Class VectorRetrievalStrategy
A retrieval strategy that scores partitions using cosine similarity between the query embedding and partition embeddings.
public sealed class VectorRetrievalStrategy : IRetrievalStrategy- Inheritance
-
VectorRetrievalStrategy
- Implements
- Inherited Members
Examples
using LMKit.Model;
using LMKit.Retrieval;
LM embeddingModel = LM.LoadFromModelID("embeddinggemma-300m");
RagEngine ragEngine = new RagEngine(embeddingModel);
// VectorRetrievalStrategy is the default, but you can set it explicitly.
ragEngine.RetrievalStrategy = new VectorRetrievalStrategy();
ragEngine.ImportText("Quantum computing uses qubits.", "docs", "physics");
var results = await ragEngine.QueryAsync("What are qubits?");Remarks
This is the default strategy used by RagEngine. It wraps the existing vector search implementation and produces identical results to the standard retrieval path.
Properties
- RequiresQueryVector
Gets a value indicating whether the strategy requires a query embedding vector.
Methods
- RetrieveAsync(IReadOnlyList<DataSource>, string, float[], int, float, bool, bool, DataFilter, CancellationToken)
Retrieves matching partitions from the given data sources.