generative-ai-python

google.generativeai.protos.SemanticRetrieverConfig

View source on GitHub

Configuration for retrieving grounding content from a Corpus or Document created using the Semantic Retriever API.

Attributes
`source`	`str` Required. Name of the resource for retrieval. Example: ``corpora/123`` or ``corpora/123/documents/abc``.
`query`	`google.ai.generativelanguage.Content` Required. Query to use for matching ``Chunk``\ s in the given resource by similarity.
`metadata_filters`	`MutableSequence[google.ai.generativelanguage.MetadataFilter]` Optional. Filters for selecting ``Document``\ s and/or ``Chunk``\ s from the resource.
`max_chunks_count`	`int` Optional. Maximum number of relevant ``Chunk``\ s to retrieve.
`minimum_relevance_score`	`float` Optional. Minimum relevance score for retrieved relevant ``Chunk``\ s.

This site is open source. Improve this page.