Core

Reranking and Two-Stage Retrieval

Two-stage retrieval pairs a cheap recall-heavy first stage that pulls dozens of candidates with a precise reranker that re-scores each one against the query. It is the standard fix when vector search returns relevant-ish chunks but the right one is not in the top few, and it trades a little latency for a lot of precision.

a free account unlocks the core curriculum tier · no card

RELATED CONCEPTS

Retrieval-Augmented Generation (RAG)Vector Databases Approximate Nearest Neighbor (ANN)Chunking Strategies

LESSONS THAT TEACH THIS

Foundations of Forward Deployed EngineeringTrace the evidence before changing the prompt22 min→Hard DeploymentsServe it from cache, send less, or send it somewhere cheaper30 min→

PRACTICE THIS IN REAL QUESTIONS

RAG & Agent System DesignWalk me through a RAG pipeline end-to-end, and tell me where it usually breaks→RAG & Agent System DesignHow would you chunk documents for retrieval, and how do you know your chunking is good?→RAG & Agent System DesignKeyword search vs vector search: what does each actually buy you in a RAG system?→LLM & GenAI FundamentalsWhat are embeddings, and how do they make semantic search work?→RAG & Agent System DesignHow would you evaluate a RAG system before letting a customer launch it?→LLM & GenAI FundamentalsWhy is the dot product the similarity score in attention and embeddings, and when should you normalize to cosine?→