| Name | Type | Description |
|---|---|---|
project_id* | str | The GCP project ID. |
region* | str | The GCP region. |
collection_id* | str | The collection ID. |
queries* | List[List[float]] | |
num_neighbors* | int | |
filter_ | dict | None | Default: None |
credentials | Optional[Credentials] | Default: None |
vector_field_name | str | Default: 'embedding' |
sparse_queries | List[dict[str, List[int] | List[float]]] | None | Default: None |
rrf_ranking_alpha | float | Default: 1.0 |
Searches for neighbors in a Vertex AI Vector Search 2.0 Collection.
List of query embeddings.
Number of neighbors to return.
Optional filter dict. Examples: {"genre": {"$eq": "Drama"}}, {"$and": [{"year": {"$gte": 1990}}, {"genre": {"$eq": "Action"}}]}
Optional credentials to use.
Name of the vector field in the collection schema.
Optional list of sparse query embeddings for hybrid search. Each sparse query should be: {"values": [...], "indices": [...]}
RRF ranking alpha parameter for hybrid search (0.0 to 1.0). NOTE: This parameter is currently not used in V2 API.
