Class HybridSearchConfig (1.65.0)

HybridSearchConfig(mapping=None, *, ignore_unknown_fields=False, **kwargs)

Config for hybrid search.

Attributes
Name	Description
`sparse_embedding_config`	`google.cloud.aiplatform_v1beta1.types.RagEmbeddingModelConfig.SparseEmbeddingConfig` Optional. The configuration for sparse embedding generation. This field is optional the default behavior depends on the vector database choice on the RagCorpus.
`dense_embedding_model_prediction_endpoint`	`google.cloud.aiplatform_v1beta1.types.RagEmbeddingModelConfig.VertexPredictionEndpoint` Required. The Vertex AI Prediction Endpoint that hosts the embedding model for dense embedding generations.

Methods

HybridSearchConfig(mapping=None, *, ignore_unknown_fields=False, **kwargs)

Config for hybrid search.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2024-09-19 UTC.