qdrant-performance-optimization
About qdrant-performance-optimization
A routing skill for diagnosing Qdrant performance issues. It directs agents to the relevant detailed skill by symptom and highlights that segment-count choices differ for latency and throughput.
Key features
- 01Symptom-based guide routing
- 02Search speed troubleshooting
- 03Indexing performance troubleshooting
- 04Memory usage troubleshooting
- 05Latency and throughput segment guidance
Use cases
- 01Investigating slow filtered queries or low QPS
- 02Troubleshooting slow index builds or bulk upserts
- 03Reducing RAM use or fitting larger datasets
Install
Copy the command and run it in a terminal.
npx skills add https:/After installing, type/qdrant-performance-optimizationin Claude Code to confirm it loaded.
Details
From the project READMEQdrant Performance Optimization
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 says | Read |
|---|---|
| Filtered queries much slower than unfiltered | search-speed-optimization/SKILL.md |
| Low QPS, cannot handle the query load | search-speed-optimization/SKILL.md |
| Individual queries take too long to return | search-speed-optimization/SKILL.md |
| Index build or HNSW build takes too long, vector upload is slow | indexing-performance-optimization/SKILL.md |
| Collection stays yellow, optimizer stuck or runs for a long time | indexing-performance-optimization/SKILL.md |
| Bulk upsert of vectors is slow | indexing-performance-optimization/SKILL.md |
| RAM usage too high, out-of-memory crashes | memory-usage-optimization/SKILL.md |
| Want to fit a larger dataset on the same hardware | memory-usage-optimization/SKILL.md |
| Reducing cost by moving data to disk | memory-usage-optimization/SKILL.md |
Latency and throughput pull opposite ways on segment count.
For latency, increase segments toward the CPU core count (default_segment_number: 16).
For throughput, use fewer and larger segments (default_segment_number: 2).
Applying the wrong direction makes the reported problem worse.