Qdrant Search Quality

by qdrant6a03d0ce8f55No licenseListed Oct 8, 2026Updated Oct 8, 2026

Diagnoses and improves Qdrant search relevance. Use when someone reports 'search results are bad', 'wrong results', 'low precision', 'low recall', 'irrelevant matches', 'missing expected results', or asks 'how to improve search quality?', 'which embedding model?', 'should I use hybrid search?', 'how to combine keyword and vector search / fusion / RRF / prefetch?', 'should I use reranking?', 'relevance feedback?', 'how to measure retrieval quality?', 'build a golden set', 'ground truth dataset', or 'how to score recall@k?'. Also use when search quality degrades after quantization, model change, or data growth.

AI-generated overview

Routes Qdrant search-quality complaints to guidance on diagnosis, hybrid search, reranking and relevance feedback.

What it does
This skill acts as a router for questions about poor Qdrant search relevance. It matches the user's reported symptom, such as low precision, low recall, missing expected results, or quality drops after quantization or a model change, to one of several guidance files and instructs the agent to read that file before answering. It also points to guidance on measuring retrieval quality, golden sets, recall@k, hybrid search with fusion or RRF, reranking, and relevance feedback. It produces routing decisions and answers drawn from the referenced guidance rather than from the routing page itself.
When to use it
Use it when someone reports bad, wrong, or irrelevant search results, missing expected matches, low precision or recall, or asks how to improve search quality. It also fits questions about embedding-model choice, hybrid keyword-plus-vector search, reranking, relevance feedback, and measuring retrieval quality with a golden set or recall@k.
Requirements
No scripts are shipped; it is instructions only. The agent needs file-reading tools (Read, Grep, Glob) and access to the referenced guidance files, which are not included in this skill folder.

Qdrant Search Quality

Route first, then answer. Match the user's symptom in the table, Read that file, and answer from it. Do not answer from this page alone: it contains routing only, not the guidance. If two rows match, read both.

The user saysRead
Search results are bad or irrelevant, wrong results, missing expected matchesdiagnosis/SKILL.md
Low recall, expected results are missingdiagnosis/SKILL.md
Low precision, too many wrong matchesdiagnosis/SKILL.md
Which embedding model to use, quality dropped after quantization, model change, or data growthdiagnosis/SKILL.md
Not sure if the model, the data, or Qdrant is at faultdiagnosis/SKILL.md
Want to measure recall, build a golden set, ground truth dataset, recall@kdiagnosis/SKILL.md
Need to combine keyword and semantic search, hybrid search, sparse + dense, fusion / RRF, prefetchsearch-strategies/hybrid-search/SKILL.md
Should I rerank, results too similar, need diversity, MMR, recommendation/discovery APIsearch-strategies/SKILL.md
Improving results with relevance feedback or user clicks, cheaper alternative to rerankingsearch-strategies/relevance-feedback/SKILL.md

Most quality issues come from the embedding model or the data, not from Qdrant's configuration — splitting chunks mid-sentence alone can drop quality 30-40%. Rule that out with exact search before tuning any Qdrant parameter: Search API

Source and attribution

Source:qdrant/skillsinskills/qdrant-search-qualityat commit6a03d0c

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal