ClassEmbeddingSimilarityHelper
Class
Provides helper methods for calculating similarity scores between an already embedded question vector and a collection of fragment Embedding instances.
Definition
Namespace:Telerik.Documents.AI.RAG
Assembly:Telerik.Documents.AI.RAG.dll
Syntax:
cs-api-definition
public static class EmbeddingSimilarityHelperInheritance: objectEmbeddingSimilarityHelper
Methods
FindClosestWithScore(float[], IList<Embedding>)
Calculates cosine-similarity scores between a question embedding vector and fragment embeddings, returning the top results ordered descending by similarity.
Declaration
cs-api-definition
public static SimilarityScore<IFragment>[] FindClosestWithScore(float[] questionVector, IList<Embedding> embeddings)Parameters
questionVector
float[]
The embedding vector of the question.
embeddings
The fragment embeddings to compare against.
Returns
SimilarityScore<IFragment>[]
Array of SimilarityScore<T> where T is IFragment.