vector-index-tuning
Skill4 starsChanged 38 days agoMITView on GitHub
Optimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization strategies, or scaling vector search infrastructure.
7 other projects use a version of this, 7 of them edited.
Adopted by
Most recently taken up by
- AtilaMedeiros/skillsedited, first seen Nov 16, 2026
- ControllableModel/SWE-Skills-Benchedited, first seen Nov 8, 2026
- DTiapan/batteryedited, first seen Oct 17, 2026
- xfstudio/skillsedited, first seen Oct 13, 2026
- Samueladewole/claude-skillsedited, first seen Oct 13, 2026
- ai4brands-design/claude-skillsedited, first seen Mar 22, 2026
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 7
- xfstudio/skills★ 926% same
- ControllableModel/SWE-Skills-Bench★ 813% same
- ai4brands-design/claude-skills★ 226% same
- CodeWithBehnam/cc-docs★ 214% same
- AtilaMedeiros/skills★ 126% same
- DTiapan/battery★ 026% same
- Samueladewole/claude-skills★ 013% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository37 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ai-debt-detectorSkill
- airflow-dag-patternsSkill
- async-python-patternsSkill
- backtesting-frameworksSkill
- create-readmeSkill
- data-engineeringSkill
- data-quality-frameworksSkill
- dataset-curationSkill
- dbt-transformation-patternsSkill
- design-doc-mermaidSkill
- embedding-strategiesSkill
- eval-harness-firstSkill
- excalidraw-diagramSkill
- execution-algorithmsSkill
- external-diagram-mermaid-generateSkill
- frontend-designSkill
- hybrid-search-implementationSkill
- improve-codebase-architectureSkill
- llm-evaluationSkill
- market-regime-detectionSkill
- mcp-builderSkill
- mcp-registry-syndicationSkill
- mcprush-gateway-deploymentSkill
- mermaid-diagramsSkill
- ml-pipeline-workflowSkill
- orchestratorSkill
- postgresql-table-designSkill
- prompt-engineering-patternsSkill
- python-testing-patternsSkill
- rag-implementationSkill
- regulatory-compliance-auditSkill
- risk-metrics-calculationSkill
- security-reviewSkill
- spark-optimizationSkill
- sql-optimization-patternsSkill
The file
Files
Vector Index Tuning
Guide to optimizing vector indexes for production performance.
When to Use This Skill
- Tuning HNSW parameters
- Implementing quantization
- Optimizing memory usage
- Reducing search latency
- Balancing recall vs speed
- Scaling to billions of vectors
Core Concepts
1. Index Type Selection
Data Size Recommended Index
────────────────────────────────────────
< 10K vectors → Flat (exact search)
10K - 1M → HNSW
1M - 100M → HNSW + Quantization
> 100M → IVF + PQ or DiskANN2. HNSW Parameters
| Parameter | Default | Effect |
| M | 16 | Connections per node, ↑ = better recall, more memory |
| efConstruction | 100 | Build quality, ↑ = better index, slower build |
| efSearch | 50 | Search quality, ↑ = better recall, slower search |
3. Quantization Types
Full Precision (FP32): 4 bytes × dimensions
Half Precision (FP16): 2 bytes × dimensions
INT8 Scalar: 1 byte × dimensions
Product Quantization: ~32-64 bytes total
Binary: dimensions/8 bytesTemplates and detailed worked examples
Full template library and detailed worked examples live in references/details.md. Read that file when you need the concrete templates.
Best Practices
Do's
- Benchmark with real queries - Synthetic may not represent production
- Monitor recall continuously - Can degrade with data drift
- Start with defaults - Tune only when needed
- Use quantization - Significant memory savings
- Consider tiered storage - Hot/cold data separation
Don'ts
- Don't over-optimize early - Profile first
- Don't ignore build time - Index updates have cost
- Don't forget reindexing - Plan for maintenance
- Don't skip warming - Cold indexes are slow
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

