KnowledgeBaseFlowNodeConfiguration¶
Structure Class¶
KnowledgeBaseFlowNodeConfiguration
dataclass
¶
Contains configurations for a knowledge base node in a flow. This node takes a query as the input and returns, as the output, the retrieved responses directly (as an array) or a response generated based on the retrieved responses. For more information, see Node types in a flow in the Amazon Bedrock User Guide.
Attributes¶
guardrail_configuration
class-attribute
instance-attribute
¶
guardrail_configuration: GuardrailConfiguration | None = None
Contains configurations for a guardrail to apply during query and response generation for the knowledge base in this configuration.
inference_configuration
class-attribute
instance-attribute
¶
inference_configuration: PromptInferenceConfiguration | None = None
Contains inference configurations for the prompt.
knowledge_base_id
class-attribute
instance-attribute
¶
knowledge_base_id: str = ''
The unique identifier of the knowledge base to query.
model_id
class-attribute
instance-attribute
¶
model_id: str | None = None
The unique identifier of the model or inference profile to use to generate a response from the query results. Omit this field if you want to return the retrieved results as an array.
number_of_results
class-attribute
instance-attribute
¶
number_of_results: int | None = None
The number of results to retrieve from the knowledge base.
orchestration_configuration
class-attribute
instance-attribute
¶
orchestration_configuration: KnowledgeBaseOrchestrationConfiguration | None = None
The configuration for orchestrating the retrieval and generation process in the knowledge base node.
prompt_template
class-attribute
instance-attribute
¶
prompt_template: KnowledgeBasePromptTemplate | None = None
A custom prompt template to use with the knowledge base for generating responses.
reranking_configuration
class-attribute
instance-attribute
¶
reranking_configuration: VectorSearchRerankingConfiguration | None = None
The configuration for reranking the retrieved results from the knowledge base to improve relevance.