Search with a vector
The query
operation searches a namespace, using a query vector. It retrieves the ids of the most similar items in a namespace, along with their similarity scores.
For guidance and examples, see Query data.
Authorizations
Body
The request for the query
operation.
The number of results to return for each query.
1 <= x <= 10000
10
The namespace to query.
"example-namespace"
The filter to apply. You can use vector metadata to limit your search. See Understanding metadata. You can use vector metadata to limit your search. See Understanding metadata.
{
"genre": { "$in": ["comedy", "documentary", "drama"] },
"year": { "$eq": 2019 }
}
Indicates whether vector values are included in the response.
true
Indicates whether metadata is included in the response as well as the ids.
true
DEPRECATED. Use vector
or id
instead.
A single query vector within a QueryRequest
.
The query vector. This should be the same length as the dimension of the index being queried. Each request can contain either the id
or vector
parameter.
[0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8]
Vector sparse data. Represented as a list of indices and a list of corresponded values, which must be with the same length.
The unique ID of the vector to be used as a query vector. Each request can contain either the vector
or id
parameter.
512
"example-vector-1"
Response
The response for the query
operation. These are the matches found for a particular query vector. The matches are ordered from most similar to least similar.
DEPRECATED. The results of each query. The order is the same as QueryRequest.queries
.
The matches for the vectors.
The namespace for the vectors.
Was this page helpful?