We recommend new projects start with resources from the AWS provider.
aws-native.bedrock.Agent
Explore with Pulumi AI
We recommend new projects start with resources from the AWS provider.
Definition of AWS::Bedrock::Agent Resource Type
Create Agent Resource
Resources are created with functions called constructors. To learn more about declaring and configuring resources, see Resources.
Constructor syntax
new Agent(name: string, args?: AgentArgs, opts?: CustomResourceOptions);
@overload
def Agent(resource_name: str,
args: Optional[AgentArgs] = None,
opts: Optional[ResourceOptions] = None)
@overload
def Agent(resource_name: str,
opts: Optional[ResourceOptions] = None,
action_groups: Optional[Sequence[AgentActionGroupArgs]] = None,
agent_name: Optional[str] = None,
agent_resource_role_arn: Optional[str] = None,
auto_prepare: Optional[bool] = None,
customer_encryption_key_arn: Optional[str] = None,
description: Optional[str] = None,
foundation_model: Optional[str] = None,
guardrail_configuration: Optional[AgentGuardrailConfigurationArgs] = None,
idle_session_ttl_in_seconds: Optional[float] = None,
instruction: Optional[str] = None,
knowledge_bases: Optional[Sequence[AgentKnowledgeBaseArgs]] = None,
prompt_override_configuration: Optional[AgentPromptOverrideConfigurationArgs] = None,
skip_resource_in_use_check_on_delete: Optional[bool] = None,
tags: Optional[Mapping[str, str]] = None,
test_alias_tags: Optional[Mapping[str, str]] = None)
func NewAgent(ctx *Context, name string, args *AgentArgs, opts ...ResourceOption) (*Agent, error)
public Agent(string name, AgentArgs? args = null, CustomResourceOptions? opts = null)
type: aws-native:bedrock:Agent
properties: # The arguments to resource properties.
options: # Bag of options to control resource's behavior.
Parameters
- name string
- The unique name of the resource.
- args AgentArgs
- The arguments to resource properties.
- opts CustomResourceOptions
- Bag of options to control resource's behavior.
- resource_name str
- The unique name of the resource.
- args AgentArgs
- The arguments to resource properties.
- opts ResourceOptions
- Bag of options to control resource's behavior.
- ctx Context
- Context object for the current deployment.
- name string
- The unique name of the resource.
- args AgentArgs
- The arguments to resource properties.
- opts ResourceOption
- Bag of options to control resource's behavior.
- name string
- The unique name of the resource.
- args AgentArgs
- The arguments to resource properties.
- opts CustomResourceOptions
- Bag of options to control resource's behavior.
- name String
- The unique name of the resource.
- args AgentArgs
- The arguments to resource properties.
- options CustomResourceOptions
- Bag of options to control resource's behavior.
Agent Resource Properties
To learn more about resource properties and how to use them, see Inputs and Outputs in the Architecture and Concepts docs.
Inputs
In Python, inputs that are objects can be passed either as argument classes or as dictionary literals.
The Agent resource accepts the following input properties:
- Action
Groups List<Pulumi.Aws Native. Bedrock. Inputs. Agent Action Group> - List of ActionGroups
- Agent
Name string - Name for a resource.
- Agent
Resource stringRole Arn - ARN of a IAM role.
- Auto
Prepare bool - Specifies whether to automatically prepare after creating or updating the agent.
- Customer
Encryption stringKey Arn - A KMS key ARN
- Description string
- Description of the Resource.
- Foundation
Model string - ARN or name of a Bedrock model.
- Guardrail
Configuration Pulumi.Aws Native. Bedrock. Inputs. Agent Guardrail Configuration - Details about the guardrail associated with the agent.
- Idle
Session doubleTtl In Seconds - Max Session Time.
- Instruction string
- Instruction for the agent.
- Knowledge
Bases List<Pulumi.Aws Native. Bedrock. Inputs. Agent Knowledge Base> - List of Agent Knowledge Bases
- Prompt
Override Pulumi.Configuration Aws Native. Bedrock. Inputs. Agent Prompt Override Configuration - Contains configurations to override prompt templates in different parts of an agent sequence. For more information, see Advanced prompts .
- Skip
Resource boolIn Use Check On Delete - Specifies whether to allow deleting agent while it is in use.
- Dictionary<string, string>
- Metadata that you can assign to a resource as key-value pairs. For more information, see the following resources:
- Dictionary<string, string>
- Metadata that you can assign to a resource as key-value pairs. For more information, see the following resources:
- Action
Groups []AgentAction Group Args - List of ActionGroups
- Agent
Name string - Name for a resource.
- Agent
Resource stringRole Arn - ARN of a IAM role.
- Auto
Prepare bool - Specifies whether to automatically prepare after creating or updating the agent.
- Customer
Encryption stringKey Arn - A KMS key ARN
- Description string
- Description of the Resource.
- Foundation
Model string - ARN or name of a Bedrock model.
- Guardrail
Configuration AgentGuardrail Configuration Args - Details about the guardrail associated with the agent.
- Idle
Session float64Ttl In Seconds - Max Session Time.
- Instruction string
- Instruction for the agent.
- Knowledge
Bases []AgentKnowledge Base Args - List of Agent Knowledge Bases
- Prompt
Override AgentConfiguration Prompt Override Configuration Args - Contains configurations to override prompt templates in different parts of an agent sequence. For more information, see Advanced prompts .
- Skip
Resource boolIn Use Check On Delete - Specifies whether to allow deleting agent while it is in use.
- map[string]string
- Metadata that you can assign to a resource as key-value pairs. For more information, see the following resources:
- map[string]string
- Metadata that you can assign to a resource as key-value pairs. For more information, see the following resources:
- action
Groups List<AgentAction Group> - List of ActionGroups
- agent
Name String - Name for a resource.
- agent
Resource StringRole Arn - ARN of a IAM role.
- auto
Prepare Boolean - Specifies whether to automatically prepare after creating or updating the agent.
- customer
Encryption StringKey Arn - A KMS key ARN
- description String
- Description of the Resource.
- foundation
Model String - ARN or name of a Bedrock model.
- guardrail
Configuration AgentGuardrail Configuration - Details about the guardrail associated with the agent.
- idle
Session DoubleTtl In Seconds - Max Session Time.
- instruction String
- Instruction for the agent.
- knowledge
Bases List<AgentKnowledge Base> - List of Agent Knowledge Bases
- prompt
Override AgentConfiguration Prompt Override Configuration - Contains configurations to override prompt templates in different parts of an agent sequence. For more information, see Advanced prompts .
- skip
Resource BooleanIn Use Check On Delete - Specifies whether to allow deleting agent while it is in use.
- Map<String,String>
- Metadata that you can assign to a resource as key-value pairs. For more information, see the following resources:
- Map<String,String>
- Metadata that you can assign to a resource as key-value pairs. For more information, see the following resources:
- action
Groups AgentAction Group[] - List of ActionGroups
- agent
Name string - Name for a resource.
- agent
Resource stringRole Arn - ARN of a IAM role.
- auto
Prepare boolean - Specifies whether to automatically prepare after creating or updating the agent.
- customer
Encryption stringKey Arn - A KMS key ARN
- description string
- Description of the Resource.
- foundation
Model string - ARN or name of a Bedrock model.
- guardrail
Configuration AgentGuardrail Configuration - Details about the guardrail associated with the agent.
- idle
Session numberTtl In Seconds - Max Session Time.
- instruction string
- Instruction for the agent.
- knowledge
Bases AgentKnowledge Base[] - List of Agent Knowledge Bases
- prompt
Override AgentConfiguration Prompt Override Configuration - Contains configurations to override prompt templates in different parts of an agent sequence. For more information, see Advanced prompts .
- skip
Resource booleanIn Use Check On Delete - Specifies whether to allow deleting agent while it is in use.
- {[key: string]: string}
- Metadata that you can assign to a resource as key-value pairs. For more information, see the following resources:
- {[key: string]: string}
- Metadata that you can assign to a resource as key-value pairs. For more information, see the following resources:
- action_
groups Sequence[AgentAction Group Args] - List of ActionGroups
- agent_
name str - Name for a resource.
- agent_
resource_ strrole_ arn - ARN of a IAM role.
- auto_
prepare bool - Specifies whether to automatically prepare after creating or updating the agent.
- customer_
encryption_ strkey_ arn - A KMS key ARN
- description str
- Description of the Resource.
- foundation_
model str - ARN or name of a Bedrock model.
- guardrail_
configuration AgentGuardrail Configuration Args - Details about the guardrail associated with the agent.
- idle_
session_ floatttl_ in_ seconds - Max Session Time.
- instruction str
- Instruction for the agent.
- knowledge_
bases Sequence[AgentKnowledge Base Args] - List of Agent Knowledge Bases
- prompt_
override_ Agentconfiguration Prompt Override Configuration Args - Contains configurations to override prompt templates in different parts of an agent sequence. For more information, see Advanced prompts .
- skip_
resource_ boolin_ use_ check_ on_ delete - Specifies whether to allow deleting agent while it is in use.
- Mapping[str, str]
- Metadata that you can assign to a resource as key-value pairs. For more information, see the following resources:
- Mapping[str, str]
- Metadata that you can assign to a resource as key-value pairs. For more information, see the following resources:
- action
Groups List<Property Map> - List of ActionGroups
- agent
Name String - Name for a resource.
- agent
Resource StringRole Arn - ARN of a IAM role.
- auto
Prepare Boolean - Specifies whether to automatically prepare after creating or updating the agent.
- customer
Encryption StringKey Arn - A KMS key ARN
- description String
- Description of the Resource.
- foundation
Model String - ARN or name of a Bedrock model.
- guardrail
Configuration Property Map - Details about the guardrail associated with the agent.
- idle
Session NumberTtl In Seconds - Max Session Time.
- instruction String
- Instruction for the agent.
- knowledge
Bases List<Property Map> - List of Agent Knowledge Bases
- prompt
Override Property MapConfiguration - Contains configurations to override prompt templates in different parts of an agent sequence. For more information, see Advanced prompts .
- skip
Resource BooleanIn Use Check On Delete - Specifies whether to allow deleting agent while it is in use.
- Map<String>
- Metadata that you can assign to a resource as key-value pairs. For more information, see the following resources:
- Map<String>
- Metadata that you can assign to a resource as key-value pairs. For more information, see the following resources:
Outputs
All input properties are implicitly available as output properties. Additionally, the Agent resource produces the following output properties:
- Agent
Arn string - Arn representation of the Agent.
- Agent
Id string - Identifier for a resource.
- Agent
Status Pulumi.Aws Native. Bedrock. Agent Status - The status of the agent and whether it is ready for use. The following statuses are possible:
- CREATING – The agent is being created.
- PREPARING – The agent is being prepared.
- PREPARED – The agent is prepared and ready to be invoked.
- NOT_PREPARED – The agent has been created but not yet prepared.
- FAILED – The agent API operation failed.
- UPDATING – The agent is being updated.
- DELETING – The agent is being deleted.
- Agent
Version string - Draft Agent Version.
- Created
At string - Time Stamp.
- Failure
Reasons List<string> - Failure Reasons for Error.
- Id string
- The provider-assigned unique ID for this managed resource.
- Prepared
At string - Time Stamp.
- Recommended
Actions List<string> - The recommended actions users can take to resolve an error in failureReasons.
- Updated
At string - Time Stamp.
- Agent
Arn string - Arn representation of the Agent.
- Agent
Id string - Identifier for a resource.
- Agent
Status AgentStatus - The status of the agent and whether it is ready for use. The following statuses are possible:
- CREATING – The agent is being created.
- PREPARING – The agent is being prepared.
- PREPARED – The agent is prepared and ready to be invoked.
- NOT_PREPARED – The agent has been created but not yet prepared.
- FAILED – The agent API operation failed.
- UPDATING – The agent is being updated.
- DELETING – The agent is being deleted.
- Agent
Version string - Draft Agent Version.
- Created
At string - Time Stamp.
- Failure
Reasons []string - Failure Reasons for Error.
- Id string
- The provider-assigned unique ID for this managed resource.
- Prepared
At string - Time Stamp.
- Recommended
Actions []string - The recommended actions users can take to resolve an error in failureReasons.
- Updated
At string - Time Stamp.
- agent
Arn String - Arn representation of the Agent.
- agent
Id String - Identifier for a resource.
- agent
Status AgentStatus - The status of the agent and whether it is ready for use. The following statuses are possible:
- CREATING – The agent is being created.
- PREPARING – The agent is being prepared.
- PREPARED – The agent is prepared and ready to be invoked.
- NOT_PREPARED – The agent has been created but not yet prepared.
- FAILED – The agent API operation failed.
- UPDATING – The agent is being updated.
- DELETING – The agent is being deleted.
- agent
Version String - Draft Agent Version.
- created
At String - Time Stamp.
- failure
Reasons List<String> - Failure Reasons for Error.
- id String
- The provider-assigned unique ID for this managed resource.
- prepared
At String - Time Stamp.
- recommended
Actions List<String> - The recommended actions users can take to resolve an error in failureReasons.
- updated
At String - Time Stamp.
- agent
Arn string - Arn representation of the Agent.
- agent
Id string - Identifier for a resource.
- agent
Status AgentStatus - The status of the agent and whether it is ready for use. The following statuses are possible:
- CREATING – The agent is being created.
- PREPARING – The agent is being prepared.
- PREPARED – The agent is prepared and ready to be invoked.
- NOT_PREPARED – The agent has been created but not yet prepared.
- FAILED – The agent API operation failed.
- UPDATING – The agent is being updated.
- DELETING – The agent is being deleted.
- agent
Version string - Draft Agent Version.
- created
At string - Time Stamp.
- failure
Reasons string[] - Failure Reasons for Error.
- id string
- The provider-assigned unique ID for this managed resource.
- prepared
At string - Time Stamp.
- recommended
Actions string[] - The recommended actions users can take to resolve an error in failureReasons.
- updated
At string - Time Stamp.
- agent_
arn str - Arn representation of the Agent.
- agent_
id str - Identifier for a resource.
- agent_
status AgentStatus - The status of the agent and whether it is ready for use. The following statuses are possible:
- CREATING – The agent is being created.
- PREPARING – The agent is being prepared.
- PREPARED – The agent is prepared and ready to be invoked.
- NOT_PREPARED – The agent has been created but not yet prepared.
- FAILED – The agent API operation failed.
- UPDATING – The agent is being updated.
- DELETING – The agent is being deleted.
- agent_
version str - Draft Agent Version.
- created_
at str - Time Stamp.
- failure_
reasons Sequence[str] - Failure Reasons for Error.
- id str
- The provider-assigned unique ID for this managed resource.
- prepared_
at str - Time Stamp.
- recommended_
actions Sequence[str] - The recommended actions users can take to resolve an error in failureReasons.
- updated_
at str - Time Stamp.
- agent
Arn String - Arn representation of the Agent.
- agent
Id String - Identifier for a resource.
- agent
Status "CREATING" | "PREPARING" | "PREPARED" | "NOT_PREPARED" | "DELETING" | "FAILED" | "VERSIONING" | "UPDATING" - The status of the agent and whether it is ready for use. The following statuses are possible:
- CREATING – The agent is being created.
- PREPARING – The agent is being prepared.
- PREPARED – The agent is prepared and ready to be invoked.
- NOT_PREPARED – The agent has been created but not yet prepared.
- FAILED – The agent API operation failed.
- UPDATING – The agent is being updated.
- DELETING – The agent is being deleted.
- agent
Version String - Draft Agent Version.
- created
At String - Time Stamp.
- failure
Reasons List<String> - Failure Reasons for Error.
- id String
- The provider-assigned unique ID for this managed resource.
- prepared
At String - Time Stamp.
- recommended
Actions List<String> - The recommended actions users can take to resolve an error in failureReasons.
- updated
At String - Time Stamp.
Supporting Types
AgentActionGroup, AgentActionGroupArgs
- Action
Group stringName - Name of the action group
- Action
Group Pulumi.Executor Aws | Pulumi.Native. Bedrock. Inputs. Agent Action Group Executor0Properties Aws Native. Bedrock. Inputs. Agent Action Group Executor1Properties - 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 Pulumi.State Aws Native. Bedrock. Agent Action Group State - Specifies whether the action group is available for the agent to invoke or not when sending an InvokeAgent request.
- Api
Schema Pulumi.Aws | Pulumi.Native. Bedrock. Inputs. Agent Api Schema0Properties Aws Native. Bedrock. Inputs. Agent Api Schema1Properties - 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 .
- Description string
- Description of action group
- Function
Schema Pulumi.Aws Native. Bedrock. Inputs. Agent Function Schema - Contains details about the function schema for the action group or the JSON or YAML-formatted payload defining the schema.
- Parent
Action Pulumi.Group Signature Aws Native. Bedrock. Agent Action Group Signature If this field is set as
AMAZON.UserInput
, the agent can request the user for additional information when trying to complete a task. Thedescription
,apiSchema
, andactionGroupExecutor
fields must be blank for this action group.During orchestration, if the 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.
- Skip
Resource boolIn Use Check On Delete - Specifies whether to allow deleting action group while it is in use.
- Action
Group stringName - Name of the action group
- Action
Group AgentExecutor Action | AgentGroup Executor0Properties Action Group Executor1Properties - 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 AgentState Action Group State - Specifies whether the action group is available for the agent to invoke or not when sending an InvokeAgent request.
- Api
Schema AgentApi | AgentSchema0Properties Api Schema1Properties - 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 .
- Description string
- Description of action group
- Function
Schema AgentFunction Schema - Contains details about the function schema for the action group or the JSON or YAML-formatted payload defining the schema.
- Parent
Action AgentGroup Signature Action Group Signature If this field is set as
AMAZON.UserInput
, the agent can request the user for additional information when trying to complete a task. Thedescription
,apiSchema
, andactionGroupExecutor
fields must be blank for this action group.During orchestration, if the 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.
- Skip
Resource boolIn Use Check On Delete - Specifies whether to allow deleting action group while it is in use.
- action
Group StringName - Name of the action group
- action
Group AgentExecutor Action | AgentGroup Executor0Properties Action Group Executor1Properties - 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 AgentState Action Group State - Specifies whether the action group is available for the agent to invoke or not when sending an InvokeAgent request.
- api
Schema AgentApi | AgentSchema0Properties Api Schema1Properties - 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 .
- description String
- Description of action group
- function
Schema AgentFunction Schema - Contains details about the function schema for the action group or the JSON or YAML-formatted payload defining the schema.
- parent
Action AgentGroup Signature Action Group Signature If this field is set as
AMAZON.UserInput
, the agent can request the user for additional information when trying to complete a task. Thedescription
,apiSchema
, andactionGroupExecutor
fields must be blank for this action group.During orchestration, if the 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.
- skip
Resource BooleanIn Use Check On Delete - Specifies whether to allow deleting action group while it is in use.
- action
Group stringName - Name of the action group
- action
Group AgentExecutor Action | AgentGroup Executor0Properties Action Group Executor1Properties - 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 AgentState Action Group State - Specifies whether the action group is available for the agent to invoke or not when sending an InvokeAgent request.
- api
Schema AgentApi | AgentSchema0Properties Api Schema1Properties - 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 .
- description string
- Description of action group
- function
Schema AgentFunction Schema - Contains details about the function schema for the action group or the JSON or YAML-formatted payload defining the schema.
- parent
Action AgentGroup Signature Action Group Signature If this field is set as
AMAZON.UserInput
, the agent can request the user for additional information when trying to complete a task. Thedescription
,apiSchema
, andactionGroupExecutor
fields must be blank for this action group.During orchestration, if the 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.
- skip
Resource booleanIn Use Check On Delete - Specifies whether to allow deleting action group while it is in use.
- action_
group_ strname - Name of the action group
- action_
group_ Agentexecutor Action | AgentGroup Executor0Properties Action Group Executor1Properties - 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_ Agentstate Action Group State - Specifies whether the action group is available for the agent to invoke or not when sending an InvokeAgent request.
- api_
schema AgentApi | AgentSchema0Properties Api Schema1Properties - 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 .
- description str
- Description of action group
- function_
schema AgentFunction Schema - Contains details about the function schema for the action group or the JSON or YAML-formatted payload defining the schema.
- parent_
action_ Agentgroup_ signature Action Group Signature If this field is set as
AMAZON.UserInput
, the agent can request the user for additional information when trying to complete a task. Thedescription
,apiSchema
, andactionGroupExecutor
fields must be blank for this action group.During orchestration, if the 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.
- skip_
resource_ boolin_ use_ check_ on_ delete - Specifies whether to allow deleting action group while it is in use.
- action
Group StringName - Name of the action group
- action
Group Property Map | Property MapExecutor - 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 "ENABLED" | "DISABLED"State - Specifies whether the action group is available for the agent to invoke or not when sending an InvokeAgent request.
- api
Schema Property Map | Property Map - 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 .
- description String
- Description of action group
- function
Schema Property Map - Contains details about the function schema for the action group or the JSON or YAML-formatted payload defining the schema.
- parent
Action "AMAZON.Group Signature User Input" | "AMAZON. Code Interpreter" If this field is set as
AMAZON.UserInput
, the agent can request the user for additional information when trying to complete a task. Thedescription
,apiSchema
, andactionGroupExecutor
fields must be blank for this action group.During orchestration, if the 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.
- skip
Resource BooleanIn Use Check On Delete - Specifies whether to allow deleting action group while it is in use.
AgentActionGroupExecutor0Properties, AgentActionGroupExecutor0PropertiesArgs
- Lambda string
- ARN of a Lambda.
- Lambda string
- ARN of a Lambda.
- lambda String
- ARN of a Lambda.
- lambda string
- ARN of a Lambda.
- lambda_ str
- ARN of a Lambda.
- lambda String
- ARN of a Lambda.
AgentActionGroupExecutor1Properties, AgentActionGroupExecutor1PropertiesArgs
AgentActionGroupSignature, AgentActionGroupSignatureArgs
- Amazon
User Input - AMAZON.UserInput
- Amazon
Code Interpreter - AMAZON.CodeInterpreter
- Agent
Action Group Signature Amazon User Input - AMAZON.UserInput
- Agent
Action Group Signature Amazon Code Interpreter - AMAZON.CodeInterpreter
- Amazon
User Input - AMAZON.UserInput
- Amazon
Code Interpreter - AMAZON.CodeInterpreter
- Amazon
User Input - AMAZON.UserInput
- Amazon
Code Interpreter - AMAZON.CodeInterpreter
- AMAZON_USER_INPUT
- AMAZON.UserInput
- AMAZON_CODE_INTERPRETER
- AMAZON.CodeInterpreter
- "AMAZON.
User Input" - AMAZON.UserInput
- "AMAZON.
Code Interpreter" - AMAZON.CodeInterpreter
AgentActionGroupState, AgentActionGroupStateArgs
- Enabled
- ENABLED
- Disabled
- DISABLED
- Agent
Action Group State Enabled - ENABLED
- Agent
Action Group State Disabled - DISABLED
- Enabled
- ENABLED
- Disabled
- DISABLED
- Enabled
- ENABLED
- Disabled
- DISABLED
- ENABLED
- ENABLED
- DISABLED
- DISABLED
- "ENABLED"
- ENABLED
- "DISABLED"
- DISABLED
AgentApiSchema0Properties, AgentApiSchema0PropertiesArgs
AgentApiSchema1Properties, AgentApiSchema1PropertiesArgs
- Payload string
- String OpenAPI Payload
- Payload string
- String OpenAPI Payload
- payload String
- String OpenAPI Payload
- payload string
- String OpenAPI Payload
- payload str
- String OpenAPI Payload
- payload String
- String OpenAPI Payload
AgentCreationMode, AgentCreationModeArgs
- Default
- DEFAULT
- Overridden
- OVERRIDDEN
- Agent
Creation Mode Default - DEFAULT
- Agent
Creation Mode Overridden - OVERRIDDEN
- Default
- DEFAULT
- Overridden
- OVERRIDDEN
- Default
- DEFAULT
- Overridden
- OVERRIDDEN
- DEFAULT
- DEFAULT
- OVERRIDDEN
- OVERRIDDEN
- "DEFAULT"
- DEFAULT
- "OVERRIDDEN"
- OVERRIDDEN
AgentCustomControlMethod, AgentCustomControlMethodArgs
- Return
Control - RETURN_CONTROL
- Agent
Custom Control Method Return Control - RETURN_CONTROL
- Return
Control - RETURN_CONTROL
- Return
Control - RETURN_CONTROL
- RETURN_CONTROL
- RETURN_CONTROL
- "RETURN_CONTROL"
- RETURN_CONTROL
AgentFunction, AgentFunctionArgs
- Name string
- Name for a resource.
- Description string
- Description of function
- Parameters
Dictionary<string, Pulumi.
Aws Native. Bedrock. Inputs. Agent Parameter Detail> - The parameters that the agent elicits from the user to fulfill the function.
- Name string
- Name for a resource.
- Description string
- Description of function
- Parameters
map[string]Agent
Parameter Detail - The parameters that the agent elicits from the user to fulfill the function.
- name String
- Name for a resource.
- description String
- Description of function
- parameters
Map<String,Agent
Parameter Detail> - The parameters that the agent elicits from the user to fulfill the function.
- name string
- Name for a resource.
- description string
- Description of function
- parameters
{[key: string]: Agent
Parameter Detail} - The parameters that the agent elicits from the user to fulfill the function.
- name str
- Name for a resource.
- description str
- Description of function
- parameters
Mapping[str, Agent
Parameter Detail] - The parameters that the agent elicits from the user to fulfill the function.
- name String
- Name for a resource.
- description String
- Description of function
- parameters Map<Property Map>
- The parameters that the agent elicits from the user to fulfill the function.
AgentFunctionSchema, AgentFunctionSchemaArgs
- Functions
List<Pulumi.
Aws Native. Bedrock. Inputs. Agent Function> - List of Function definitions
- Functions
[]Agent
Function - List of Function definitions
- functions
List<Agent
Function> - List of Function definitions
- functions
Agent
Function[] - List of Function definitions
- functions
Sequence[Agent
Function] - List of Function definitions
- functions List<Property Map>
- List of Function definitions
AgentGuardrailConfiguration, AgentGuardrailConfigurationArgs
- Guardrail
Identifier string - Identifier for the guardrail, could be the id or the arn
- Guardrail
Version string - Version of the guardrail
- Guardrail
Identifier string - Identifier for the guardrail, could be the id or the arn
- Guardrail
Version string - Version of the guardrail
- guardrail
Identifier String - Identifier for the guardrail, could be the id or the arn
- guardrail
Version String - Version of the guardrail
- guardrail
Identifier string - Identifier for the guardrail, could be the id or the arn
- guardrail
Version string - Version of the guardrail
- guardrail_
identifier str - Identifier for the guardrail, could be the id or the arn
- guardrail_
version str - Version of the guardrail
- guardrail
Identifier String - Identifier for the guardrail, could be the id or the arn
- guardrail
Version String - Version of the guardrail
AgentInferenceConfiguration, AgentInferenceConfigurationArgs
- Maximum
Length double - Maximum length of output
- Stop
Sequences List<string> - List of stop sequences
- Temperature double
- Controls randomness, higher values increase diversity
- Top
K double - Sample from the k most likely next tokens
- Top
P double - Cumulative probability cutoff for token selection
- Maximum
Length float64 - Maximum length of output
- Stop
Sequences []string - List of stop sequences
- Temperature float64
- Controls randomness, higher values increase diversity
- Top
K float64 - Sample from the k most likely next tokens
- Top
P float64 - Cumulative probability cutoff for token selection
- maximum
Length Double - Maximum length of output
- stop
Sequences List<String> - List of stop sequences
- temperature Double
- Controls randomness, higher values increase diversity
- top
K Double - Sample from the k most likely next tokens
- top
P Double - Cumulative probability cutoff for token selection
- maximum
Length number - Maximum length of output
- stop
Sequences string[] - List of stop sequences
- temperature number
- Controls randomness, higher values increase diversity
- top
K number - Sample from the k most likely next tokens
- top
P number - Cumulative probability cutoff for token selection
- maximum_
length float - Maximum length of output
- stop_
sequences Sequence[str] - List of stop sequences
- temperature float
- Controls randomness, higher values increase diversity
- top_
k float - Sample from the k most likely next tokens
- top_
p float - Cumulative probability cutoff for token selection
- maximum
Length Number - Maximum length of output
- stop
Sequences List<String> - List of stop sequences
- temperature Number
- Controls randomness, higher values increase diversity
- top
K Number - Sample from the k most likely next tokens
- top
P Number - Cumulative probability cutoff for token selection
AgentKnowledgeBase, AgentKnowledgeBaseArgs
- Description string
- Description of the Resource.
- Knowledge
Base stringId - Identifier for a resource.
- Knowledge
Base Pulumi.State Aws Native. Bedrock. Agent Knowledge Base State - Specifies whether to use the knowledge base or not when sending an InvokeAgent request.
- Description string
- Description of the Resource.
- Knowledge
Base stringId - Identifier for a resource.
- Knowledge
Base AgentState Knowledge Base State - Specifies whether to use the knowledge base or not when sending an InvokeAgent request.
- description String
- Description of the Resource.
- knowledge
Base StringId - Identifier for a resource.
- knowledge
Base AgentState Knowledge Base State - Specifies whether to use the knowledge base or not when sending an InvokeAgent request.
- description string
- Description of the Resource.
- knowledge
Base stringId - Identifier for a resource.
- knowledge
Base AgentState Knowledge Base State - Specifies whether to use the knowledge base or not when sending an InvokeAgent request.
- description str
- Description of the Resource.
- knowledge_
base_ strid - Identifier for a resource.
- knowledge_
base_ Agentstate Knowledge Base State - Specifies whether to use the knowledge base or not when sending an InvokeAgent request.
- description String
- Description of the Resource.
- knowledge
Base StringId - Identifier for a resource.
- knowledge
Base "ENABLED" | "DISABLED"State - Specifies whether to use the knowledge base or not when sending an InvokeAgent request.
AgentKnowledgeBaseState, AgentKnowledgeBaseStateArgs
- Enabled
- ENABLED
- Disabled
- DISABLED
- Agent
Knowledge Base State Enabled - ENABLED
- Agent
Knowledge Base State Disabled - DISABLED
- Enabled
- ENABLED
- Disabled
- DISABLED
- Enabled
- ENABLED
- Disabled
- DISABLED
- ENABLED
- ENABLED
- DISABLED
- DISABLED
- "ENABLED"
- ENABLED
- "DISABLED"
- DISABLED
AgentParameterDetail, AgentParameterDetailArgs
- Type
Pulumi.
Aws Native. Bedrock. Agent Type - The data type of the parameter.
- Description string
- Description of function parameter.
- Required bool
- Information about if a parameter is required for function call. Default to false.
- Type
Agent
Type - The data type of the parameter.
- Description string
- Description of function parameter.
- Required bool
- Information about if a parameter is required for function call. Default to false.
- type
Agent
Type - The data type of the parameter.
- description String
- Description of function parameter.
- required Boolean
- Information about if a parameter is required for function call. Default to false.
- type
Agent
Type - The data type of the parameter.
- description string
- Description of function parameter.
- required boolean
- Information about if a parameter is required for function call. Default to false.
- type
Agent
Type - The data type of the parameter.
- description str
- Description of function parameter.
- required bool
- Information about if a parameter is required for function call. Default to false.
- type "string" | "number" | "integer" | "boolean" | "array"
- The data type of the parameter.
- description String
- Description of function parameter.
- required Boolean
- Information about if a parameter is required for function call. Default to false.
AgentPromptConfiguration, AgentPromptConfigurationArgs
- Base
Prompt stringTemplate - Base Prompt Template.
- Inference
Configuration Pulumi.Aws Native. Bedrock. Inputs. Agent Inference Configuration - Contains inference parameters to use when the agent invokes a foundation model in the part of the agent sequence defined by the
promptType
. For more information, see Inference parameters for foundation models . - Parser
Mode Pulumi.Aws Native. Bedrock. Agent Creation Mode - Specifies whether to override the default parser Lambda function when parsing the raw foundation model output in the part of the agent sequence defined by the
promptType
. If you set the field asOVERRIDEN
, theoverrideLambda
field in the PromptOverrideConfiguration must be specified with the ARN of a Lambda function. - Prompt
Creation Pulumi.Mode Aws Native. Bedrock. Agent Creation Mode - Specifies whether to override the default prompt template for this
promptType
. Set this value toOVERRIDDEN
to use the prompt that you provide in thebasePromptTemplate
. If you leave it asDEFAULT
, the agent uses a default prompt template. - Prompt
State Pulumi.Aws Native. Bedrock. Agent Prompt State - Specifies whether to allow the inline agent to carry out the step specified in the
promptType
. If you set this value toDISABLED
, the agent skips that step. The default state for eachpromptType
is as follows.PRE_PROCESSING
–ENABLED
ORCHESTRATION
–ENABLED
KNOWLEDGE_BASE_RESPONSE_GENERATION
–ENABLED
POST_PROCESSING
–DISABLED
- Prompt
Type Pulumi.Aws Native. Bedrock. Agent Prompt Type - The step in the agent sequence that this prompt configuration applies to.
- Base
Prompt stringTemplate - Base Prompt Template.
- Inference
Configuration AgentInference Configuration - Contains inference parameters to use when the agent invokes a foundation model in the part of the agent sequence defined by the
promptType
. For more information, see Inference parameters for foundation models . - Parser
Mode AgentCreation Mode - Specifies whether to override the default parser Lambda function when parsing the raw foundation model output in the part of the agent sequence defined by the
promptType
. If you set the field asOVERRIDEN
, theoverrideLambda
field in the PromptOverrideConfiguration must be specified with the ARN of a Lambda function. - Prompt
Creation AgentMode Creation Mode - Specifies whether to override the default prompt template for this
promptType
. Set this value toOVERRIDDEN
to use the prompt that you provide in thebasePromptTemplate
. If you leave it asDEFAULT
, the agent uses a default prompt template. - Prompt
State AgentPrompt State - Specifies whether to allow the inline agent to carry out the step specified in the
promptType
. If you set this value toDISABLED
, the agent skips that step. The default state for eachpromptType
is as follows.PRE_PROCESSING
–ENABLED
ORCHESTRATION
–ENABLED
KNOWLEDGE_BASE_RESPONSE_GENERATION
–ENABLED
POST_PROCESSING
–DISABLED
- Prompt
Type AgentPrompt Type - The step in the agent sequence that this prompt configuration applies to.
- base
Prompt StringTemplate - Base Prompt Template.
- inference
Configuration AgentInference Configuration - Contains inference parameters to use when the agent invokes a foundation model in the part of the agent sequence defined by the
promptType
. For more information, see Inference parameters for foundation models . - parser
Mode AgentCreation Mode - Specifies whether to override the default parser Lambda function when parsing the raw foundation model output in the part of the agent sequence defined by the
promptType
. If you set the field asOVERRIDEN
, theoverrideLambda
field in the PromptOverrideConfiguration must be specified with the ARN of a Lambda function. - prompt
Creation AgentMode Creation Mode - Specifies whether to override the default prompt template for this
promptType
. Set this value toOVERRIDDEN
to use the prompt that you provide in thebasePromptTemplate
. If you leave it asDEFAULT
, the agent uses a default prompt template. - prompt
State AgentPrompt State - Specifies whether to allow the inline agent to carry out the step specified in the
promptType
. If you set this value toDISABLED
, the agent skips that step. The default state for eachpromptType
is as follows.PRE_PROCESSING
–ENABLED
ORCHESTRATION
–ENABLED
KNOWLEDGE_BASE_RESPONSE_GENERATION
–ENABLED
POST_PROCESSING
–DISABLED
- prompt
Type AgentPrompt Type - The step in the agent sequence that this prompt configuration applies to.
- base
Prompt stringTemplate - Base Prompt Template.
- inference
Configuration AgentInference Configuration - Contains inference parameters to use when the agent invokes a foundation model in the part of the agent sequence defined by the
promptType
. For more information, see Inference parameters for foundation models . - parser
Mode AgentCreation Mode - Specifies whether to override the default parser Lambda function when parsing the raw foundation model output in the part of the agent sequence defined by the
promptType
. If you set the field asOVERRIDEN
, theoverrideLambda
field in the PromptOverrideConfiguration must be specified with the ARN of a Lambda function. - prompt
Creation AgentMode Creation Mode - Specifies whether to override the default prompt template for this
promptType
. Set this value toOVERRIDDEN
to use the prompt that you provide in thebasePromptTemplate
. If you leave it asDEFAULT
, the agent uses a default prompt template. - prompt
State AgentPrompt State - Specifies whether to allow the inline agent to carry out the step specified in the
promptType
. If you set this value toDISABLED
, the agent skips that step. The default state for eachpromptType
is as follows.PRE_PROCESSING
–ENABLED
ORCHESTRATION
–ENABLED
KNOWLEDGE_BASE_RESPONSE_GENERATION
–ENABLED
POST_PROCESSING
–DISABLED
- prompt
Type AgentPrompt Type - The step in the agent sequence that this prompt configuration applies to.
- base_
prompt_ strtemplate - Base Prompt Template.
- inference_
configuration AgentInference Configuration - Contains inference parameters to use when the agent invokes a foundation model in the part of the agent sequence defined by the
promptType
. For more information, see Inference parameters for foundation models . - parser_
mode AgentCreation Mode - Specifies whether to override the default parser Lambda function when parsing the raw foundation model output in the part of the agent sequence defined by the
promptType
. If you set the field asOVERRIDEN
, theoverrideLambda
field in the PromptOverrideConfiguration must be specified with the ARN of a Lambda function. - prompt_
creation_ Agentmode Creation Mode - Specifies whether to override the default prompt template for this
promptType
. Set this value toOVERRIDDEN
to use the prompt that you provide in thebasePromptTemplate
. If you leave it asDEFAULT
, the agent uses a default prompt template. - prompt_
state AgentPrompt State - Specifies whether to allow the inline agent to carry out the step specified in the
promptType
. If you set this value toDISABLED
, the agent skips that step. The default state for eachpromptType
is as follows.PRE_PROCESSING
–ENABLED
ORCHESTRATION
–ENABLED
KNOWLEDGE_BASE_RESPONSE_GENERATION
–ENABLED
POST_PROCESSING
–DISABLED
- prompt_
type AgentPrompt Type - The step in the agent sequence that this prompt configuration applies to.
- base
Prompt StringTemplate - Base Prompt Template.
- inference
Configuration Property Map - Contains inference parameters to use when the agent invokes a foundation model in the part of the agent sequence defined by the
promptType
. For more information, see Inference parameters for foundation models . - parser
Mode "DEFAULT" | "OVERRIDDEN" - Specifies whether to override the default parser Lambda function when parsing the raw foundation model output in the part of the agent sequence defined by the
promptType
. If you set the field asOVERRIDEN
, theoverrideLambda
field in the PromptOverrideConfiguration must be specified with the ARN of a Lambda function. - prompt
Creation "DEFAULT" | "OVERRIDDEN"Mode - Specifies whether to override the default prompt template for this
promptType
. Set this value toOVERRIDDEN
to use the prompt that you provide in thebasePromptTemplate
. If you leave it asDEFAULT
, the agent uses a default prompt template. - prompt
State "ENABLED" | "DISABLED" - Specifies whether to allow the inline agent to carry out the step specified in the
promptType
. If you set this value toDISABLED
, the agent skips that step. The default state for eachpromptType
is as follows.PRE_PROCESSING
–ENABLED
ORCHESTRATION
–ENABLED
KNOWLEDGE_BASE_RESPONSE_GENERATION
–ENABLED
POST_PROCESSING
–DISABLED
- prompt
Type "PRE_PROCESSING" | "ORCHESTRATION" | "POST_PROCESSING" | "KNOWLEDGE_BASE_RESPONSE_GENERATION" - The step in the agent sequence that this prompt configuration applies to.
AgentPromptOverrideConfiguration, AgentPromptOverrideConfigurationArgs
- Prompt
Configurations List<Pulumi.Aws Native. Bedrock. Inputs. Agent Prompt Configuration> - List of BasePromptConfiguration
- Override
Lambda string - ARN of a Lambda.
- Prompt
Configurations []AgentPrompt Configuration - List of BasePromptConfiguration
- Override
Lambda string - ARN of a Lambda.
- prompt
Configurations List<AgentPrompt Configuration> - List of BasePromptConfiguration
- override
Lambda String - ARN of a Lambda.
- prompt
Configurations AgentPrompt Configuration[] - List of BasePromptConfiguration
- override
Lambda string - ARN of a Lambda.
- prompt_
configurations Sequence[AgentPrompt Configuration] - List of BasePromptConfiguration
- override_
lambda str - ARN of a Lambda.
- prompt
Configurations List<Property Map> - List of BasePromptConfiguration
- override
Lambda String - ARN of a Lambda.
AgentPromptState, AgentPromptStateArgs
- Enabled
- ENABLED
- Disabled
- DISABLED
- Agent
Prompt State Enabled - ENABLED
- Agent
Prompt State Disabled - DISABLED
- Enabled
- ENABLED
- Disabled
- DISABLED
- Enabled
- ENABLED
- Disabled
- DISABLED
- ENABLED
- ENABLED
- DISABLED
- DISABLED
- "ENABLED"
- ENABLED
- "DISABLED"
- DISABLED
AgentPromptType, AgentPromptTypeArgs
- Pre
Processing - PRE_PROCESSING
- Orchestration
- ORCHESTRATION
- Post
Processing - POST_PROCESSING
- Knowledge
Base Response Generation - KNOWLEDGE_BASE_RESPONSE_GENERATION
- Agent
Prompt Type Pre Processing - PRE_PROCESSING
- Agent
Prompt Type Orchestration - ORCHESTRATION
- Agent
Prompt Type Post Processing - POST_PROCESSING
- Agent
Prompt Type Knowledge Base Response Generation - KNOWLEDGE_BASE_RESPONSE_GENERATION
- Pre
Processing - PRE_PROCESSING
- Orchestration
- ORCHESTRATION
- Post
Processing - POST_PROCESSING
- Knowledge
Base Response Generation - KNOWLEDGE_BASE_RESPONSE_GENERATION
- Pre
Processing - PRE_PROCESSING
- Orchestration
- ORCHESTRATION
- Post
Processing - POST_PROCESSING
- Knowledge
Base Response Generation - KNOWLEDGE_BASE_RESPONSE_GENERATION
- PRE_PROCESSING
- PRE_PROCESSING
- ORCHESTRATION
- ORCHESTRATION
- POST_PROCESSING
- POST_PROCESSING
- KNOWLEDGE_BASE_RESPONSE_GENERATION
- KNOWLEDGE_BASE_RESPONSE_GENERATION
- "PRE_PROCESSING"
- PRE_PROCESSING
- "ORCHESTRATION"
- ORCHESTRATION
- "POST_PROCESSING"
- POST_PROCESSING
- "KNOWLEDGE_BASE_RESPONSE_GENERATION"
- KNOWLEDGE_BASE_RESPONSE_GENERATION
AgentS3Identifier, AgentS3IdentifierArgs
- S3Bucket
Name string - A bucket in S3.
- S3Object
Key string - A object key in S3.
- S3Bucket
Name string - A bucket in S3.
- S3Object
Key string - A object key in S3.
- s3Bucket
Name String - A bucket in S3.
- s3Object
Key String - A object key in S3.
- s3Bucket
Name string - A bucket in S3.
- s3Object
Key string - A object key in S3.
- s3_
bucket_ strname - A bucket in S3.
- s3_
object_ strkey - A object key in S3.
- s3Bucket
Name String - A bucket in S3.
- s3Object
Key String - A object key in S3.
AgentStatus, AgentStatusArgs
- Creating
- CREATING
- Preparing
- PREPARING
- Prepared
- PREPARED
- Not
Prepared - NOT_PREPARED
- Deleting
- DELETING
- Failed
- FAILED
- Versioning
- VERSIONING
- Updating
- UPDATING
- Agent
Status Creating - CREATING
- Agent
Status Preparing - PREPARING
- Agent
Status Prepared - PREPARED
- Agent
Status Not Prepared - NOT_PREPARED
- Agent
Status Deleting - DELETING
- Agent
Status Failed - FAILED
- Agent
Status Versioning - VERSIONING
- Agent
Status Updating - UPDATING
- Creating
- CREATING
- Preparing
- PREPARING
- Prepared
- PREPARED
- Not
Prepared - NOT_PREPARED
- Deleting
- DELETING
- Failed
- FAILED
- Versioning
- VERSIONING
- Updating
- UPDATING
- Creating
- CREATING
- Preparing
- PREPARING
- Prepared
- PREPARED
- Not
Prepared - NOT_PREPARED
- Deleting
- DELETING
- Failed
- FAILED
- Versioning
- VERSIONING
- Updating
- UPDATING
- CREATING
- CREATING
- PREPARING
- PREPARING
- PREPARED
- PREPARED
- NOT_PREPARED
- NOT_PREPARED
- DELETING
- DELETING
- FAILED
- FAILED
- VERSIONING
- VERSIONING
- UPDATING
- UPDATING
- "CREATING"
- CREATING
- "PREPARING"
- PREPARING
- "PREPARED"
- PREPARED
- "NOT_PREPARED"
- NOT_PREPARED
- "DELETING"
- DELETING
- "FAILED"
- FAILED
- "VERSIONING"
- VERSIONING
- "UPDATING"
- UPDATING
AgentType, AgentTypeArgs
- String
- string
- Number
- number
- Integer
- integer
- Boolean
- boolean
- Array
- array
- Agent
Type String - string
- Agent
Type Number - number
- Agent
Type Integer - integer
- Agent
Type Boolean - boolean
- Agent
Type Array - array
- String
- string
- Number
- number
- Integer
- integer
- Boolean
- boolean
- Array
- array
- String
- string
- Number
- number
- Integer
- integer
- Boolean
- boolean
- Array
- array
- STRING
- string
- NUMBER
- number
- INTEGER
- integer
- BOOLEAN
- boolean
- ARRAY
- array
- "string"
- string
- "number"
- number
- "integer"
- integer
- "boolean"
- boolean
- "array"
- array
Package Details
- Repository
- AWS Native pulumi/pulumi-aws-native
- License
- Apache-2.0
We recommend new projects start with resources from the AWS provider.