TFIDFRetriever<T>

Models & Types ยท AiDotNet.RetrievalAugmentedGeneration.Retrievers

TF-IDF (Term Frequency-Inverse Document Frequency) retrieval strategy with cached statistics.

Inheritance: RetrieverBase<T> โ†’ TFIDFRetriever<T>

For Beginners

TF-IDF ranks documents by how unique and frequent terms are.

This implementation uses a cache to avoid recalculating term statistics on every search, dramatically improving performance for repeated queries. The cache is automatically refreshed when documents are added, removed or changed.

How It Works

Implements production-ready TF-IDF retrieval with intelligent caching to avoid recomputing statistics on every query. The cache is automatically invalidated when the corpus changes (a document added, removed or replaced, even when the document count stays the same), ensuring accuracy while maximizing performance.

Constructors

Constructor Summary
TFIDFRetriever(IDocumentStore<T> documentStore, int defaultTopK)