IT lexicon AI & ML RAG pipeline

RAG pipeline

AI & ML På svenska → Updated: 2026-07-30

The full chain from document to answer: ingest (parse + chunk) → embedstore in vector DB → query: retrieve → optionally rerankgenerate.

Naive RAG: plain top-k cosine search. Modern RAG includes: chunking strategy (semantic, sliding window, recursive, late chunking), hybrid search (vector + BM25), reranker (cross-encoder such as Cohere Rerank), query expansion (HyDE, multi-query), context compression, contextual retrieval (Anthropic's technique). Larger LLM context windows made the "just send everything" competitor ("long context vs RAG") attractive but worse and more expensive.

← Back to the lexicon