Retriever
Also known as: First-stage retriever, Recall model
The fast first-stage search in RAG: bi-encoder or BM25 fetching a shortlist for the reranker or LLM.
The fast first stage of a RAG pipeline. Uses precomputed embeddings (bi-encoder) or an inverted index (BM25) to scan millions of documents in milliseconds and hand a shortlist of tens or hundreds of candidates to a downstream reranker or directly to the LLM.
In practice
Every production RAG interview covers the two-stage pipeline. The retriever is where recall lives, and its choice (dense vs sparse vs hybrid) drives cost, freshness, and quality.
How it compares
The retriever fetches a shortlist fast; the reranker scores that shortlist more accurately per pair.
A bi-encoder is one way to build a retriever: independent embeddings of query and docs compared by vector similarity.
Comparisons that include Retriever
Related topics
Related terms
Retrieval-Augmented Generation (RAG)
Fetch relevant docs at inference time and stuff them into the prompt so the model can answer from real data.
Embeddings
Dense numeric vectors that capture meaning; close vectors = similar text.
Chunking
Cutting documents into retrievable pieces before embedding them.
Context Window
The max number of tokens a model can attend to at once.
Hallucination
When a model confidently makes up something that isn't true.
AI System Design
End-to-end design of production LLM systems: ingestion, retrieval, serving, eval, monitoring.