BaseVectorQuery interface
The query parameters for vector and hybrid search queries.
Properties
| exhaustive | When true, triggers an exhaustive k-nearest neighbor search across all vectors within the vector index. Useful for scenarios where exact matches are critical, such as determining ground truth values. |
| fields | Vector Fields of type Collection(Edm.Single) to be included in the vector searched. |
| filter |
The OData filter expression to apply to this specific vector query. If no filter expression is defined at the vector level, the expression defined in the top level filter parameter is used instead. |
| kind | Known values supported by the servicevector: Vector query where a raw vector value is provided. text: Vector query where a text value that needs to be vectorized is provided. imageUrl: Vector query where an url that represents an image value that needs to be vectorized is provided. imageBinary: Vector query where a base 64 encoded binary of an image that needs to be vectorized is provided. |
| k |
Number of nearest neighbors to return as top hits. |
| per |
Controls how many vectors can be matched from each document in a vector search query. Setting it to 1 ensures at most one vector per document is matched, guaranteeing results come from distinct documents. Setting it to 0 (unlimited) allows multiple relevant vectors from the same document to be matched. Default is 0. |
| threshold | The threshold used for vector queries. Note this can only be set if all 'fields' use the same similarity metric. |
| weight | Relative weight of the vector query when compared to other vector query and/or the text query within the same search request. This value is used when combining the results of multiple ranking lists produced by the different vector queries and/or the results retrieved through the text query. The higher the weight, the higher the documents that matched that query will be in the final ranking. Default is 1.0 and the value needs to be a positive number larger than zero. |
Property Details
exhaustive
When true, triggers an exhaustive k-nearest neighbor search across all vectors within the vector index. Useful for scenarios where exact matches are critical, such as determining ground truth values.
exhaustive?: booleanProperty Value
boolean
fields
Vector Fields of type Collection(Edm.Single) to be included in the vector searched.
fields?: SearchFieldArray<TModel>Property Value
SearchFieldArray<TModel>
filterOverride
The OData filter expression to apply to this specific vector query. If no filter expression is defined at the vector level, the expression defined in the top level filter parameter is used instead.
filterOverride?: stringProperty Value
string
kind
Known values supported by the service
vector: Vector query where a raw vector value is provided. text: Vector query where a text value that needs to be vectorized is provided. imageUrl: Vector query where an url that represents an image value that needs to be vectorized is provided. imageBinary: Vector query where a base 64 encoded binary of an image that needs to be vectorized is provided.
kind: "text" | "vector" | "imageUrl" | "imageBinary"Property Value
"text" | "vector" | "imageUrl" | "imageBinary"
kNearestNeighborsCount
Number of nearest neighbors to return as top hits.
kNearestNeighborsCount?: numberProperty Value
number
perDocumentVectorLimit
Controls how many vectors can be matched from each document in a vector search query. Setting it to 1 ensures at most one vector per document is matched, guaranteeing results come from distinct documents. Setting it to 0 (unlimited) allows multiple relevant vectors from the same document to be matched. Default is 0.
perDocumentVectorLimit?: numberProperty Value
number
threshold
The threshold used for vector queries. Note this can only be set if all 'fields' use the same similarity metric.
threshold?: VectorThresholdProperty Value
weight
Relative weight of the vector query when compared to other vector query and/or the text query within the same search request. This value is used when combining the results of multiple ranking lists produced by the different vector queries and/or the results retrieved through the text query. The higher the weight, the higher the documents that matched that query will be in the final ranking. Default is 1.0 and the value needs to be a positive number larger than zero.
weight?: numberProperty Value
number
