Retrieval & Agents
Reranking
A second pass that reorders retrieved results by relevance, surfacing the best few before they reach the model.
A first retrieval pass is fast but rough, often returning dozens of loosely relevant passages. A reranker then scores each candidate against the query with a more accurate, more expensive model and pushes the truly relevant ones to the top. Feeding the model only those best few improves answer quality and keeps the context window focused.
Related terms
Retrieval-Augmented Generation
A technique that looks up relevant documents and feeds them to a model so its answers are grounded in real sources.
Semantic Search
Search that matches on meaning rather than exact keywords, so related ideas surface even with different wording.
Hybrid Search
Combining keyword search with meaning-based vector search to get the strengths of both.
Context Window
The maximum amount of text, measured in tokens, that a model can consider at once.