Best for
- Use when someone reports 'results are bad', 'wrong results', 'not relevant results', 'missing matches', 'recall is low', 'approximate search worse than exact', 'which embedding model', or 'quality dropped after quantiza…
Source profileQuality 68/100
github/awesome-copilot/skills/qdrant-search-quality/diagnosis/SKILL.md
qdrant-search-quality-diagnosis
Diagnoses Qdrant search quality issues. Use when someone reports 'results are bad', 'wrong results', 'not relevant results', 'missing matches', 'recall is low', 'approximate search worse than exact', 'which embedding model', or 'quality dropped after quantization'. Also use when search quality degrades without obvious changes.
- Source repository stars
- 37,126
- Declared platforms
- 0
- Static risk flags
- 1
- Last source update
- 2026-07-28
- Source checked
- 2026-07-28
Decision brief
What it does—and where it fits
Before tuning, establish baselines. Use exact KNN as ground truth, compare against approximate HNSW. Target 95% recall@K for production.
Not for
- Tasks that require unconfirmed production actions or broad system permissions.
- Environments where the pinned source and install steps cannot be inspected.
Compatibility matrix
Platform support, with evidence labels
| Platform | Status | Evidence | What to check |
|---|---|---|---|
| Codex | Not declared | No explicit evidence | Portability before use |
| Claude Code | Not declared | No explicit evidence | Portability before use |
| Cursor | Not declared | No explicit evidence | Portability before use |
| Gemini CLI | Not declared | No explicit evidence | Portability before use |
Installation
Inspect first. Install second.
The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.
Source-detected install commandSource
npx skills add https://github.com/github/awesome-copilot --skill "skills/qdrant-search-quality/diagnosis"Safe inspection promptEditorial
Inspect the Agent Skill "qdrant-search-quality-diagnosis" from https://github.com/github/awesome-copilot/blob/9933dcad5be5caeb288cebcd370eeeb2fc2f1685/skills/qdrant-search-quality/diagnosis/SKILL.md at commit 9933dcad5be5caeb288cebcd370eeeb2fc2f1685. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.
Workflow
What the source asks the agent to do
- 01
Don't Know What's Wrong Yet
Use when: results are irrelevant or missing expected matches and you need to isolate the cause.
Test with exact=true to bypass HNSW approximation Search APIExact search bad = model or search pipeline problem. Exact good, approximate bad = tune HNSW.Check if quantization degrades quality (compare with and without) - 02
Approximate Search Worse Than Exact
Use when: exact search returns good results but HNSW approximation misses them.
Increase hnswef at query time Search paramsIncrease efconstruct (200+ for high quality) HNSW configIncrease m (16 default, 32 for high recall) HNSW config - 03
Wrong Embedding Model
Use when: exact search also returns bad results.
Use when: exact search also returns bad results.Test top 3 MTEB models on 100-1000 sample queries, measure recall@10. Domain-specific models often outperform general models. Hosted inference - 04
Unoptimized Search Pipeline
Use when: exact search also returns bad results and model choice is confirmed by user.
Use when: exact search also returns bad results and model choice is confirmed by user.Optimize search according to advanced search-strategies skill.
Permission review
Static risk signals and limitations
Network access
The documentation includes network, browsing, or remote request actions.
Test with `exact=true` to bypass HNSW approximation [Search API](https://search.qdrant.tech/md/documentation/tutorials-search-engineering/retrieval-quality/?s=standard-mode-vs-exact-search)Network access
The documentation includes network, browsing, or remote request actions.
If duplicate results from chunked documents, use Grouping API to deduplicate [Grouping](https://search.qdrant.tech/md/documentation/search/search/?s=grouping-api)Evidence record
Why each signal appears
EvidenceSourceComputedTestedEditorial
| Signal | Value | Evidence type | Meaning |
|---|---|---|---|
| Quality score | 68/100 | Computed | Documentation, specificity, maintenance, and trust rules |
| Repository stars | 37,126 | Source | Repository attention, not individual Skill quality |
| Compatibility | 0 platforms | Source | Declared in the catalog source record |
| Usage guide | automated source guide | Editorial | Generated or reviewed according to the visible evidence level |
Pinned source
Provenance and original SKILL.md
- Repository
- github/awesome-copilot
- Skill path
- skills/qdrant-search-quality/diagnosis/SKILL.md
- Commit
- 9933dcad5be5caeb288cebcd370eeeb2fc2f1685
- License
- MIT
- Collected
- 2026-07-28
- Default branch
- main
View the original SKILL.md
How to Diagnose Bad Search Quality
Before tuning, establish baselines. Use exact KNN as ground truth, compare against approximate HNSW. Target >95% recall@K for production.
Don't Know What's Wrong Yet
Use when: results are irrelevant or missing expected matches and you need to isolate the cause.
- Test with
exact=trueto bypass HNSW approximation Search API - Exact search bad = model or search pipeline problem. Exact good, approximate bad = tune HNSW.
- Check if quantization degrades quality (compare with and without)
- Check if filters are too restrictive (then you might need to use ACORN)
- If duplicate results from chunked documents, use Grouping API to deduplicate Grouping
Payload filtering and sparse vector search are different things. Metadata (dates, categories, tags) goes in payload for filtering. Text content goes in sparse vectors for search.
Approximate Search Worse Than Exact
Use when: exact search returns good results but HNSW approximation misses them.
- Increase
hnsw_efat query time Search params - Increase
ef_construct(200+ for high quality) HNSW config - Increase
m(16 default, 32 for high recall) HNSW config - Enable oversampling + rescore with quantization Search with quantization
- ACORN for filtered queries (v1.16+) ACORN
Binary quantization requires rescore. Without it, quality loss is severe. Use oversampling (3-5x minimum for binary) to recover recall. Always test quantization impact on your data before production. Quantization
Wrong Embedding Model
Use when: exact search also returns bad results.
Test top 3 MTEB models on 100-1000 sample queries, measure recall@10. Domain-specific models often outperform general models. Hosted inference
Unoptimized Search Pipeline
Use when: exact search also returns bad results and model choice is confirmed by user.
Optimize search according to advanced search-strategies skill.
What NOT to Do
- Tune Qdrant before verifying the model is right for the task (most quality issues are model issues)
- Use binary quantization without rescore (severe quality loss)
- Set
hnsw_eflower than results requested (guaranteed bad recall) - Skip payload indexes on filtered fields then blame quality (HNSW can't traverse filtered-out nodes, and filterable HNSW is built only if payload indexes were set up prior)
- Deploy without baseline recall or other search relevance metrics (no way to measure regressions)
- Confuse payload filtering with sparse vector search (different things, different config)