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 Set up a knowledge base.

To create a managed knowledge base, provide a managedKnowledgeBaseConfiguration during creation. For more information, see Build a managed knowledge base.

• Provide the name and an optional description.

• Provide the Amazon Resource Name (ARN) with permissions to create a knowledge base in the roleArn field.

• For managed knowledge bases, set embeddingModelType to MANAGED to use the service-managed embedding model, or CUSTOM with an embeddingModelArn to use your own. To use your own KMS key for encryption, provide the ARN in serverSideEncryptionConfiguration. No vector store configuration is required for managed knowledge bases.

• For self-managed knowledge bases, provide the embedding model to use in the embeddingModelArn field in the knowledgeBaseConfiguration object.

• For self-managed knowledge bases, provide the configuration for your vector store in the storageConfiguration object.

  • For an Amazon OpenSearch Service database, use the opensearchServerlessConfiguration object. For more information, see Create a vector store in Amazon OpenSearch Service.

  • For an Amazon Aurora database, use the RdsConfiguration object. For more information, see Create a vector store in Amazon Aurora.

  • For a Pinecone database, use the pineconeConfiguration object. For more information, see Create a vector store in Pinecone.

  • For a Redis Enterprise Cloud database, use the redisEnterpriseCloudConfiguration object. For more information, see Create a vector store in Redis Enterprise Cloud.