SemanticSearchBehaviorProperties.ScoreThresholdFilter Property

Controls how the ScoreThreshold is applied during filtering.

Namespace : DevExpress.AIIntegration.WinForms

Assembly : DevExpress.AIIntegration.WinForms.SemanticSearch.v25.2.dll

NuGet Package : DevExpress.AIIntegration.WinForms.SemanticSearch

csharp

[DefaultValue(ScoreThresholdFilter.None)]
public ScoreThresholdFilter ScoreThresholdFilter { get; set; }

<DefaultValue(ScoreThresholdFilter.None)>
Public Property ScoreThresholdFilter As ScoreThresholdFilter

Property Value

Type	Default	Description
DevExpress.AIIntegration.SemanticSearch.ScoreThresholdFilter	None

A value that controls how the ScoreThreshold is applied during filtering.

Remarks

In your vectorized data model, you must annotate a vector field with the VectorStoreVector attribute and specify the desired similarity metric using the DistanceFunction property:

csharp

using Microsoft.Extensions.VectorData;

// Define a record stored in the vector store for semantic search.
public class VectorStoreRecord {
    // A unique identifier for the record in a vector store.
    [VectorStoreKey]
    public string Key { get; set; }

    // Azure OpenAI (embedding model) produces 1536-dimensional vectors.
    // Specify how vector data is stored and compared in a vector store.
    // This example uses cosine similarity as the distance function for comparisons.
    [VectorStoreVector(1536, DistanceFunction = DistanceFunction.CosineDistance)]
    public string Vector { get; set; }
}

Warning

The VectorStoreVector attribute indicates the preferred distance function, but the vector store ultimately determines which similarity metric is supported. If your vector store does not support the specified function, it will throw a runtime error.

Use the following properties to configure similarity filtering:

Score Threshold

The SemanticSearchBehavior.Properties.ScoreThreshold property specifies the minimum or maximum score at which search results are considered relevant. The actual meaning of the score depends on the selected similarity metric/distance function. For example:

Cosine Similarity

Value	Description
`1.0`	Vectors are identical (maximum similarity)
`0.0`	Vectors are orthogonal (no similarity)
`-1.0`	Vectors are opposite

Cosine Distance

Value	Description
`0.0`	Vectors are identical (maximum similarity)
`1.0`	Vectors are orthogonal (no similarity)
`2.0`	Vectors are opposite

Score Threshold Filter

The SemanticSearchBehavior.Properties.ScoreThresholdFilter property specifies how the ScoreThreshold is applied during filtering:

Value	Description
`None`	No filtering is applied. All results are returned regardless of score.
`GreaterOrEqual`	Include results with a score greater than or equal to `ScoreThreshold`. Used with Cosine Similarity , where higher scores mean greater similarity.
`LessOrEqual`	Include results with a score less than or equal to `ScoreThreshold`. Used with Cosine Distance , where lower scores mean greater similarity.

Examples

Cosine Similarity Filtering

Returns results with similarity scores from 0.5 to 1.0:

csharp

// Higher = more similar
semanticSearchBehavior.ScoreThreshold = 0.5;
semanticSearchBehavior.ScoreThresholdFilter = ScoreThresholdFilter.GreaterOrEqual;

Cosine Distance Filtering

Returns results with distance scores from 0.0 to 0.5:

csharp

// Lower = more similar
semanticSearchBehavior.ScoreThreshold = 0.5;
semanticSearchBehavior.ScoreThresholdFilter = ScoreThresholdFilter.LessOrEqual;

See the following help topic for additional information: Semantic Search.