Definition of AWS::Bedrock::KnowledgeBase Resource Type
knowledge_base_configuration
(Attributes) Contains details about the embeddings model used for the knowledge base. (see below for nested schema)name
(String) The name of the knowledge base.role_arn
(String) The ARN of the IAM role with permissions to invoke API operations on the knowledge base. The ARN must begin with AmazonBedrockExecutionRoleForKnowledgeBase_storage_configuration
(Attributes) The vector store service in which the knowledge base is stored. (see below for nested schema)description
(String) Description of the Resource.tags
(Map of String) A map of tag keys and valuescreated_at
(String) The time at which the knowledge base was created.failure_reasons
(List of String) A list of reasons that the API operation on the knowledge base failed.id
(String) Uniquely identifies the resource.knowledge_base_arn
(String) The ARN of the knowledge base.knowledge_base_id
(String) The unique identifier of the knowledge base.status
(String) The status of a knowledge base.updated_at
(String) The time at which the knowledge base was last updated.knowledge_base_configuration
Required:
type
(String) The type of a knowledge base.vector_knowledge_base_configuration
(Attributes) Contains details about the model used to create vector embeddings for the knowledge base. (see below for nested schema)knowledge_base_configuration.vector_knowledge_base_configuration
Required:
embedding_model_arn
(String) The ARN of the model used to create vector embeddings for the knowledge base.storage_configuration
Required:
type
(String) The storage type of a knowledge base.Optional:
opensearch_serverless_configuration
(Attributes) Contains the storage configuration of the knowledge base in Amazon OpenSearch Service. (see below for nested schema)pinecone_configuration
(Attributes) Contains the storage configuration of the knowledge base in Pinecone. (see below for nested schema)rds_configuration
(Attributes) Contains details about the storage configuration of the knowledge base in Amazon RDS. For more information, see Create a vector index in Amazon RDS. (see below for nested schema)storage_configuration.opensearch_serverless_configuration
Required:
collection_arn
(String) The ARN of the OpenSearch Service vector store.field_mapping
(Attributes) A mapping of Bedrock Knowledge Base fields to OpenSearch Serverless field names (see below for nested schema)vector_index_name
(String) The name of the vector store.storage_configuration.opensearch_serverless_configuration.field_mapping
Required:
metadata_field
(String) The name of the field in which Amazon Bedrock stores metadata about the vector store.text_field
(String) The name of the field in which Amazon Bedrock stores the raw text from your data. The text is split according to the chunking strategy you choose.vector_field
(String) The name of the field in which Amazon Bedrock stores the vector embeddings for your data sources.storage_configuration.pinecone_configuration
Required:
connection_string
(String) The endpoint URL for your index management page.credentials_secret_arn
(String) The ARN of the secret that you created in AWS Secrets Manager that is linked to your Pinecone API key.field_mapping
(Attributes) Contains the names of the fields to which to map information about the vector store. (see below for nested schema)Optional:
namespace
(String) The namespace to be used to write new data to your database.storage_configuration.pinecone_configuration.field_mapping
Required:
metadata_field
(String) The name of the field in which Amazon Bedrock stores metadata about the vector store.text_field
(String) The name of the field in which Amazon Bedrock stores the raw text from your data. The text is split according to the chunking strategy you choose.storage_configuration.rds_configuration
Required:
credentials_secret_arn
(String) The ARN of the secret that you created in AWS Secrets Manager that is linked to your Amazon RDS database.database_name
(String) The name of your Amazon RDS database.field_mapping
(Attributes) Contains the names of the fields to which to map information about the vector store. (see below for nested schema)resource_arn
(String) The ARN of the vector store.table_name
(String) The name of the table in the database.storage_configuration.rds_configuration.field_mapping
Required:
metadata_field
(String) The name of the field in which Amazon Bedrock stores metadata about the vector store.primary_key_field
(String) The name of the field in which Amazon Bedrock stores the ID for each entry.text_field
(String) The name of the field in which Amazon Bedrock stores the raw text from your data. The text is split according to the chunking strategy you choose.vector_field
(String) The name of the field in which Amazon Bedrock stores the vector embeddings for your data sources.Import is supported using the following syntax:
$ terraform import awscc_bedrock_knowledge_base.example <resource ID>