Coding & Refactoringlow risk
qdrant-scaling-query-volume
Guides Qdrant query volume scaling. Use when someone asks 'query returns too many results', 'scroll performance', 'large limit values', 'paginating search results', 'fetching many vectors', or 'high cardinality results'.
github/awesome-copilot·skills/qdrant-scaling/scaling-query-volume/SKILL.md
95/ 100质量分
导入这个 Skill
选择你的 coding agent，复制项目级或个人级安装命令。
导入当前项目.agents/skills/scaling-query-volume
npx skills add https://github.com/github/awesome-copilot/tree/0aaced533251f5b86c69dfbc5e55db74c4b4d1af/skills/qdrant-scaling/scaling-query-volume -a codex -y导入个人环境~/.agents/skills/scaling-query-volume
npx skills add https://github.com/github/awesome-copilot/tree/0aaced533251f5b86c69dfbc5e55db74c4b4d1af/skills/qdrant-scaling/scaling-query-volume -a codex -g -y导入当前项目.claude/skills/scaling-query-volume
npx skills add https://github.com/github/awesome-copilot/tree/0aaced533251f5b86c69dfbc5e55db74c4b4d1af/skills/qdrant-scaling/scaling-query-volume -a claude-code -y导入个人环境~/.claude/skills/scaling-query-volume
npx skills add https://github.com/github/awesome-copilot/tree/0aaced533251f5b86c69dfbc5e55db74c4b4d1af/skills/qdrant-scaling/scaling-query-volume -a claude-code -g -y导入当前项目.agents/skills/scaling-query-volume
npx skills add https://github.com/github/awesome-copilot/tree/0aaced533251f5b86c69dfbc5e55db74c4b4d1af/skills/qdrant-scaling/scaling-query-volume -a github-copilot -y导入个人环境~/.copilot/skills/scaling-query-volume
npx skills add https://github.com/github/awesome-copilot/tree/0aaced533251f5b86c69dfbc5e55db74c4b4d1af/skills/qdrant-scaling/scaling-query-volume -a github-copilot -g -y导入当前项目.agents/skills/scaling-query-volume
npx skills add https://github.com/github/awesome-copilot/tree/0aaced533251f5b86c69dfbc5e55db74c4b4d1af/skills/qdrant-scaling/scaling-query-volume -a cursor -y导入个人环境~/.cursor/skills/scaling-query-volume
npx skills add https://github.com/github/awesome-copilot/tree/0aaced533251f5b86c69dfbc5e55db74c4b4d1af/skills/qdrant-scaling/scaling-query-volume -a cursor -g -y导入当前项目.agents/skills/scaling-query-volume
npx skills add https://github.com/github/awesome-copilot/tree/0aaced533251f5b86c69dfbc5e55db74c4b4d1af/skills/qdrant-scaling/scaling-query-volume -a gemini-cli -y导入个人环境~/.gemini/skills/scaling-query-volume
npx skills add https://github.com/github/awesome-copilot/tree/0aaced533251f5b86c69dfbc5e55db74c4b4d1af/skills/qdrant-scaling/scaling-query-volume -a gemini-cli -g -yNative Gemini CLI
gemini skills install https://github.com/github/awesome-copilot.git --scope workspace --path skills/qdrant-scaling/scaling-query-volume⚠ 安装命令使用开源 skills CLI。执行前请检查来源、脚本和权限。
Skill 指令
在 GitHub 查看原始文件 ↗# Scaling for Query Volume Problem: When a query has a large limit (e.g. 1000) and there are multiple shards (e.g. 10), naively each shard must return the full 1000 results — totaling 10,000 scored points transferred and merged. This is wasteful since data is randomly distributed across auto-shards. ## Core idea Instead of asking every shard for the full limit, ask each shard for a smaller limit computed via Poisson distribution statistics, then merge. This is safe because auto-sharding guarantees random, independent data distribution. ## When it activates - More than 1 shard - Auto-sharding is in use (all queried shards share the same shard key) - The request's limit + offset >= SHARD_QUERY_SUBSAMPLING_LIMIT (128) - The query is not exact ## Key tradeoff The strategy trades a small probability of slightly incomplete results for a large reduction in inter-shard data transfer, especially for high-limit queries across many shards. The 1.2x safety factor and the 99.9% Poisson threshold keep the error rate very low — comparable to inaccuracies already introduced by approximate vector indices like HNSW.