create_knowledge_base ¶

def create_knowledge_base(
    self,
    name: "capo_bedrock_agent.types.name.Name",
    role_arn: "capo_bedrock_agent.types.knowledge_base_role_arn.KnowledgeBaseRoleArn",
    knowledge_base_configuration: "capo_bedrock_agent.types.knowledge_base_configuration.KnowledgeBaseConfiguration",
    *,
    config_overrides: Optional[BedrockAgentClientConfig] = None,
    client_token: Optional[
        "capo_bedrock_agent.types.client_token.ClientToken"
    ] = None,
    description: Optional[
        "capo_bedrock_agent.types.description.Description"
    ] = None,
    storage_configuration: Optional[
        "capo_bedrock_agent.types.storage_configuration.StorageConfiguration"
    ] = None,
    tags: Optional["capo_bedrock_agent.types.tags_map.TagsMap"] = None,
) -> "capo_bedrock_agent.types.create_knowledge_base_response.CreateKnowledgeBaseResponse":
    """<p>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 <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/knowlege-base-prereq.html">Set up a knowledge base</a>.</p> <note> <p>To create a managed knowledge base, provide a <code>managedKnowledgeBaseConfiguration</code> during creation. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/kb-build-managed.html">Build a managed knowledge base</a>.</p> </note> <ul> <li> <p>Provide the <code>name</code> and an optional <code>description</code>.</p> </li> <li> <p>Provide the Amazon Resource Name (ARN) with permissions to create a knowledge base in the <code>roleArn</code> field.</p> </li> <li> <p>For managed knowledge bases, set <code>embeddingModelType</code> to <code>MANAGED</code> to use the service-managed embedding model, or <code>CUSTOM</code> with an <code>embeddingModelArn</code> to use your own. To use your own KMS key for encryption, provide the ARN in <code>serverSideEncryptionConfiguration</code>. No vector store configuration is required for managed knowledge bases.</p> </li> <li> <p>For self-managed knowledge bases, provide the embedding model to use in the <code>embeddingModelArn</code> field in the <code>knowledgeBaseConfiguration</code> object.</p> </li> <li> <p>For self-managed knowledge bases, provide the configuration for your vector store in the <code>storageConfiguration</code> object.</p> <ul> <li> <p>For an Amazon OpenSearch Service database, use the <code>opensearchServerlessConfiguration</code> object. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/knowledge-base-setup-oss.html">Create a vector store in Amazon OpenSearch Service</a>.</p> </li> <li> <p>For an Amazon Aurora database, use the <code>RdsConfiguration</code> object. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/knowledge-base-setup-rds.html">Create a vector store in Amazon Aurora</a>.</p> </li> <li> <p>For a Pinecone database, use the <code>pineconeConfiguration</code> object. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/knowledge-base-setup-pinecone.html">Create a vector store in Pinecone</a>.</p> </li> <li> <p>For a Redis Enterprise Cloud database, use the <code>redisEnterpriseCloudConfiguration</code> object. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/knowledge-base-setup-redis.html">Create a vector store in Redis Enterprise Cloud</a>.</p> </li> </ul> </li> </ul>

    Args:
        client_token: <p>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 <a href="https://docs.aws.amazon.com/AWSEC2/latest/APIReference/Run_Instance_Idempotency.html">Ensuring idempotency</a>.</p>
        name: <p>A name for the knowledge base.</p>
        description: <p>A description of the knowledge base.</p>
        role_arn: <p>The Amazon Resource Name (ARN) of the IAM role with permissions to invoke API operations on the knowledge base.</p>
        knowledge_base_configuration: <p>Contains details about the embeddings model used for the knowledge base.</p>
        storage_configuration: <p>Contains details about the configuration of the vector database used for the knowledge base.</p>
        tags: <p>Specify the key-value pairs for the tags that you want to attach to your knowledge base in this object.</p>

    Raises:
        capo_bedrock_agent.errors.access_denied_exception.AccessDeniedException: <p>The request is denied because of missing access permissions.</p>
        capo_bedrock_agent.errors.conflict_exception.ConflictException: <p>There was a conflict performing an operation.</p>
        capo_bedrock_agent.errors.internal_server_exception.InternalServerException: <p>An internal server error occurred. Retry your request.</p>
        capo_bedrock_agent.errors.service_quota_exceeded_exception.ServiceQuotaExceededException: <p>The number of requests exceeds the service quota. Resubmit your request later.</p>
        capo_bedrock_agent.errors.throttling_exception.ThrottlingException: <p>The number of requests exceeds the limit. Resubmit your request later.</p>
        capo_bedrock_agent.errors.validation_exception.ValidationException: <p>Input validation failed. Check your request parameters and retry the request.</p>
        capo_bedrock_agent.errors.UnknownServiceError: The service returned an error code this client does not model.
    """

    def _handler(
        req: "OperationRequest[capo_bedrock_agent.types.create_knowledge_base_request.CreateKnowledgeBaseRequest]",
    ) -> OperationResponse[
        "capo_bedrock_agent.types.create_knowledge_base_response.CreateKnowledgeBaseResponse"
    ]:
        import capo_bedrock_agent._operations.amazon_bedrock_agent_build_time_lambda.create_knowledge_base

        output, http_response = (
            capo_bedrock_agent._operations.amazon_bedrock_agent_build_time_lambda.create_knowledge_base.create_knowledge_base(
                req.options, req.input
            )
        )
        return OperationResponse(output=output, response=http_response)

    def _redact_input(
        input_: "capo_bedrock_agent.types.create_knowledge_base_request.CreateKnowledgeBaseRequest",
    ) -> dict[str, Any]:
        import capo_bedrock_agent.types.create_knowledge_base_request

        return (
            capo_bedrock_agent.types.create_knowledge_base_request.redact_sensitive(
                input_
            )
        )

    def _redact_output(
        output: "capo_bedrock_agent.types.create_knowledge_base_response.CreateKnowledgeBaseResponse",
    ) -> dict[str, Any]:
        import capo_bedrock_agent.types.create_knowledge_base_response

        return capo_bedrock_agent.types.create_knowledge_base_response.redact_sensitive(
            output
        )

    interceptors_, options_ = self.operation_options(
        config_overrides,
        OperationLogging(
            "CreateKnowledgeBase",
            redact_input=_redact_input,
            redact_output=_redact_output,
        ),
    )
    input_: capo_bedrock_agent.types.create_knowledge_base_request.CreateKnowledgeBaseRequest = {
        "name": name,
        "role_arn": role_arn,
        "knowledge_base_configuration": knowledge_base_configuration,
    }
    if client_token is None:
        client_token = str(uuid.uuid4())
    input_["client_token"] = client_token
    if description is not None:
        input_["description"] = description
    if storage_configuration is not None:
        input_["storage_configuration"] = storage_configuration
    if tags is not None:
        input_["tags"] = tags

    response = execute_pipeline(
        OperationRequest(input=input_, options=options_),
        handler=_handler,
        interceptors=list(interceptors_),
    )
    response.response.close()
    return response.output