Retrieval Search

These words describe semantic matching, indexing, and steps that improve retrieval quality.

How to recognize this theme

Terms used when systems look up related text or documents.

In a daily board, this category groups terms by their shared role. Look for four cards that describe the same mechanism, risk area, or workflow rather than four words that merely sound similar.

Educational context

These entries are vocabulary notes for learning. They are not project endorsements, token recommendations, exchange rankings, or trading signals.

Similarity Search

Similarity search finds items that are close to a query in embedding or feature space.

Vector Store

A vector store keeps embeddings so systems can search by semantic similarity.

Chunking

Chunking breaks long content into smaller pieces that are easier to index and retrieve.

Reranker

A reranker scores retrieved items again to improve the final ordering for a query.