Answers from the documentation; checking which model is on duty
Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
qdrant-search-quality - Skill - OpenSmartRoute
Skillv1.0.0
qdrant-search-quality
Diagnoses and improves Qdrant search relevance. Use when someone reports 'search results are bad', 'wrong results', 'low precision', 'low recall', 'irrelevant matches', 'missing expected results', or…
Imported from qdrant/skills (skills/qdrant-search-quality/SKILL.md) via skills.sh. Install upstream with npx skills add qdrant/skills --skill qdrant-search-quality. Copyright stays with the author.
Qdrant Search Quality
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
Search results are bad or irrelevant, wrong results, missing expected matches
diagnosis/SKILL.md
Low recall, expected results are missing
diagnosis/SKILL.md
Low precision, too many wrong matches
diagnosis/SKILL.md
Which embedding model to use, quality dropped after quantization, model change, or data growth
diagnosis/SKILL.md
Not sure if the model, the data, or Qdrant is at fault
diagnosis/SKILL.md
Want to measure recall, build a golden set, ground truth dataset, recall@k
diagnosis/SKILL.md
Is my improvement real, statistically significant, fine-tune the embedding model
diagnosis/SKILL.md
Need to combine keyword and semantic search, hybrid search, sparse + dense, fusion / RRF, prefetch
search-strategies/hybrid-search/SKILL.md
Should I rerank, results too similar, need diversity, MMR, recommendation/discovery API
search-strategies/SKILL.md
Improving results with relevance feedback or user clicks, cheaper alternative to reranking
search-strategies/relevance-feedback/SKILL.md
Most quality issues come from the embedding model or the data, not from Qdrant's configuration — splitting chunks mid-sentence alone can drop quality 30-40%.
Rule that out with exact search before tuning any Qdrant parameter:
Search API
Installed into a catalogue, chosen by a router
Install qdrant-search-quality and it becomes one more candidate the router can pick - when it fits.
A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.
When a provider is down or over quota the request moves on; the trace says it did.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - a plan picks it for its slotcurl-s-X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
qdrant-skills-qdrant-search-quality.ocm.jsonjson
{
"ocm": "1",
"id": "qdrant-skills-qdrant-search-quality",
"kind": "skill",
"name": "qdrant-search-quality",
"description": "Diagnoses and improves Qdrant search relevance. Use when someone reports 'search results are bad', 'wrong results', 'low precision', 'low recall', 'irrelevant matches', 'missing expected results', or asks 'how to improve search quality?', 'which embedding model?', 'should I use hybrid search?', 'how to combine keyword and vector search / fusion / RRF / prefetch?', 'should I use reranking?', 'relevance feedback?', 'how to measure retrieval quality?', 'build a golden set', 'ground truth dataset', 'how to score recall@k?', 'is my improvement real / statistically significant?', or 'should I fine-tune my embedding model?'. Also use when search quality degrades after quantization, model change, or data growth.",
"publisher": "qdrant",
"version": "1.0.0",
"capabilities": {
"domains": [
"medical",
"coding"
],
"tags": [
"skill-md",
"skills-sh"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Diagnoses and improves Qdrant search relevance. Use when someone reports 'search results are bad', 'wrong results', 'low precision', 'low recall', 'irrelevant matches', 'missing expected results', or asks 'how to improve search quality?', 'which embedding model?', 'should I use hybrid search?', 'how to combine keyword and vector search / fusion / RRF / prefetch?', 'should I use reranking?', 'relevance feedback?', 'how to measure retrieval quality?', 'build a golden set', 'ground truth dataset', 'how to score recall@k?', 'is my improvement real / statistically significant?', or 'should I fine-tune my embedding model?'. Also use when search quality degrades after quantization, model change, or data growth."
],
"primary": false,
"metadata": {
"source": {
"provider": "skills.sh",
"repository": "https://github.com/qdrant/skills",
"path": "skills/qdrant-search-quality/SKILL.md",
"ref": "HEAD",
"url": "https://www.skills.sh/qdrant/skills/qdrant-search-quality",
"key": "qdrant/skills/skills/qdrant-search-quality/SKILL.md"
},
"allowed_tools": [
"Read",
"Grep",
"Glob"
]
},
"instructions": "# Qdrant Search Quality\n\nRoute first, then answer. Match the user's symptom in the table, `Read` that file, and answer from it.\nDo not answer from this page alone: it contains routing only, not the guidance. If two rows match, read both.\n\n| The user says | Read |\n|---|---|\n| Search results are bad or irrelevant, wrong results, missing expected matches | `diagnosis/SKILL.md` |\n| Low recall, expected results are missing | `diagnosis/SKILL.md` |\n| Low precision, too many wrong matches | `diagnosis/SKILL.md` |\n| Which embedding model to use, quality dropped after quantization, model change, or data growth | `diagnosis/SKILL.md` |\n| Not sure if the model, the data, or Qdrant is at fault | `diagnosis/SKILL.md` |\n| Want to measure recall, build a golden set, ground truth dataset, recall@k | `diagnosis/SKILL.md` |\n| Is my improvement real, statistically significant, fine-tune the embedding model | `diagnosis/SKILL.md` |\n| Need to combine keyword and semantic search, hybrid search, sparse + dense, fusion / RRF, prefetch | `search-strategies/hybrid-search/SKILL.md` |\n| Should I rerank, results too similar, need diversity, MMR, recommendation/discovery API | `search-strategies/SKILL.md` |\n| Improving results with relevance feedback or user clicks, cheaper alternative to reranking | `search-strategies/relevance-feedback/SKILL.md` |\n\nMost quality issues come from the embedding model or the data, not from Qdrant's configuration — splitting chunks mid-sentence alone can drop quality 30-40%.\nRule that out with exact search before tuning any Qdrant parameter:\n[Search API](https://skills.qdrant.tech/md/documentation/search/search/?s=search-api)",
"cost": {
"context_tokens": 413
}
}
Fetch it by URL: GET /api/v1/registry/qdrant-skills-qdrant-search-quality/manifest?version=1.0.0
Reviews
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.