AgenticRetrieveStreamRequest ¶

class AgenticRetrieveStreamRequest(TypedDict, closed=True):
    messages: "capo_bedrock_agent_runtime.types.agentic_retrieve_messages.AgenticRetrieveMessages"
    """<p>The list of messages for the agentic retrieval conversation.</p>"""
    retrievers: "capo_bedrock_agent_runtime.types.agentic_retrievers.AgenticRetrievers"
    """<p>The list of retrievers to use for agentic retrieval.</p>"""
    agentic_retrieve_configuration: "capo_bedrock_agent_runtime.types.agentic_retrieve_configuration.AgenticRetrieveConfiguration"
    """<p>Configuration settings for the agentic retrieval operation.</p>"""
    policy_configuration: NotRequired[
        "capo_bedrock_agent_runtime.types.agentic_retrieve_policy_configuration.AgenticRetrievePolicyConfiguration"
    ]
    """<p>Policy configuration for guardrails and content filtering.</p>"""
    next_token: NotRequired["capo_bedrock_agent_runtime.types.next_token.NextToken"]
    """<p>Opaque continuation token for paginated results.</p>"""
    user_context: NotRequired[
        "capo_bedrock_agent_runtime.types.user_context.UserContext"
    ]
    """<p>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.</p>"""
    memory_configuration: NotRequired[
        "capo_bedrock_agent_runtime.types.agentic_retrieve_memory_configuration.AgenticRetrieveMemoryConfiguration"
    ]
    """<p>The configuration for using an Amazon Bedrock AgentCore Memory resource with this retrieval.</p>"""
    generate_response: "bool"
    """<p>Whether to generate a response based on the retrieved results.</p>"""