VertexAISearchRetriever

Filter expression.

Comma-separated list of fields to order by.

Canonical filter expression.

If True return Extractive Answers, otherwise return Extractive Segments or Snippets.

The maximum number of documents to return.

The maximum number of extractive answers to return per search result.

The maximum number of extractive segments to return per search result.

If True, the relevance score for each extractive segment will be included in the search results.

This can be useful for ranking or filtering segments.

Specifies the number of text segments preceding the matched segment to return.

This provides context before the relevant text.

Value must be between 1 and 3.

Specifies the number of text segments following the matched segment to return.

This provides context after the relevant text.

Value must be between 1 and 3.

Specification to determine under which conditions query expansion should occur.

0 - Unspecified query expansion condition. In this case, server behavior defaults to disabled. 1 - Disabled query expansion. Only the exact search query is used, even if SearchResponse.total_size is zero. 2 - Automatic query expansion built by the Search API.

Specification to determine under which conditions query expansion should occur.

0 - Unspecified spell correction mode. In this case, server behavior defaults to auto. 1 - Suggestion only. Search API will try to find a spell suggestion if there is any and put in the SearchResponse.corrected_query. The spell suggestion will not be used as the search query. 2 - Automatic spell correction built by the Search API. Search will be based on the corrected query if found.

The field path for the custom embedding used in the Vertex AI datastore schema.

Controls the ranking of results.

Value should be between 0 and 1.

Will generate the ranking_expression in the following manner:

"{custom_embedding_ratio} * dotProduct({custom_embedding_field_path}) + {1 - custom_embedding_ratio} * relevance_score"