VectorKnowledgeBaseConfiguration - Amazon Bedrock (original) (raw)

Contains details about the model used to create vector embeddings for the knowledge base.

Contents

embeddingModelArn

The Amazon Resource Name (ARN) of the model used to create vector embeddings for the knowledge base.

Type: String

Length Constraints: Minimum length of 20. Maximum length of 2048.

Pattern: (arn:aws(-[^:]{1,12})?:(bedrock|sagemaker):[a-z0-9-]{1,20}:([0-9]{12})?:([a-z-]+/)?)?([a-zA-Z0-9.-]{1,63}){0,2}(([:][a-z0-9-]{1,63}){0,2})?(/[a-z0-9]{1,12})?

Required: Yes

embeddingModelConfiguration

The embeddings model configuration details for the vector model used in Knowledge Base.

Type: EmbeddingModelConfiguration object

Required: No

If you include multimodal data from your data source, use this object to specify configurations for the storage location of the images extracted from your documents. These images can be retrieved and returned to the end user. They can also be used in generation when using RetrieveAndGenerate.

Type: SupplementalDataStorageConfiguration object

Required: No

See Also

For more information about using this API in one of the language-specific AWS SDKs, see the following:

• AWS SDK for C++
• AWS SDK for Java V2
• AWS SDK for Ruby V3

VectorIngestionConfiguration

VectorSearchBedrockRerankingConfiguration

Did this page help you? - Yes

Thanks for letting us know we're doing a good job!

If you've got a moment, please tell us what we did right so we can do more of it.

Did this page help you? - No

Thanks for letting us know this page needs work. We're sorry we let you down.

If you've got a moment, please tell us how we can make the documentation better.