About qdrant-search-quality
qdrant-search-quality is a skill for diagnosing and improving Qdrant search relevance. It helps practitioners distinguish embedding, data, configuration, and query-strategy issues before tuning search settings.
Key features
- 01Isolate embedding, data, and configuration issues
- 02Test exact search
- 03Tune HNSW parameters
- 04Choose embedding models
- 05Apply hybrid search and reranking
Use cases
- 01Investigate low search relevance
- 02Check whether chunk boundaries harm results
- 03Improve ranking with reranking or relevance feedback
Install
Copy the command and run it in a terminal.
npx skills add https:/After installing, type/qdrant-search-qualityin Claude Code to confirm it loaded.
Details
From the project READMEQdrant Search Quality
First determine whether the problem is the embedding model, Qdrant configuration, or the query strategy. Most quality issues come from the model or data, not from Qdrant itself. If search quality is low, inspect how chunks are being passed to Qdrant before tuning any parameters. Splitting mid-sentence can drop quality 30-40%.
- Start by testing with exact search to isolate the problem Search API
Diagnosis and Tuning
Isolate the source of quality issues, tune HNSW parameters, and choose the right embedding model. Diagnosis and Tuning
Search Strategies
Hybrid search, reranking, relevance feedback, and exploration APIs for improving result quality. Search Strategies