agentic_retrieve_stream¶
Operation¶
Async only
This operation uses an event stream, so only the asynchronous client supports it.
agentic_retrieve_stream
async
¶
agentic_retrieve_stream(request: AgenticRetrieveStreamInput | AgenticRetrieveStreamInputDict | None = None, /, *, plugins: list[Plugin] | None = None, **kwargs: Unpack[AgenticRetrieveStreamInputDict]) -> AsyncOutputEventStream[AgenticRetrieveStreamResponseOutput, AgenticRetrieveStreamOutput]
Retrieves information from one or more knowledge bases using an agentic approach. Agentic retrieval uses a foundation model to intelligently decompose complex queries into sub-queries and iteratively retrieve relevant information from your knowledge bases. This approach improves retrieval accuracy for complex, multi-step questions that a single retrieval pass might not fully address.
The operation returns results through a stream that includes retrieval results, trace events for visibility into the process, and a generated response synthesized from the results by default, which can be turned off.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
request
|
AgenticRetrieveStreamInput | AgenticRetrieveStreamInputDict | None
|
The input as a model or dictionary. Pass this or keyword arguments, not both. |
None
|
plugins
|
list[Plugin] | None
|
A list of callables that modify the configuration dynamically. Changes made by these plugins only apply for the duration of the operation execution and will not affect any other operation invocations. |
None
|
**kwargs
|
Unpack[AgenticRetrieveStreamInputDict]
|
The input fields as keyword arguments. |
{}
|
Returns:
| Type | Description |
|---|---|
AsyncOutputEventStream[AgenticRetrieveStreamResponseOutput, AgenticRetrieveStreamOutput]
|
An |
Input¶
Pass the input as keyword arguments, a positional dictionary, or a positional model object. Pass plugins separately as a keyword argument.
AgenticRetrieveStreamInputDict
¶
Bases: TypedDict
Dictionary form of AgenticRetrieveStreamInput.
Attributes¶
agentic_retrieve_configuration
instance-attribute
¶
agentic_retrieve_configuration: Required[AgenticRetrieveConfiguration | AgenticRetrieveConfigurationDict]
Configuration settings for the agentic retrieval operation.
generate_response
instance-attribute
¶
generate_response: bool | None
Whether to generate a response based on the retrieved results.
memory_configuration
instance-attribute
¶
memory_configuration: AgenticRetrieveMemoryConfiguration | AgenticRetrieveMemoryConfigurationDict | None
The configuration for using an Amazon Bedrock AgentCore Memory resource with this retrieval.
messages
instance-attribute
¶
messages: Required[Sequence[AgenticRetrieveMessage | AgenticRetrieveMessageDict]]
The list of messages for the agentic retrieval conversation.
next_token
instance-attribute
¶
next_token: str | None
Opaque continuation token for paginated results.
policy_configuration
instance-attribute
¶
policy_configuration: AgenticRetrievePolicyConfiguration | AgenticRetrievePolicyConfigurationDict | None
Policy configuration for guardrails and content filtering.
retrieval_instruction_configuration
instance-attribute
¶
retrieval_instruction_configuration: AgenticRetrieveInstructionConfiguration | AgenticRetrieveInstructionConfigurationDict | None
A retrieval instruction to apply to this request.
retrievers
instance-attribute
¶
retrievers: Required[Sequence[AgenticRetriever | AgenticRetrieverDict]]
The list of retrievers to use for agentic retrieval.
user_context
instance-attribute
¶
user_context: UserContext | UserContextDict | None
Contains information about the user making the request. This is used for access control filtering to ensure that retrieval results only include documents the user is authorized to access.
AgenticRetrieveStreamInput
dataclass
¶
Bases: _SerdeShape
Request structure for the agentic retrieve stream operation.
Attributes¶
agentic_retrieve_configuration
class-attribute
instance-attribute
¶
agentic_retrieve_configuration: AgenticRetrieveConfiguration | None = ...
Configuration settings for the agentic retrieval operation.
generate_response
class-attribute
instance-attribute
¶
generate_response: bool = ...
Whether to generate a response based on the retrieved results.
memory_configuration
class-attribute
instance-attribute
¶
memory_configuration: AgenticRetrieveMemoryConfiguration | None = ...
The configuration for using an Amazon Bedrock AgentCore Memory resource with this retrieval.
messages
class-attribute
instance-attribute
¶
messages: list[AgenticRetrieveMessage] | None = ...
The list of messages for the agentic retrieval conversation.
next_token
class-attribute
instance-attribute
¶
next_token: str | None = ...
Opaque continuation token for paginated results.
policy_configuration
class-attribute
instance-attribute
¶
policy_configuration: AgenticRetrievePolicyConfiguration | None = ...
Policy configuration for guardrails and content filtering.
retrieval_instruction_configuration
class-attribute
instance-attribute
¶
retrieval_instruction_configuration: AgenticRetrieveInstructionConfiguration | None = ...
A retrieval instruction to apply to this request.
retrievers
class-attribute
instance-attribute
¶
retrievers: list[AgenticRetriever] | None = ...
The list of retrievers to use for agentic retrieval.
user_context
class-attribute
instance-attribute
¶
user_context: UserContext | None = ...
Contains information about the user making the request. This is used for access control filtering to ensure that retrieval results only include documents the user is authorized to access.
Output¶
This operation returns an AsyncOutputEventStream for server-to-client streaming.
Event Stream Structure¶
Output Event Type¶
AgenticRetrieveStreamResponseOutput
Initial Response Structure¶
AgenticRetrieveStreamOutput
dataclass
¶
Bases: _SerdeShape
Response structure for the agentic retrieve stream operation.