FlatIndex<T>

Models & Types · AiDotNet.RetrievalAugmentedGeneration.VectorSearch.Indexes

Flat index that performs exact brute-force similarity search.

Implements: IVectorIndex<T>

How It Works

This is the simplest and most accurate index type, comparing the query against every vector in the index. It guarantees exact nearest neighbors but has O(n) search complexity where n is the number of vectors. Best for small datasets (< 10K vectors) where accuracy is critical.

Constructors

Constructor Summary
FlatIndex(ISimilarityMetric<T> metric) Initializes a new instance of the FlatIndex class.

Properties

Property Summary
int Count { get; }

Methods

Method Summary
List<ValueTuple<string, T>> Search(Vector<T> query, int k)
bool Remove(string id)
void Add(string id, Vector<T> vector)
void AddBatch(Dictionary<string, Vector<T>> vectors)
void Clear()