Retrieval

Predict the shape of recall and latency on an IVF index of 10M vectors as nprobe sweeps from 1 to 50.

Why does every production retrieval system use approximate nearest-neighbor search instead of exact search past a certain corpus size?

Pick the 2026 task where an encoder-only transformer still beats a decoder-only LLM

Bi-encoders vs cross-encoders, where does attention cross the query and document?

How is long-term memory typically implemented in an agent?

Flashcard: how is agentic RAG different from single-shot RAG?

Explain how MCP differs from RAG and when to choose each approach

How does MCP differ from RAG, and when would you choose one over the other?

How does agentic RAG differ from single shot RAG, and what does putting retrieval inside the loop enable?

What does agentic RAG uniquely enable compared to naive single shot RAG?

HNSW vs IVF, when do you pick each for a production vector index?

Match each vector index type to its primary characteristic.

What does RAG primarily help with in LLM-based applications?