Class: Aws::BedrockAgent::Client

Inherits:
Seahorse::Client::Base show all
Includes:
ClientStubs
Defined in:
gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb

Overview

An API client for BedrockAgent. To construct a client, you need to configure a :region and :credentials.

client = Aws::BedrockAgent::Client.new(
  region: region_name,
  credentials: credentials,
  # ...
)

For details on configuring region and credentials see the developer guide.

See #initialize for a full list of supported configuration options.

Instance Attribute Summary

Attributes inherited from Seahorse::Client::Base

#config, #handlers

API Operations collapse

Instance Method Summary collapse

Methods included from ClientStubs

#api_requests, #stub_data, #stub_responses

Methods inherited from Seahorse::Client::Base

add_plugin, api, clear_plugins, define, new, #operation_names, plugins, remove_plugin, set_api, set_plugins

Methods included from Seahorse::Client::HandlerBuilder

#handle, #handle_request, #handle_response

Constructor Details

#initialize(options) ⇒ Client

Returns a new instance of Client.

Parameters:

  • options (Hash)

Options Hash (options):

  • :plugins (Array<Seahorse::Client::Plugin>) — default: []] —

    A list of plugins to apply to the client. Each plugin is either a class name or an instance of a plugin class.

  • :credentials (required, Aws::CredentialProvider) —

    Your AWS credentials. This can be an instance of any one of the following classes:

    • Aws::Credentials - Used for configuring static, non-refreshing credentials.

    • Aws::SharedCredentials - Used for loading static credentials from a shared file, such as ~/.aws/config.

    • Aws::AssumeRoleCredentials - Used when you need to assume a role.

    • Aws::AssumeRoleWebIdentityCredentials - Used when you need to assume a role after providing credentials via the web.

    • Aws::SSOCredentials - Used for loading credentials from AWS SSO using an access token generated from aws login.

    • Aws::ProcessCredentials - Used for loading credentials from a process that outputs to stdout.

    • Aws::InstanceProfileCredentials - Used for loading credentials from an EC2 IMDS on an EC2 instance.

    • Aws::ECSCredentials - Used for loading credentials from instances running in ECS.

    • Aws::CognitoIdentityCredentials - Used for loading credentials from the Cognito Identity service.

    When :credentials are not configured directly, the following locations will be searched for credentials:

    • Aws.config[:credentials]
    • The :access_key_id, :secret_access_key, :session_token, and :account_id options.
    • ENV['AWS_ACCESS_KEY_ID'], ENV['AWS_SECRET_ACCESS_KEY'], ENV['AWS_SESSION_TOKEN'], and ENV['AWS_ACCOUNT_ID']
    • ~/.aws/credentials
    • ~/.aws/config
    • EC2/ECS IMDS instance profile - When used by default, the timeouts are very aggressive. Construct and pass an instance of Aws::InstanceProfileCredentials or Aws::ECSCredentials to enable retries and extended timeouts. Instance profile credential fetching can be disabled by setting ENV['AWS_EC2_METADATA_DISABLED'] to true.
  • :region (required, String) —

    The AWS region to connect to. The configured :region is used to determine the service :endpoint. When not passed, a default :region is searched for in the following locations:

    • Aws.config[:region]
    • ENV['AWS_REGION']
    • ENV['AMAZON_REGION']
    • ENV['AWS_DEFAULT_REGION']
    • ~/.aws/credentials
    • ~/.aws/config
  • :access_key_id (String)
  • :account_id (String)
  • :active_endpoint_cache (Boolean) — default: false —

    When set to true, a thread polling for endpoints will be running in the background every 60 secs (default). Defaults to false.

  • :adaptive_retry_wait_to_fill (Boolean) — default: true —

    Used only in adaptive retry mode. When true, the request will sleep until there is sufficent client side capacity to retry the request. When false, the request will raise a RetryCapacityNotAvailableError and will not retry instead of sleeping.

  • :client_side_monitoring (Boolean) — default: false —

    When true, client-side metrics will be collected for all API requests from this client.

  • :client_side_monitoring_client_id (String) — default: "" —

    Allows you to provide an identifier for this client which will be attached to all generated client side metrics. Defaults to an empty string.

  • :client_side_monitoring_host (String) — default: "127.0.0.1" —

    Allows you to specify the DNS hostname or IPv4 or IPv6 address that the client side monitoring agent is running on, where client metrics will be published via UDP.

  • :client_side_monitoring_port (Integer) — default: 31000 —

    Required for publishing client metrics. The port that the client side monitoring agent is running on, where client metrics will be published via UDP.

  • :client_side_monitoring_publisher (Aws::ClientSideMonitoring::Publisher) — default: Aws::ClientSideMonitoring::Publisher —

    Allows you to provide a custom client-side monitoring publisher class. By default, will use the Client Side Monitoring Agent Publisher.

  • :convert_params (Boolean) — default: true —

    When true, an attempt is made to coerce request parameters into the required types.

  • :correct_clock_skew (Boolean) — default: true —

    Used only in standard and adaptive retry modes. Specifies whether to apply a clock skew correction and retry requests with skewed client clocks.

  • :defaults_mode (String) — default: "legacy" —

    See DefaultsModeConfiguration for a list of the accepted modes and the configuration defaults that are included.

  • :disable_host_prefix_injection (Boolean) — default: false —

    Set to true to disable SDK automatically adding host prefix to default service endpoint when available.

  • :disable_request_compression (Boolean) — default: false —

    When set to 'true' the request body will not be compressed for supported operations.

  • :endpoint (String, URI::HTTPS, URI::HTTP) —

    Normally you should not configure the :endpoint option directly. This is normally constructed from the :region option. Configuring :endpoint is normally reserved for connecting to test or custom endpoints. The endpoint should be a URI formatted like:

    'http://example.com'
'https://example.com'
'http://example.com:123'
  • :endpoint_cache_max_entries (Integer) — default: 1000 —

    Used for the maximum size limit of the LRU cache storing endpoints data for endpoint discovery enabled operations. Defaults to 1000.

  • :endpoint_cache_max_threads (Integer) — default: 10 —

    Used for the maximum threads in use for polling endpoints to be cached, defaults to 10.

  • :endpoint_cache_poll_interval (Integer) — default: 60 —

    When :endpoint_discovery and :active_endpoint_cache is enabled, Use this option to config the time interval in seconds for making requests fetching endpoints information. Defaults to 60 sec.

  • :endpoint_discovery (Boolean) — default: false —

    When set to true, endpoint discovery will be enabled for operations when available.

  • :ignore_configured_endpoint_urls (Boolean) —

    Setting to true disables use of endpoint URLs provided via environment variables and the shared configuration file.

  • :log_formatter (Aws::Log::Formatter) — default: Aws::Log::Formatter.default —

    The log formatter.

  • :log_level (Symbol) — default: :info —

    The log level to send messages to the :logger at.

  • :logger (Logger) —

    The Logger instance to send log messages to. If this option is not set, logging will be disabled.

  • :max_attempts (Integer) — default: 3 —

    An integer representing the maximum number attempts that will be made for a single request, including the initial attempt. For example, setting this value to 5 will result in a request being retried up to 4 times. Used in standard and adaptive retry modes.

  • :profile (String) — default: "default" —

    Used when loading credentials from the shared credentials file at HOME/.aws/credentials. When not specified, 'default' is used.

  • :request_min_compression_size_bytes (Integer) — default: 10240 —

    The minimum size in bytes that triggers compression for request bodies. The value must be non-negative integer value between 0 and 10485780 bytes inclusive.

  • :retry_backoff (Proc) —

    A proc or lambda used for backoff. Defaults to 2**retries * retry_base_delay. This option is only used in the legacy retry mode.

  • :retry_base_delay (Float) — default: 0.3 —

    The base delay in seconds used by the default backoff function. This option is only used in the legacy retry mode.

  • :retry_jitter (Symbol) — default: :none —

    A delay randomiser function used by the default backoff function. Some predefined functions can be referenced by name - :none, :equal, :full, otherwise a Proc that takes and returns a number. This option is only used in the legacy retry mode.

    @see https://www.awsarchitectureblog.com/2015/03/backoff.html

  • :retry_limit (Integer) — default: 3 —

    The maximum number of times to retry failed requests. Only ~ 500 level server errors and certain ~ 400 level client errors are retried. Generally, these are throttling errors, data checksum errors, networking errors, timeout errors, auth errors, endpoint discovery, and errors from expired credentials. This option is only used in the legacy retry mode.

  • :retry_max_delay (Integer) — default: 0 —

    The maximum number of seconds to delay between retries (0 for no limit) used by the default backoff function. This option is only used in the legacy retry mode.

  • :retry_mode (String) — default: "legacy" —

    Specifies which retry algorithm to use. Values are:

    • legacy - The pre-existing retry behavior. This is default value if no retry mode is provided.

    • standard - A standardized set of retry rules across the AWS SDKs. This includes support for retry quotas, which limit the number of unsuccessful retries a client can make.

    • adaptive - An experimental retry mode that includes all the functionality of standard mode along with automatic client side throttling. This is a provisional mode that may change behavior in the future.

  • :sdk_ua_app_id (String) —

    A unique and opaque application ID that is appended to the User-Agent header as app/sdk_ua_app_id. It should have a maximum length of 50. This variable is sourced from environment variable AWS_SDK_UA_APP_ID or the shared config profile attribute sdk_ua_app_id.

  • :secret_access_key (String)
  • :session_token (String)
  • :sigv4a_signing_region_set (Array) —

    A list of regions that should be signed with SigV4a signing. When not passed, a default :sigv4a_signing_region_set is searched for in the following locations:

    • Aws.config[:sigv4a_signing_region_set]
    • ENV['AWS_SIGV4A_SIGNING_REGION_SET']
    • ~/.aws/config
  • :stub_responses (Boolean) — default: false —

    Causes the client to return stubbed responses. By default fake responses are generated and returned. You can specify the response data to return or errors to raise by calling ClientStubs#stub_responses. See ClientStubs for more information.

    Please note When response stubbing is enabled, no HTTP requests are made, and retries are disabled.

  • :telemetry_provider (Aws::Telemetry::TelemetryProviderBase) — default: Aws::Telemetry::NoOpTelemetryProvider —

    Allows you to provide a telemetry provider, which is used to emit telemetry data. By default, uses NoOpTelemetryProvider which will not record or emit any telemetry data. The SDK supports the following telemetry providers:

    • OpenTelemetry (OTel) - To use the OTel provider, install and require the opentelemetry-sdk gem and then, pass in an instance of a Aws::Telemetry::OTelProvider for telemetry provider.
  • :token_provider (Aws::TokenProvider) —

    A Bearer Token Provider. This can be an instance of any one of the following classes:

    • Aws::StaticTokenProvider - Used for configuring static, non-refreshing tokens.

    • Aws::SSOTokenProvider - Used for loading tokens from AWS SSO using an access token generated from aws login.

    When :token_provider is not configured directly, the Aws::TokenProviderChain will be used to search for tokens configured for your profile in shared configuration files.

  • :use_dualstack_endpoint (Boolean) —

    When set to true, dualstack enabled endpoints (with .aws TLD) will be used if available.

  • :use_fips_endpoint (Boolean) —

    When set to true, fips compatible endpoints will be used if available. When a fips region is used, the region is normalized and this config is set to true.

  • :validate_params (Boolean) — default: true —

    When true, request parameters are validated before sending the request.

  • :endpoint_provider (Aws::BedrockAgent::EndpointProvider) —

    The endpoint provider used to resolve endpoints. Any object that responds to #resolve_endpoint(parameters) where parameters is a Struct similar to Aws::BedrockAgent::EndpointParameters.

  • :http_continue_timeout (Float) — default: 1 —

    The number of seconds to wait for a 100-continue response before sending the request body. This option has no effect unless the request has "Expect" header set to "100-continue". Defaults to nil which disables this behaviour. This value can safely be set per request on the session.

  • :http_idle_timeout (Float) — default: 5 —

    The number of seconds a connection is allowed to sit idle before it is considered stale. Stale connections are closed and removed from the pool before making a request.

  • :http_open_timeout (Float) — default: 15 —

    The default number of seconds to wait for response data. This value can safely be set per-request on the session.

  • :http_proxy (URI::HTTP, String) —

    A proxy to send requests through. Formatted like 'http://proxy.com:123'.

  • :http_read_timeout (Float) — default: 60 —

    The default number of seconds to wait for response data. This value can safely be set per-request on the session.

  • :http_wire_trace (Boolean) — default: false —

    When true, HTTP debug output will be sent to the :logger.

  • :on_chunk_received (Proc) —

    When a Proc object is provided, it will be used as callback when each chunk of the response body is received. It provides three arguments: the chunk, the number of bytes received, and the total number of bytes in the response (or nil if the server did not send a content-length).

  • :on_chunk_sent (Proc) —

    When a Proc object is provided, it will be used as callback when each chunk of the request body is sent. It provides three arguments: the chunk, the number of bytes read from the body, and the total number of bytes in the body.

  • :raise_response_errors (Boolean) — default: true —

    When true, response errors are raised.

  • :ssl_ca_bundle (String) —

    Full path to the SSL certificate authority bundle file that should be used when verifying peer certificates. If you do not pass :ssl_ca_bundle or :ssl_ca_directory the the system default will be used if available.

  • :ssl_ca_directory (String) —

    Full path of the directory that contains the unbundled SSL certificate authority files for verifying peer certificates. If you do not pass :ssl_ca_bundle or :ssl_ca_directory the the system default will be used if available.

  • :ssl_ca_store (String) —

    Sets the X509::Store to verify peer certificate.

  • :ssl_cert (OpenSSL::X509::Certificate) —

    Sets a client certificate when creating http connections.

  • :ssl_key (OpenSSL::PKey) —

    Sets a client key when creating http connections.

  • :ssl_timeout (Float) —

    Sets the SSL timeout in seconds

  • :ssl_verify_peer (Boolean) — default: true —

    When true, SSL peer certificates are verified when establishing a connection.



444
445
446
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 444

def initialize(*args)
  super
end

Instance Method Details

#associate_agent_knowledge_base(params = {}) ⇒ Types::AssociateAgentKnowledgeBaseResponse

Associates a knowledge base with an agent. If a knowledge base is associated and its indexState is set to Enabled, the agent queries the knowledge base for information to augment its response to the user.

Examples:

Request syntax with placeholder values


resp = client.associate_agent_knowledge_base({
  agent_id: "Id", # required
  agent_version: "DraftVersion", # required
  description: "Description", # required
  knowledge_base_id: "Id", # required
  knowledge_base_state: "ENABLED", # accepts ENABLED, DISABLED
})

Response structure


resp.agent_knowledge_base.agent_id #=> String
resp.agent_knowledge_base.agent_version #=> String
resp.agent_knowledge_base.created_at #=> Time
resp.agent_knowledge_base.description #=> String
resp.agent_knowledge_base.knowledge_base_id #=> String
resp.agent_knowledge_base.knowledge_base_state #=> String, one of "ENABLED", "DISABLED"
resp.agent_knowledge_base.updated_at #=> Time

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :agent_id (required, String) —

    The unique identifier of the agent with which you want to associate the knowledge base.

  • :agent_version (required, String) —

    The version of the agent with which you want to associate the knowledge base.

  • :description (required, String) —

    A description of what the agent should use the knowledge base for.

  • :knowledge_base_id (required, String) —

    The unique identifier of the knowledge base to associate with the agent.

  • :knowledge_base_state (String) —

    Specifies whether to use the knowledge base or not when sending an InvokeAgent request.

Returns:

See Also:



506
507
508
509
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 506

def associate_agent_knowledge_base(params = {}, options = {})
  req = build_request(:associate_agent_knowledge_base, params)
  req.send_request(options)
end

#create_agent(params = {}) ⇒ Types::CreateAgentResponse

Creates an agent that orchestrates interactions between foundation models, data sources, software applications, user conversations, and APIs to carry out tasks to help customers.

  • Specify the following fields for security purposes.

    • agentResourceRoleArn – The Amazon Resource Name (ARN) of the role with permissions to invoke API operations on an agent.

    • (Optional) customerEncryptionKeyArn – The Amazon Resource Name (ARN) of a KMS key to encrypt the creation of the agent.

    • (Optional) idleSessionTTLinSeconds – Specify the number of seconds for which the agent should maintain session information. After this time expires, the subsequent InvokeAgent request begins a new session.

  • To enable your agent to retain conversational context across multiple sessions, include a memoryConfiguration object. For more information, see Configure memory.

  • To override the default prompt behavior for agent orchestration and to use advanced prompts, include a promptOverrideConfiguration object. For more information, see Advanced prompts.

  • If your agent fails to be created, the response returns a list of failureReasons alongside a list of recommendedActions for you to troubleshoot.

  • The agent instructions will not be honored if your agent has only one knowledge base, uses default prompts, has no action group, and user input is disabled.

Examples:

Request syntax with placeholder values


resp = client.create_agent({
  agent_name: "Name", # required
  agent_resource_role_arn: "AgentRoleArn",
  client_token: "ClientToken",
  custom_orchestration: {
    executor: {
      lambda: "LambdaArn",
    },
  },
  customer_encryption_key_arn: "KmsKeyArn",
  description: "Description",
  foundation_model: "ModelIdentifier",
  guardrail_configuration: {
    guardrail_identifier: "GuardrailIdentifier",
    guardrail_version: "GuardrailVersion",
  },
  idle_session_ttl_in_seconds: 1,
  instruction: "Instruction",
  memory_configuration: {
    enabled_memory_types: ["SESSION_SUMMARY"], # required, accepts SESSION_SUMMARY
    storage_days: 1,
  },
  orchestration_type: "DEFAULT", # accepts DEFAULT, CUSTOM_ORCHESTRATION
  prompt_override_configuration: {
    override_lambda: "LambdaArn",
    prompt_configurations: [ # required
      {
        base_prompt_template: "BasePromptTemplate",
        inference_configuration: {
          maximum_length: 1,
          stop_sequences: ["String"],
          temperature: 1.0,
          top_k: 1,
          top_p: 1.0,
        },
        parser_mode: "DEFAULT", # accepts DEFAULT, OVERRIDDEN
        prompt_creation_mode: "DEFAULT", # accepts DEFAULT, OVERRIDDEN
        prompt_state: "ENABLED", # accepts ENABLED, DISABLED
        prompt_type: "PRE_PROCESSING", # accepts PRE_PROCESSING, ORCHESTRATION, POST_PROCESSING, KNOWLEDGE_BASE_RESPONSE_GENERATION
      },
    ],
  },
  tags: {
    "TagKey" => "TagValue",
  },
})

Response structure


resp.agent.agent_arn #=> String
resp.agent.agent_id #=> String
resp.agent.agent_name #=> String
resp.agent.agent_resource_role_arn #=> String
resp.agent.agent_status #=> String, one of "CREATING", "PREPARING", "PREPARED", "NOT_PREPARED", "DELETING", "FAILED", "VERSIONING", "UPDATING"
resp.agent.agent_version #=> String
resp.agent.client_token #=> String
resp.agent.created_at #=> Time
resp.agent.custom_orchestration.executor.lambda #=> String
resp.agent.customer_encryption_key_arn #=> String
resp.agent.description #=> String
resp.agent.failure_reasons #=> Array
resp.agent.failure_reasons[0] #=> String
resp.agent.foundation_model #=> String
resp.agent.guardrail_configuration.guardrail_identifier #=> String
resp.agent.guardrail_configuration.guardrail_version #=> String
resp.agent.idle_session_ttl_in_seconds #=> Integer
resp.agent.instruction #=> String
resp.agent.memory_configuration.enabled_memory_types #=> Array
resp.agent.memory_configuration.enabled_memory_types[0] #=> String, one of "SESSION_SUMMARY"
resp.agent.memory_configuration.storage_days #=> Integer
resp.agent.orchestration_type #=> String, one of "DEFAULT", "CUSTOM_ORCHESTRATION"
resp.agent.prepared_at #=> Time
resp.agent.prompt_override_configuration.override_lambda #=> String
resp.agent.prompt_override_configuration.prompt_configurations #=> Array
resp.agent.prompt_override_configuration.prompt_configurations[0].base_prompt_template #=> String
resp.agent.prompt_override_configuration.prompt_configurations[0].inference_configuration.maximum_length #=> Integer
resp.agent.prompt_override_configuration.prompt_configurations[0].inference_configuration.stop_sequences #=> Array
resp.agent.prompt_override_configuration.prompt_configurations[0].inference_configuration.stop_sequences[0] #=> String
resp.agent.prompt_override_configuration.prompt_configurations[0].inference_configuration.temperature #=> Float
resp.agent.prompt_override_configuration.prompt_configurations[0].inference_configuration.top_k #=> Integer
resp.agent.prompt_override_configuration.prompt_configurations[0].inference_configuration.top_p #=> Float
resp.agent.prompt_override_configuration.prompt_configurations[0].parser_mode #=> String, one of "DEFAULT", "OVERRIDDEN"
resp.agent.prompt_override_configuration.prompt_configurations[0].prompt_creation_mode #=> String, one of "DEFAULT", "OVERRIDDEN"
resp.agent.prompt_override_configuration.prompt_configurations[0].prompt_state #=> String, one of "ENABLED", "DISABLED"
resp.agent.prompt_override_configuration.prompt_configurations[0].prompt_type #=> String, one of "PRE_PROCESSING", "ORCHESTRATION", "POST_PROCESSING", "KNOWLEDGE_BASE_RESPONSE_GENERATION"
resp.agent.recommended_actions #=> Array
resp.agent.recommended_actions[0] #=> String
resp.agent.updated_at #=> Time

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :agent_name (required, String) —

    A name for the agent that you create.

  • :agent_resource_role_arn (String) —

    The Amazon Resource Name (ARN) of the IAM role with permissions to invoke API operations on the agent.

  • :client_token (String) —

    A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.

    A suitable default value is auto-generated. You should normally not need to pass this option.**

  • :custom_orchestration (Types::CustomOrchestration) —

    Contains details of the custom orchestration configured for the agent.

  • :customer_encryption_key_arn (String) —

    The Amazon Resource Name (ARN) of the KMS key with which to encrypt the agent.

  • :description (String) —

    A description of the agent.

  • :foundation_model (String) —

    The identifier for the model that you want to be used for orchestration by the agent you create.

    The modelId to provide depends on the type of model or throughput that you use:

  • :guardrail_configuration (Types::GuardrailConfiguration) —

    The unique Guardrail configuration assigned to the agent when it is created.

  • :idle_session_ttl_in_seconds (Integer) —

    The number of seconds for which Amazon Bedrock keeps information about a user's conversation with the agent.

    A user interaction remains active for the amount of time specified. If no conversation occurs during this time, the session expires and Amazon Bedrock deletes any data provided before the timeout.

  • :instruction (String) —

    Instructions that tell the agent what it should do and how it should interact with users.

  • :memory_configuration (Types::MemoryConfiguration) —

    Contains the details of the memory configured for the agent.

  • :orchestration_type (String) —

    Specifies the type of orchestration strategy for the agent. This is set to DEFAULT orchestration type, by default.

  • :prompt_override_configuration (Types::PromptOverrideConfiguration) —

    Contains configurations to override prompts in different parts of an agent sequence. For more information, see Advanced prompts.

  • :tags (Hash<String,String>) —

    Any tags that you want to attach to the agent.

Returns:

See Also:



750
751
752
753
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 750

def create_agent(params = {}, options = {})
  req = build_request(:create_agent, params)
  req.send_request(options)
end

#create_agent_action_group(params = {}) ⇒ Types::CreateAgentActionGroupResponse

Creates an action group for an agent. An action group represents the actions that an agent can carry out for the customer by defining the APIs that an agent can call and the logic for calling them.

To allow your agent to request the user for additional information when trying to complete a task, add an action group with the parentActionGroupSignature field set to AMAZON.UserInput.

To allow your agent to generate, run, and troubleshoot code when trying to complete a task, add an action group with the parentActionGroupSignature field set to AMAZON.CodeInterpreter.

You must leave the description, apiSchema, and actionGroupExecutor fields blank for this action group. During orchestration, if your agent determines that it needs to invoke an API in an action group, but doesn't have enough information to complete the API request, it will invoke this action group instead and return an Observation reprompting the user for more information.

Examples:

Request syntax with placeholder values


resp = client.create_agent_action_group({
  action_group_executor: {
    custom_control: "RETURN_CONTROL", # accepts RETURN_CONTROL
    lambda: "LambdaArn",
  },
  action_group_name: "Name", # required
  action_group_state: "ENABLED", # accepts ENABLED, DISABLED
  agent_id: "Id", # required
  agent_version: "DraftVersion", # required
  api_schema: {
    payload: "Payload",
    s3: {
      s3_bucket_name: "S3BucketName",
      s3_object_key: "S3ObjectKey",
    },
  },
  client_token: "ClientToken",
  description: "Description",
  function_schema: {
    functions: [
      {
        description: "FunctionDescription",
        name: "Name", # required
        parameters: {
          "Name" => {
            description: "ParameterDescription",
            required: false,
            type: "string", # required, accepts string, number, integer, boolean, array
          },
        },
        require_confirmation: "ENABLED", # accepts ENABLED, DISABLED
      },
    ],
  },
  parent_action_group_signature: "AMAZON.UserInput", # accepts AMAZON.UserInput, AMAZON.CodeInterpreter
})

Response structure


resp.agent_action_group.action_group_executor.custom_control #=> String, one of "RETURN_CONTROL"
resp.agent_action_group.action_group_executor.lambda #=> String
resp.agent_action_group.action_group_id #=> String
resp.agent_action_group.action_group_name #=> String
resp.agent_action_group.action_group_state #=> String, one of "ENABLED", "DISABLED"
resp.agent_action_group.agent_id #=> String
resp.agent_action_group.agent_version #=> String
resp.agent_action_group.api_schema.payload #=> String
resp.agent_action_group.api_schema.s3.s3_bucket_name #=> String
resp.agent_action_group.api_schema.s3.s3_object_key #=> String
resp.agent_action_group.client_token #=> String
resp.agent_action_group.created_at #=> Time
resp.agent_action_group.description #=> String
resp.agent_action_group.function_schema.functions #=> Array
resp.agent_action_group.function_schema.functions[0].description #=> String
resp.agent_action_group.function_schema.functions[0].name #=> String
resp.agent_action_group.function_schema.functions[0].parameters #=> Hash
resp.agent_action_group.function_schema.functions[0].parameters["Name"].description #=> String
resp.agent_action_group.function_schema.functions[0].parameters["Name"].required #=> Boolean
resp.agent_action_group.function_schema.functions[0].parameters["Name"].type #=> String, one of "string", "number", "integer", "boolean", "array"
resp.agent_action_group.function_schema.functions[0].require_confirmation #=> String, one of "ENABLED", "DISABLED"
resp.agent_action_group.parent_action_signature #=> String, one of "AMAZON.UserInput", "AMAZON.CodeInterpreter"
resp.agent_action_group.updated_at #=> Time

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :action_group_executor (Types::ActionGroupExecutor) —

    The Amazon Resource Name (ARN) of the Lambda function containing the business logic that is carried out upon invoking the action or the custom control method for handling the information elicited from the user.

  • :action_group_name (required, String) —

    The name to give the action group.

  • :action_group_state (String) —

    Specifies whether the action group is available for the agent to invoke or not when sending an InvokeAgent request.

  • :agent_id (required, String) —

    The unique identifier of the agent for which to create the action group.

  • :agent_version (required, String) —

    The version of the agent for which to create the action group.

  • :api_schema (Types::APISchema) —

    Contains either details about the S3 object containing the OpenAPI schema for the action group or the JSON or YAML-formatted payload defining the schema. For more information, see Action group OpenAPI schemas.

  • :client_token (String) —

    A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.

    A suitable default value is auto-generated. You should normally not need to pass this option.**

  • :description (String) —

    A description of the action group.

  • :function_schema (Types::FunctionSchema) —

    Contains details about the function schema for the action group or the JSON or YAML-formatted payload defining the schema.

  • :parent_action_group_signature (String) —

    To allow your agent to request the user for additional information when trying to complete a task, set this field to AMAZON.UserInput. You must leave the description, apiSchema, and actionGroupExecutor fields blank for this action group.

    To allow your agent to generate, run, and troubleshoot code when trying to complete a task, set this field to AMAZON.CodeInterpreter. You must leave the description, apiSchema, and actionGroupExecutor fields blank for this action group.

    During orchestration, if your agent determines that it needs to invoke an API in an action group, but doesn't have enough information to complete the API request, it will invoke this action group instead and return an Observation reprompting the user for more information.

Returns:

See Also:



925
926
927
928
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 925

def create_agent_action_group(params = {}, options = {})
  req = build_request(:create_agent_action_group, params)
  req.send_request(options)
end

#create_agent_alias(params = {}) ⇒ Types::CreateAgentAliasResponse

Creates an alias of an agent that can be used to deploy the agent.

Examples:

Request syntax with placeholder values


resp = client.create_agent_alias({
  agent_alias_name: "Name", # required
  agent_id: "Id", # required
  client_token: "ClientToken",
  description: "Description",
  routing_configuration: [
    {
      agent_version: "Version",
      provisioned_throughput: "ProvisionedModelIdentifier",
    },
  ],
  tags: {
    "TagKey" => "TagValue",
  },
})

Response structure


resp.agent_alias.agent_alias_arn #=> String
resp.agent_alias.agent_alias_history_events #=> Array
resp.agent_alias.agent_alias_history_events[0].end_date #=> Time
resp.agent_alias.agent_alias_history_events[0].routing_configuration #=> Array
resp.agent_alias.agent_alias_history_events[0].routing_configuration[0].agent_version #=> String
resp.agent_alias.agent_alias_history_events[0].routing_configuration[0].provisioned_throughput #=> String
resp.agent_alias.agent_alias_history_events[0].start_date #=> Time
resp.agent_alias.agent_alias_id #=> String
resp.agent_alias.agent_alias_name #=> String
resp.agent_alias.agent_alias_status #=> String, one of "CREATING", "PREPARED", "FAILED", "UPDATING", "DELETING"
resp.agent_alias.agent_id #=> String
resp.agent_alias.client_token #=> String
resp.agent_alias.created_at #=> Time
resp.agent_alias.description #=> String
resp.agent_alias.failure_reasons #=> Array
resp.agent_alias.failure_reasons[0] #=> String
resp.agent_alias.routing_configuration #=> Array
resp.agent_alias.routing_configuration[0].agent_version #=> String
resp.agent_alias.routing_configuration[0].provisioned_throughput #=> String
resp.agent_alias.updated_at #=> Time

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :agent_alias_name (required, String) —

    The name of the alias.

  • :agent_id (required, String) —

    The unique identifier of the agent.

  • :client_token (String) —

    A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.

    A suitable default value is auto-generated. You should normally not need to pass this option.**

  • :description (String) —

    A description of the alias of the agent.

  • :routing_configuration (Array<Types::AgentAliasRoutingConfigurationListItem>) —

    Contains details about the routing configuration of the alias.

  • :tags (Hash<String,String>) —

    Any tags that you want to attach to the alias of the agent.

Returns:

See Also:



1009
1010
1011
1012
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 1009

def create_agent_alias(params = {}, options = {})
  req = build_request(:create_agent_alias, params)
  req.send_request(options)
end

#create_data_source(params = {}) ⇒ Types::CreateDataSourceResponse

Connects a knowledge base to a data source. You specify the configuration for the specific data source service in the dataSourceConfiguration field.

You can't change the chunkingConfiguration after you create the data source connector.

Examples:

Request syntax with placeholder values


resp = client.create_data_source({
  client_token: "ClientToken",
  data_deletion_policy: "RETAIN", # accepts RETAIN, DELETE
  data_source_configuration: { # required
    confluence_configuration: {
      crawler_configuration: {
        filter_configuration: {
          pattern_object_filter: {
            filters: [ # required
              {
                exclusion_filters: ["FilterPattern"],
                inclusion_filters: ["FilterPattern"],
                object_type: "FilteredObjectType", # required
              },
            ],
          },
          type: "PATTERN", # required, accepts PATTERN
        },
      },
      source_configuration: { # required
        auth_type: "BASIC", # required, accepts BASIC, OAUTH2_CLIENT_CREDENTIALS
        credentials_secret_arn: "SecretArn", # required
        host_type: "SAAS", # required, accepts SAAS
        host_url: "HttpsUrl", # required
      },
    },
    s3_configuration: {
      bucket_arn: "S3BucketArn", # required
      bucket_owner_account_id: "BucketOwnerAccountId",
      inclusion_prefixes: ["S3Prefix"],
    },
    salesforce_configuration: {
      crawler_configuration: {
        filter_configuration: {
          pattern_object_filter: {
            filters: [ # required
              {
                exclusion_filters: ["FilterPattern"],
                inclusion_filters: ["FilterPattern"],
                object_type: "FilteredObjectType", # required
              },
            ],
          },
          type: "PATTERN", # required, accepts PATTERN
        },
      },
      source_configuration: { # required
        auth_type: "OAUTH2_CLIENT_CREDENTIALS", # required, accepts OAUTH2_CLIENT_CREDENTIALS
        credentials_secret_arn: "SecretArn", # required
        host_url: "HttpsUrl", # required
      },
    },
    share_point_configuration: {
      crawler_configuration: {
        filter_configuration: {
          pattern_object_filter: {
            filters: [ # required
              {
                exclusion_filters: ["FilterPattern"],
                inclusion_filters: ["FilterPattern"],
                object_type: "FilteredObjectType", # required
              },
            ],
          },
          type: "PATTERN", # required, accepts PATTERN
        },
      },
      source_configuration: { # required
        auth_type: "OAUTH2_CLIENT_CREDENTIALS", # required, accepts OAUTH2_CLIENT_CREDENTIALS
        credentials_secret_arn: "SecretArn", # required
        domain: "SharePointDomain", # required
        host_type: "ONLINE", # required, accepts ONLINE
        site_urls: ["HttpsUrl"], # required
        tenant_id: "Microsoft365TenantId",
      },
    },
    type: "S3", # required, accepts S3, WEB, CONFLUENCE, SALESFORCE, SHAREPOINT, CUSTOM
    web_configuration: {
      crawler_configuration: {
        crawler_limits: {
          rate_limit: 1,
        },
        exclusion_filters: ["FilterPattern"],
        inclusion_filters: ["FilterPattern"],
        scope: "HOST_ONLY", # accepts HOST_ONLY, SUBDOMAINS
      },
      source_configuration: { # required
        url_configuration: { # required
          seed_urls: [
            {
              url: "Url",
            },
          ],
        },
      },
    },
  },
  description: "Description",
  knowledge_base_id: "Id", # required
  name: "Name", # required
  server_side_encryption_configuration: {
    kms_key_arn: "KmsKeyArn",
  },
  vector_ingestion_configuration: {
    chunking_configuration: {
      chunking_strategy: "FIXED_SIZE", # required, accepts FIXED_SIZE, NONE, HIERARCHICAL, SEMANTIC
      fixed_size_chunking_configuration: {
        max_tokens: 1, # required
        overlap_percentage: 1, # required
      },
      hierarchical_chunking_configuration: {
        level_configurations: [ # required
          {
            max_tokens: 1, # required
          },
        ],
        overlap_tokens: 1, # required
      },
      semantic_chunking_configuration: {
        breakpoint_percentile_threshold: 1, # required
        buffer_size: 1, # required
        max_tokens: 1, # required
      },
    },
    custom_transformation_configuration: {
      intermediate_storage: { # required
        s3_location: { # required
          uri: "S3BucketUri", # required
        },
      },
      transformations: [ # required
        {
          step_to_apply: "POST_CHUNKING", # required, accepts POST_CHUNKING
          transformation_function: { # required
            transformation_lambda_configuration: { # required
              lambda_arn: "LambdaArn", # required
            },
          },
        },
      ],
    },
    parsing_configuration: {
      bedrock_foundation_model_configuration: {
        model_arn: "BedrockModelArn", # required
        parsing_prompt: {
          parsing_prompt_text: "ParsingPromptText", # required
        },
      },
      parsing_strategy: "BEDROCK_FOUNDATION_MODEL", # required, accepts BEDROCK_FOUNDATION_MODEL
    },
  },
})

Response structure


resp.data_source.created_at #=> Time
resp.data_source.data_deletion_policy #=> String, one of "RETAIN", "DELETE"
resp.data_source.data_source_configuration.confluence_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters #=> Array
resp.data_source.data_source_configuration.confluence_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters[0].exclusion_filters #=> Array
resp.data_source.data_source_configuration.confluence_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters[0].exclusion_filters[0] #=> String
resp.data_source.data_source_configuration.confluence_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters[0].inclusion_filters #=> Array
resp.data_source.data_source_configuration.confluence_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters[0].inclusion_filters[0] #=> String
resp.data_source.data_source_configuration.confluence_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters[0].object_type #=> String
resp.data_source.data_source_configuration.confluence_configuration.crawler_configuration.filter_configuration.type #=> String, one of "PATTERN"
resp.data_source.data_source_configuration.confluence_configuration.source_configuration.auth_type #=> String, one of "BASIC", "OAUTH2_CLIENT_CREDENTIALS"
resp.data_source.data_source_configuration.confluence_configuration.source_configuration.credentials_secret_arn #=> String
resp.data_source.data_source_configuration.confluence_configuration.source_configuration.host_type #=> String, one of "SAAS"
resp.data_source.data_source_configuration.confluence_configuration.source_configuration.host_url #=> String
resp.data_source.data_source_configuration.s3_configuration.bucket_arn #=> String
resp.data_source.data_source_configuration.s3_configuration. #=> String
resp.data_source.data_source_configuration.s3_configuration.inclusion_prefixes #=> Array
resp.data_source.data_source_configuration.s3_configuration.inclusion_prefixes[0] #=> String
resp.data_source.data_source_configuration.salesforce_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters #=> Array
resp.data_source.data_source_configuration.salesforce_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters[0].exclusion_filters #=> Array
resp.data_source.data_source_configuration.salesforce_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters[0].exclusion_filters[0] #=> String
resp.data_source.data_source_configuration.salesforce_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters[0].inclusion_filters #=> Array
resp.data_source.data_source_configuration.salesforce_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters[0].inclusion_filters[0] #=> String
resp.data_source.data_source_configuration.salesforce_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters[0].object_type #=> String
resp.data_source.data_source_configuration.salesforce_configuration.crawler_configuration.filter_configuration.type #=> String, one of "PATTERN"
resp.data_source.data_source_configuration.salesforce_configuration.source_configuration.auth_type #=> String, one of "OAUTH2_CLIENT_CREDENTIALS"
resp.data_source.data_source_configuration.salesforce_configuration.source_configuration.credentials_secret_arn #=> String
resp.data_source.data_source_configuration.salesforce_configuration.source_configuration.host_url #=> String
resp.data_source.data_source_configuration.share_point_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters #=> Array
resp.data_source.data_source_configuration.share_point_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters[0].exclusion_filters #=> Array
resp.data_source.data_source_configuration.share_point_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters[0].exclusion_filters[0] #=> String
resp.data_source.data_source_configuration.share_point_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters[0].inclusion_filters #=> Array
resp.data_source.data_source_configuration.share_point_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters[0].inclusion_filters[0] #=> String
resp.data_source.data_source_configuration.share_point_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters[0].object_type #=> String
resp.data_source.data_source_configuration.share_point_configuration.crawler_configuration.filter_configuration.type #=> String, one of "PATTERN"
resp.data_source.data_source_configuration.share_point_configuration.source_configuration.auth_type #=> String, one of "OAUTH2_CLIENT_CREDENTIALS"
resp.data_source.data_source_configuration.share_point_configuration.source_configuration.credentials_secret_arn #=> String
resp.data_source.data_source_configuration.share_point_configuration.source_configuration.domain #=> String
resp.data_source.data_source_configuration.share_point_configuration.source_configuration.host_type #=> String, one of "ONLINE"
resp.data_source.data_source_configuration.share_point_configuration.source_configuration.site_urls #=> Array
resp.data_source.data_source_configuration.share_point_configuration.source_configuration.site_urls[0] #=> String
resp.data_source.data_source_configuration.share_point_configuration.source_configuration.tenant_id #=> String
resp.data_source.data_source_configuration.type #=> String, one of "S3", "WEB", "CONFLUENCE", "SALESFORCE", "SHAREPOINT", "CUSTOM"
resp.data_source.data_source_configuration.web_configuration.crawler_configuration.crawler_limits.rate_limit #=> Integer
resp.data_source.data_source_configuration.web_configuration.crawler_configuration.exclusion_filters #=> Array
resp.data_source.data_source_configuration.web_configuration.crawler_configuration.exclusion_filters[0] #=> String
resp.data_source.data_source_configuration.web_configuration.crawler_configuration.inclusion_filters #=> Array
resp.data_source.data_source_configuration.web_configuration.crawler_configuration.inclusion_filters[0] #=> String
resp.data_source.data_source_configuration.web_configuration.crawler_configuration.scope #=> String, one of "HOST_ONLY", "SUBDOMAINS"
resp.data_source.data_source_configuration.web_configuration.source_configuration.url_configuration.seed_urls #=> Array
resp.data_source.data_source_configuration.web_configuration.source_configuration.url_configuration.seed_urls[0].url #=> String
resp.data_source.data_source_id #=> String
resp.data_source.description #=> String
resp.data_source.failure_reasons #=> Array
resp.data_source.failure_reasons[0] #=> String
resp.data_source.knowledge_base_id #=> String
resp.data_source.name #=> String
resp.data_source.server_side_encryption_configuration.kms_key_arn #=> String
resp.data_source.status #=> String, one of "AVAILABLE", "DELETING", "DELETE_UNSUCCESSFUL"
resp.data_source.updated_at #=> Time
resp.data_source.vector_ingestion_configuration.chunking_configuration.chunking_strategy #=> String, one of "FIXED_SIZE", "NONE", "HIERARCHICAL", "SEMANTIC"
resp.data_source.vector_ingestion_configuration.chunking_configuration.fixed_size_chunking_configuration.max_tokens #=> Integer
resp.data_source.vector_ingestion_configuration.chunking_configuration.fixed_size_chunking_configuration.overlap_percentage #=> Integer
resp.data_source.vector_ingestion_configuration.chunking_configuration.hierarchical_chunking_configuration.level_configurations #=> Array
resp.data_source.vector_ingestion_configuration.chunking_configuration.hierarchical_chunking_configuration.level_configurations[0].max_tokens #=> Integer
resp.data_source.vector_ingestion_configuration.chunking_configuration.hierarchical_chunking_configuration.overlap_tokens #=> Integer
resp.data_source.vector_ingestion_configuration.chunking_configuration.semantic_chunking_configuration.breakpoint_percentile_threshold #=> Integer
resp.data_source.vector_ingestion_configuration.chunking_configuration.semantic_chunking_configuration.buffer_size #=> Integer
resp.data_source.vector_ingestion_configuration.chunking_configuration.semantic_chunking_configuration.max_tokens #=> Integer
resp.data_source.vector_ingestion_configuration.custom_transformation_configuration.intermediate_storage.s3_location.uri #=> String
resp.data_source.vector_ingestion_configuration.custom_transformation_configuration.transformations #=> Array
resp.data_source.vector_ingestion_configuration.custom_transformation_configuration.transformations[0].step_to_apply #=> String, one of "POST_CHUNKING"
resp.data_source.vector_ingestion_configuration.custom_transformation_configuration.transformations[0].transformation_function.transformation_lambda_configuration.lambda_arn #=> String
resp.data_source.vector_ingestion_configuration.parsing_configuration.bedrock_foundation_model_configuration.model_arn #=> String
resp.data_source.vector_ingestion_configuration.parsing_configuration.bedrock_foundation_model_configuration.parsing_prompt.parsing_prompt_text #=> String
resp.data_source.vector_ingestion_configuration.parsing_configuration.parsing_strategy #=> String, one of "BEDROCK_FOUNDATION_MODEL"

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :client_token (String) —

    A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.

    A suitable default value is auto-generated. You should normally not need to pass this option.**

  • :data_deletion_policy (String) —

    The data deletion policy for the data source.

    You can set the data deletion policy to:

    • DELETE: Deletes all data from your data source that’s converted into vector embeddings upon deletion of a knowledge base or data source resource. Note that the vector store itself is not deleted, only the data. This flag is ignored if an Amazon Web Services account is deleted.

    • RETAIN: Retains all data from your data source that’s converted into vector embeddings upon deletion of a knowledge base or data source resource. Note that the vector store itself is not deleted if you delete a knowledge base or data source resource.

  • :data_source_configuration (required, Types::DataSourceConfiguration) —

    The connection configuration for the data source.

  • :description (String) —

    A description of the data source.

  • :knowledge_base_id (required, String) —

    The unique identifier of the knowledge base to which to add the data source.

  • :name (required, String) —

    The name of the data source.

  • :server_side_encryption_configuration (Types::ServerSideEncryptionConfiguration) —

    Contains details about the server-side encryption for the data source.

  • :vector_ingestion_configuration (Types::VectorIngestionConfiguration) —

    Contains details about how to ingest the documents in the data source.

Returns:

See Also:



1310
1311
1312
1313
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 1310

def create_data_source(params = {}, options = {})
  req = build_request(:create_data_source, params)
  req.send_request(options)
end

#create_flow(params = {}) ⇒ Types::CreateFlowResponse

Creates a prompt flow that you can use to send an input through various steps to yield an output. Configure nodes, each of which corresponds to a step of the flow, and create connections between the nodes to create paths to different outputs. For more information, see How it works and Create a flow in Amazon Bedrock in the Amazon Bedrock User Guide.

Examples:

Request syntax with placeholder values


resp = client.create_flow({
  client_token: "ClientToken",
  customer_encryption_key_arn: "KmsKeyArn",
  definition: {
    connections: [
      {
        configuration: {
          conditional: {
            condition: "FlowConditionName", # required
          },
          data: {
            source_output: "FlowNodeOutputName", # required
            target_input: "FlowNodeInputName", # required
          },
        },
        name: "FlowConnectionName", # required
        source: "FlowNodeName", # required
        target: "FlowNodeName", # required
        type: "Data", # required, accepts Data, Conditional
      },
    ],
    nodes: [
      {
        configuration: {
          agent: {
            agent_alias_arn: "AgentAliasArn", # required
          },
          collector: {
          },
          condition: {
            conditions: [ # required
              {
                expression: "FlowConditionExpression",
                name: "FlowConditionName", # required
              },
            ],
          },
          input: {
          },
          iterator: {
          },
          knowledge_base: {
            guardrail_configuration: {
              guardrail_identifier: "GuardrailIdentifier",
              guardrail_version: "GuardrailVersion",
            },
            knowledge_base_id: "KnowledgeBaseId", # required
            model_id: "KnowledgeBaseModelIdentifier",
          },
          lambda_function: {
            lambda_arn: "LambdaArn", # required
          },
          lex: {
            bot_alias_arn: "LexBotAliasArn", # required
            locale_id: "LexBotLocaleId", # required
          },
          output: {
          },
          prompt: {
            guardrail_configuration: {
              guardrail_identifier: "GuardrailIdentifier",
              guardrail_version: "GuardrailVersion",
            },
            source_configuration: { # required
              inline: {
                additional_model_request_fields: {
                },
                inference_configuration: {
                  text: {
                    max_tokens: 1,
                    stop_sequences: ["String"],
                    temperature: 1.0,
                    top_p: 1.0,
                  },
                },
                model_id: "PromptModelIdentifier", # required
                template_configuration: { # required
                  chat: {
                    input_variables: [
                      {
                        name: "PromptInputVariableName",
                      },
                    ],
                    messages: [ # required
                      {
                        content: [ # required
                          {
                            text: "String",
                          },
                        ],
                        role: "user", # required, accepts user, assistant
                      },
                    ],
                    system: [
                      {
                        text: "NonEmptyString",
                      },
                    ],
                    tool_configuration: {
                      tool_choice: {
                        any: {
                        },
                        auto: {
                        },
                        tool: {
                          name: "ToolName", # required
                        },
                      },
                      tools: [ # required
                        {
                          tool_spec: {
                            description: "NonEmptyString",
                            input_schema: { # required
                              json: {
                              },
                            },
                            name: "ToolName", # required
                          },
                        },
                      ],
                    },
                  },
                  text: {
                    input_variables: [
                      {
                        name: "PromptInputVariableName",
                      },
                    ],
                    text: "TextPrompt", # required
                  },
                },
                template_type: "TEXT", # required, accepts TEXT, CHAT
              },
              resource: {
                prompt_arn: "PromptArn", # required
              },
            },
          },
          retrieval: {
            service_configuration: { # required
              s3: {
                bucket_name: "S3BucketName", # required
              },
            },
          },
          storage: {
            service_configuration: { # required
              s3: {
                bucket_name: "S3BucketName", # required
              },
            },
          },
        },
        inputs: [
          {
            expression: "FlowNodeInputExpression", # required
            name: "FlowNodeInputName", # required
            type: "String", # required, accepts String, Number, Boolean, Object, Array
          },
        ],
        name: "FlowNodeName", # required
        outputs: [
          {
            name: "FlowNodeOutputName", # required
            type: "String", # required, accepts String, Number, Boolean, Object, Array
          },
        ],
        type: "Input", # required, accepts Input, Output, KnowledgeBase, Condition, Lex, Prompt, LambdaFunction, Storage, Agent, Retrieval, Iterator, Collector
      },
    ],
  },
  description: "FlowDescription",
  execution_role_arn: "FlowExecutionRoleArn", # required
  name: "FlowName", # required
  tags: {
    "TagKey" => "TagValue",
  },
})

Response structure


resp.arn #=> String
resp.created_at #=> Time
resp.customer_encryption_key_arn #=> String
resp.definition.connections #=> Array
resp.definition.connections[0].configuration.conditional.condition #=> String
resp.definition.connections[0].configuration.data.source_output #=> String
resp.definition.connections[0].configuration.data.target_input #=> String
resp.definition.connections[0].name #=> String
resp.definition.connections[0].source #=> String
resp.definition.connections[0].target #=> String
resp.definition.connections[0].type #=> String, one of "Data", "Conditional"
resp.definition.nodes #=> Array
resp.definition.nodes[0].configuration.agent.agent_alias_arn #=> String
resp.definition.nodes[0].configuration.condition.conditions #=> Array
resp.definition.nodes[0].configuration.condition.conditions[0].expression #=> String
resp.definition.nodes[0].configuration.condition.conditions[0].name #=> String
resp.definition.nodes[0].configuration.knowledge_base.guardrail_configuration.guardrail_identifier #=> String
resp.definition.nodes[0].configuration.knowledge_base.guardrail_configuration.guardrail_version #=> String
resp.definition.nodes[0].configuration.knowledge_base.knowledge_base_id #=> String
resp.definition.nodes[0].configuration.knowledge_base.model_id #=> String
resp.definition.nodes[0].configuration.lambda_function.lambda_arn #=> String
resp.definition.nodes[0].configuration.lex.bot_alias_arn #=> String
resp.definition.nodes[0].configuration.lex.locale_id #=> String
resp.definition.nodes[0].configuration.prompt.guardrail_configuration.guardrail_identifier #=> String
resp.definition.nodes[0].configuration.prompt.guardrail_configuration.guardrail_version #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.inference_configuration.text.max_tokens #=> Integer
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.inference_configuration.text.stop_sequences #=> Array
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.inference_configuration.text.stop_sequences[0] #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.inference_configuration.text.temperature #=> Float
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.inference_configuration.text.top_p #=> Float
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.model_id #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.input_variables #=> Array
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.input_variables[0].name #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.messages #=> Array
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.messages[0].content #=> Array
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.messages[0].content[0].text #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.messages[0].role #=> String, one of "user", "assistant"
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.system #=> Array
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.system[0].text #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.tool_configuration.tool_choice.tool.name #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.tool_configuration.tools #=> Array
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.tool_configuration.tools[0].tool_spec.description #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.tool_configuration.tools[0].tool_spec.name #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.text.input_variables #=> Array
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.text.input_variables[0].name #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.text.text #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_type #=> String, one of "TEXT", "CHAT"
resp.definition.nodes[0].configuration.prompt.source_configuration.resource.prompt_arn #=> String
resp.definition.nodes[0].configuration.retrieval.service_configuration.s3.bucket_name #=> String
resp.definition.nodes[0].configuration.storage.service_configuration.s3.bucket_name #=> String
resp.definition.nodes[0].inputs #=> Array
resp.definition.nodes[0].inputs[0].expression #=> String
resp.definition.nodes[0].inputs[0].name #=> String
resp.definition.nodes[0].inputs[0].type #=> String, one of "String", "Number", "Boolean", "Object", "Array"
resp.definition.nodes[0].name #=> String
resp.definition.nodes[0].outputs #=> Array
resp.definition.nodes[0].outputs[0].name #=> String
resp.definition.nodes[0].outputs[0].type #=> String, one of "String", "Number", "Boolean", "Object", "Array"
resp.definition.nodes[0].type #=> String, one of "Input", "Output", "KnowledgeBase", "Condition", "Lex", "Prompt", "LambdaFunction", "Storage", "Agent", "Retrieval", "Iterator", "Collector"
resp.description #=> String
resp.execution_role_arn #=> String
resp.id #=> String
resp.name #=> String
resp.status #=> String, one of "Failed", "Prepared", "Preparing", "NotPrepared"
resp.updated_at #=> Time
resp.version #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :client_token (String) —

    A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.

    A suitable default value is auto-generated. You should normally not need to pass this option.**

  • :customer_encryption_key_arn (String) —

    The Amazon Resource Name (ARN) of the KMS key to encrypt the flow.

  • :definition (Types::FlowDefinition) —

    A definition of the nodes and connections between nodes in the flow.

  • :description (String) —

    A description for the flow.

  • :execution_role_arn (required, String) —

    The Amazon Resource Name (ARN) of the service role with permissions to create and manage a flow. For more information, see Create a service role for flows in Amazon Bedrock in the Amazon Bedrock User Guide.

  • :name (required, String) —

    A name for the flow.

  • :tags (Hash<String,String>) —

    Any tags that you want to attach to the flow. For more information, see Tagging resources in Amazon Bedrock.

Returns:

See Also:



1637
1638
1639
1640
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 1637

def create_flow(params = {}, options = {})
  req = build_request(:create_flow, params)
  req.send_request(options)
end

#create_flow_alias(params = {}) ⇒ Types::CreateFlowAliasResponse

Creates an alias of a flow for deployment. For more information, see Deploy a flow in Amazon Bedrock in the Amazon Bedrock User Guide.

Examples:

Request syntax with placeholder values


resp = client.create_flow_alias({
  client_token: "ClientToken",
  description: "Description",
  flow_identifier: "FlowIdentifier", # required
  name: "Name", # required
  routing_configuration: [ # required
    {
      flow_version: "Version",
    },
  ],
  tags: {
    "TagKey" => "TagValue",
  },
})

Response structure


resp.arn #=> String
resp.created_at #=> Time
resp.description #=> String
resp.flow_id #=> String
resp.id #=> String
resp.name #=> String
resp.routing_configuration #=> Array
resp.routing_configuration[0].flow_version #=> String
resp.updated_at #=> Time

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :client_token (String) —

    A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.

    A suitable default value is auto-generated. You should normally not need to pass this option.**

  • :description (String) —

    A description for the alias.

  • :flow_identifier (required, String) —

    The unique identifier of the flow for which to create an alias.

  • :name (required, String) —

    A name for the alias.

  • :routing_configuration (required, Array<Types::FlowAliasRoutingConfigurationListItem>) —

    Contains information about the version to which to map the alias.

  • :tags (Hash<String,String>) —

    Any tags that you want to attach to the alias of the flow. For more information, see Tagging resources in Amazon Bedrock.

Returns:

See Also:



1726
1727
1728
1729
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 1726

def create_flow_alias(params = {}, options = {})
  req = build_request(:create_flow_alias, params)
  req.send_request(options)
end

#create_flow_version(params = {}) ⇒ Types::CreateFlowVersionResponse

Creates a version of the flow that you can deploy. For more information, see Deploy a flow in Amazon Bedrock in the Amazon Bedrock User Guide.

Examples:

Request syntax with placeholder values


resp = client.create_flow_version({
  client_token: "ClientToken",
  description: "FlowDescription",
  flow_identifier: "FlowIdentifier", # required
})

Response structure


resp.arn #=> String
resp.created_at #=> Time
resp.customer_encryption_key_arn #=> String
resp.definition.connections #=> Array
resp.definition.connections[0].configuration.conditional.condition #=> String
resp.definition.connections[0].configuration.data.source_output #=> String
resp.definition.connections[0].configuration.data.target_input #=> String
resp.definition.connections[0].name #=> String
resp.definition.connections[0].source #=> String
resp.definition.connections[0].target #=> String
resp.definition.connections[0].type #=> String, one of "Data", "Conditional"
resp.definition.nodes #=> Array
resp.definition.nodes[0].configuration.agent.agent_alias_arn #=> String
resp.definition.nodes[0].configuration.condition.conditions #=> Array
resp.definition.nodes[0].configuration.condition.conditions[0].expression #=> String
resp.definition.nodes[0].configuration.condition.conditions[0].name #=> String
resp.definition.nodes[0].configuration.knowledge_base.guardrail_configuration.guardrail_identifier #=> String
resp.definition.nodes[0].configuration.knowledge_base.guardrail_configuration.guardrail_version #=> String
resp.definition.nodes[0].configuration.knowledge_base.knowledge_base_id #=> String
resp.definition.nodes[0].configuration.knowledge_base.model_id #=> String
resp.definition.nodes[0].configuration.lambda_function.lambda_arn #=> String
resp.definition.nodes[0].configuration.lex.bot_alias_arn #=> String
resp.definition.nodes[0].configuration.lex.locale_id #=> String
resp.definition.nodes[0].configuration.prompt.guardrail_configuration.guardrail_identifier #=> String
resp.definition.nodes[0].configuration.prompt.guardrail_configuration.guardrail_version #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.inference_configuration.text.max_tokens #=> Integer
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.inference_configuration.text.stop_sequences #=> Array
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.inference_configuration.text.stop_sequences[0] #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.inference_configuration.text.temperature #=> Float
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.inference_configuration.text.top_p #=> Float
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.model_id #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.input_variables #=> Array
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.input_variables[0].name #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.messages #=> Array
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.messages[0].content #=> Array
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.messages[0].content[0].text #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.messages[0].role #=> String, one of "user", "assistant"
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.system #=> Array
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.system[0].text #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.tool_configuration.tool_choice.tool.name #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.tool_configuration.tools #=> Array
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.tool_configuration.tools[0].tool_spec.description #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.tool_configuration.tools[0].tool_spec.name #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.text.input_variables #=> Array
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.text.input_variables[0].name #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.text.text #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_type #=> String, one of "TEXT", "CHAT"
resp.definition.nodes[0].configuration.prompt.source_configuration.resource.prompt_arn #=> String
resp.definition.nodes[0].configuration.retrieval.service_configuration.s3.bucket_name #=> String
resp.definition.nodes[0].configuration.storage.service_configuration.s3.bucket_name #=> String
resp.definition.nodes[0].inputs #=> Array
resp.definition.nodes[0].inputs[0].expression #=> String
resp.definition.nodes[0].inputs[0].name #=> String
resp.definition.nodes[0].inputs[0].type #=> String, one of "String", "Number", "Boolean", "Object", "Array"
resp.definition.nodes[0].name #=> String
resp.definition.nodes[0].outputs #=> Array
resp.definition.nodes[0].outputs[0].name #=> String
resp.definition.nodes[0].outputs[0].type #=> String, one of "String", "Number", "Boolean", "Object", "Array"
resp.definition.nodes[0].type #=> String, one of "Input", "Output", "KnowledgeBase", "Condition", "Lex", "Prompt", "LambdaFunction", "Storage", "Agent", "Retrieval", "Iterator", "Collector"
resp.description #=> String
resp.execution_role_arn #=> String
resp.id #=> String
resp.name #=> String
resp.status #=> String, one of "Failed", "Prepared", "Preparing", "NotPrepared"
resp.version #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :client_token (String) —

    A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.

    A suitable default value is auto-generated. You should normally not need to pass this option.**

  • :description (String) —

    A description of the version of the flow.

  • :flow_identifier (required, String) —

    The unique identifier of the flow that you want to create a version of.

Returns:

See Also:



1852
1853
1854
1855
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 1852

def create_flow_version(params = {}, options = {})
  req = build_request(:create_flow_version, params)
  req.send_request(options)
end

#create_knowledge_base(params = {}) ⇒ Types::CreateKnowledgeBaseResponse

Creates a knowledge base. A knowledge base contains your data sources so that Large Language Models (LLMs) can use your data. To create a knowledge base, you must first set up your data sources and configure a supported vector store. For more information, see Set up a knowledge base.

If you prefer to let Amazon Bedrock create and manage a vector store for you in Amazon OpenSearch Service, use the console. For more information, see Create a knowledge base.

  • Provide the name and an optional description.

  • Provide the Amazon Resource Name (ARN) with permissions to create a knowledge base in the roleArn field.

  • Provide the embedding model to use in the embeddingModelArn field in the knowledgeBaseConfiguration object.

  • Provide the configuration for your vector store in the storageConfiguration object.

Examples:

Request syntax with placeholder values


resp = client.create_knowledge_base({
  client_token: "ClientToken",
  description: "Description",
  knowledge_base_configuration: { # required
    type: "VECTOR", # required, accepts VECTOR
    vector_knowledge_base_configuration: {
      embedding_model_arn: "BedrockEmbeddingModelArn", # required
      embedding_model_configuration: {
        bedrock_embedding_model_configuration: {
          dimensions: 1,
          embedding_data_type: "FLOAT32", # accepts FLOAT32, BINARY
        },
      },
    },
  },
  name: "Name", # required
  role_arn: "KnowledgeBaseRoleArn", # required
  storage_configuration: { # required
    mongo_db_atlas_configuration: {
      collection_name: "MongoDbAtlasCollectionName", # required
      credentials_secret_arn: "SecretArn", # required
      database_name: "MongoDbAtlasDatabaseName", # required
      endpoint: "MongoDbAtlasEndpoint", # required
      endpoint_service_name: "MongoDbAtlasEndpointServiceName",
      field_mapping: { # required
        metadata_field: "FieldName", # required
        text_field: "FieldName", # required
        vector_field: "FieldName", # required
      },
      vector_index_name: "MongoDbAtlasIndexName", # required
    },
    opensearch_serverless_configuration: {
      collection_arn: "OpenSearchServerlessCollectionArn", # required
      field_mapping: { # required
        metadata_field: "FieldName", # required
        text_field: "FieldName", # required
        vector_field: "FieldName", # required
      },
      vector_index_name: "OpenSearchServerlessIndexName", # required
    },
    pinecone_configuration: {
      connection_string: "PineconeConnectionString", # required
      credentials_secret_arn: "SecretArn", # required
      field_mapping: { # required
        metadata_field: "FieldName", # required
        text_field: "FieldName", # required
      },
      namespace: "PineconeNamespace",
    },
    rds_configuration: {
      credentials_secret_arn: "SecretArn", # required
      database_name: "RdsDatabaseName", # required
      field_mapping: { # required
        metadata_field: "ColumnName", # required
        primary_key_field: "ColumnName", # required
        text_field: "ColumnName", # required
        vector_field: "ColumnName", # required
      },
      resource_arn: "RdsArn", # required
      table_name: "RdsTableName", # required
    },
    redis_enterprise_cloud_configuration: {
      credentials_secret_arn: "SecretArn", # required
      endpoint: "RedisEnterpriseCloudEndpoint", # required
      field_mapping: { # required
        metadata_field: "FieldName", # required
        text_field: "FieldName", # required
        vector_field: "FieldName", # required
      },
      vector_index_name: "RedisEnterpriseCloudIndexName", # required
    },
    type: "OPENSEARCH_SERVERLESS", # required, accepts OPENSEARCH_SERVERLESS, PINECONE, REDIS_ENTERPRISE_CLOUD, RDS, MONGO_DB_ATLAS
  },
  tags: {
    "TagKey" => "TagValue",
  },
})

Response structure


resp.knowledge_base.created_at #=> Time
resp.knowledge_base.description #=> String
resp.knowledge_base.failure_reasons #=> Array
resp.knowledge_base.failure_reasons[0] #=> String
resp.knowledge_base.knowledge_base_arn #=> String
resp.knowledge_base.knowledge_base_configuration.type #=> String, one of "VECTOR"
resp.knowledge_base.knowledge_base_configuration.vector_knowledge_base_configuration.embedding_model_arn #=> String
resp.knowledge_base.knowledge_base_configuration.vector_knowledge_base_configuration.embedding_model_configuration.bedrock_embedding_model_configuration.dimensions #=> Integer
resp.knowledge_base.knowledge_base_configuration.vector_knowledge_base_configuration.embedding_model_configuration.bedrock_embedding_model_configuration.embedding_data_type #=> String, one of "FLOAT32", "BINARY"
resp.knowledge_base.knowledge_base_id #=> String
resp.knowledge_base.name #=> String
resp.knowledge_base.role_arn #=> String
resp.knowledge_base.status #=> String, one of "CREATING", "ACTIVE", "DELETING", "UPDATING", "FAILED", "DELETE_UNSUCCESSFUL"
resp.knowledge_base.storage_configuration.mongo_db_atlas_configuration.collection_name #=> String
resp.knowledge_base.storage_configuration.mongo_db_atlas_configuration.credentials_secret_arn #=> String
resp.knowledge_base.storage_configuration.mongo_db_atlas_configuration.database_name #=> String
resp.knowledge_base.storage_configuration.mongo_db_atlas_configuration.endpoint #=> String
resp.knowledge_base.storage_configuration.mongo_db_atlas_configuration.endpoint_service_name #=> String
resp.knowledge_base.storage_configuration.mongo_db_atlas_configuration.field_mapping.metadata_field #=> String
resp.knowledge_base.storage_configuration.mongo_db_atlas_configuration.field_mapping.text_field #=> String
resp.knowledge_base.storage_configuration.mongo_db_atlas_configuration.field_mapping.vector_field #=> String
resp.knowledge_base.storage_configuration.mongo_db_atlas_configuration.vector_index_name #=> String
resp.knowledge_base.storage_configuration.opensearch_serverless_configuration.collection_arn #=> String
resp.knowledge_base.storage_configuration.opensearch_serverless_configuration.field_mapping.metadata_field #=> String
resp.knowledge_base.storage_configuration.opensearch_serverless_configuration.field_mapping.text_field #=> String
resp.knowledge_base.storage_configuration.opensearch_serverless_configuration.field_mapping.vector_field #=> String
resp.knowledge_base.storage_configuration.opensearch_serverless_configuration.vector_index_name #=> String
resp.knowledge_base.storage_configuration.pinecone_configuration.connection_string #=> String
resp.knowledge_base.storage_configuration.pinecone_configuration.credentials_secret_arn #=> String
resp.knowledge_base.storage_configuration.pinecone_configuration.field_mapping.metadata_field #=> String
resp.knowledge_base.storage_configuration.pinecone_configuration.field_mapping.text_field #=> String
resp.knowledge_base.storage_configuration.pinecone_configuration.namespace #=> String
resp.knowledge_base.storage_configuration.rds_configuration.credentials_secret_arn #=> String
resp.knowledge_base.storage_configuration.rds_configuration.database_name #=> String
resp.knowledge_base.storage_configuration.rds_configuration.field_mapping.metadata_field #=> String
resp.knowledge_base.storage_configuration.rds_configuration.field_mapping.primary_key_field #=> String
resp.knowledge_base.storage_configuration.rds_configuration.field_mapping.text_field #=> String
resp.knowledge_base.storage_configuration.rds_configuration.field_mapping.vector_field #=> String
resp.knowledge_base.storage_configuration.rds_configuration.resource_arn #=> String
resp.knowledge_base.storage_configuration.rds_configuration.table_name #=> String
resp.knowledge_base.storage_configuration.redis_enterprise_cloud_configuration.credentials_secret_arn #=> String
resp.knowledge_base.storage_configuration.redis_enterprise_cloud_configuration.endpoint #=> String
resp.knowledge_base.storage_configuration.redis_enterprise_cloud_configuration.field_mapping.metadata_field #=> String
resp.knowledge_base.storage_configuration.redis_enterprise_cloud_configuration.field_mapping.text_field #=> String
resp.knowledge_base.storage_configuration.redis_enterprise_cloud_configuration.field_mapping.vector_field #=> String
resp.knowledge_base.storage_configuration.redis_enterprise_cloud_configuration.vector_index_name #=> String
resp.knowledge_base.storage_configuration.type #=> String, one of "OPENSEARCH_SERVERLESS", "PINECONE", "REDIS_ENTERPRISE_CLOUD", "RDS", "MONGO_DB_ATLAS"
resp.knowledge_base.updated_at #=> Time

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :client_token (String) —

    A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.

    A suitable default value is auto-generated. You should normally not need to pass this option.**

  • :description (String) —

    A description of the knowledge base.

  • :knowledge_base_configuration (required, Types::KnowledgeBaseConfiguration) —

    Contains details about the embeddings model used for the knowledge base.

  • :name (required, String) —

    A name for the knowledge base.

  • :role_arn (required, String) —

    The Amazon Resource Name (ARN) of the IAM role with permissions to invoke API operations on the knowledge base.

  • :storage_configuration (required, Types::StorageConfiguration) —

    Contains details about the configuration of the vector database used for the knowledge base.

  • :tags (Hash<String,String>) —

    Specify the key-value pairs for the tags that you want to attach to your knowledge base in this object.

Returns:

See Also:



2078
2079
2080
2081
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 2078

def create_knowledge_base(params = {}, options = {})
  req = build_request(:create_knowledge_base, params)
  req.send_request(options)
end

#create_prompt(params = {}) ⇒ Types::CreatePromptResponse

Creates a prompt in your prompt library that you can add to a flow. For more information, see Prompt management in Amazon Bedrock, Create a prompt using Prompt management and Prompt flows in Amazon Bedrock in the Amazon Bedrock User Guide.

Examples:

Request syntax with placeholder values


resp = client.create_prompt({
  client_token: "ClientToken",
  customer_encryption_key_arn: "KmsKeyArn",
  default_variant: "PromptVariantName",
  description: "PromptDescription",
  name: "PromptName", # required
  tags: {
    "TagKey" => "TagValue",
  },
  variants: [
    {
      additional_model_request_fields: {
      },
      gen_ai_resource: {
        agent: {
          agent_identifier: "AgentAliasArn", # required
        },
      },
      inference_configuration: {
        text: {
          max_tokens: 1,
          stop_sequences: ["String"],
          temperature: 1.0,
          top_p: 1.0,
        },
      },
      metadata: [
        {
          key: "PromptMetadataKey", # required
          value: "PromptMetadataValue", # required
        },
      ],
      model_id: "PromptModelIdentifier",
      name: "PromptVariantName", # required
      template_configuration: { # required
        chat: {
          input_variables: [
            {
              name: "PromptInputVariableName",
            },
          ],
          messages: [ # required
            {
              content: [ # required
                {
                  text: "String",
                },
              ],
              role: "user", # required, accepts user, assistant
            },
          ],
          system: [
            {
              text: "NonEmptyString",
            },
          ],
          tool_configuration: {
            tool_choice: {
              any: {
              },
              auto: {
              },
              tool: {
                name: "ToolName", # required
              },
            },
            tools: [ # required
              {
                tool_spec: {
                  description: "NonEmptyString",
                  input_schema: { # required
                    json: {
                    },
                  },
                  name: "ToolName", # required
                },
              },
            ],
          },
        },
        text: {
          input_variables: [
            {
              name: "PromptInputVariableName",
            },
          ],
          text: "TextPrompt", # required
        },
      },
      template_type: "TEXT", # required, accepts TEXT, CHAT
    },
  ],
})

Response structure


resp.arn #=> String
resp.created_at #=> Time
resp.customer_encryption_key_arn #=> String
resp.default_variant #=> String
resp.description #=> String
resp.id #=> String
resp.name #=> String
resp.updated_at #=> Time
resp.variants #=> Array
resp.variants[0].gen_ai_resource.agent.agent_identifier #=> String
resp.variants[0].inference_configuration.text.max_tokens #=> Integer
resp.variants[0].inference_configuration.text.stop_sequences #=> Array
resp.variants[0].inference_configuration.text.stop_sequences[0] #=> String
resp.variants[0].inference_configuration.text.temperature #=> Float
resp.variants[0].inference_configuration.text.top_p #=> Float
resp.variants[0].metadata #=> Array
resp.variants[0].metadata[0].key #=> String
resp.variants[0].metadata[0].value #=> String
resp.variants[0].model_id #=> String
resp.variants[0].name #=> String
resp.variants[0].template_configuration.chat.input_variables #=> Array
resp.variants[0].template_configuration.chat.input_variables[0].name #=> String
resp.variants[0].template_configuration.chat.messages #=> Array
resp.variants[0].template_configuration.chat.messages[0].content #=> Array
resp.variants[0].template_configuration.chat.messages[0].content[0].text #=> String
resp.variants[0].template_configuration.chat.messages[0].role #=> String, one of "user", "assistant"
resp.variants[0].template_configuration.chat.system #=> Array
resp.variants[0].template_configuration.chat.system[0].text #=> String
resp.variants[0].template_configuration.chat.tool_configuration.tool_choice.tool.name #=> String
resp.variants[0].template_configuration.chat.tool_configuration.tools #=> Array
resp.variants[0].template_configuration.chat.tool_configuration.tools[0].tool_spec.description #=> String
resp.variants[0].template_configuration.chat.tool_configuration.tools[0].tool_spec.name #=> String
resp.variants[0].template_configuration.text.input_variables #=> Array
resp.variants[0].template_configuration.text.input_variables[0].name #=> String
resp.variants[0].template_configuration.text.text #=> String
resp.variants[0].template_type #=> String, one of "TEXT", "CHAT"
resp.version #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :client_token (String) —

    A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.

    A suitable default value is auto-generated. You should normally not need to pass this option.**

  • :customer_encryption_key_arn (String) —

    The Amazon Resource Name (ARN) of the KMS key to encrypt the prompt.

  • :default_variant (String) —

    The name of the default variant for the prompt. This value must match the name field in the relevant PromptVariant object.

  • :description (String) —

    A description for the prompt.

  • :name (required, String) —

    A name for the prompt.

  • :tags (Hash<String,String>) —

    Any tags that you want to attach to the prompt. For more information, see Tagging resources in Amazon Bedrock.

  • :variants (Array<Types::PromptVariant>) —

    A list of objects, each containing details about a variant of the prompt.

Returns:

See Also:



2289
2290
2291
2292
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 2289

def create_prompt(params = {}, options = {})
  req = build_request(:create_prompt, params)
  req.send_request(options)
end

#create_prompt_version(params = {}) ⇒ Types::CreatePromptVersionResponse

Creates a static snapshot of your prompt that can be deployed to production. For more information, see Deploy prompts using Prompt management by creating versions in the Amazon Bedrock User Guide.

Examples:

Request syntax with placeholder values


resp = client.create_prompt_version({
  client_token: "ClientToken",
  description: "PromptDescription",
  prompt_identifier: "PromptIdentifier", # required
  tags: {
    "TagKey" => "TagValue",
  },
})

Response structure


resp.arn #=> String
resp.created_at #=> Time
resp.customer_encryption_key_arn #=> String
resp.default_variant #=> String
resp.description #=> String
resp.id #=> String
resp.name #=> String
resp.updated_at #=> Time
resp.variants #=> Array
resp.variants[0].gen_ai_resource.agent.agent_identifier #=> String
resp.variants[0].inference_configuration.text.max_tokens #=> Integer
resp.variants[0].inference_configuration.text.stop_sequences #=> Array
resp.variants[0].inference_configuration.text.stop_sequences[0] #=> String
resp.variants[0].inference_configuration.text.temperature #=> Float
resp.variants[0].inference_configuration.text.top_p #=> Float
resp.variants[0].metadata #=> Array
resp.variants[0].metadata[0].key #=> String
resp.variants[0].metadata[0].value #=> String
resp.variants[0].model_id #=> String
resp.variants[0].name #=> String
resp.variants[0].template_configuration.chat.input_variables #=> Array
resp.variants[0].template_configuration.chat.input_variables[0].name #=> String
resp.variants[0].template_configuration.chat.messages #=> Array
resp.variants[0].template_configuration.chat.messages[0].content #=> Array
resp.variants[0].template_configuration.chat.messages[0].content[0].text #=> String
resp.variants[0].template_configuration.chat.messages[0].role #=> String, one of "user", "assistant"
resp.variants[0].template_configuration.chat.system #=> Array
resp.variants[0].template_configuration.chat.system[0].text #=> String
resp.variants[0].template_configuration.chat.tool_configuration.tool_choice.tool.name #=> String
resp.variants[0].template_configuration.chat.tool_configuration.tools #=> Array
resp.variants[0].template_configuration.chat.tool_configuration.tools[0].tool_spec.description #=> String
resp.variants[0].template_configuration.chat.tool_configuration.tools[0].tool_spec.name #=> String
resp.variants[0].template_configuration.text.input_variables #=> Array
resp.variants[0].template_configuration.text.input_variables[0].name #=> String
resp.variants[0].template_configuration.text.text #=> String
resp.variants[0].template_type #=> String, one of "TEXT", "CHAT"
resp.version #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :client_token (String) —

    A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.

    A suitable default value is auto-generated. You should normally not need to pass this option.**

  • :description (String) —

    A description for the version of the prompt.

  • :prompt_identifier (required, String) —

    The unique identifier of the prompt that you want to create a version of.

  • :tags (Hash<String,String>) —

    Any tags that you want to attach to the version of the prompt. For more information, see Tagging resources in Amazon Bedrock.

Returns:

See Also:



2398
2399
2400
2401
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 2398

def create_prompt_version(params = {}, options = {})
  req = build_request(:create_prompt_version, params)
  req.send_request(options)
end

#delete_agent(params = {}) ⇒ Types::DeleteAgentResponse

Deletes an agent.

Examples:

Request syntax with placeholder values


resp = client.delete_agent({
  agent_id: "Id", # required
  skip_resource_in_use_check: false,
})

Response structure


resp.agent_id #=> String
resp.agent_status #=> String, one of "CREATING", "PREPARING", "PREPARED", "NOT_PREPARED", "DELETING", "FAILED", "VERSIONING", "UPDATING"

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :agent_id (required, String) —

    The unique identifier of the agent to delete.

  • :skip_resource_in_use_check (Boolean) —

    By default, this value is false and deletion is stopped if the resource is in use. If you set it to true, the resource will be deleted even if the resource is in use.

Returns:

See Also:



2434
2435
2436
2437
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 2434

def delete_agent(params = {}, options = {})
  req = build_request(:delete_agent, params)
  req.send_request(options)
end

#delete_agent_action_group(params = {}) ⇒ Struct

Deletes an action group in an agent.

Examples:

Request syntax with placeholder values


resp = client.delete_agent_action_group({
  action_group_id: "Id", # required
  agent_id: "Id", # required
  agent_version: "DraftVersion", # required
  skip_resource_in_use_check: false,
})

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :action_group_id (required, String) —

    The unique identifier of the action group to delete.

  • :agent_id (required, String) —

    The unique identifier of the agent that the action group belongs to.

  • :agent_version (required, String) —

    The version of the agent that the action group belongs to.

  • :skip_resource_in_use_check (Boolean) —

    By default, this value is false and deletion is stopped if the resource is in use. If you set it to true, the resource will be deleted even if the resource is in use.

Returns:

  • (Struct) —

    Returns an empty response.

See Also:



2470
2471
2472
2473
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 2470

def delete_agent_action_group(params = {}, options = {})
  req = build_request(:delete_agent_action_group, params)
  req.send_request(options)
end

#delete_agent_alias(params = {}) ⇒ Types::DeleteAgentAliasResponse

Deletes an alias of an agent.

Examples:

Request syntax with placeholder values


resp = client.delete_agent_alias({
  agent_alias_id: "AgentAliasId", # required
  agent_id: "Id", # required
})

Response structure


resp.agent_alias_id #=> String
resp.agent_alias_status #=> String, one of "CREATING", "PREPARED", "FAILED", "UPDATING", "DELETING"
resp.agent_id #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :agent_alias_id (required, String) —

    The unique identifier of the alias to delete.

  • :agent_id (required, String) —

    The unique identifier of the agent that the alias belongs to.

Returns:

See Also:



2506
2507
2508
2509
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 2506

def delete_agent_alias(params = {}, options = {})
  req = build_request(:delete_agent_alias, params)
  req.send_request(options)
end

#delete_agent_version(params = {}) ⇒ Types::DeleteAgentVersionResponse

Deletes a version of an agent.

Examples:

Request syntax with placeholder values


resp = client.delete_agent_version({
  agent_id: "Id", # required
  agent_version: "NumericalVersion", # required
  skip_resource_in_use_check: false,
})

Response structure


resp.agent_id #=> String
resp.agent_status #=> String, one of "CREATING", "PREPARING", "PREPARED", "NOT_PREPARED", "DELETING", "FAILED", "VERSIONING", "UPDATING"
resp.agent_version #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :agent_id (required, String) —

    The unique identifier of the agent that the version belongs to.

  • :agent_version (required, String) —

    The version of the agent to delete.

  • :skip_resource_in_use_check (Boolean) —

    By default, this value is false and deletion is stopped if the resource is in use. If you set it to true, the resource will be deleted even if the resource is in use.

Returns:

See Also:



2548
2549
2550
2551
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 2548

def delete_agent_version(params = {}, options = {})
  req = build_request(:delete_agent_version, params)
  req.send_request(options)
end

#delete_data_source(params = {}) ⇒ Types::DeleteDataSourceResponse

Deletes a data source from a knowledge base.

Examples:

Request syntax with placeholder values


resp = client.delete_data_source({
  data_source_id: "Id", # required
  knowledge_base_id: "Id", # required
})

Response structure


resp.data_source_id #=> String
resp.knowledge_base_id #=> String
resp.status #=> String, one of "AVAILABLE", "DELETING", "DELETE_UNSUCCESSFUL"

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :data_source_id (required, String) —

    The unique identifier of the data source to delete.

  • :knowledge_base_id (required, String) —

    The unique identifier of the knowledge base from which to delete the data source.

Returns:

See Also:



2585
2586
2587
2588
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 2585

def delete_data_source(params = {}, options = {})
  req = build_request(:delete_data_source, params)
  req.send_request(options)
end

#delete_flow(params = {}) ⇒ Types::DeleteFlowResponse

Deletes a flow.

Examples:

Request syntax with placeholder values


resp = client.delete_flow({
  flow_identifier: "FlowIdentifier", # required
  skip_resource_in_use_check: false,
})

Response structure


resp.id #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :flow_identifier (required, String) —

    The unique identifier of the flow.

  • :skip_resource_in_use_check (Boolean) —

    By default, this value is false and deletion is stopped if the resource is in use. If you set it to true, the resource will be deleted even if the resource is in use.

Returns:

See Also:



2619
2620
2621
2622
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 2619

def delete_flow(params = {}, options = {})
  req = build_request(:delete_flow, params)
  req.send_request(options)
end

#delete_flow_alias(params = {}) ⇒ Types::DeleteFlowAliasResponse

Deletes an alias of a flow.

Examples:

Request syntax with placeholder values


resp = client.delete_flow_alias({
  alias_identifier: "FlowAliasIdentifier", # required
  flow_identifier: "FlowIdentifier", # required
})

Response structure


resp.flow_id #=> String
resp.id #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :alias_identifier (required, String) —

    The unique identifier of the alias to be deleted.

  • :flow_identifier (required, String) —

    The unique identifier of the flow that the alias belongs to.

Returns:

See Also:



2653
2654
2655
2656
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 2653

def delete_flow_alias(params = {}, options = {})
  req = build_request(:delete_flow_alias, params)
  req.send_request(options)
end

#delete_flow_version(params = {}) ⇒ Types::DeleteFlowVersionResponse

Deletes a version of a flow.

Examples:

Request syntax with placeholder values


resp = client.delete_flow_version({
  flow_identifier: "FlowIdentifier", # required
  flow_version: "NumericalVersion", # required
  skip_resource_in_use_check: false,
})

Response structure


resp.id #=> String
resp.version #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :flow_identifier (required, String) —

    The unique identifier of the flow whose version that you want to delete

  • :flow_version (required, String) —

    The version of the flow that you want to delete.

  • :skip_resource_in_use_check (Boolean) —

    By default, this value is false and deletion is stopped if the resource is in use. If you set it to true, the resource will be deleted even if the resource is in use.

Returns:

See Also:



2694
2695
2696
2697
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 2694

def delete_flow_version(params = {}, options = {})
  req = build_request(:delete_flow_version, params)
  req.send_request(options)
end

#delete_knowledge_base(params = {}) ⇒ Types::DeleteKnowledgeBaseResponse

Deletes a knowledge base. Before deleting a knowledge base, you should disassociate the knowledge base from any agents that it is associated with by making a DisassociateAgentKnowledgeBase request.

Examples:

Request syntax with placeholder values


resp = client.delete_knowledge_base({
  knowledge_base_id: "Id", # required
})

Response structure


resp.knowledge_base_id #=> String
resp.status #=> String, one of "CREATING", "ACTIVE", "DELETING", "UPDATING", "FAILED", "DELETE_UNSUCCESSFUL"

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :knowledge_base_id (required, String) —

    The unique identifier of the knowledge base to delete.

Returns:

See Also:



2730
2731
2732
2733
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 2730

def delete_knowledge_base(params = {}, options = {})
  req = build_request(:delete_knowledge_base, params)
  req.send_request(options)
end

#delete_knowledge_base_documents(params = {}) ⇒ Types::DeleteKnowledgeBaseDocumentsResponse

Deletes documents from a data source and syncs the changes to the knowledge base that is connected to it. For more information, see Ingest documents into a knowledge base in real-time in the Amazon Bedrock User Guide.

Examples:

Request syntax with placeholder values


resp = client.delete_knowledge_base_documents({
  client_token: "ClientToken",
  data_source_id: "Id", # required
  document_identifiers: [ # required
    {
      custom: {
        id: "CustomDocumentIdentifierIdString", # required
      },
      data_source_type: "CUSTOM", # required, accepts CUSTOM, S3
      s3: {
        uri: "S3BucketUri", # required
      },
    },
  ],
  knowledge_base_id: "Id", # required
})

Response structure


resp.document_details #=> Array
resp.document_details[0].data_source_id #=> String
resp.document_details[0].identifier.custom.id #=> String
resp.document_details[0].identifier.data_source_type #=> String, one of "CUSTOM", "S3"
resp.document_details[0].identifier.s3.uri #=> String
resp.document_details[0].knowledge_base_id #=> String
resp.document_details[0].status #=> String, one of "INDEXED", "PARTIALLY_INDEXED", "PENDING", "FAILED", "METADATA_PARTIALLY_INDEXED", "METADATA_UPDATE_FAILED", "IGNORED", "NOT_FOUND", "STARTING", "IN_PROGRESS", "DELETING", "DELETE_IN_PROGRESS"
resp.document_details[0].status_reason #=> String
resp.document_details[0].updated_at #=> Time

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :client_token (String) —

    A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.

    A suitable default value is auto-generated. You should normally not need to pass this option.**

  • :data_source_id (required, String) —

    The unique identifier of the data source that contains the documents.

  • :document_identifiers (required, Array<Types::DocumentIdentifier>) —

    A list of objects, each of which contains information to identify a document to delete.

  • :knowledge_base_id (required, String) —

    The unique identifier of the knowledge base that is connected to the data source.

Returns:

See Also:



2807
2808
2809
2810
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 2807

def delete_knowledge_base_documents(params = {}, options = {})
  req = build_request(:delete_knowledge_base_documents, params)
  req.send_request(options)
end

#delete_prompt(params = {}) ⇒ Types::DeletePromptResponse

Deletes a prompt or a version of it, depending on whether you include the promptVersion field or not. For more information, see Delete prompts from the Prompt management tool and Delete a version of a prompt from the Prompt management tool in the Amazon Bedrock User Guide.

Examples:

Request syntax with placeholder values


resp = client.delete_prompt({
  prompt_identifier: "PromptIdentifier", # required
  prompt_version: "NumericalVersion",
})

Response structure


resp.id #=> String
resp.version #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :prompt_identifier (required, String) —

    The unique identifier of the prompt.

  • :prompt_version (String) —

    The version of the prompt to delete. To delete the prompt, omit this field.

Returns:

See Also:



2851
2852
2853
2854
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 2851

def delete_prompt(params = {}, options = {})
  req = build_request(:delete_prompt, params)
  req.send_request(options)
end

#disassociate_agent_knowledge_base(params = {}) ⇒ Struct

Disassociates a knowledge base from an agent.

Examples:

Request syntax with placeholder values


resp = client.disassociate_agent_knowledge_base({
  agent_id: "Id", # required
  agent_version: "DraftVersion", # required
  knowledge_base_id: "Id", # required
})

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :agent_id (required, String) —

    The unique identifier of the agent from which to disassociate the knowledge base.

  • :agent_version (required, String) —

    The version of the agent from which to disassociate the knowledge base.

  • :knowledge_base_id (required, String) —

    The unique identifier of the knowledge base to disassociate.

Returns:

  • (Struct) —

    Returns an empty response.

See Also:



2883
2884
2885
2886
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 2883

def disassociate_agent_knowledge_base(params = {}, options = {})
  req = build_request(:disassociate_agent_knowledge_base, params)
  req.send_request(options)
end

#get_agent(params = {}) ⇒ Types::GetAgentResponse

Gets information about an agent.

Examples:

Request syntax with placeholder values


resp = client.get_agent({
  agent_id: "Id", # required
})

Response structure


resp.agent.agent_arn #=> String
resp.agent.agent_id #=> String
resp.agent.agent_name #=> String
resp.agent.agent_resource_role_arn #=> String
resp.agent.agent_status #=> String, one of "CREATING", "PREPARING", "PREPARED", "NOT_PREPARED", "DELETING", "FAILED", "VERSIONING", "UPDATING"
resp.agent.agent_version #=> String
resp.agent.client_token #=> String
resp.agent.created_at #=> Time
resp.agent.custom_orchestration.executor.lambda #=> String
resp.agent.customer_encryption_key_arn #=> String
resp.agent.description #=> String
resp.agent.failure_reasons #=> Array
resp.agent.failure_reasons[0] #=> String
resp.agent.foundation_model #=> String
resp.agent.guardrail_configuration.guardrail_identifier #=> String
resp.agent.guardrail_configuration.guardrail_version #=> String
resp.agent.idle_session_ttl_in_seconds #=> Integer
resp.agent.instruction #=> String
resp.agent.memory_configuration.enabled_memory_types #=> Array
resp.agent.memory_configuration.enabled_memory_types[0] #=> String, one of "SESSION_SUMMARY"
resp.agent.memory_configuration.storage_days #=> Integer
resp.agent.orchestration_type #=> String, one of "DEFAULT", "CUSTOM_ORCHESTRATION"
resp.agent.prepared_at #=> Time
resp.agent.prompt_override_configuration.override_lambda #=> String
resp.agent.prompt_override_configuration.prompt_configurations #=> Array
resp.agent.prompt_override_configuration.prompt_configurations[0].base_prompt_template #=> String
resp.agent.prompt_override_configuration.prompt_configurations[0].inference_configuration.maximum_length #=> Integer
resp.agent.prompt_override_configuration.prompt_configurations[0].inference_configuration.stop_sequences #=> Array
resp.agent.prompt_override_configuration.prompt_configurations[0].inference_configuration.stop_sequences[0] #=> String
resp.agent.prompt_override_configuration.prompt_configurations[0].inference_configuration.temperature #=> Float
resp.agent.prompt_override_configuration.prompt_configurations[0].inference_configuration.top_k #=> Integer
resp.agent.prompt_override_configuration.prompt_configurations[0].inference_configuration.top_p #=> Float
resp.agent.prompt_override_configuration.prompt_configurations[0].parser_mode #=> String, one of "DEFAULT", "OVERRIDDEN"
resp.agent.prompt_override_configuration.prompt_configurations[0].prompt_creation_mode #=> String, one of "DEFAULT", "OVERRIDDEN"
resp.agent.prompt_override_configuration.prompt_configurations[0].prompt_state #=> String, one of "ENABLED", "DISABLED"
resp.agent.prompt_override_configuration.prompt_configurations[0].prompt_type #=> String, one of "PRE_PROCESSING", "ORCHESTRATION", "POST_PROCESSING", "KNOWLEDGE_BASE_RESPONSE_GENERATION"
resp.agent.recommended_actions #=> Array
resp.agent.recommended_actions[0] #=> String
resp.agent.updated_at #=> Time

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :agent_id (required, String) —

    The unique identifier of the agent.

Returns:

See Also:



2949
2950
2951
2952
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 2949

def get_agent(params = {}, options = {})
  req = build_request(:get_agent, params)
  req.send_request(options)
end

#get_agent_action_group(params = {}) ⇒ Types::GetAgentActionGroupResponse

Gets information about an action group for an agent.

Examples:

Request syntax with placeholder values


resp = client.get_agent_action_group({
  action_group_id: "Id", # required
  agent_id: "Id", # required
  agent_version: "Version", # required
})

Response structure


resp.agent_action_group.action_group_executor.custom_control #=> String, one of "RETURN_CONTROL"
resp.agent_action_group.action_group_executor.lambda #=> String
resp.agent_action_group.action_group_id #=> String
resp.agent_action_group.action_group_name #=> String
resp.agent_action_group.action_group_state #=> String, one of "ENABLED", "DISABLED"
resp.agent_action_group.agent_id #=> String
resp.agent_action_group.agent_version #=> String
resp.agent_action_group.api_schema.payload #=> String
resp.agent_action_group.api_schema.s3.s3_bucket_name #=> String
resp.agent_action_group.api_schema.s3.s3_object_key #=> String
resp.agent_action_group.client_token #=> String
resp.agent_action_group.created_at #=> Time
resp.agent_action_group.description #=> String
resp.agent_action_group.function_schema.functions #=> Array
resp.agent_action_group.function_schema.functions[0].description #=> String
resp.agent_action_group.function_schema.functions[0].name #=> String
resp.agent_action_group.function_schema.functions[0].parameters #=> Hash
resp.agent_action_group.function_schema.functions[0].parameters["Name"].description #=> String
resp.agent_action_group.function_schema.functions[0].parameters["Name"].required #=> Boolean
resp.agent_action_group.function_schema.functions[0].parameters["Name"].type #=> String, one of "string", "number", "integer", "boolean", "array"
resp.agent_action_group.function_schema.functions[0].require_confirmation #=> String, one of "ENABLED", "DISABLED"
resp.agent_action_group.parent_action_signature #=> String, one of "AMAZON.UserInput", "AMAZON.CodeInterpreter"
resp.agent_action_group.updated_at #=> Time

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :action_group_id (required, String) —

    The unique identifier of the action group for which to get information.

  • :agent_id (required, String) —

    The unique identifier of the agent that the action group belongs to.

  • :agent_version (required, String) —

    The version of the agent that the action group belongs to.

Returns:

See Also:



3008
3009
3010
3011
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 3008

def get_agent_action_group(params = {}, options = {})
  req = build_request(:get_agent_action_group, params)
  req.send_request(options)
end

#get_agent_alias(params = {}) ⇒ Types::GetAgentAliasResponse

Gets information about an alias of an agent.

Examples:

Request syntax with placeholder values


resp = client.get_agent_alias({
  agent_alias_id: "AgentAliasId", # required
  agent_id: "Id", # required
})

Response structure


resp.agent_alias.agent_alias_arn #=> String
resp.agent_alias.agent_alias_history_events #=> Array
resp.agent_alias.agent_alias_history_events[0].end_date #=> Time
resp.agent_alias.agent_alias_history_events[0].routing_configuration #=> Array
resp.agent_alias.agent_alias_history_events[0].routing_configuration[0].agent_version #=> String
resp.agent_alias.agent_alias_history_events[0].routing_configuration[0].provisioned_throughput #=> String
resp.agent_alias.agent_alias_history_events[0].start_date #=> Time
resp.agent_alias.agent_alias_id #=> String
resp.agent_alias.agent_alias_name #=> String
resp.agent_alias.agent_alias_status #=> String, one of "CREATING", "PREPARED", "FAILED", "UPDATING", "DELETING"
resp.agent_alias.agent_id #=> String
resp.agent_alias.client_token #=> String
resp.agent_alias.created_at #=> Time
resp.agent_alias.description #=> String
resp.agent_alias.failure_reasons #=> Array
resp.agent_alias.failure_reasons[0] #=> String
resp.agent_alias.routing_configuration #=> Array
resp.agent_alias.routing_configuration[0].agent_version #=> String
resp.agent_alias.routing_configuration[0].provisioned_throughput #=> String
resp.agent_alias.updated_at #=> Time

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :agent_alias_id (required, String) —

    The unique identifier of the alias for which to get information.

  • :agent_id (required, String) —

    The unique identifier of the agent to which the alias to get information belongs.

Returns:

See Also:



3060
3061
3062
3063
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 3060

def get_agent_alias(params = {}, options = {})
  req = build_request(:get_agent_alias, params)
  req.send_request(options)
end

#get_agent_knowledge_base(params = {}) ⇒ Types::GetAgentKnowledgeBaseResponse

Gets information about a knowledge base associated with an agent.

Examples:

Request syntax with placeholder values


resp = client.get_agent_knowledge_base({
  agent_id: "Id", # required
  agent_version: "Version", # required
  knowledge_base_id: "Id", # required
})

Response structure


resp.agent_knowledge_base.agent_id #=> String
resp.agent_knowledge_base.agent_version #=> String
resp.agent_knowledge_base.created_at #=> Time
resp.agent_knowledge_base.description #=> String
resp.agent_knowledge_base.knowledge_base_id #=> String
resp.agent_knowledge_base.knowledge_base_state #=> String, one of "ENABLED", "DISABLED"
resp.agent_knowledge_base.updated_at #=> Time

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :agent_id (required, String) —

    The unique identifier of the agent with which the knowledge base is associated.

  • :agent_version (required, String) —

    The version of the agent with which the knowledge base is associated.

  • :knowledge_base_id (required, String) —

    The unique identifier of the knowledge base associated with the agent.

Returns:

See Also:



3103
3104
3105
3106
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 3103

def get_agent_knowledge_base(params = {}, options = {})
  req = build_request(:get_agent_knowledge_base, params)
  req.send_request(options)
end

#get_agent_version(params = {}) ⇒ Types::GetAgentVersionResponse

Gets details about a version of an agent.

Examples:

Request syntax with placeholder values


resp = client.get_agent_version({
  agent_id: "Id", # required
  agent_version: "NumericalVersion", # required
})

Response structure


resp.agent_version.agent_arn #=> String
resp.agent_version.agent_id #=> String
resp.agent_version.agent_name #=> String
resp.agent_version.agent_resource_role_arn #=> String
resp.agent_version.agent_status #=> String, one of "CREATING", "PREPARING", "PREPARED", "NOT_PREPARED", "DELETING", "FAILED", "VERSIONING", "UPDATING"
resp.agent_version.created_at #=> Time
resp.agent_version.customer_encryption_key_arn #=> String
resp.agent_version.description #=> String
resp.agent_version.failure_reasons #=> Array
resp.agent_version.failure_reasons[0] #=> String
resp.agent_version.foundation_model #=> String
resp.agent_version.guardrail_configuration.guardrail_identifier #=> String
resp.agent_version.guardrail_configuration.guardrail_version #=> String
resp.agent_version.idle_session_ttl_in_seconds #=> Integer
resp.agent_version.instruction #=> String
resp.agent_version.memory_configuration.enabled_memory_types #=> Array
resp.agent_version.memory_configuration.enabled_memory_types[0] #=> String, one of "SESSION_SUMMARY"
resp.agent_version.memory_configuration.storage_days #=> Integer
resp.agent_version.prompt_override_configuration.override_lambda #=> String
resp.agent_version.prompt_override_configuration.prompt_configurations #=> Array
resp.agent_version.prompt_override_configuration.prompt_configurations[0].base_prompt_template #=> String
resp.agent_version.prompt_override_configuration.prompt_configurations[0].inference_configuration.maximum_length #=> Integer
resp.agent_version.prompt_override_configuration.prompt_configurations[0].inference_configuration.stop_sequences #=> Array
resp.agent_version.prompt_override_configuration.prompt_configurations[0].inference_configuration.stop_sequences[0] #=> String
resp.agent_version.prompt_override_configuration.prompt_configurations[0].inference_configuration.temperature #=> Float
resp.agent_version.prompt_override_configuration.prompt_configurations[0].inference_configuration.top_k #=> Integer
resp.agent_version.prompt_override_configuration.prompt_configurations[0].inference_configuration.top_p #=> Float
resp.agent_version.prompt_override_configuration.prompt_configurations[0].parser_mode #=> String, one of "DEFAULT", "OVERRIDDEN"
resp.agent_version.prompt_override_configuration.prompt_configurations[0].prompt_creation_mode #=> String, one of "DEFAULT", "OVERRIDDEN"
resp.agent_version.prompt_override_configuration.prompt_configurations[0].prompt_state #=> String, one of "ENABLED", "DISABLED"
resp.agent_version.prompt_override_configuration.prompt_configurations[0].prompt_type #=> String, one of "PRE_PROCESSING", "ORCHESTRATION", "POST_PROCESSING", "KNOWLEDGE_BASE_RESPONSE_GENERATION"
resp.agent_version.recommended_actions #=> Array
resp.agent_version.recommended_actions[0] #=> String
resp.agent_version.updated_at #=> Time
resp.agent_version.version #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :agent_id (required, String) —

    The unique identifier of the agent.

  • :agent_version (required, String) —

    The version of the agent.

Returns:

See Also:



3169
3170
3171
3172
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 3169

def get_agent_version(params = {}, options = {})
  req = build_request(:get_agent_version, params)
  req.send_request(options)
end

#get_data_source(params = {}) ⇒ Types::GetDataSourceResponse

Gets information about a data source.

Examples:

Request syntax with placeholder values


resp = client.get_data_source({
  data_source_id: "Id", # required
  knowledge_base_id: "Id", # required
})

Response structure


resp.data_source.created_at #=> Time
resp.data_source.data_deletion_policy #=> String, one of "RETAIN", "DELETE"
resp.data_source.data_source_configuration.confluence_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters #=> Array
resp.data_source.data_source_configuration.confluence_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters[0].exclusion_filters #=> Array
resp.data_source.data_source_configuration.confluence_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters[0].exclusion_filters[0] #=> String
resp.data_source.data_source_configuration.confluence_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters[0].inclusion_filters #=> Array
resp.data_source.data_source_configuration.confluence_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters[0].inclusion_filters[0] #=> String
resp.data_source.data_source_configuration.confluence_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters[0].object_type #=> String
resp.data_source.data_source_configuration.confluence_configuration.crawler_configuration.filter_configuration.type #=> String, one of "PATTERN"
resp.data_source.data_source_configuration.confluence_configuration.source_configuration.auth_type #=> String, one of "BASIC", "OAUTH2_CLIENT_CREDENTIALS"
resp.data_source.data_source_configuration.confluence_configuration.source_configuration.credentials_secret_arn #=> String
resp.data_source.data_source_configuration.confluence_configuration.source_configuration.host_type #=> String, one of "SAAS"
resp.data_source.data_source_configuration.confluence_configuration.source_configuration.host_url #=> String
resp.data_source.data_source_configuration.s3_configuration.bucket_arn #=> String
resp.data_source.data_source_configuration.s3_configuration. #=> String
resp.data_source.data_source_configuration.s3_configuration.inclusion_prefixes #=> Array
resp.data_source.data_source_configuration.s3_configuration.inclusion_prefixes[0] #=> String
resp.data_source.data_source_configuration.salesforce_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters #=> Array
resp.data_source.data_source_configuration.salesforce_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters[0].exclusion_filters #=> Array
resp.data_source.data_source_configuration.salesforce_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters[0].exclusion_filters[0] #=> String
resp.data_source.data_source_configuration.salesforce_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters[0].inclusion_filters #=> Array
resp.data_source.data_source_configuration.salesforce_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters[0].inclusion_filters[0] #=> String
resp.data_source.data_source_configuration.salesforce_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters[0].object_type #=> String
resp.data_source.data_source_configuration.salesforce_configuration.crawler_configuration.filter_configuration.type #=> String, one of "PATTERN"
resp.data_source.data_source_configuration.salesforce_configuration.source_configuration.auth_type #=> String, one of "OAUTH2_CLIENT_CREDENTIALS"
resp.data_source.data_source_configuration.salesforce_configuration.source_configuration.credentials_secret_arn #=> String
resp.data_source.data_source_configuration.salesforce_configuration.source_configuration.host_url #=> String
resp.data_source.data_source_configuration.share_point_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters #=> Array
resp.data_source.data_source_configuration.share_point_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters[0].exclusion_filters #=> Array
resp.data_source.data_source_configuration.share_point_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters[0].exclusion_filters[0] #=> String
resp.data_source.data_source_configuration.share_point_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters[0].inclusion_filters #=> Array
resp.data_source.data_source_configuration.share_point_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters[0].inclusion_filters[0] #=> String
resp.data_source.data_source_configuration.share_point_configuration.crawler_configuration.filter_configuration.pattern_object_filter.filters[0].object_type #=> String
resp.data_source.data_source_configuration.share_point_configuration.crawler_configuration.filter_configuration.type #=> String, one of "PATTERN"
resp.data_source.data_source_configuration.share_point_configuration.source_configuration.auth_type #=> String, one of "OAUTH2_CLIENT_CREDENTIALS"
resp.data_source.data_source_configuration.share_point_configuration.source_configuration.credentials_secret_arn #=> String
resp.data_source.data_source_configuration.share_point_configuration.source_configuration.domain #=> String
resp.data_source.data_source_configuration.share_point_configuration.source_configuration.host_type #=> String, one of "ONLINE"
resp.data_source.data_source_configuration.share_point_configuration.source_configuration.site_urls #=> Array
resp.data_source.data_source_configuration.share_point_configuration.source_configuration.site_urls[0] #=> String
resp.data_source.data_source_configuration.share_point_configuration.source_configuration.tenant_id #=> String
resp.data_source.data_source_configuration.type #=> String, one of "S3", "WEB", "CONFLUENCE", "SALESFORCE", "SHAREPOINT", "CUSTOM"
resp.data_source.data_source_configuration.web_configuration.crawler_configuration.crawler_limits.rate_limit #=> Integer
resp.data_source.data_source_configuration.web_configuration.crawler_configuration.exclusion_filters #=> Array
resp.data_source.data_source_configuration.web_configuration.crawler_configuration.exclusion_filters[0] #=> String
resp.data_source.data_source_configuration.web_configuration.crawler_configuration.inclusion_filters #=> Array
resp.data_source.data_source_configuration.web_configuration.crawler_configuration.inclusion_filters[0] #=> String
resp.data_source.data_source_configuration.web_configuration.crawler_configuration.scope #=> String, one of "HOST_ONLY", "SUBDOMAINS"
resp.data_source.data_source_configuration.web_configuration.source_configuration.url_configuration.seed_urls #=> Array
resp.data_source.data_source_configuration.web_configuration.source_configuration.url_configuration.seed_urls[0].url #=> String
resp.data_source.data_source_id #=> String
resp.data_source.description #=> String
resp.data_source.failure_reasons #=> Array
resp.data_source.failure_reasons[0] #=> String
resp.data_source.knowledge_base_id #=> String
resp.data_source.name #=> String
resp.data_source.server_side_encryption_configuration.kms_key_arn #=> String
resp.data_source.status #=> String, one of "AVAILABLE", "DELETING", "DELETE_UNSUCCESSFUL"
resp.data_source.updated_at #=> Time
resp.data_source.vector_ingestion_configuration.chunking_configuration.chunking_strategy #=> String, one of "FIXED_SIZE", "NONE", "HIERARCHICAL", "SEMANTIC"
resp.data_source.vector_ingestion_configuration.chunking_configuration.fixed_size_chunking_configuration.max_tokens #=> Integer
resp.data_source.vector_ingestion_configuration.chunking_configuration.fixed_size_chunking_configuration.overlap_percentage #=> Integer
resp.data_source.vector_ingestion_configuration.chunking_configuration.hierarchical_chunking_configuration.level_configurations #=> Array
resp.data_source.vector_ingestion_configuration.chunking_configuration.hierarchical_chunking_configuration.level_configurations[0].max_tokens #=> Integer
resp.data_source.vector_ingestion_configuration.chunking_configuration.hierarchical_chunking_configuration.overlap_tokens #=> Integer
resp.data_source.vector_ingestion_configuration.chunking_configuration.semantic_chunking_configuration.breakpoint_percentile_threshold #=> Integer
resp.data_source.vector_ingestion_configuration.chunking_configuration.semantic_chunking_configuration.buffer_size #=> Integer
resp.data_source.vector_ingestion_configuration.chunking_configuration.semantic_chunking_configuration.max_tokens #=> Integer
resp.data_source.vector_ingestion_configuration.custom_transformation_configuration.intermediate_storage.s3_location.uri #=> String
resp.data_source.vector_ingestion_configuration.custom_transformation_configuration.transformations #=> Array
resp.data_source.vector_ingestion_configuration.custom_transformation_configuration.transformations[0].step_to_apply #=> String, one of "POST_CHUNKING"
resp.data_source.vector_ingestion_configuration.custom_transformation_configuration.transformations[0].transformation_function.transformation_lambda_configuration.lambda_arn #=> String
resp.data_source.vector_ingestion_configuration.parsing_configuration.bedrock_foundation_model_configuration.model_arn #=> String
resp.data_source.vector_ingestion_configuration.parsing_configuration.bedrock_foundation_model_configuration.parsing_prompt.parsing_prompt_text #=> String
resp.data_source.vector_ingestion_configuration.parsing_configuration.parsing_strategy #=> String, one of "BEDROCK_FOUNDATION_MODEL"

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :data_source_id (required, String) —

    The unique identifier of the data source.

  • :knowledge_base_id (required, String) —

    The unique identifier of the knowledge base for the data source.

Returns:

See Also:



3275
3276
3277
3278
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 3275

def get_data_source(params = {}, options = {})
  req = build_request(:get_data_source, params)
  req.send_request(options)
end

#get_flow(params = {}) ⇒ Types::GetFlowResponse

Retrieves information about a flow. For more information, see Manage a flow in Amazon Bedrock in the Amazon Bedrock User Guide.

Examples:

Request syntax with placeholder values


resp = client.get_flow({
  flow_identifier: "FlowIdentifier", # required
})

Response structure


resp.arn #=> String
resp.created_at #=> Time
resp.customer_encryption_key_arn #=> String
resp.definition.connections #=> Array
resp.definition.connections[0].configuration.conditional.condition #=> String
resp.definition.connections[0].configuration.data.source_output #=> String
resp.definition.connections[0].configuration.data.target_input #=> String
resp.definition.connections[0].name #=> String
resp.definition.connections[0].source #=> String
resp.definition.connections[0].target #=> String
resp.definition.connections[0].type #=> String, one of "Data", "Conditional"
resp.definition.nodes #=> Array
resp.definition.nodes[0].configuration.agent.agent_alias_arn #=> String
resp.definition.nodes[0].configuration.condition.conditions #=> Array
resp.definition.nodes[0].configuration.condition.conditions[0].expression #=> String
resp.definition.nodes[0].configuration.condition.conditions[0].name #=> String
resp.definition.nodes[0].configuration.knowledge_base.guardrail_configuration.guardrail_identifier #=> String
resp.definition.nodes[0].configuration.knowledge_base.guardrail_configuration.guardrail_version #=> String
resp.definition.nodes[0].configuration.knowledge_base.knowledge_base_id #=> String
resp.definition.nodes[0].configuration.knowledge_base.model_id #=> String
resp.definition.nodes[0].configuration.lambda_function.lambda_arn #=> String
resp.definition.nodes[0].configuration.lex.bot_alias_arn #=> String
resp.definition.nodes[0].configuration.lex.locale_id #=> String
resp.definition.nodes[0].configuration.prompt.guardrail_configuration.guardrail_identifier #=> String
resp.definition.nodes[0].configuration.prompt.guardrail_configuration.guardrail_version #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.inference_configuration.text.max_tokens #=> Integer
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.inference_configuration.text.stop_sequences #=> Array
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.inference_configuration.text.stop_sequences[0] #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.inference_configuration.text.temperature #=> Float
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.inference_configuration.text.top_p #=> Float
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.model_id #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.input_variables #=> Array
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.input_variables[0].name #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.messages #=> Array
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.messages[0].content #=> Array
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.messages[0].content[0].text #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.messages[0].role #=> String, one of "user", "assistant"
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.system #=> Array
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.system[0].text #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.tool_configuration.tool_choice.tool.name #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.tool_configuration.tools #=> Array
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.tool_configuration.tools[0].tool_spec.description #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.tool_configuration.tools[0].tool_spec.name #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.text.input_variables #=> Array
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.text.input_variables[0].name #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.text.text #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_type #=> String, one of "TEXT", "CHAT"
resp.definition.nodes[0].configuration.prompt.source_configuration.resource.prompt_arn #=> String
resp.definition.nodes[0].configuration.retrieval.service_configuration.s3.bucket_name #=> String
resp.definition.nodes[0].configuration.storage.service_configuration.s3.bucket_name #=> String
resp.definition.nodes[0].inputs #=> Array
resp.definition.nodes[0].inputs[0].expression #=> String
resp.definition.nodes[0].inputs[0].name #=> String
resp.definition.nodes[0].inputs[0].type #=> String, one of "String", "Number", "Boolean", "Object", "Array"
resp.definition.nodes[0].name #=> String
resp.definition.nodes[0].outputs #=> Array
resp.definition.nodes[0].outputs[0].name #=> String
resp.definition.nodes[0].outputs[0].type #=> String, one of "String", "Number", "Boolean", "Object", "Array"
resp.definition.nodes[0].type #=> String, one of "Input", "Output", "KnowledgeBase", "Condition", "Lex", "Prompt", "LambdaFunction", "Storage", "Agent", "Retrieval", "Iterator", "Collector"
resp.description #=> String
resp.execution_role_arn #=> String
resp.id #=> String
resp.name #=> String
resp.status #=> String, one of "Failed", "Prepared", "Preparing", "NotPrepared"
resp.updated_at #=> Time
resp.validations #=> Array
resp.validations[0].details.cyclic_connection.connection #=> String
resp.validations[0].details.duplicate_condition_expression.expression #=> String
resp.validations[0].details.duplicate_condition_expression.node #=> String
resp.validations[0].details.duplicate_connections.source #=> String
resp.validations[0].details.duplicate_connections.target #=> String
resp.validations[0].details.incompatible_connection_data_type.connection #=> String
resp.validations[0].details.malformed_condition_expression.cause #=> String
resp.validations[0].details.malformed_condition_expression.condition #=> String
resp.validations[0].details.malformed_condition_expression.node #=> String
resp.validations[0].details.malformed_node_input_expression.cause #=> String
resp.validations[0].details.malformed_node_input_expression.input #=> String
resp.validations[0].details.malformed_node_input_expression.node #=> String
resp.validations[0].details.mismatched_node_input_type.expected_type #=> String, one of "String", "Number", "Boolean", "Object", "Array"
resp.validations[0].details.mismatched_node_input_type.input #=> String
resp.validations[0].details.mismatched_node_input_type.node #=> String
resp.validations[0].details.mismatched_node_output_type.expected_type #=> String, one of "String", "Number", "Boolean", "Object", "Array"
resp.validations[0].details.mismatched_node_output_type.node #=> String
resp.validations[0].details.mismatched_node_output_type.output #=> String
resp.validations[0].details.missing_connection_configuration.connection #=> String
resp.validations[0].details.missing_default_condition.node #=> String
resp.validations[0].details.missing_node_configuration.node #=> String
resp.validations[0].details.missing_node_input.input #=> String
resp.validations[0].details.missing_node_input.node #=> String
resp.validations[0].details.missing_node_output.node #=> String
resp.validations[0].details.missing_node_output.output #=> String
resp.validations[0].details.multiple_node_input_connections.input #=> String
resp.validations[0].details.multiple_node_input_connections.node #=> String
resp.validations[0].details.unfulfilled_node_input.input #=> String
resp.validations[0].details.unfulfilled_node_input.node #=> String
resp.validations[0].details.unknown_connection_condition.connection #=> String
resp.validations[0].details.unknown_connection_source.connection #=> String
resp.validations[0].details.unknown_connection_source_output.connection #=> String
resp.validations[0].details.unknown_connection_target.connection #=> String
resp.validations[0].details.unknown_connection_target_input.connection #=> String
resp.validations[0].details.unreachable_node.node #=> String
resp.validations[0].details.unsatisfied_connection_conditions.connection #=> String
resp.validations[0].message #=> String
resp.validations[0].severity #=> String, one of "Warning", "Error"
resp.validations[0].type #=> String, one of "CyclicConnection", "DuplicateConnections", "DuplicateConditionExpression", "UnreachableNode", "UnknownConnectionSource", "UnknownConnectionSourceOutput", "UnknownConnectionTarget", "UnknownConnectionTargetInput", "UnknownConnectionCondition", "MalformedConditionExpression", "MalformedNodeInputExpression", "MismatchedNodeInputType", "MismatchedNodeOutputType", "IncompatibleConnectionDataType", "MissingConnectionConfiguration", "MissingDefaultCondition", "MissingEndingNodes", "MissingNodeConfiguration", "MissingNodeInput", "MissingNodeOutput", "MissingStartingNodes", "MultipleNodeInputConnections", "UnfulfilledNodeInput", "UnsatisfiedConnectionConditions", "Unspecified"
resp.version #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :flow_identifier (required, String) —

    The unique identifier of the flow.

Returns:

See Also:



3424
3425
3426
3427
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 3424

def get_flow(params = {}, options = {})
  req = build_request(:get_flow, params)
  req.send_request(options)
end

#get_flow_alias(params = {}) ⇒ Types::GetFlowAliasResponse

Retrieves information about a flow. For more information, see Deploy a flow in Amazon Bedrock in the Amazon Bedrock User Guide.

Examples:

Request syntax with placeholder values


resp = client.get_flow_alias({
  alias_identifier: "FlowAliasIdentifier", # required
  flow_identifier: "FlowIdentifier", # required
})

Response structure


resp.arn #=> String
resp.created_at #=> Time
resp.description #=> String
resp.flow_id #=> String
resp.id #=> String
resp.name #=> String
resp.routing_configuration #=> Array
resp.routing_configuration[0].flow_version #=> String
resp.updated_at #=> Time

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :alias_identifier (required, String) —

    The unique identifier of the alias for which to retrieve information.

  • :flow_identifier (required, String) —

    The unique identifier of the flow that the alias belongs to.

Returns:

See Also:



3476
3477
3478
3479
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 3476

def get_flow_alias(params = {}, options = {})
  req = build_request(:get_flow_alias, params)
  req.send_request(options)
end

#get_flow_version(params = {}) ⇒ Types::GetFlowVersionResponse

Retrieves information about a version of a flow. For more information, see Deploy a flow in Amazon Bedrock in the Amazon Bedrock User Guide.

Examples:

Request syntax with placeholder values


resp = client.get_flow_version({
  flow_identifier: "FlowIdentifier", # required
  flow_version: "NumericalVersion", # required
})

Response structure


resp.arn #=> String
resp.created_at #=> Time
resp.customer_encryption_key_arn #=> String
resp.definition.connections #=> Array
resp.definition.connections[0].configuration.conditional.condition #=> String
resp.definition.connections[0].configuration.data.source_output #=> String
resp.definition.connections[0].configuration.data.target_input #=> String
resp.definition.connections[0].name #=> String
resp.definition.connections[0].source #=> String
resp.definition.connections[0].target #=> String
resp.definition.connections[0].type #=> String, one of "Data", "Conditional"
resp.definition.nodes #=> Array
resp.definition.nodes[0].configuration.agent.agent_alias_arn #=> String
resp.definition.nodes[0].configuration.condition.conditions #=> Array
resp.definition.nodes[0].configuration.condition.conditions[0].expression #=> String
resp.definition.nodes[0].configuration.condition.conditions[0].name #=> String
resp.definition.nodes[0].configuration.knowledge_base.guardrail_configuration.guardrail_identifier #=> String
resp.definition.nodes[0].configuration.knowledge_base.guardrail_configuration.guardrail_version #=> String
resp.definition.nodes[0].configuration.knowledge_base.knowledge_base_id #=> String
resp.definition.nodes[0].configuration.knowledge_base.model_id #=> String
resp.definition.nodes[0].configuration.lambda_function.lambda_arn #=> String
resp.definition.nodes[0].configuration.lex.bot_alias_arn #=> String
resp.definition.nodes[0].configuration.lex.locale_id #=> String
resp.definition.nodes[0].configuration.prompt.guardrail_configuration.guardrail_identifier #=> String
resp.definition.nodes[0].configuration.prompt.guardrail_configuration.guardrail_version #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.inference_configuration.text.max_tokens #=> Integer
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.inference_configuration.text.stop_sequences #=> Array
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.inference_configuration.text.stop_sequences[0] #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.inference_configuration.text.temperature #=> Float
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.inference_configuration.text.top_p #=> Float
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.model_id #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.input_variables #=> Array
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.input_variables[0].name #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.messages #=> Array
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.messages[0].content #=> Array
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.messages[0].content[0].text #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.messages[0].role #=> String, one of "user", "assistant"
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.system #=> Array
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.system[0].text #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.tool_configuration.tool_choice.tool.name #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.tool_configuration.tools #=> Array
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.tool_configuration.tools[0].tool_spec.description #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.chat.tool_configuration.tools[0].tool_spec.name #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.text.input_variables #=> Array
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.text.input_variables[0].name #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_configuration.text.text #=> String
resp.definition.nodes[0].configuration.prompt.source_configuration.inline.template_type #=> String, one of "TEXT", "CHAT"
resp.definition.nodes[0].configuration.prompt.source_configuration.resource.prompt_arn #=> String
resp.definition.nodes[0].configuration.retrieval.service_configuration.s3.bucket_name #=> String
resp.definition.nodes[0].configuration.storage.service_configuration.s3.bucket_name #=> String
resp.definition.nodes[0].inputs #=> Array
resp.definition.nodes[0].inputs[0].expression #=> String
resp.definition.nodes[0].inputs[0].name #=> String
resp.definition.nodes[0].inputs[0].type #=> String, one of "String", "Number", "Boolean", "Object", "Array"
resp.definition.nodes[0].name #=> String
resp.definition.nodes[0].outputs #=> Array
resp.definition.nodes[0].outputs[0].name #=> String
resp.definition.nodes[0].outputs[0].type #=> String, one of "String", "Number", "Boolean", "Object", "Array"
resp.definition.nodes[0].type #=> String, one of "Input", "Output", "KnowledgeBase", "Condition", "Lex", "Prompt", "LambdaFunction", "Storage", "Agent", "Retrieval", "Iterator", "Collector"
resp.description #=> String
resp.execution_role_arn #=> String
resp.id #=> String
resp.name #=> String
resp.status #=> String, one of "Failed", "Prepared", "Preparing", "NotPrepared"
resp.version #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :flow_identifier (required, String) —

    The unique identifier of the flow for which to get information.

  • :flow_version (required, String) —

    The version of the flow for which to get information.

Returns:

See Also:



3587
3588
3589
3590
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 3587

def get_flow_version(params = {}, options = {})
  req = build_request(:get_flow_version, params)
  req.send_request(options)
end

#get_ingestion_job(params = {}) ⇒ Types::GetIngestionJobResponse

Gets information about a data ingestion job. Data sources are ingested into your knowledge base so that Large Language Models (LLMs) can use your data.

Examples:

Request syntax with placeholder values


resp = client.get_ingestion_job({
  data_source_id: "Id", # required
  ingestion_job_id: "Id", # required
  knowledge_base_id: "Id", # required
})

Response structure


resp.ingestion_job.data_source_id #=> String
resp.ingestion_job.description #=> String
resp.ingestion_job.failure_reasons #=> Array
resp.ingestion_job.failure_reasons[0] #=> String
resp.ingestion_job.ingestion_job_id #=> String
resp.ingestion_job.knowledge_base_id #=> String
resp.ingestion_job.started_at #=> Time
resp.ingestion_job.statistics.number_of_documents_deleted #=> Integer
resp.ingestion_job.statistics.number_of_documents_failed #=> Integer
resp.ingestion_job.statistics.number_of_documents_scanned #=> Integer
resp.ingestion_job.statistics.number_of_metadata_documents_modified #=> Integer
resp.ingestion_job.statistics.number_of_metadata_documents_scanned #=> Integer
resp.ingestion_job.statistics.number_of_modified_documents_indexed #=> Integer
resp.ingestion_job.statistics.number_of_new_documents_indexed #=> Integer
resp.ingestion_job.status #=> String, one of "STARTING", "IN_PROGRESS", "COMPLETE", "FAILED", "STOPPING", "STOPPED"
resp.ingestion_job.updated_at #=> Time

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :data_source_id (required, String) —

    The unique identifier of the data source for the data ingestion job you want to get information on.

  • :ingestion_job_id (required, String) —

    The unique identifier of the data ingestion job you want to get information on.

  • :knowledge_base_id (required, String) —

    The unique identifier of the knowledge base for the data ingestion job you want to get information on.

Returns:

See Also:



3643
3644
3645
3646
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 3643

def get_ingestion_job(params = {}, options = {})
  req = build_request(:get_ingestion_job, params)
  req.send_request(options)
end

#get_knowledge_base(params = {}) ⇒ Types::GetKnowledgeBaseResponse

Gets information about a knoweldge base.

Examples:

Request syntax with placeholder values


resp = client.get_knowledge_base({
  knowledge_base_id: "Id", # required
})

Response structure


resp.knowledge_base.created_at #=> Time
resp.knowledge_base.description #=> String
resp.knowledge_base.failure_reasons #=> Array
resp.knowledge_base.failure_reasons[0] #=> String
resp.knowledge_base.knowledge_base_arn #=> String
resp.knowledge_base.knowledge_base_configuration.type #=> String, one of "VECTOR"
resp.knowledge_base.knowledge_base_configuration.vector_knowledge_base_configuration.embedding_model_arn #=> String
resp.knowledge_base.knowledge_base_configuration.vector_knowledge_base_configuration.embedding_model_configuration.bedrock_embedding_model_configuration.dimensions #=> Integer
resp.knowledge_base.knowledge_base_configuration.vector_knowledge_base_configuration.embedding_model_configuration.bedrock_embedding_model_configuration.embedding_data_type #=> String, one of "FLOAT32", "BINARY"
resp.knowledge_base.knowledge_base_id #=> String
resp.knowledge_base.name #=> String
resp.knowledge_base.role_arn #=> String
resp.knowledge_base.status #=> String, one of "CREATING", "ACTIVE", "DELETING", "UPDATING", "FAILED", "DELETE_UNSUCCESSFUL"
resp.knowledge_base.storage_configuration.mongo_db_atlas_configuration.collection_name #=> String
resp.knowledge_base.storage_configuration.mongo_db_atlas_configuration.credentials_secret_arn #=> String
resp.knowledge_base.storage_configuration.mongo_db_atlas_configuration.database_name #=> String
resp.knowledge_base.storage_configuration.mongo_db_atlas_configuration.endpoint #=> String
resp.knowledge_base.storage_configuration.mongo_db_atlas_configuration.endpoint_service_name #=> String
resp.knowledge_base.storage_configuration.mongo_db_atlas_configuration.field_mapping.metadata_field #=> String
resp.knowledge_base.storage_configuration.mongo_db_atlas_configuration.field_mapping.text_field #=> String
resp.knowledge_base.storage_configuration.mongo_db_atlas_configuration.field_mapping.vector_field #=> String
resp.knowledge_base.storage_configuration.mongo_db_atlas_configuration.vector_index_name #=> String
resp.knowledge_base.storage_configuration.opensearch_serverless_configuration.collection_arn #=> String
resp.knowledge_base.storage_configuration.opensearch_serverless_configuration.field_mapping.metadata_field #=> String
resp.knowledge_base.storage_configuration.opensearch_serverless_configuration.field_mapping.text_field #=> String
resp.knowledge_base.storage_configuration.opensearch_serverless_configuration.field_mapping.vector_field #=> String
resp.knowledge_base.storage_configuration.opensearch_serverless_configuration.vector_index_name #=> String
resp.knowledge_base.storage_configuration.pinecone_configuration.connection_string #=> String
resp.knowledge_base.storage_configuration.pinecone_configuration.credentials_secret_arn #=> String
resp.knowledge_base.storage_configuration.pinecone_configuration.field_mapping.metadata_field #=> String
resp.knowledge_base.storage_configuration.pinecone_configuration.field_mapping.text_field #=> String
resp.knowledge_base.storage_configuration.pinecone_configuration.namespace #=> String
resp.knowledge_base.storage_configuration.rds_configuration.credentials_secret_arn #=> String
resp.knowledge_base.storage_configuration.rds_configuration.database_name #=> String
resp.knowledge_base.storage_configuration.rds_configuration.field_mapping.metadata_field #=> String
resp.knowledge_base.storage_configuration.rds_configuration.field_mapping.primary_key_field #=> String
resp.knowledge_base.storage_configuration.rds_configuration.field_mapping.text_field #=> String
resp.knowledge_base.storage_configuration.rds_configuration.field_mapping.vector_field #=> String
resp.knowledge_base.storage_configuration.rds_configuration.resource_arn #=> String
resp.knowledge_base.storage_configuration.rds_configuration.table_name #=> String
resp.knowledge_base.storage_configuration.redis_enterprise_cloud_configuration.credentials_secret_arn #=> String
resp.knowledge_base.storage_configuration.redis_enterprise_cloud_configuration.endpoint #=> String
resp.knowledge_base.storage_configuration.redis_enterprise_cloud_configuration.field_mapping.metadata_field #=> String
resp.knowledge_base.storage_configuration.redis_enterprise_cloud_configuration.field_mapping.text_field #=> String
resp.knowledge_base.storage_configuration.redis_enterprise_cloud_configuration.field_mapping.vector_field #=> String
resp.knowledge_base.storage_configuration.redis_enterprise_cloud_configuration.vector_index_name #=> String
resp.knowledge_base.storage_configuration.type #=> String, one of "OPENSEARCH_SERVERLESS", "PINECONE", "REDIS_ENTERPRISE_CLOUD", "RDS", "MONGO_DB_ATLAS"
resp.knowledge_base.updated_at #=> Time

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :knowledge_base_id (required, String) —

    The unique identifier of the knowledge base you want to get information on.

Returns:

See Also:



3719
3720
3721
3722
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 3719

def get_knowledge_base(params = {}, options = {})
  req = build_request(:get_knowledge_base, params)
  req.send_request(options)
end

#get_knowledge_base_documents(params = {}) ⇒ Types::GetKnowledgeBaseDocumentsResponse

Retrieves specific documents from a data source that is connected to a knowledge base. For more information, see Ingest documents into a knowledge base in real-time in the Amazon Bedrock User Guide.

Examples:

Request syntax with placeholder values


resp = client.get_knowledge_base_documents({
  data_source_id: "Id", # required
  document_identifiers: [ # required
    {
      custom: {
        id: "CustomDocumentIdentifierIdString", # required
      },
      data_source_type: "CUSTOM", # required, accepts CUSTOM, S3
      s3: {
        uri: "S3BucketUri", # required
      },
    },
  ],
  knowledge_base_id: "Id", # required
})

Response structure


resp.document_details #=> Array
resp.document_details[0].data_source_id #=> String
resp.document_details[0].identifier.custom.id #=> String
resp.document_details[0].identifier.data_source_type #=> String, one of "CUSTOM", "S3"
resp.document_details[0].identifier.s3.uri #=> String
resp.document_details[0].knowledge_base_id #=> String
resp.document_details[0].status #=> String, one of "INDEXED", "PARTIALLY_INDEXED", "PENDING", "FAILED", "METADATA_PARTIALLY_INDEXED", "METADATA_UPDATE_FAILED", "IGNORED", "NOT_FOUND", "STARTING", "IN_PROGRESS", "DELETING", "DELETE_IN_PROGRESS"
resp.document_details[0].status_reason #=> String
resp.document_details[0].updated_at #=> Time

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :data_source_id (required, String) —

    The unique identifier of the data source that contains the documents.

  • :document_identifiers (required, Array<Types::DocumentIdentifier>) —

    A list of objects, each of which contains information to identify a document for which to retrieve information.

  • :knowledge_base_id (required, String) —

    The unique identifier of the knowledge base that is connected to the data source.

Returns:

See Also:



3781
3782
3783
3784
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 3781

def get_knowledge_base_documents(params = {}, options = {})
  req = build_request(:get_knowledge_base_documents, params)
  req.send_request(options)
end

#get_prompt(params = {}) ⇒ Types::GetPromptResponse

Retrieves information about the working draft (DRAFT version) of a prompt or a version of it, depending on whether you include the promptVersion field or not. For more information, see View information about prompts using Prompt management and View information about a version of your prompt in the Amazon Bedrock User Guide.

Examples:

Request syntax with placeholder values


resp = client.get_prompt({
  prompt_identifier: "PromptIdentifier", # required
  prompt_version: "Version",
})

Response structure


resp.arn #=> String
resp.created_at #=> Time
resp.customer_encryption_key_arn #=> String
resp.default_variant #=> String
resp.description #=> String
resp.id #=> String
resp.name #=> String
resp.updated_at #=> Time
resp.variants #=> Array
resp.variants[0].gen_ai_resource.agent.agent_identifier #=> String
resp.variants[0].inference_configuration.text.max_tokens #=> Integer
resp.variants[0].inference_configuration.text.stop_sequences #=> Array
resp.variants[0].inference_configuration.text.stop_sequences[0] #=> String
resp.variants[0].inference_configuration.text.temperature #=> Float
resp.variants[0].inference_configuration.text.top_p #=> Float
resp.variants[0].metadata #=> Array
resp.variants[0].metadata[0].key #=> String
resp.variants[0].metadata[0].value #=> String
resp.variants[0].model_id #=> String
resp.variants[0].name #=> String
resp.variants[0].template_configuration.chat.input_variables #=> Array
resp.variants[0].template_configuration.chat.input_variables[0].name #=> String
resp.variants[0].template_configuration.chat.messages #=> Array
resp.variants[0].template_configuration.chat.messages[0].content #=> Array
resp.variants[0].template_configuration.chat.messages[0].content[0].text #=> String
resp.variants[0].template_configuration.chat.messages[0].role #=> String, one of "user", "assistant"
resp.variants[0].template_configuration.chat.system #=> Array
resp.variants[0].template_configuration.chat.system[0].text #=> String
resp.variants[0].template_configuration.chat.tool_configuration.tool_choice.tool.name #=> String
resp.variants[0].template_configuration.chat.tool_configuration.tools #=> Array
resp.variants[0].template_configuration.chat.tool_configuration.tools[0].tool_spec.description #=> String
resp.variants[0].template_configuration.chat.tool_configuration.tools[0].tool_spec.name #=> String
resp.variants[0].template_configuration.text.input_variables #=> Array
resp.variants[0].template_configuration.text.input_variables[0].name #=> String
resp.variants[0].template_configuration.text.text #=> String
resp.variants[0].template_type #=> String, one of "TEXT", "CHAT"
resp.version #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :prompt_identifier (required, String) —

    The unique identifier of the prompt.

  • :prompt_version (String) —

    The version of the prompt about which you want to retrieve information. Omit this field to return information about the working draft of the prompt.

Returns:

See Also:



3870
3871
3872
3873
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 3870

def get_prompt(params = {}, options = {})
  req = build_request(:get_prompt, params)
  req.send_request(options)
end

#ingest_knowledge_base_documents(params = {}) ⇒ Types::IngestKnowledgeBaseDocumentsResponse

Ingests documents directly into the knowledge base that is connected to the data source. The dataSourceType specified in the content for each document must match the type of the data source that you specify in the header. For more information, see Ingest documents into a knowledge base in real-time in the Amazon Bedrock User Guide.

Examples:

Request syntax with placeholder values


resp = client.ingest_knowledge_base_documents({
  client_token: "ClientToken",
  data_source_id: "Id", # required
  documents: [ # required
    {
      content: { # required
        custom: {
          custom_document_identifier: { # required
            id: "CustomDocumentIdentifierIdString", # required
          },
          inline_content: {
            byte_content: {
              data: "data", # required
              mime_type: "ByteContentDocMimeTypeString", # required
            },
            text_content: {
              data: "Data", # required
            },
            type: "BYTE", # required, accepts BYTE, TEXT
          },
          s3_location: {
            bucket_owner_account_id: "BucketOwnerAccountId",
            uri: "S3ObjectUri", # required
          },
          source_type: "IN_LINE", # required, accepts IN_LINE, S3_LOCATION
        },
        data_source_type: "CUSTOM", # required, accepts CUSTOM, S3
        s3: {
          s3_location: { # required
            uri: "S3BucketUri", # required
          },
        },
      },
      metadata: {
        inline_attributes: [
          {
            key: "Key", # required
            value: { # required
              boolean_value: false,
              number_value: 1.0,
              string_list_value: ["StringValue"],
              string_value: "StringValue",
              type: "BOOLEAN", # required, accepts BOOLEAN, NUMBER, STRING, STRING_LIST
            },
          },
        ],
        s3_location: {
          bucket_owner_account_id: "BucketOwnerAccountId",
          uri: "S3ObjectUri", # required
        },
        type: "IN_LINE_ATTRIBUTE", # required, accepts IN_LINE_ATTRIBUTE, S3_LOCATION
      },
    },
  ],
  knowledge_base_id: "Id", # required
})

Response structure


resp.document_details #=> Array
resp.document_details[0].data_source_id #=> String
resp.document_details[0].identifier.custom.id #=> String
resp.document_details[0].identifier.data_source_type #=> String, one of "CUSTOM", "S3"
resp.document_details[0].identifier.s3.uri #=> String
resp.document_details[0].knowledge_base_id #=> String
resp.document_details[0].status #=> String, one of "INDEXED", "PARTIALLY_INDEXED", "PENDING", "FAILED", "METADATA_PARTIALLY_INDEXED", "METADATA_UPDATE_FAILED", "IGNORED", "NOT_FOUND", "STARTING", "IN_PROGRESS", "DELETING", "DELETE_IN_PROGRESS"
resp.document_details[0].status_reason #=> String
resp.document_details[0].updated_at #=> Time

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :client_token (String) —

    A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.

    A suitable default value is auto-generated. You should normally not need to pass this option.**

  • :data_source_id (required, String) —

    The unique identifier of the data source connected to the knowledge base that you're adding documents to.

  • :documents (required, Array<Types::KnowledgeBaseDocument>) —

    A list of objects, each of which contains information about the documents to add.

  • :knowledge_base_id (required, String) —

    The unique identifier of the knowledge base to ingest the documents into.

Returns:

See Also:



3989
3990
3991
3992
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 3989

def ingest_knowledge_base_documents(params = {}, options = {})
  req = build_request(:ingest_knowledge_base_documents, params)
  req.send_request(options)
end

#list_agent_action_groups(params = {}) ⇒ Types::ListAgentActionGroupsResponse

Lists the action groups for an agent and information about each one.

The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.

Examples:

Request syntax with placeholder values


resp = client.list_agent_action_groups({
  agent_id: "Id", # required
  agent_version: "Version", # required
  max_results: 1,
  next_token: "NextToken",
})

Response structure


resp.action_group_summaries #=> Array
resp.action_group_summaries[0].action_group_id #=> String
resp.action_group_summaries[0].action_group_name #=> String
resp.action_group_summaries[0].action_group_state #=> String, one of "ENABLED", "DISABLED"
resp.action_group_summaries[0].description #=> String
resp.action_group_summaries[0].updated_at #=> Time
resp.next_token #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :agent_id (required, String) —

    The unique identifier of the agent.

  • :agent_version (required, String) —

    The version of the agent.

  • :max_results (Integer) —

    The maximum number of results to return in the response. If the total number of results is greater than this value, use the token returned in the response in the nextToken field when making another request to return the next batch of results.

  • :next_token (String) —

    If the total number of results is greater than the maxResults value provided in the request, enter the token returned in the nextToken field in the response in this field to return the next batch of results.

Returns:

See Also:



4044
4045
4046
4047
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 4044

def list_agent_action_groups(params = {}, options = {})
  req = build_request(:list_agent_action_groups, params)
  req.send_request(options)
end

#list_agent_aliases(params = {}) ⇒ Types::ListAgentAliasesResponse

Lists the aliases of an agent and information about each one.

The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.

Examples:

Request syntax with placeholder values


resp = client.list_agent_aliases({
  agent_id: "Id", # required
  max_results: 1,
  next_token: "NextToken",
})

Response structure


resp.agent_alias_summaries #=> Array
resp.agent_alias_summaries[0].agent_alias_id #=> String
resp.agent_alias_summaries[0].agent_alias_name #=> String
resp.agent_alias_summaries[0].agent_alias_status #=> String, one of "CREATING", "PREPARED", "FAILED", "UPDATING", "DELETING"
resp.agent_alias_summaries[0].created_at #=> Time
resp.agent_alias_summaries[0].description #=> String
resp.agent_alias_summaries[0].routing_configuration #=> Array
resp.agent_alias_summaries[0].routing_configuration[0].agent_version #=> String
resp.agent_alias_summaries[0].routing_configuration[0].provisioned_throughput #=> String
resp.agent_alias_summaries[0].updated_at #=> Time
resp.next_token #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :agent_id (required, String) —

    The unique identifier of the agent.

  • :max_results (Integer) —

    The maximum number of results to return in the response. If the total number of results is greater than this value, use the token returned in the response in the nextToken field when making another request to return the next batch of results.

  • :next_token (String) —

    If the total number of results is greater than the maxResults value provided in the request, enter the token returned in the nextToken field in the response in this field to return the next batch of results.

Returns:

See Also:



4099
4100
4101
4102
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 4099

def list_agent_aliases(params = {}, options = {})
  req = build_request(:list_agent_aliases, params)
  req.send_request(options)
end

#list_agent_knowledge_bases(params = {}) ⇒ Types::ListAgentKnowledgeBasesResponse

Lists knowledge bases associated with an agent and information about each one.

The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.

Examples:

Request syntax with placeholder values


resp = client.list_agent_knowledge_bases({
  agent_id: "Id", # required
  agent_version: "Version", # required
  max_results: 1,
  next_token: "NextToken",
})

Response structure


resp.agent_knowledge_base_summaries #=> Array
resp.agent_knowledge_base_summaries[0].description #=> String
resp.agent_knowledge_base_summaries[0].knowledge_base_id #=> String
resp.agent_knowledge_base_summaries[0].knowledge_base_state #=> String, one of "ENABLED", "DISABLED"
resp.agent_knowledge_base_summaries[0].updated_at #=> Time
resp.next_token #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :agent_id (required, String) —

    The unique identifier of the agent for which to return information about knowledge bases associated with it.

  • :agent_version (required, String) —

    The version of the agent for which to return information about knowledge bases associated with it.

  • :max_results (Integer) —

    The maximum number of results to return in the response. If the total number of results is greater than this value, use the token returned in the response in the nextToken field when making another request to return the next batch of results.

  • :next_token (String) —

    If the total number of results is greater than the maxResults value provided in the request, enter the token returned in the nextToken field in the response in this field to return the next batch of results.

Returns:

See Also:



4156
4157
4158
4159
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 4156

def list_agent_knowledge_bases(params = {}, options = {})
  req = build_request(:list_agent_knowledge_bases, params)
  req.send_request(options)
end

#list_agent_versions(params = {}) ⇒ Types::ListAgentVersionsResponse

Lists the versions of an agent and information about each version.

The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.

Examples:

Request syntax with placeholder values


resp = client.list_agent_versions({
  agent_id: "Id", # required
  max_results: 1,
  next_token: "NextToken",
})

Response structure


resp.agent_version_summaries #=> Array
resp.agent_version_summaries[0].agent_name #=> String
resp.agent_version_summaries[0].agent_status #=> String, one of "CREATING", "PREPARING", "PREPARED", "NOT_PREPARED", "DELETING", "FAILED", "VERSIONING", "UPDATING"
resp.agent_version_summaries[0].agent_version #=> String
resp.agent_version_summaries[0].created_at #=> Time
resp.agent_version_summaries[0].description #=> String
resp.agent_version_summaries[0].guardrail_configuration.guardrail_identifier #=> String
resp.agent_version_summaries[0].guardrail_configuration.guardrail_version #=> String
resp.agent_version_summaries[0].updated_at #=> Time
resp.next_token #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :agent_id (required, String) —

    The unique identifier of the agent.

  • :max_results (Integer) —

    The maximum number of results to return in the response. If the total number of results is greater than this value, use the token returned in the response in the nextToken field when making another request to return the next batch of results.

  • :next_token (String) —

    If the total number of results is greater than the maxResults value provided in the request, enter the token returned in the nextToken field in the response in this field to return the next batch of results.

Returns:

See Also:



4210
4211
4212
4213
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 4210

def list_agent_versions(params = {}, options = {})
  req = build_request(:list_agent_versions, params)
  req.send_request(options)
end

#list_agents(params = {}) ⇒ Types::ListAgentsResponse

Lists the agents belonging to an account and information about each agent.

The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.

Examples:

Request syntax with placeholder values


resp = client.list_agents({
  max_results: 1,
  next_token: "NextToken",
})

Response structure


resp.agent_summaries #=> Array
resp.agent_summaries[0].agent_id #=> String
resp.agent_summaries[0].agent_name #=> String
resp.agent_summaries[0].agent_status #=> String, one of "CREATING", "PREPARING", "PREPARED", "NOT_PREPARED", "DELETING", "FAILED", "VERSIONING", "UPDATING"
resp.agent_summaries[0].description #=> String
resp.agent_summaries[0].guardrail_configuration.guardrail_identifier #=> String
resp.agent_summaries[0].guardrail_configuration.guardrail_version #=> String
resp.agent_summaries[0].latest_agent_version #=> String
resp.agent_summaries[0].updated_at #=> Time
resp.next_token #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :max_results (Integer) —

    The maximum number of results to return in the response. If the total number of results is greater than this value, use the token returned in the response in the nextToken field when making another request to return the next batch of results.

  • :next_token (String) —

    If the total number of results is greater than the maxResults value provided in the request, enter the token returned in the nextToken field in the response in this field to return the next batch of results.

Returns:

See Also:



4261
4262
4263
4264
 
# File 'gems/aws-sdk-bedrockagent/lib/aws-sdk-bedrockagent/client.rb', line 4261

def list_agents(params = {}, options = {})
  req = build_request(:list_agents, params)
  req.send_request(options)
end

#list_data_sources(params = {}) ⇒ Types::ListDataSourcesResponse

Lists the data sources in a knowledge base and information about each one.

The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.

Examples:

Request syntax with placeholder values


resp = client.list_data_sources({
  knowledge_base_id: "Id", # required
  max_results: 1,
  next_token: "NextToken",
})

Response structure


resp.data_source_summaries #=> Array
resp.data_source_summaries[0].data_source_id #=> String
resp.data_source_summaries[0].description #=> String
resp.data_source_summaries[0].knowledge_base_id #=> String
resp.data_source_summaries[0].name #=> String
resp.data_source_summaries[0].status #=> String, one of "AVAILABLE", "DELETING", "DELETE_UNSUCCESSFUL"
resp.data_source_summaries[0].updated_at #=> Time
resp.next_token #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :knowledge_base_id (required, String) —

    The unique identifier of the knowledge base for which to return a list of information.

  • :max_results (Integer) —

    The maximum number of results to return in the response. If the total number of results is greater than this value, use the token returned in the response in the nextToken field when making another request to return the next batch of results.