BedrockEmbeddingModelConfiguration

Configuration settings for processing audio content in multimodal knowledge bases.

Type: Array of AudioConfiguration objects

Array Members: Fixed number of 1 item.

Required: No

The dimensions details for the vector configuration used on the Bedrock embeddings model.

Type: Integer

Valid Range: Minimum value of 0. Maximum value of 4096.

Required: No

The data type for the vectors when using a model to convert text into vector embeddings. The model must support the specified data type for vector embeddings. Floating-point (float32) is the default data type, and is supported by most models for vector embeddings. See Supported embeddings models for information on the available models and their vector data types.

Type: String

Valid Values: FLOAT32 | BINARY

Required: No

Model-specific configuration for the embedding model, provided as a JSON object. Use this field to specify settings that apply to the embedding model that you selected, such as how audio and video files are divided into segments.

The fields that this object accepts depend on the embedding model. For the settings that each model accepts, see the documentation for that model.

For an example of a CreateKnowledgeBase request that uses this field to configure a multimodal embedding model, see the Examples section of CreateKnowledgeBase.

Type: JSON value

Required: No

Configuration settings for processing video content in multimodal knowledge bases.

Type: Array of VideoConfiguration objects

Array Members: Fixed number of 1 item.

Required: No