Tag: retrieval
All the articles with the tag "retrieval".
Vector Search: Exact Search and the Approximate Indexes
Updated:Finding the nearest embeddings is easy and linear; every index trades a little recall for a lot of speed. Similarity metrics and when they agree, why trees fail in high dimensions, and LSH, IVF, product quantization with a worked 8-byte code, and HNSW as a navigable small world, with an interactive graph search. Then all of them measured with FAISS on 71,865 real sentence embeddings: recall against latency and bytes per vector.
Reranking and Late Interaction: Cross-Encoders to ColBERT
Updated:Retrieval has to be cheap per document because it scores every document; reranking can be expensive per document because it only sees the top few. The bi-encoder and cross-encoder, their cost per query computed, ColBERT's late interaction and MaxSim worked token by token, why max and not mean, hard negatives, index sizes with ColBERTv2's compression, and LLM rerankers. Then cross-encoder reranking measured on the English and Vietnamese benchmark of Semantic and Hybrid Search, with what it gains and what it costs.
Beyond Vector RAG: Agentic, Graph and Vectorless Retrieval
Updated:When one retrieval pass can't answer the question, there are three ways to go further: let the model decide what to fetch next (agentic RAG), fetch structure instead of chunks (GraphRAG), or navigate a document's own outline instead of embedding it (vectorless retrieval). How each works and what it costs, with GraphRAG's indexing bill computed for this blog, and keyword, dense, hybrid and LLM-navigated retrieval compared on 30 questions about it.