Skip to content
Quantoros

Your semantic search fails for short queries (1–3 words). How do you improve it?

NLPLevel: IntermediateTroubleshooting Scenarios

Your semantic search fails for short queries (1–3 words). How do you improve it?

Hints
  • Separate text representation, modeling and evaluation.
  • Check ambiguity, rare terms and training versus target text distributions.

Answer

Short queries produce poor embeddings — one token embeddings are ambiguous:

  • "Python" → programming language? snake? Monty Python?

Fixes:

  1. HyDE (Hypothetical Document Embeddings): generate a hypothetical full answer to the short query, embed that
  2. Query expansion: use an LLM to expand the short query into a full sentence: "Python" → "Python programming language tutorial and documentation"
  3. Keyword augmentation: combine vector search with BM25 — keyword search works well for short, specific queries
  4. Contextual queries: use conversation context to expand the query (if user asked about programming earlier, "Python" is the language)

Source and licence: JustInCache & contributors — Awesome AI Interviews · Apache-2.0

Related questions