overrideLambda' => '<string>',
                        'parserMode' => 'DEFAULT|OVERRIDDEN',
                        'promptCreationMode' => 'DEFAULT|OVERRIDDEN',
                        'text' => '<string>',
                        'traceId' => '<string>',
                        'type' => 'PRE_PROCESSING|ORCHESTRATION|KNOWLEDGE_BASE_RESPONSE_GENERATION|POST_PROCESSING',
                    ],
                    'observation' => [
                        'actionGroupInvocationOutput' => [
                            'text' => '<string>',
                        ],
                        'finalResponse' => [
                            'text' => '<string>',
                        ],
                        'knowledgeBaseLookupOutput' => [
                            'retrievedReferences' => [
                                [
                                    'content' => [
                                        'text' => '<string>',
                                    ],
                                    'location' => [
                                        's3Location' => [
                                            'uri' => '<string>',
                                        ],
                                        'type' => 'S3',
                                    ],
                                    'metadata' => [
                                        '<RetrievalResultMetadataKey>' => [
                                        ],
                                        // ...
                                    ],
                                ],
                                // ...
                            ],
                        ],
                        'repromptResponse' => [
                            'source' => 'ACTION_GROUP|KNOWLEDGE_BASE|PARSER',
                            'text' => '<string>',
                        ],
                        'traceId' => '<string>',
                        'type' => 'ACTION_GROUP|KNOWLEDGE_BASE|FINISH|ASK_USER|REPROMPT',
                    ],
                    'rationale' => [
                        'text' => '<string>',
                        'traceId' => '<string>',
                    ],
                ],
                'postProcessingTrace' => [
                    'modelInvocationInput' => [
                        'inferenceConfiguration' => [
                            'maximumLength' => <integer>,
                            'stopSequences' => ['<string>', ...],
                            'temperature' => <float>,
                            'topK' => <integer>,
                            'topP' => <float>,
                        ],
                        'overrideLambda' => '<string>',
                        'parserMode' => 'DEFAULT|OVERRIDDEN',
                        'promptCreationMode' => 'DEFAULT|OVERRIDDEN',
                        'text' => '<string>',
                        'traceId' => '<string>',
                        'type' => 'PRE_PROCESSING|ORCHESTRATION|KNOWLEDGE_BASE_RESPONSE_GENERATION|POST_PROCESSING',
                    ],
                    'modelInvocationOutput' => [
                        'parsedResponse' => [
                            'text' => '<string>',
                        ],
                        'traceId' => '<string>',
                    ],
                ],
                'preProcessingTrace' => [
                    'modelInvocationInput' => [
                        'inferenceConfiguration' => [
                            'maximumLength' => <integer>,
                            'stopSequences' => ['<string>', ...],
                            'temperature' => <float>,
                            'topK' => <integer>,
                            'topP' => <float>,
                        ],
                        'overrideLambda' => '<string>',
                        'parserMode' => 'DEFAULT|OVERRIDDEN',
                        'promptCreationMode' => 'DEFAULT|OVERRIDDEN',
                        'text' => '<string>',
                        'traceId' => '<string>',
                        'type' => 'PRE_PROCESSING|ORCHESTRATION|KNOWLEDGE_BASE_RESPONSE_GENERATION|POST_PROCESSING',
                    ],
                    'modelInvocationOutput' => [
                        'parsedResponse' => [
                            'isValid' => true || false,
                            'rationale' => '<string>',
                        ],
                        'traceId' => '<string>',
                    ],
                ],
            ],
        ],
        'validationException' => [
            'message' => '<string>',
        ],
    ],
    'contentType' => '<string>',
    'sessionId' => '<string>',
]

Result Details

Members
completion
Required: Yes
Type: EventParsingIterator supplying the following structures: AccessDeniedException, BadGatewayException, PayloadPart, ConflictException, DependencyFailedException, InternalServerException, ResourceNotFoundException, ReturnControlPayload, ServiceQuotaExceededException, ThrottlingException, TracePart, ValidationException

The agent's response to the user prompt.

contentType
Required: Yes
Type: string

The MIME type of the input data in the request. The default value is application/json.

sessionId
Required: Yes
Type: string

The unique identifier of the session with the agent.

Using an EventParsingIterator

To use an EventParsingIterator, you will need to loop over the events it will generate and check the top-level field to determine which type of event it is.

foreach($result['completion'] as $event) {
    if (isset($event['accessDeniedException'])) {
        // Handle the 'accessDeniedException' event.
    } else if (isset($event['badGatewayException'])) {
        // Handle the 'badGatewayException' event.
    } else if (isset($event['chunk'])) {
        // Handle the 'chunk' event.
    } else if (isset($event['conflictException'])) {
        // Handle the 'conflictException' event.
    } else if (isset($event['dependencyFailedException'])) {
        // Handle the 'dependencyFailedException' event.
    } else if (isset($event['internalServerException'])) {
        // Handle the 'internalServerException' event.
    } else if (isset($event['resourceNotFoundException'])) {
        // Handle the 'resourceNotFoundException' event.
    } else if (isset($event['returnControl'])) {
        // Handle the 'returnControl' event.
    } else if (isset($event['serviceQuotaExceededException'])) {
        // Handle the 'serviceQuotaExceededException' event.
    } else if (isset($event['throttlingException'])) {
        // Handle the 'throttlingException' event.
    } else if (isset($event['trace'])) {
        // Handle the 'trace' event.
    } else if (isset($event['validationException'])) {
        // Handle the 'validationException' event.
    }
}

Errors

ConflictException:

There was a conflict performing an operation. Resolve the conflict and retry your request.

ResourceNotFoundException:

The specified resource Amazon Resource Name (ARN) was not found. Check the Amazon Resource Name (ARN) and try your request again.

ValidationException:

Input validation failed. Check your request parameters and retry the request.

InternalServerException:

An internal server error occurred. Retry your request.

DependencyFailedException:

There was an issue with a dependency. Check the resource configurations and retry the request.

BadGatewayException:

There was an issue with a dependency due to a server issue. Retry your request.

ThrottlingException:

The number of requests exceeds the limit. Resubmit your request later.

AccessDeniedException:

The request is denied because of missing access permissions. Check your permissions and retry your request.

ServiceQuotaExceededException:

The number of requests exceeds the service quota. Resubmit your request later.

Retrieve 

$result = $client->retrieve([/* ... */]);
$promise = $client->retrieveAsync([/* ... */]);

Queries a knowledge base and retrieves information from it.

Parameter Syntax

$result = $client->retrieve([
    'knowledgeBaseId' => '<string>', // REQUIRED
    'nextToken' => '<string>',
    'retrievalConfiguration' => [
        'vectorSearchConfiguration' => [ // REQUIRED
            'filter' => [
                'andAll' => [
                    [...], // RECURSIVE
                    // ...
                ],
                'equals' => [
                    'key' => '<string>', // REQUIRED
                    'value' => [ // REQUIRED
                    ],
                ],
                'greaterThan' => [
                    'key' => '<string>', // REQUIRED
                    'value' => [ // REQUIRED
                    ],
                ],
                'greaterThanOrEquals' => [
                    'key' => '<string>', // REQUIRED
                    'value' => [ // REQUIRED
                    ],
                ],
                'in' => [
                    'key' => '<string>', // REQUIRED
                    'value' => [ // REQUIRED
                    ],
                ],
                'lessThan' => [
                    'key' => '<string>', // REQUIRED
                    'value' => [ // REQUIRED
                    ],
                ],
                'lessThanOrEquals' => [
                    'key' => '<string>', // REQUIRED
                    'value' => [ // REQUIRED
                    ],
                ],
                'listContains' => [
                    'key' => '<string>', // REQUIRED
                    'value' => [ // REQUIRED
                    ],
                ],
                'notEquals' => [
                    'key' => '<string>', // REQUIRED
                    'value' => [ // REQUIRED
                    ],
                ],
                'notIn' => [
                    'key' => '<string>', // REQUIRED
                    'value' => [ // REQUIRED
                    ],
                ],
                'orAll' => [
                    [...], // RECURSIVE
                    // ...
                ],
                'startsWith' => [
                    'key' => '<string>', // REQUIRED
                    'value' => [ // REQUIRED
                    ],
                ],
                'stringContains' => [
                    'key' => '<string>', // REQUIRED
                    'value' => [ // REQUIRED
                    ],
                ],
            ],
            'numberOfResults' => <integer>,
            'overrideSearchType' => 'HYBRID|SEMANTIC',
        ],
    ],
    'retrievalQuery' => [ // REQUIRED
        'text' => '<string>', // REQUIRED
    ],
]);

Parameter Details

Members
knowledgeBaseId
Required: Yes
Type: string

The unique identifier of the knowledge base to query.

nextToken
Type: string

If there are more results than can fit in the response, the response returns a nextToken. Use this token in the nextToken field of another request to retrieve the next batch of results.

retrievalConfiguration
Type: KnowledgeBaseRetrievalConfiguration structure

Contains configurations for the knowledge base query and retrieval process. For more information, see Query configurations.

retrievalQuery
Required: Yes
Type: KnowledgeBaseQuery structure

Contains the query to send the knowledge base.

Result Syntax

[
    'nextToken' => '<string>',
    'retrievalResults' => [
        [
            'content' => [
                'text' => '<string>',
            ],
            'location' => [
                's3Location' => [
                    'uri' => '<string>',
                ],
                'type' => 'S3',
            ],
            'metadata' => [
                '<RetrievalResultMetadataKey>' => [
                ],
                // ...
            ],
            'score' => <float>,
        ],
        // ...
    ],
]

Result Details

Members
nextToken
Type: string

If there are more results than can fit in the response, the response returns a nextToken. Use this token in the nextToken field of another request to retrieve the next batch of results.

retrievalResults
Required: Yes
Type: Array of KnowledgeBaseRetrievalResult structures

A list of results from querying the knowledge base.

Errors

ConflictException:

There was a conflict performing an operation. Resolve the conflict and retry your request.

ResourceNotFoundException:

The specified resource Amazon Resource Name (ARN) was not found. Check the Amazon Resource Name (ARN) and try your request again.

ValidationException:

Input validation failed. Check your request parameters and retry the request.

InternalServerException:

An internal server error occurred. Retry your request.

DependencyFailedException:

There was an issue with a dependency. Check the resource configurations and retry the request.

BadGatewayException:

There was an issue with a dependency due to a server issue. Retry your request.

ThrottlingException:

The number of requests exceeds the limit. Resubmit your request later.

AccessDeniedException:

The request is denied because of missing access permissions. Check your permissions and retry your request.

ServiceQuotaExceededException:

The number of requests exceeds the service quota. Resubmit your request later.

RetrieveAndGenerate 

$result = $client->retrieveAndGenerate([/* ... */]);
$promise = $client->retrieveAndGenerateAsync([/* ... */]);

Queries a knowledge base and generates responses based on the retrieved results. The response only cites sources that are relevant to the query.

Parameter Syntax

$result = $client->retrieveAndGenerate([
    'input' => [ // REQUIRED
        'text' => '<string>', // REQUIRED
    ],
    'retrieveAndGenerateConfiguration' => [
        'externalSourcesConfiguration' => [
            'generationConfiguration' => [
                'additionalModelRequestFields' => [
                    '<AdditionalModelRequestFieldsKey>' => [
                    ],
                    // ...
                ],
                'guardrailConfiguration' => [
                    'guardrailId' => '<string>', // REQUIRED
                    'guardrailVersion' => '<string>', // REQUIRED
                ],
                'inferenceConfig' => [
                    'textInferenceConfig' => [
                        'maxTokens' => <integer>,
                        'stopSequences' => ['<string>', ...],
                        'temperature' => <float>,
                        'topP' => <float>,
                    ],
                ],
                'promptTemplate' => [
                    'textPromptTemplate' => '<string>',
                ],
            ],
            'modelArn' => '<string>', // REQUIRED
            'sources' => [ // REQUIRED
                [
                    'byteContent' => [
                        'contentType' => '<string>', // REQUIRED
                        'data' => <string || resource || Psr\Http\Message\StreamInterface>, // REQUIRED
                        'identifier' => '<string>', // REQUIRED
                    ],
                    's3Location' => [
                        'uri' => '<string>', // REQUIRED
                    ],
                    'sourceType' => 'S3|BYTE_CONTENT', // REQUIRED
                ],
                // ...
            ],
        ],
        'knowledgeBaseConfiguration' => [
            'generationConfiguration' => [
                'additionalModelRequestFields' => [
                    '<AdditionalModelRequestFieldsKey>' => [
                    ],
                    // ...
                ],
                'guardrailConfiguration' => [
                    'guardrailId' => '<string>', // REQUIRED
                    'guardrailVersion' => '<string>', // REQUIRED
                ],
                'inferenceConfig' => [
                    'textInferenceConfig' => [
                        'maxTokens' => <integer>,
                        'stopSequences' => ['<string>', ...],
                        'temperature' => <float>,
                        'topP' => <float>,
                    ],
                ],
                'promptTemplate' => [
                    'textPromptTemplate' => '<string>',
                ],
            ],
            'knowledgeBaseId' => '<string>', // REQUIRED
            'modelArn' => '<string>', // REQUIRED
            'retrievalConfiguration' => [
                'vectorSearchConfiguration' => [ // REQUIRED
                    'filter' => [
                        'andAll' => [
                            [...], // RECURSIVE
                            // ...
                        ],
                        'equals' => [
                            'key' => '<string>', // REQUIRED
                            'value' => [ // REQUIRED
                            ],
                        ],
                        'greaterThan' => [
                            'key' => '<string>', // REQUIRED
                            'value' => [ // REQUIRED
                            ],
                        ],
                        'greaterThanOrEquals' => [
                            'key' => '<string>', // REQUIRED
                            'value' => [ // REQUIRED
                            ],
                        ],
                        'in' => [
                            'key' => '<string>', // REQUIRED
                            'value' => [ // REQUIRED
                            ],
                        ],
                        'lessThan' => [
                            'key' => '<string>', // REQUIRED
                            'value' => [ // REQUIRED
                            ],
                        ],
                        'lessThanOrEquals' => [
                            'key' => '<string>', // REQUIRED
                            'value' => [ // REQUIRED
                            ],
                        ],
                        'listContains' => [
                            'key' => '<string>', // REQUIRED
                            'value' => [ // REQUIRED
                            ],
                        ],
                        'notEquals' => [
                            'key' => '<string>', // REQUIRED
                            'value' => [ // REQUIRED
                            ],
                        ],
                        'notIn' => [
                            'key' => '<string>', // REQUIRED
                            'value' => [ // REQUIRED
                            ],
                        ],
                        'orAll' => [
                            [...], // RECURSIVE
                            // ...
                        ],
                        'startsWith' => [
                            'key' => '<string>', // REQUIRED
                            'value' => [ // REQUIRED
                            ],
                        ],
                        'stringContains' => [
                            'key' => '<string>', // REQUIRED
                            'value' => [ // REQUIRED
                            ],
                        ],
                    ],
                    'numberOfResults' => <integer>,
                    'overrideSearchType' => 'HYBRID|SEMANTIC',
                ],
            ],
        ],
        'type' => 'KNOWLEDGE_BASE|EXTERNAL_SOURCES', // REQUIRED
    ],
    'sessionConfiguration' => [
        'kmsKeyArn' => '<string>', // REQUIRED
    ],
    'sessionId' => '<string>',
]);

Parameter Details

Members
input
Required: Yes
Type: RetrieveAndGenerateInput structure

Contains the query to be made to the knowledge base.

retrieveAndGenerateConfiguration
Type: RetrieveAndGenerateConfiguration structure

Contains configurations for the knowledge base query and retrieval process. For more information, see Query configurations.

sessionConfiguration
Type: RetrieveAndGenerateSessionConfiguration structure

Contains details about the session with the knowledge base.

sessionId
Type: string

The unique identifier of the session. Reuse the same value to continue the same session with the knowledge base.

Result Syntax

[
    'citations' => [
        [
            'generatedResponsePart' => [
                'textResponsePart' => [
                    'span' => [
                        'end' => <integer>,
                        'start' => <integer>,
                    ],
                    'text' => '<string>',
                ],
            ],
            'retrievedReferences' => [
                [
                    'content' => [
                        'text' => '<string>',
                    ],
                    'location' => [
                        's3Location' => [
                            'uri' => '<string>',
                        ],
                        'type' => 'S3',
                    ],
                    'metadata' => [
                        '<RetrievalResultMetadataKey>' => [
                        ],
                        // ...
                    ],
                ],
                // ...
            ],
        ],
        // ...
    ],
    'guardrailAction' => 'INTERVENED|NONE',
    'output' => [
        'text' => '<string>',
    ],
    'sessionId' => '<string>',
]

Result Details

Members
citations
Type: Array of Citation structures

A list of segments of the generated response that are based on sources in the knowledge base, alongside information about the sources.

guardrailAction
Type: string

Specifies if there is a guardrail intervention in the response.

output
Required: Yes
Type: RetrieveAndGenerateOutput structure

Contains the response generated from querying the knowledge base.

sessionId
Required: Yes
Type: string

The unique identifier of the session. Reuse the same value to continue the same session with the knowledge base.

Errors

ConflictException:

There was a conflict performing an operation. Resolve the conflict and retry your request.

ResourceNotFoundException:

The specified resource Amazon Resource Name (ARN) was not found. Check the Amazon Resource Name (ARN) and try your request again.

ValidationException:

Input validation failed. Check your request parameters and retry the request.

InternalServerException:

An internal server error occurred. Retry your request.

DependencyFailedException:

There was an issue with a dependency. Check the resource configurations and retry the request.

BadGatewayException:

There was an issue with a dependency due to a server issue. Retry your request.

ThrottlingException:

The number of requests exceeds the limit. Resubmit your request later.

AccessDeniedException:

The request is denied because of missing access permissions. Check your permissions and retry your request.

ServiceQuotaExceededException:

The number of requests exceeds the service quota. Resubmit your request later.

Shapes

AccessDeniedException

Description

The request is denied because of missing access permissions. Check your permissions and retry your request.

Members
message
Type: string

ActionGroupInvocationInput

Description

Contains information about the action group being invoked. For more information about the possible structures, see the InvocationInput tab in OrchestrationTrace in the Amazon Bedrock User Guide.

Members
actionGroupName
Type: string

The name of the action group.

apiPath
Type: string

The path to the API to call, based off the action group.

function
Type: string

The function in the action group to call.

parameters
Type: Array of Parameter structures

The parameters in the Lambda input event.

requestBody
Type: RequestBody structure

The parameters in the request body for the Lambda input event.

verb
Type: string

The API method being used, based off the action group.

ActionGroupInvocationOutput

Description

Contains the JSON-formatted string returned by the API invoked by the action group.

Members
text
Type: string

The JSON-formatted string returned by the API invoked by the action group.

AdditionalModelRequestFieldsValue

Members

ApiInvocationInput

Description

Contains information about the API operation that the agent predicts should be called.

This data type is used in the following API operations:

Members
actionGroup
Required: Yes
Type: string

The action group that the API operation belongs to.

apiPath
Type: string

The path to the API operation.

httpMethod
Type: string

The HTTP method of the API operation.

parameters
Type: Array of ApiParameter structures

The parameters to provide for the API request, as the agent elicited from the user.

requestBody
Type: ApiRequestBody structure

The request body to provide for the API request, as the agent elicited from the user.

ApiParameter

Description

Information about a parameter to provide to the API request.

This data type is used in the following API operations:

Members
name
Type: string

The name of the parameter.

type
Type: string

The data type for the parameter.

value
Type: string

The value of the parameter.

ApiRequestBody

Description

The request body to provide for the API request, as the agent elicited from the user.

This data type is used in the following API operations:

Members
content
Type: Associative array of custom strings keys (String) to PropertyParameters structures

The content of the request body. The key of the object in this field is a media type defining the format of the request body.

ApiResult

Description

Contains information about the API operation that was called from the action group and the response body that was returned.

This data type is used in the following API operations:

Members
actionGroup
Required: Yes
Type: string

The action group that the API operation belongs to.

apiPath
Type: string

The path to the API operation.

httpMethod
Type: string

The HTTP method for the API operation.

httpStatusCode
Type: int

http status code from API execution response (for example: 200, 400, 500).

responseBody
Type: Associative array of custom strings keys (String) to ContentBody structures

The response body from the API operation. The key of the object is the content type (currently, only TEXT is supported). The response may be returned directly or from the Lambda function.

responseState
Type: string

Controls the final response state returned to end user when API/Function execution failed. When this state is FAILURE, the request would fail with dependency failure exception. When this state is REPROMPT, the API/function response will be sent to model for re-prompt

Attribution

Description

Contains citations for a part of an agent response.

Members
citations
Type: Array of Citation structures

A list of citations and related information for a part of an agent response.

BadGatewayException

Description

There was an issue with a dependency due to a server issue. Retry your request.

Members
message
Type: string
resourceName
Type: string

The name of the dependency that caused the issue, such as Amazon Bedrock, Lambda, or STS.

ByteContentDoc

Description

This property contains the document to chat with, along with its attributes.

Members
contentType
Required: Yes
Type: string

The MIME type of the document contained in the wrapper object.

data
Required: Yes
Type: blob (string|resource|Psr\Http\Message\StreamInterface)

The byte value of the file to upload, encoded as a Base-64 string.

identifier
Required: Yes
Type: string

The file name of the document contained in the wrapper object.

Citation

Description

An object containing a segment of the generated response that is based on a source in the knowledge base, alongside information about the source.

This data type is used in the following API operations:

Members
generatedResponsePart
Type: GeneratedResponsePart structure

Contains the generated response and metadata

retrievedReferences
Type: Array of RetrievedReference structures

Contains metadata about the sources cited for the generated response.

ConflictException

Description

There was a conflict performing an operation. Resolve the conflict and retry your request.

Members
message
Type: string

ContentBody

Description

Contains the body of the API response.

This data type is used in the following API operations:

Members
body
Type: string

The body of the API response.

DependencyFailedException

Description

There was an issue with a dependency. Check the resource configurations and retry the request.

Members
message
Type: string
resourceName
Type: string

The name of the dependency that caused the issue, such as Amazon Bedrock, Lambda, or STS.

ExternalSource

Description

The unique external source of the content contained in the wrapper object.

Members
byteContent
Type: ByteContentDoc structure

The identifier, contentType, and data of the external source wrapper object.

s3Location
Type: S3ObjectDoc structure

The S3 location of the external source wrapper object.

sourceType
Required: Yes
Type: string

The source type of the external source wrapper object.

ExternalSourcesGenerationConfiguration

Description

Contains the generation configuration of the external source wrapper object.

Members
additionalModelRequestFields
Type: Associative array of custom strings keys (AdditionalModelRequestFieldsKey) to document (null|bool|string|numeric) or an (array|associative array) whose members are all valid documentss

Additional model parameters and their corresponding values not included in the textInferenceConfig structure for an external source. Takes in custom model parameters specific to the language model being used.

guardrailConfiguration
Type: GuardrailConfiguration structure

The configuration details for the guardrail.

inferenceConfig
Type: InferenceConfig structure

Configuration settings for inference when using RetrieveAndGenerate to generate responses while using an external source.

promptTemplate
Type: PromptTemplate structure

Contain the textPromptTemplate string for the external source wrapper object.

ExternalSourcesRetrieveAndGenerateConfiguration

Description

The configurations of the external source wrapper object in the retrieveAndGenerate function.

Members
generationConfiguration
Type: ExternalSourcesGenerationConfiguration structure

The prompt used with the external source wrapper object with the retrieveAndGenerate function.

modelArn
Required: Yes
Type: string

The modelArn used with the external source wrapper object in the retrieveAndGenerate function.

sources
Required: Yes
Type: Array of ExternalSource structures

The document used with the external source wrapper object in the retrieveAndGenerate function.

FailureTrace

Description

Contains information about the failure of the interaction.

Members
failureReason
Type: string

The reason the interaction failed.

traceId
Type: string

The unique identifier of the trace.

FilterAttribute

Description

Specifies the name that the metadata attribute must match and the value to which to compare the value of the metadata attribute. For more information, see Query configurations.

This data type is used in the following API operations:

Members
key
Required: Yes
Type: string

The name that the metadata attribute must match.

value
Required: Yes
Type: document (null|bool|string|numeric) or an (array|associative array) whose members are all valid documents

The value to whcih to compare the value of the metadata attribute.

FilterValue

Members

FinalResponse

Description

Contains details about the response to the user.

Members
text
Type: string

The text in the response to the user.

FunctionInvocationInput

Description

Contains information about the function that the agent predicts should be called.

This data type is used in the following API operations:

Members
actionGroup
Required: Yes
Type: string

The action group that the function belongs to.

function
Type: string

The name of the function.

parameters
Type: Array of FunctionParameter structures

A list of parameters of the function.

FunctionParameter

Description

Contains information about a parameter of the function.

This data type is used in the following API operations:

Members
name
Type: string

The name of the parameter.

type
Type: string

The data type of the parameter.

value
Type: string

The value of the parameter.

FunctionResult

Description

Contains information about the function that was called from the action group and the response that was returned.

This data type is used in the following API operations:

Members
actionGroup
Required: Yes
Type: string

The action group that the function belongs to.

function
Type: string

The name of the function that was called.

responseBody
Type: Associative array of custom strings keys (String) to ContentBody structures

The response from the function call using the parameters. The key of the object is the content type (currently, only TEXT is supported). The response may be returned directly or from the Lambda function.

responseState
Type: string

Controls the final response state returned to end user when API/Function execution failed. When this state is FAILURE, the request would fail with dependency failure exception. When this state is REPROMPT, the API/function response will be sent to model for re-prompt

GeneratedResponsePart

Description

Contains metadata about a part of the generated response that is accompanied by a citation.

This data type is used in the following API operations:

Members
textResponsePart
Type: TextResponsePart structure

Contains metadata about a textual part of the generated response that is accompanied by a citation.

GenerationConfiguration

Description

Contains configurations for response generation based on the knowledge base query results.

This data type is used in the following API operations:

Members
additionalModelRequestFields
Type: Associative array of custom strings keys (AdditionalModelRequestFieldsKey) to document (null|bool|string|numeric) or an (array|associative array) whose members are all valid documentss

Additional model parameters and corresponding values not included in the textInferenceConfig structure for a knowledge base. This allows users to provide custom model parameters specific to the language model being used.

guardrailConfiguration
Type: GuardrailConfiguration structure

The configuration details for the guardrail.

inferenceConfig
Type: InferenceConfig structure

Configuration settings for inference when using RetrieveAndGenerate to generate responses while using a knowledge base as a source.

promptTemplate
Type: PromptTemplate structure

Contains the template for the prompt that's sent to the model for response generation.

GuardrailAssessment

Description

Assessment details of the content analyzed by Guardrails.

Members
contentPolicy
Type: GuardrailContentPolicyAssessment structure

Content policy details of the Guardrail.

sensitiveInformationPolicy
Type: GuardrailSensitiveInformationPolicyAssessment structure

Sensitive Information policy details of Guardrail.

topicPolicy
Type: GuardrailTopicPolicyAssessment structure

Topic policy details of the Guardrail.

wordPolicy
Type: GuardrailWordPolicyAssessment structure

Word policy details of the Guardrail.

GuardrailConfiguration

Description

The configuration details for the guardrail.

Members
guardrailId
Required: Yes
Type: string

The unique identifier for the guardrail.

guardrailVersion
Required: Yes
Type: string

The version of the guardrail.

GuardrailContentFilter

Description

Details of the content filter used in the Guardrail.

Members
action
Type: string

The action placed on the content by the Guardrail filter.

confidence
Type: string

The confidence level regarding the content detected in the filter by the Guardrail.

type
Type: string

The type of content detected in the filter by the Guardrail.

GuardrailContentPolicyAssessment

Description

The details of the policy assessment in the Guardrails filter.

Members
filters
Type: Array of GuardrailContentFilter structures

The filter details of the policy assessment used in the Guardrails filter.

GuardrailCustomWord

Description

The custom word details for the filter in the Guardrail.

Members
action
Type: string

The action details for the custom word filter in the Guardrail.

match
Type: string

The match details for the custom word filter in the Guardrail.

GuardrailManagedWord

Description

The managed word details for the filter in the Guardrail.

Members
action
Type: string

The action details for the managed word filter in the Guardrail.

match
Type: string

The match details for the managed word filter in the Guardrail.

type
Type: string

The type details for the managed word filter in the Guardrail.

GuardrailPiiEntityFilter

Description

The Guardrail filter to identify and remove personally identifiable information (PII).

Members
action
Type: string

The action of the Guardrail filter to identify and remove PII.

match
Type: string

The match to settings in the Guardrail filter to identify and remove PII.

type
Type: string

The type of PII the Guardrail filter has identified and removed.

GuardrailRegexFilter

Description

The details for the regex filter used in the Guardrail.

Members
action
Type: string

The action details for the regex filter used in the Guardrail.

match
Type: string

The match details for the regex filter used in the Guardrail.

name
Type: string

The name details for the regex filter used in the Guardrail.

regex
Type: string

The regex details for the regex filter used in the Guardrail.

GuardrailSensitiveInformationPolicyAssessment

Description

The details of the sensitive policy assessment used in the Guardrail.

Members
piiEntities
Type: Array of GuardrailPiiEntityFilter structures

The details of the PII entities used in the sensitive policy assessment for the Guardrail.

regexes
Type: Array of GuardrailRegexFilter structures

The details of the regexes used in the sensitive policy assessment for the Guardrail.

GuardrailTopic

Description

The details for a specific topic defined in the Guardrail.

Members
action
Type: string

The action details on a specific topic in the Guardrail.

name
Type: string

The name details on a specific topic in the Guardrail.

type
Type: string

The type details on a specific topic in the Guardrail.

GuardrailTopicPolicyAssessment

Description

The details of the policy assessment used in the Guardrail.

Members
topics
Type: Array of GuardrailTopic structures

The topic details of the policy assessment used in the Guardrail.

GuardrailTrace

Description

The trace details used in the Guardrail.

Members
action
Type: string

The trace action details used with the Guardrail.

inputAssessments
Type: Array of GuardrailAssessment structures

The details of the input assessments used in the Guardrail Trace.

outputAssessments
Type: Array of GuardrailAssessment structures

The details of the output assessments used in the Guardrail Trace.

traceId
Type: string

The details of the trace Id used in the Guardrail Trace.

GuardrailWordPolicyAssessment

Description

The assessment details for words defined in the Guardrail filter.

Members
customWords
Type: Array of GuardrailCustomWord structures

The custom word details for words defined in the Guardrail filter.

managedWordLists
Type: Array of GuardrailManagedWord structures

The managed word lists for words defined in the Guardrail filter.

InferenceConfig

Description

The configuration for inference settings when generating responses using RetrieveAndGenerate.

Members
textInferenceConfig
Type: TextInferenceConfig structure

Configuration settings specific to text generation while generating responses using RetrieveAndGenerate.

InferenceConfiguration

Description

Specifications about the inference parameters that were provided alongside the prompt. These are specified in the PromptOverrideConfiguration object that was set when the agent was created or updated. For more information, see Inference parameters for foundation models.

Members
maximumLength
Type: int

The maximum number of tokens allowed in the generated response.

stopSequences
Type: Array of strings

A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response.

temperature
Type: float

The likelihood of the model selecting higher-probability options while generating a response. A lower value makes the model more likely to choose higher-probability options, while a higher value makes the model more likely to choose lower-probability options.

topK
Type: int

While generating a response, the model determines the probability of the following token at each point of generation. The value that you set for topK is the number of most-likely candidates from which the model chooses the next token in the sequence. For example, if you set topK to 50, the model selects the next token from among the top 50 most likely choices.

topP
Type: float

While generating a response, the model determines the probability of the following token at each point of generation. The value that you set for Top P determines the number of most-likely candidates from which the model chooses the next token in the sequence. For example, if you set topP to 80, the model only selects the next token from the top 80% of the probability distribution of next tokens.

InternalServerException

Description

An internal server error occurred. Retry your request.

Members
message
Type: string

InvocationInput

Description

Contains information pertaining to the action group or knowledge base that is being invoked.

Members
actionGroupInvocationInput
Type: ActionGroupInvocationInput structure

Contains information about the action group to be invoked.

invocationType
Type: string

Specifies whether the agent is invoking an action group or a knowledge base.

knowledgeBaseLookupInput
Type: KnowledgeBaseLookupInput structure

Contains details about the knowledge base to look up and the query to be made.

traceId
Type: string

The unique identifier of the trace.

InvocationInputMember

Description

Contains details about the API operation or function that the agent predicts should be called.

This data type is used in the following API operations:

Members
apiInvocationInput
Type: ApiInvocationInput structure

Contains information about the API operation that the agent predicts should be called.

functionInvocationInput
Type: FunctionInvocationInput structure

Contains information about the function that the agent predicts should be called.

KnowledgeBaseLookupInput

Description

Contains details about the knowledge base to look up and the query to be made.

Members
knowledgeBaseId
Type: string

The unique identifier of the knowledge base to look up.

text
Type: string

The query made to the knowledge base.

KnowledgeBaseLookupOutput

Description

Contains details about the results from looking up the knowledge base.

Members
retrievedReferences
Type: Array of RetrievedReference structures

Contains metadata about the sources cited for the generated response.

KnowledgeBaseQuery

Description

Contains the query made to the knowledge base.

This data type is used in the following API operations:

Members
text
Required: Yes
Type: string

The text of the query made to the knowledge base.

KnowledgeBaseRetrievalConfiguration

Description

Contains configurations for the knowledge base query and retrieval process. For more information, see Query configurations.

This data type is used in the following API operations:

Members
vectorSearchConfiguration
Required: Yes
Type: KnowledgeBaseVectorSearchConfiguration structure

Contains details about how the results from the vector search should be returned. For more information, see Query configurations.

KnowledgeBaseRetrievalResult

Description

Details about a result from querying the knowledge base.

This data type is used in the following API operations:

Members
content
Required: Yes
Type: RetrievalResultContent structure

Contains a chunk of text from a data source in the knowledge base.

location
Type: RetrievalResultLocation structure

Contains information about the location of the data source.

metadata
Type: Associative array of custom strings keys (RetrievalResultMetadataKey) to document (null|bool|string|numeric) or an (array|associative array) whose members are all valid documentss

Contains metadata attributes and their values for the file in the data source. For more information, see Metadata and filtering.

score
Type: double

The level of relevance of the result to the query.

KnowledgeBaseRetrieveAndGenerateConfiguration

Description

Contains details about the resource being queried.

This data type is used in the following API operations:

Members
generationConfiguration
Type: GenerationConfiguration structure

Contains configurations for response generation based on the knowwledge base query results.

knowledgeBaseId
Required: Yes
Type: string

The unique identifier of the knowledge base that is queried and the foundation model used for generation.

modelArn
Required: Yes
Type: string

The ARN of the foundation model used to generate a response.

retrievalConfiguration
Type: KnowledgeBaseRetrievalConfiguration structure

Contains configurations for how to retrieve and return the knowledge base query.

KnowledgeBaseVectorSearchConfiguration

Description

Configurations for how to perform the search query and return results. For more information, see Query configurations.

This data type is used in the following API operations:

Members
filter
Type: RetrievalFilter structure

Specifies the filters to use on the metadata in the knowledge base data sources before returning results. For more information, see Query configurations.

numberOfResults
Type: int

The number of source chunks to retrieve.

overrideSearchType
Type: string

By default, Amazon Bedrock decides a search strategy for you. If you're using an Amazon OpenSearch Serverless vector store that contains a filterable text field, you can specify whether to query the knowledge base with a HYBRID search using both vector embeddings and raw text, or SEMANTIC search using only vector embeddings. For other vector store configurations, only SEMANTIC search is available. For more information, see Test a knowledge base.

ModelInvocationInput

Description

The input for the pre-processing step.

  • The type matches the agent step.

  • The text contains the prompt.

  • The inferenceConfiguration, parserMode, and overrideLambda values are set in the PromptOverrideConfiguration object that was set when the agent was created or updated.

Members
inferenceConfiguration
Type: InferenceConfiguration structure

Specifications about the inference parameters that were provided alongside the prompt. These are specified in the PromptOverrideConfiguration object that was set when the agent was created or updated. For more information, see Inference parameters for foundation models.

overrideLambda
Type: string

The ARN of the Lambda function to use when parsing the raw foundation model output in parts of the agent sequence.

parserMode
Type: string

Specifies whether to override the default parser Lambda function when parsing the raw foundation model output in the part of the agent sequence defined by the promptType.

promptCreationMode
Type: string

Specifies whether the default prompt template was OVERRIDDEN. If it was, the basePromptTemplate that was set in the PromptOverrideConfiguration object when the agent was created or updated is used instead.

text
Type: string

The text that prompted the agent at this step.

traceId
Type: string

The unique identifier of the trace.

type
Type: string

The step in the agent sequence.

Observation

Description

Contains the result or output of an action group or knowledge base, or the response to the user.

Members
actionGroupInvocationOutput
Type: ActionGroupInvocationOutput structure

Contains the JSON-formatted string returned by the API invoked by the action group.

finalResponse
Type: FinalResponse structure

Contains details about the response to the user.

knowledgeBaseLookupOutput
Type: KnowledgeBaseLookupOutput structure

Contains details about the results from looking up the knowledge base.

repromptResponse
Type: RepromptResponse structure

Contains details about the response to reprompt the input.

traceId
Type: string

The unique identifier of the trace.

type
Type: string

Specifies what kind of information the agent returns in the observation. The following values are possible.

  • ACTION_GROUP – The agent returns the result of an action group.

  • KNOWLEDGE_BASE – The agent returns information from a knowledge base.

  • FINISH – The agent returns a final response to the user with no follow-up.

  • ASK_USER – The agent asks the user a question.

  • REPROMPT – The agent prompts the user again for the same information.

OrchestrationTrace

Description

Details about the orchestration step, in which the agent determines the order in which actions are executed and which knowledge bases are retrieved.

Members
invocationInput
Type: InvocationInput structure

Contains information pertaining to the action group or knowledge base that is being invoked.

modelInvocationInput
Type: ModelInvocationInput structure

The input for the orchestration step.

  • The type is ORCHESTRATION.

  • The text contains the prompt.

  • The inferenceConfiguration, parserMode, and overrideLambda values are set in the PromptOverrideConfiguration object that was set when the agent was created or updated.

observation
Type: Observation structure

Details about the observation (the output of the action group Lambda or knowledge base) made by the agent.

rationale
Type: Rationale structure

Details about the reasoning, based on the input, that the agent uses to justify carrying out an action group or getting information from a knowledge base.

Parameter

Description

A parameter for the API request or function.

Members
name
Type: string

The name of the parameter.

type
Type: string

The type of the parameter.

value
Type: string

The value of the parameter.

PayloadPart

Description

Contains a part of an agent response and citations for it.

Members
attribution
Type: Attribution structure

Contains citations for a part of an agent response.

bytes
Type: blob (string|resource|Psr\Http\Message\StreamInterface)

A part of the agent response in bytes.

PostProcessingModelInvocationOutput

Description

The foundation model output from the post-processing step.

Members
parsedResponse
Type: PostProcessingParsedResponse structure

Details about the response from the Lambda parsing of the output of the post-processing step.

traceId
Type: string

The unique identifier of the trace.

PostProcessingParsedResponse

Description

Details about the response from the Lambda parsing of the output from the post-processing step.

Members
text
Type: string

The text returned by the parser.

PostProcessingTrace

Description

Details about the post-processing step, in which the agent shapes the response.

Members
modelInvocationInput
Type: ModelInvocationInput structure

The input for the post-processing step.

  • The type is POST_PROCESSING.

  • The text contains the prompt.

  • The inferenceConfiguration, parserMode, and overrideLambda values are set in the PromptOverrideConfiguration object that was set when the agent was created or updated.

modelInvocationOutput
Type: PostProcessingModelInvocationOutput structure

The foundation model output from the post-processing step.

PreProcessingModelInvocationOutput

Description

The foundation model output from the pre-processing step.

Members
parsedResponse
Type: PreProcessingParsedResponse structure

Details about the response from the Lambda parsing of the output of the pre-processing step.

traceId
Type: string

The unique identifier of the trace.

PreProcessingParsedResponse

Description

Details about the response from the Lambda parsing of the output from the pre-processing step.

Members
isValid
Type: boolean

Whether the user input is valid or not. If false, the agent doesn't proceed to orchestration.

rationale
Type: string

The text returned by the parsing of the pre-processing step, explaining the steps that the agent plans to take in orchestration, if the user input is valid.

PreProcessingTrace

Description

Details about the pre-processing step, in which the agent contextualizes and categorizes user inputs.

Members
modelInvocationInput
Type: ModelInvocationInput structure

The input for the pre-processing step.

  • The type is PRE_PROCESSING.

  • The text contains the prompt.

  • The inferenceConfiguration, parserMode, and overrideLambda values are set in the PromptOverrideConfiguration object that was set when the agent was created or updated.

modelInvocationOutput
Type: PreProcessingModelInvocationOutput structure

The foundation model output from the pre-processing step.

PromptTemplate

Description

Contains the template for the prompt that's sent to the model for response generation. For more information, see Knowledge base prompt templates.

This data type is used in the following API operations:

Members
textPromptTemplate
Type: string

The template for the prompt that's sent to the model for response generation. You can include prompt placeholders, which become replaced before the prompt is sent to the model to provide instructions and context to the model. In addition, you can include XML tags to delineate meaningful sections of the prompt template.

For more information, see the following resources:

PropertyParameters

Description

Contains the parameters in the request body.

Members
properties
Type: Array of Parameter structures

A list of parameters in the request body.

Rationale

Description

Contains the reasoning, based on the input, that the agent uses to justify carrying out an action group or getting information from a knowledge base.

Members
text
Type: string

The reasoning or thought process of the agent, based on the input.

traceId
Type: string

The unique identifier of the trace step.

RepromptResponse

Description

Contains details about the agent's response to reprompt the input.

Members
source
Type: string

Specifies what output is prompting the agent to reprompt the input.

text
Type: string

The text reprompting the input.

RequestBody

Description

The parameters in the API request body.

Members
content
Type: Associative array of custom strings keys (String) to Parameter structuress

The content in the request body.

ResourceNotFoundException

Description

The specified resource Amazon Resource Name (ARN) was not found. Check the Amazon Resource Name (ARN) and try your request again.

Members
message
Type: string

ResponseStream

Description

The response from invoking the agent and associated citations and trace information.

Members
accessDeniedException
Type: AccessDeniedException structure

The request is denied because of missing access permissions. Check your permissions and retry your request.

badGatewayException
Type: BadGatewayException structure

There was an issue with a dependency due to a server issue. Retry your request.

chunk
Type: PayloadPart structure

Contains a part of an agent response and citations for it.

conflictException
Type: ConflictException structure

There was a conflict performing an operation. Resolve the conflict and retry your request.

dependencyFailedException
Type: DependencyFailedException structure

There was an issue with a dependency. Check the resource configurations and retry the request.

internalServerException
Type: InternalServerException structure

An internal server error occurred. Retry your request.

resourceNotFoundException
Type: ResourceNotFoundException structure

The specified resource Amazon Resource Name (ARN) was not found. Check the Amazon Resource Name (ARN) and try your request again.

returnControl
Type: ReturnControlPayload structure

Contains the parameters and information that the agent elicited from the customer to carry out an action. This information is returned to the system and can be used in your own setup for fulfilling the action.

serviceQuotaExceededException
Type: ServiceQuotaExceededException structure

The number of requests exceeds the service quota. Resubmit your request later.

throttlingException
Type: ThrottlingException structure

The number of requests exceeds the limit. Resubmit your request later.

trace
Type: TracePart structure

Contains information about the agent and session, alongside the agent's reasoning process and results from calling actions and querying knowledge bases and metadata about the trace. You can use the trace to understand how the agent arrived at the response it provided the customer. For more information, see Trace events.

validationException
Type: ValidationException structure

Input validation failed. Check your request parameters and retry the request.

RetrievalFilter

Description

Specifies the filters to use on the metadata attributes in the knowledge base data sources before returning results. For more information, see Query configurations. See the examples below to see how to use these filters.

This data type is used in the following API operations:

Members
andAll
Type: Array of RetrievalFilter structures

Knowledge base data sources are returned if their metadata attributes fulfill all the filter conditions inside this list.

equals
Type: FilterAttribute structure

Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value matches the value in this object.

The following example would return data sources with an animal attribute whose value is cat:

"equals": { "key": "animal", "value": "cat" }

greaterThan
Type: FilterAttribute structure

Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is greater than the value in this object.

The following example would return data sources with an year attribute whose value is greater than 1989:

"greaterThan": { "key": "year", "value": 1989 }

greaterThanOrEquals
Type: FilterAttribute structure

Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is greater than or equal to the value in this object.

The following example would return data sources with an year attribute whose value is greater than or equal to 1989:

"greaterThanOrEquals": { "key": "year", "value": 1989 }

in
Type: FilterAttribute structure

Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is in the list specified in the value in this object.

The following example would return data sources with an animal attribute that is either cat or dog:

"in": { "key": "animal", "value": ["cat", "dog"] }

lessThan
Type: FilterAttribute structure

Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is less than the value in this object.

The following example would return data sources with an year attribute whose value is less than to 1989.

"lessThan": { "key": "year", "value": 1989 }

lessThanOrEquals
Type: FilterAttribute structure

Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is less than or equal to the value in this object.

The following example would return data sources with an year attribute whose value is less than or equal to 1989.

"lessThanOrEquals": { "key": "year", "value": 1989 }

listContains
Type: FilterAttribute structure

Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is a list that contains the value as one of its members.

The following example would return data sources with an animals attribute that is a list containing a cat member (for example ["dog", "cat"]).

"listContains": { "key": "animals", "value": "cat" }

notEquals
Type: FilterAttribute structure

Knowledge base data sources that contain a metadata attribute whose name matches the key and whose value doesn't match the value in this object are returned.

The following example would return data sources that don't contain an animal attribute whose value is cat.

"notEquals": { "key": "animal", "value": "cat" }

notIn
Type: FilterAttribute structure

Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value isn't in the list specified in the value in this object.

The following example would return data sources whose animal attribute is neither cat nor dog.

"notIn": { "key": "animal", "value": ["cat", "dog"] }

orAll
Type: Array of RetrievalFilter structures

Knowledge base data sources are returned if their metadata attributes fulfill at least one of the filter conditions inside this list.

startsWith
Type: FilterAttribute structure

Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value starts with the value in this object. This filter is currently only supported for Amazon OpenSearch Serverless vector stores.

The following example would return data sources with an animal attribute starts with ca (for example, cat or camel).

"startsWith": { "key": "animal", "value": "ca" }

stringContains
Type: FilterAttribute structure

Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is one of the following:

  • A string that contains the value as a substring. The following example would return data sources with an animal attribute that contains the substring at (for example cat).

    "stringContains": { "key": "animal", "value": "at" }

  • A list with a member that contains the value as a substring. The following example would return data sources with an animals attribute that is a list containing a member that contains the substring at (for example ["dog", "cat"]).

    "stringContains": { "key": "animals", "value": "at" }

RetrievalResultContent

Description

Contains the cited text from the data source.

This data type is used in the following API operations:

Members
text
Required: Yes
Type: string

The cited text from the data source.

RetrievalResultLocation

Description

Contains information about the location of the data source.

This data type is used in the following API operations:

Members
s3Location
Type: RetrievalResultS3Location structure

Contains the S3 location of the data source.

type
Required: Yes
Type: string

The type of the location of the data source.

RetrievalResultMetadataValue

Members

RetrievalResultS3Location

Description

Contains the S3 location of the data source.

This data type is used in the following API operations:

Members
uri
Type: string

The S3 URI of the data source.

RetrieveAndGenerateConfiguration

Description

Contains details about the resource being queried.

This data type is used in the following API operations:

Members
externalSourcesConfiguration
Type: ExternalSourcesRetrieveAndGenerateConfiguration structure

The configuration used with the external source wrapper object in the retrieveAndGenerate function.

knowledgeBaseConfiguration
Type: KnowledgeBaseRetrieveAndGenerateConfiguration structure

Contains details about the resource being queried.

type
Required: Yes
Type: string

The type of resource that is queried by the request.

RetrieveAndGenerateInput

Description

Contains the query made to the knowledge base.

This data type is used in the following API operations:

Members
text
Required: Yes
Type: string

The query made to the knowledge base.

RetrieveAndGenerateOutput

Description

Contains the response generated from querying the knowledge base.

This data type is used in the following API operations:

Members
text
Required: Yes
Type: string

The response generated from querying the knowledge base.

RetrieveAndGenerateSessionConfiguration

Description

Contains configuration about the session with the knowledge base.

This data type is used in the following API operations:

Members
kmsKeyArn
Required: Yes
Type: string

The ARN of the KMS key encrypting the session.

RetrievedReference

Description

Contains metadata about a source cited for the generated response.

This data type is used in the following API operations:

Members
content
Type: RetrievalResultContent structure

Contains the cited text from the data source.

location
Type: RetrievalResultLocation structure

Contains information about the location of the data source.

metadata
Type: Associative array of custom strings keys (RetrievalResultMetadataKey) to document (null|bool|string|numeric) or an (array|associative array) whose members are all valid documentss

Contains metadata attributes and their values for the file in the data source. For more information, see Metadata and filtering.

ReturnControlPayload

Description

Contains information to return from the action group that the agent has predicted to invoke.

This data type is used in the following API operations:

Members
invocationId
Type: string

The identifier of the action group invocation.

invocationInputs
Type: Array of InvocationInputMember structures

A list of objects that contain information about the parameters and inputs that need to be sent into the API operation or function, based on what the agent determines from its session with the user.

S3ObjectDoc

Description

The unique wrapper object of the document from the S3 location.

Members
uri
Required: Yes
Type: string

The file location of the S3 wrapper object.

ServiceQuotaExceededException

Description

The number of requests exceeds the service quota. Resubmit your request later.

Members
message
Type: string

SessionState

Description

Contains parameters that specify various attributes that persist across a session or prompt. You can define session state attributes as key-value pairs when writing a Lambda function for an action group or pass them when making an InvokeAgent request. Use session state attributes to control and provide conversational context for your agent and to help customize your agent's behavior. For more information, see Control session context.

Members
invocationId
Type: string

The identifier of the invocation of an action. This value must match the invocationId returned in the InvokeAgent response for the action whose results are provided in the returnControlInvocationResults field. For more information, see Return control to the agent developer and Control session context.

promptSessionAttributes
Type: Associative array of custom strings keys (String) to strings

Contains attributes that persist across a prompt and the values of those attributes. These attributes replace the $prompt_session_attributes$ placeholder variable in the orchestration prompt template. For more information, see Prompt template placeholder variables.

returnControlInvocationResults
Type: Array of InvocationResultMember structures

Contains information about the results from the action group invocation. For more information, see Return control to the agent developer and Control session context.

If you include this field, the inputText field will be ignored.

sessionAttributes
Type: Associative array of custom strings keys (String) to strings

Contains attributes that persist across a session and the values of those attributes.

Span

Description

Contains information about where the text with a citation begins and ends in the generated output.

This data type is used in the following API operations:

Members
end
Type: int

Where the text with a citation ends in the generated output.

start
Type: int

Where the text with a citation starts in the generated output.

TextInferenceConfig

Description

Configuration settings for text generation using a language model via the RetrieveAndGenerate operation. Includes parameters like temperature, top-p, maximum token count, and stop sequences.

The valid range of maxTokens depends on the accepted values for your chosen model's inference parameters. To see the inference parameters for your model, see Inference parameters for foundation models.

Members
maxTokens
Type: int

The maximum number of tokens to generate in the output text. Do not use the minimum of 0 or the maximum of 65536. The limit values described here are arbitary values, for actual values consult the limits defined by your specific model.

stopSequences
Type: Array of strings

A list of sequences of characters that, if generated, will cause the model to stop generating further tokens. Do not use a minimum length of 1 or a maximum length of 1000. The limit values described here are arbitary values, for actual values consult the limits defined by your specific model.

temperature
Type: float

Controls the random-ness of text generated by the language model, influencing how much the model sticks to the most predictable next words versus exploring more surprising options. A lower temperature value (e.g. 0.2 or 0.3) makes model outputs more deterministic or predictable, while a higher temperature (e.g. 0.8 or 0.9) makes the outputs more creative or unpredictable.

topP
Type: float

A probability distribution threshold which controls what the model considers for the set of possible next tokens. The model will only consider the top p% of the probability distribution when generating the next token.

TextResponsePart

Description

Contains the part of the generated text that contains a citation, alongside where it begins and ends.

This data type is used in the following API operations:

Members
span
Type: Span structure

Contains information about where the text with a citation begins and ends in the generated output.

text
Type: string

The part of the generated text that contains a citation.

ThrottlingException

Description

The number of requests exceeds the limit. Resubmit your request later.

Members
message
Type: string

Trace

Description

Contains one part of the agent's reasoning process and results from calling API actions and querying knowledge bases. You can use the trace to understand how the agent arrived at the response it provided the customer. For more information, see Trace enablement.

Members
failureTrace
Type: FailureTrace structure

Contains information about the failure of the interaction.

guardrailTrace
Type: GuardrailTrace structure

The trace details for a trace defined in the Guardrail filter.

orchestrationTrace
Type: OrchestrationTrace structure

Details about the orchestration step, in which the agent determines the order in which actions are executed and which knowledge bases are retrieved.

postProcessingTrace
Type: PostProcessingTrace structure

Details about the post-processing step, in which the agent shapes the response..

preProcessingTrace
Type: PreProcessingTrace structure

Details about the pre-processing step, in which the agent contextualizes and categorizes user inputs.

TracePart

Description

Contains information about the agent and session, alongside the agent's reasoning process and results from calling API actions and querying knowledge bases and metadata about the trace. You can use the trace to understand how the agent arrived at the response it provided the customer. For more information, see Trace enablement.

Members
agentAliasId
Type: string

The unique identifier of the alias of the agent.

agentId
Type: string

The unique identifier of the agent.

agentVersion
Type: string

The version of the agent.

sessionId
Type: string

The unique identifier of the session with the agent.

trace
Type: Trace structure

Contains one part of the agent's reasoning process and results from calling API actions and querying knowledge bases. You can use the trace to understand how the agent arrived at the response it provided the customer. For more information, see Trace enablement.

ValidationException

Description

Input validation failed. Check your request parameters and retry the request.

Members
message
Type: string