·
Last changedVersion:
This version passed the hardening gate. Hardening applied 1 targeted change, normalized allowed-tools to the canonical single-string form, and preserved all other text. Classified findings before hardening: 0. Classified findings closed: 0. Classified findings remaining: 0. Unclassified scanner findings remaining: 0. Review findings closed: 1. Review findings remaining: 6.
None
None
Expand | File | Group | Subtype | Severity | Status |
|---|
No findings available
0 findings
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.
Isolate the source of quality issues, tune HNSW parameters, and choose the right embedding model. Diagnosis and Tuning
Hybrid search, reranking, relevance feedback, and exploration APIs for improving result quality. Search Strategies
Get started with chainctlchainctl skill install public/github/qdrant-search-quality:latest
Bring Chainguard's hardening pipeline to your first-party skills — custom rulesets, automated remediation, full audit trail.
skills.chainreg.biz/public/github.com/github/skills/qdrant-search-quality:latest
MIT
HARDENING.md
LICENSE
SKILL.md
diagnosis/SKILL.md
search-strategies/SKILL.md