Expanding the candidate pool via relevance feedback, as an alternative to reranking when a dense retriever is too weak. Use when someone asks about 'Qdrant's Relevance Feedback API', 'improving dense search relevance/recall', 'how to discover/get more relevant results from vector search', 'cheaper/better alternative to reranking', 'using a more heavy/big embedding model for dense search but…
安装
npx skills add qdrant/skills --skill qdrant-relevance-feedbacknpx skills add qdrant/skills --skill qdrant-relevance-feedback -a claude-code -gnpx skills add qdrant/skills --skill qdrant-relevance-feedback -a codex -ggemini skills install https://github.com/qdrant/skills.git --path skills/qdrant-search-quality/search-strategies/relevance-feedbackgh skill install qdrant/skills qdrant-relevance-feedbackgit clone --depth 1 https://github.com/qdrant/skills /tmp/qdrant__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/qdrant__skills/skills/qdrant-search-quality/search-strategies/relevance-feedback ~/.claude/skills/qdrant-relevance-feedback # Claude Code
cp -R /tmp/qdrant__skills/skills/qdrant-search-quality/search-strategies/relevance-feedback ~/.agents/skills/qdrant-relevance-feedback # Codex, Cursor, Gemini CLI, Copilot, OpenCode