[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-qdrant-qdrant-search-strategies":3,"mdc-s1gfhi-key":48,"related-org-qdrant-qdrant-search-strategies":326,"related-repo-qdrant-qdrant-search-strategies":480},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":23,"repoUrl":24,"updatedAt":25,"license":26,"forks":27,"topics":28,"repo":43,"sourceUrl":46,"mdContent":47},"qdrant-search-strategies","select Qdrant search strategies","Guides Qdrant search strategy selection. Use when someone asks 'should I use hybrid search?', 'how to rerank?', 'results are not relevant', 'I don't get needed results from my dataset but they're there', 'retrieval quality is not good enough', 'results too similar', 'need diversity', 'MMR', 'relevance feedback', 'recommendation API', 'discovery API', or 'missing keyword matches'",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"qdrant","Qdrant","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fqdrant.png",[12,16,17,20],{"name":13,"slug":14,"type":15},"Performance","performance","tag",{"name":9,"slug":8,"type":15},{"name":18,"slug":19,"type":15},"Database","database",{"name":21,"slug":22,"type":15},"Search","search",197,"https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fskills","2026-07-16T05:59:15.263716",null,23,[29,30,31,32,33,34,35,36,37,14,8,38,39,40,41,42],"agent-skills","ai-agents","claude-code","codex","cursor","embeddings","hybrid-search","monitoring","multitenancy","quantization","scaling","search-quality","vector-database","vector-search",{"repoUrl":24,"stars":23,"forks":27,"topics":44,"description":45},[29,30,31,32,33,34,35,36,37,14,8,38,39,40,41,42],"Agent skills for Qdrant vector search: scaling, performance optimization, search quality, monitoring, deployment, model migration, version upgrades, and SDK usage across Python, TypeScript, Rust, Go, .NET, Java","https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fskills\u002Ftree\u002FHEAD\u002Fskills\u002Fqdrant-search-quality\u002Fsearch-strategies","---\nname: qdrant-search-strategies\ndescription: \"Guides Qdrant search strategy selection. Use when someone asks 'should I use hybrid search?', 'how to rerank?', 'results are not relevant', 'I don't get needed results from my dataset but they're there', 'retrieval quality is not good enough', 'results too similar', 'need diversity', 'MMR', 'relevance feedback', 'recommendation API', 'discovery API', or 'missing keyword matches'\"\nallowed-tools:\n  - Read\n  - Grep\n  - Glob\n---\n\n# How to Improve Search Results with Advanced Strategies\n\nThese strategies complement basic vector search. Use them after confirming the embedding model is fitting the task and HNSW config is correct. If exact search returns bad results, verify the selection of the embedding model (retriever) first.\nIf the user wants to use a weaker embedding model because it is small, fast, and cheap, use reranking or relevance feedback to improve search quality.\n\n## Missing Keyword Matches or Need to Combine Multiple Search Signals\n\nUse when: pure vector search misses keyword\u002Fdomain term matches, or the use case benefits from combining searches on multiple representations (including languages and modalities) of the same item.\n\nSee how to use [hybrid search](https:\u002F\u002Fskills.qdrant.tech\u002Fqdrant-search-quality\u002Fsearch-strategies\u002Fhybrid-search\u002FSKILL.md)\n\n## Right Documents Found But Not in the Top Results\n\nUse when: good recall but poor precision (right docs in top-100, not top-10).\n\n- See how to use [Multistage queries](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fsearch\u002Fhybrid-queries\u002F?s=multi-stage-queries), for example with late interaction rerankers through [Multivectors](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fvectors\u002F?s=multivectors).\n- Cross-encoder rerankers via FastEmbed [Rerankers](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Ffastembed\u002Ffastembed-rerankers\u002F)\n\n## Dense Retriever Misses Relevant Items or Reranking Is Too Costly\n\nUse when: dense retriever misses relevant items you know exist in the collection; relevant documents lie outside the initial ANN retrieval pool; reranking a large candidate pool is too slow or expensive; using a small\u002Fcheap embedding model but need quality close to a larger model; or want to improve top-1\u002F3 precision without the full cost of reranking.\n\nSee [Relevance Feedback in Qdrant](https:\u002F\u002Fskills.qdrant.tech\u002Fqdrant-search-quality\u002Fsearch-strategies\u002Frelevance-feedback\u002FSKILL.md)\n\n## Results Too Similar\n\nUse when: top results are redundant, near-duplicates, or lack diversity. Common in dense content domains (academic papers, product catalogs).\n\n- Use MMR (v1.15+) as a query parameter with `diversity` to balance relevance and diversity [MMR](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fsearch\u002Fsearch-relevance\u002F?s=maximal-marginal-relevance-mmr)\n- Start with `diversity=0.5`, lower for more precision, higher for more exploration\n- MMR is slower than standard search. Only use when redundancy is an actual problem.\n\n## Want to improve search results based on examples (positive and negative)\n\nUse when: you can provide positive and negative example points to steer search closer to positive and further from negative.\n\n- Recommendation API: positive\u002Fnegative examples to recommend fitting vectors [Recommendation API](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fsearch\u002Fexplore\u002F?s=recommendation-api)\n  - Best score strategy: better for diverse examples, supports negative-only [Best score](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fsearch\u002Fexplore\u002F?s=best-score-strategy)\n- Discovery API: context pairs (positive\u002Fnegative) to constrain search regions without a request target [Discovery](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fsearch\u002Fexplore\u002F?s=discovery-api)\n\n## Have Business Logic Behind Results Relevance\n\nUse when: results should be additionally ranked according to some business logic based on data, like recency or distance.\n\nCheck how to set up in [Score Boosting docs](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fsearch\u002Fsearch-relevance\u002F?s=score-boosting)\n\n## What NOT to Do\n\n- Use hybrid search before verifying pure vector search quality (adds complexity, may mask model issues)\n- Skip evaluation when adding relevance feedback — score the end-to-end pipeline to confirm it actually helps [Pipeline Output Quality](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fimprove-search\u002Fpipeline-output-quality\u002F)\n",{"data":49,"body":54},{"name":4,"description":6,"allowed-tools":50},[51,52,53],"Read","Grep","Glob",{"type":55,"children":56},"root",[57,66,72,79,84,98,104,109,148,154,159,171,177,182,224,230,235,277,283,288,300,306],{"type":58,"tag":59,"props":60,"children":62},"element","h1",{"id":61},"how-to-improve-search-results-with-advanced-strategies",[63],{"type":64,"value":65},"text","How to Improve Search Results with Advanced Strategies",{"type":58,"tag":67,"props":68,"children":69},"p",{},[70],{"type":64,"value":71},"These strategies complement basic vector search. Use them after confirming the embedding model is fitting the task and HNSW config is correct. If exact search returns bad results, verify the selection of the embedding model (retriever) first.\nIf the user wants to use a weaker embedding model because it is small, fast, and cheap, use reranking or relevance feedback to improve search quality.",{"type":58,"tag":73,"props":74,"children":76},"h2",{"id":75},"missing-keyword-matches-or-need-to-combine-multiple-search-signals",[77],{"type":64,"value":78},"Missing Keyword Matches or Need to Combine Multiple Search Signals",{"type":58,"tag":67,"props":80,"children":81},{},[82],{"type":64,"value":83},"Use when: pure vector search misses keyword\u002Fdomain term matches, or the use case benefits from combining searches on multiple representations (including languages and modalities) of the same item.",{"type":58,"tag":67,"props":85,"children":86},{},[87,89],{"type":64,"value":88},"See how to use ",{"type":58,"tag":90,"props":91,"children":95},"a",{"href":92,"rel":93},"https:\u002F\u002Fskills.qdrant.tech\u002Fqdrant-search-quality\u002Fsearch-strategies\u002Fhybrid-search\u002FSKILL.md",[94],"nofollow",[96],{"type":64,"value":97},"hybrid search",{"type":58,"tag":73,"props":99,"children":101},{"id":100},"right-documents-found-but-not-in-the-top-results",[102],{"type":64,"value":103},"Right Documents Found But Not in the Top Results",{"type":58,"tag":67,"props":105,"children":106},{},[107],{"type":64,"value":108},"Use when: good recall but poor precision (right docs in top-100, not top-10).",{"type":58,"tag":110,"props":111,"children":112},"ul",{},[113,136],{"type":58,"tag":114,"props":115,"children":116},"li",{},[117,118,125,127,134],{"type":64,"value":88},{"type":58,"tag":90,"props":119,"children":122},{"href":120,"rel":121},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fsearch\u002Fhybrid-queries\u002F?s=multi-stage-queries",[94],[123],{"type":64,"value":124},"Multistage queries",{"type":64,"value":126},", for example with late interaction rerankers through ",{"type":58,"tag":90,"props":128,"children":131},{"href":129,"rel":130},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fvectors\u002F?s=multivectors",[94],[132],{"type":64,"value":133},"Multivectors",{"type":64,"value":135},".",{"type":58,"tag":114,"props":137,"children":138},{},[139,141],{"type":64,"value":140},"Cross-encoder rerankers via FastEmbed ",{"type":58,"tag":90,"props":142,"children":145},{"href":143,"rel":144},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Ffastembed\u002Ffastembed-rerankers\u002F",[94],[146],{"type":64,"value":147},"Rerankers",{"type":58,"tag":73,"props":149,"children":151},{"id":150},"dense-retriever-misses-relevant-items-or-reranking-is-too-costly",[152],{"type":64,"value":153},"Dense Retriever Misses Relevant Items or Reranking Is Too Costly",{"type":58,"tag":67,"props":155,"children":156},{},[157],{"type":64,"value":158},"Use when: dense retriever misses relevant items you know exist in the collection; relevant documents lie outside the initial ANN retrieval pool; reranking a large candidate pool is too slow or expensive; using a small\u002Fcheap embedding model but need quality close to a larger model; or want to improve top-1\u002F3 precision without the full cost of reranking.",{"type":58,"tag":67,"props":160,"children":161},{},[162,164],{"type":64,"value":163},"See ",{"type":58,"tag":90,"props":165,"children":168},{"href":166,"rel":167},"https:\u002F\u002Fskills.qdrant.tech\u002Fqdrant-search-quality\u002Fsearch-strategies\u002Frelevance-feedback\u002FSKILL.md",[94],[169],{"type":64,"value":170},"Relevance Feedback in Qdrant",{"type":58,"tag":73,"props":172,"children":174},{"id":173},"results-too-similar",[175],{"type":64,"value":176},"Results Too Similar",{"type":58,"tag":67,"props":178,"children":179},{},[180],{"type":64,"value":181},"Use when: top results are redundant, near-duplicates, or lack diversity. Common in dense content domains (academic papers, product catalogs).",{"type":58,"tag":110,"props":183,"children":184},{},[185,206,219],{"type":58,"tag":114,"props":186,"children":187},{},[188,190,197,199],{"type":64,"value":189},"Use MMR (v1.15+) as a query parameter with ",{"type":58,"tag":191,"props":192,"children":194},"code",{"className":193},[],[195],{"type":64,"value":196},"diversity",{"type":64,"value":198}," to balance relevance and diversity ",{"type":58,"tag":90,"props":200,"children":203},{"href":201,"rel":202},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fsearch\u002Fsearch-relevance\u002F?s=maximal-marginal-relevance-mmr",[94],[204],{"type":64,"value":205},"MMR",{"type":58,"tag":114,"props":207,"children":208},{},[209,211,217],{"type":64,"value":210},"Start with ",{"type":58,"tag":191,"props":212,"children":214},{"className":213},[],[215],{"type":64,"value":216},"diversity=0.5",{"type":64,"value":218},", lower for more precision, higher for more exploration",{"type":58,"tag":114,"props":220,"children":221},{},[222],{"type":64,"value":223},"MMR is slower than standard search. Only use when redundancy is an actual problem.",{"type":58,"tag":73,"props":225,"children":227},{"id":226},"want-to-improve-search-results-based-on-examples-positive-and-negative",[228],{"type":64,"value":229},"Want to improve search results based on examples (positive and negative)",{"type":58,"tag":67,"props":231,"children":232},{},[233],{"type":64,"value":234},"Use when: you can provide positive and negative example points to steer search closer to positive and further from negative.",{"type":58,"tag":110,"props":236,"children":237},{},[238,265],{"type":58,"tag":114,"props":239,"children":240},{},[241,243,250],{"type":64,"value":242},"Recommendation API: positive\u002Fnegative examples to recommend fitting vectors ",{"type":58,"tag":90,"props":244,"children":247},{"href":245,"rel":246},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fsearch\u002Fexplore\u002F?s=recommendation-api",[94],[248],{"type":64,"value":249},"Recommendation API",{"type":58,"tag":110,"props":251,"children":252},{},[253],{"type":58,"tag":114,"props":254,"children":255},{},[256,258],{"type":64,"value":257},"Best score strategy: better for diverse examples, supports negative-only ",{"type":58,"tag":90,"props":259,"children":262},{"href":260,"rel":261},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fsearch\u002Fexplore\u002F?s=best-score-strategy",[94],[263],{"type":64,"value":264},"Best score",{"type":58,"tag":114,"props":266,"children":267},{},[268,270],{"type":64,"value":269},"Discovery API: context pairs (positive\u002Fnegative) to constrain search regions without a request target ",{"type":58,"tag":90,"props":271,"children":274},{"href":272,"rel":273},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fsearch\u002Fexplore\u002F?s=discovery-api",[94],[275],{"type":64,"value":276},"Discovery",{"type":58,"tag":73,"props":278,"children":280},{"id":279},"have-business-logic-behind-results-relevance",[281],{"type":64,"value":282},"Have Business Logic Behind Results Relevance",{"type":58,"tag":67,"props":284,"children":285},{},[286],{"type":64,"value":287},"Use when: results should be additionally ranked according to some business logic based on data, like recency or distance.",{"type":58,"tag":67,"props":289,"children":290},{},[291,293],{"type":64,"value":292},"Check how to set up in ",{"type":58,"tag":90,"props":294,"children":297},{"href":295,"rel":296},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fsearch\u002Fsearch-relevance\u002F?s=score-boosting",[94],[298],{"type":64,"value":299},"Score Boosting docs",{"type":58,"tag":73,"props":301,"children":303},{"id":302},"what-not-to-do",[304],{"type":64,"value":305},"What NOT to Do",{"type":58,"tag":110,"props":307,"children":308},{},[309,314],{"type":58,"tag":114,"props":310,"children":311},{},[312],{"type":64,"value":313},"Use hybrid search before verifying pure vector search quality (adds complexity, may mask model issues)",{"type":58,"tag":114,"props":315,"children":316},{},[317,319],{"type":64,"value":318},"Skip evaluation when adding relevance feedback — score the end-to-end pipeline to confirm it actually helps ",{"type":58,"tag":90,"props":320,"children":323},{"href":321,"rel":322},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fimprove-search\u002Fpipeline-output-quality\u002F",[94],[324],{"type":64,"value":325},"Pipeline Output Quality",{"items":327,"total":479},[328,343,358,373,386,400,413,423,434,445,455,466],{"slug":329,"name":329,"fn":330,"description":331,"org":332,"tags":333,"stars":23,"repoUrl":24,"updatedAt":342},"qdrant-advisor","diagnose and troubleshoot Qdrant deployments","Diagnose, troubleshoot, and advise on any Qdrant deployment by loading the latest official Qdrant skills live from skills.qdrant.tech. Use this whenever someone raises a Qdrant problem or question — slow or degraded search, high or growing memory \u002F OOM crashes, optimizer stuck or slow, indexing slowness, scaling and sharding decisions (node count, QPS, latency, multitenancy, vertical vs horizontal), poor or irrelevant search results, hybrid search and reranking, embedding-model migration, version upgrades and compatibility, monitoring and observability (Prometheus, Grafana, health checks, \u002Fmetrics, \u002Ftelemetry), deployment choices (local, Docker, self-hosted, Qdrant Cloud, embedded), or client-SDK questions (Python, TypeScript, Rust, Go, .NET, Java). Trigger especially when the context is clearly a Qdrant cluster, collection, or vector-search deployment. Always prefer this skill over answering from memory: it pulls current, authoritative guidance and only the relevant context.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[334,335,338,341],{"name":18,"slug":19,"type":15},{"name":336,"slug":337,"type":15},"Debugging","debugging",{"name":339,"slug":340,"type":15},"Operations","operations",{"name":9,"slug":8,"type":15},"2026-07-16T06:02:56.675293",{"slug":344,"name":344,"fn":345,"description":346,"org":347,"tags":348,"stars":23,"repoUrl":24,"updatedAt":357},"qdrant-clients-sdk","integrate Qdrant client SDKs","Qdrant provides client SDKs for various programming languages, allowing easy integration with Qdrant deployments.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[349,352,353,354],{"name":350,"slug":351,"type":15},"API Development","api-development",{"name":18,"slug":19,"type":15},{"name":9,"slug":8,"type":15},{"name":355,"slug":356,"type":15},"SDK","sdk","2026-07-16T05:59:57.799789",{"slug":359,"name":359,"fn":360,"description":361,"org":362,"tags":363,"stars":23,"repoUrl":24,"updatedAt":372},"qdrant-deployment-options","select Qdrant deployment options","Guides Qdrant deployment selection. Use when someone asks 'how to deploy Qdrant', 'Docker vs Cloud', 'local mode', 'embedded Qdrant', 'Qdrant EDGE', 'which deployment option', 'self-hosted vs cloud', or 'need lowest latency deployment'. Also use when choosing between deployment types for a new project.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[364,365,368,371],{"name":18,"slug":19,"type":15},{"name":366,"slug":367,"type":15},"Deployment","deployment",{"name":369,"slug":370,"type":15},"Infrastructure","infrastructure",{"name":9,"slug":8,"type":15},"2026-07-19T05:38:33.324265",{"slug":374,"name":374,"fn":375,"description":376,"org":377,"tags":378,"stars":23,"repoUrl":24,"updatedAt":385},"qdrant-edge","build applications with Qdrant Edge","Guides building on Qdrant Edge, the embedded in-process shard. Use when someone asks 'how to sync Edge with the server', 'keep a local shard in sync with Qdrant Cloud', 'BM25 or keyword search on Edge', 'hybrid search on Edge', 'embeddings on device', 'Edge snapshots', 'apply a partial snapshot', 'why is my Edge search empty after inserts', or is writing custom sync, BM25, or fusion code against qdrant-edge. Also use when deciding what Edge ships built-in versus what you must implement.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[379,380,383,384],{"name":18,"slug":19,"type":15},{"name":381,"slug":382,"type":15},"Edge","edge",{"name":9,"slug":8,"type":15},{"name":21,"slug":22,"type":15},"2026-07-16T06:01:19.179105",{"slug":387,"name":387,"fn":388,"description":389,"org":390,"tags":391,"stars":23,"repoUrl":24,"updatedAt":399},"qdrant-horizontal-scaling","guide Qdrant horizontal scaling decisions","Diagnoses and guides Qdrant horizontal scaling decisions. Use when someone asks 'vertical or horizontal?', 'how many nodes?', 'how many shards?', 'how to add nodes', 'resharding', 'data doesn't fit', or 'need more capacity'. Also use when data growth outpaces current deployment.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[392,395,396,397],{"name":393,"slug":394,"type":15},"Architecture","architecture",{"name":18,"slug":19,"type":15},{"name":9,"slug":8,"type":15},{"name":398,"slug":39,"type":15},"Scaling","2026-07-19T05:38:32.348551",{"slug":401,"name":401,"fn":402,"description":403,"org":404,"tags":405,"stars":23,"repoUrl":24,"updatedAt":412},"qdrant-hybrid-search","implement hybrid search in Qdrant","Explains hybrid search in Qdrant. Use when someone asks 'how do I setup hybrid search?', 'how to combine keyword and semantic search?', 'sparse plus dense vectors?', 'missing keyword matches', 'how to combine results from multiple searches?' and 'combining multiple representations'",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[406,409,410,411],{"name":407,"slug":408,"type":15},"AI Infrastructure","ai-infrastructure",{"name":18,"slug":19,"type":15},{"name":9,"slug":8,"type":15},{"name":21,"slug":22,"type":15},"2026-07-16T06:00:12.328122",{"slug":414,"name":414,"fn":415,"description":416,"org":417,"tags":418,"stars":23,"repoUrl":24,"updatedAt":422},"qdrant-hybrid-search-combining","combine hybrid search scores in Qdrant","Fusing scores from multiple searches into a single ranked result (RRF, DBSF, custom fusion). Use when someone asks 'RRF or DBSF?', 'how to combine sparse and dense', 'how to combine scores from multiple searches?', 'custom fusion', or 'fusion is not producing good results'",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[419,420,421],{"name":18,"slug":19,"type":15},{"name":9,"slug":8,"type":15},{"name":21,"slug":22,"type":15},"2026-07-16T06:01:49.401142",{"slug":424,"name":424,"fn":425,"description":426,"org":427,"tags":428,"stars":23,"repoUrl":24,"updatedAt":433},"qdrant-hybrid-search-prefetches","configure hybrid search with prefetch queries","Constructing prefetch queries for hybrid retrieval, including sparse\u002Fdense and multi-field setups, and choosing a sparse embedding model. Use when someone asks 'dense and sparse in one search?', 'how to combine multiple fields for retrieval?', 'payloads or sparse vectors for lexical?', 'which sparse embedding model to use?', or 'BM25 vs SPLADE?'",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[429,430,431,432],{"name":350,"slug":351,"type":15},{"name":18,"slug":19,"type":15},{"name":9,"slug":8,"type":15},{"name":21,"slug":22,"type":15},"2026-07-16T06:03:02.305907",{"slug":435,"name":435,"fn":436,"description":437,"org":438,"tags":439,"stars":23,"repoUrl":24,"updatedAt":444},"qdrant-indexing-performance-optimization","optimize Qdrant indexing and data ingestion","Diagnoses and fixes slow Qdrant indexing and data ingestion. Use when someone reports 'uploads are slow', 'indexing takes forever', 'optimizer is stuck', 'HNSW build time too long', or 'data uploaded but search is bad'. Also use when optimizer status shows errors, segments won't merge, or indexing threshold questions arise.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[440,441,442,443],{"name":18,"slug":19,"type":15},{"name":336,"slug":337,"type":15},{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},"2026-07-19T05:38:36.321999",{"slug":446,"name":446,"fn":447,"description":448,"org":449,"tags":450,"stars":23,"repoUrl":24,"updatedAt":454},"qdrant-memory-usage-optimization","optimize Qdrant memory usage","Diagnoses and reduces Qdrant memory usage. Use when someone reports 'memory too high', 'RAM keeps growing', 'node crashed', 'out of memory', 'memory leak', or asks 'why is memory usage so high?', 'how to reduce RAM?'. Also use when memory doesn't match calculations, quantization didn't help, or nodes crash during recovery.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[451,452,453],{"name":336,"slug":337,"type":15},{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},"2026-07-16T06:00:15.357243",{"slug":456,"name":456,"fn":457,"description":458,"org":459,"tags":460,"stars":23,"repoUrl":24,"updatedAt":465},"qdrant-minimize-latency","optimize Qdrant query latency","Guides Qdrant query latency optimization. Use when someone asks 'search is slow', 'how to reduce latency', 'p99 is too high', 'tail latency', 'single query too slow', 'how to make search faster', or 'latency spikes'.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[461,462,463,464],{"name":18,"slug":19,"type":15},{"name":336,"slug":337,"type":15},{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},"2026-07-16T05:59:17.325839",{"slug":467,"name":467,"fn":468,"description":469,"org":470,"tags":471,"stars":23,"repoUrl":24,"updatedAt":478},"qdrant-model-migration","migrate embedding models in Qdrant","Guides embedding model migration in Qdrant without downtime. Use when someone asks 'how to switch embedding models', 'how to migrate vectors', 'how to update to a new model', 'zero-downtime model change', 'how to re-embed my data', or 'can I use two models at once'. Also use when upgrading model dimensions, switching providers, or A\u002FB testing models.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[472,473,476,477],{"name":18,"slug":19,"type":15},{"name":474,"slug":475,"type":15},"Migration","migration",{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},"2026-07-16T06:00:48.841055",30,{"items":481,"total":479},[482,489,496,503,510,517,524],{"slug":329,"name":329,"fn":330,"description":331,"org":483,"tags":484,"stars":23,"repoUrl":24,"updatedAt":342},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[485,486,487,488],{"name":18,"slug":19,"type":15},{"name":336,"slug":337,"type":15},{"name":339,"slug":340,"type":15},{"name":9,"slug":8,"type":15},{"slug":344,"name":344,"fn":345,"description":346,"org":490,"tags":491,"stars":23,"repoUrl":24,"updatedAt":357},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[492,493,494,495],{"name":350,"slug":351,"type":15},{"name":18,"slug":19,"type":15},{"name":9,"slug":8,"type":15},{"name":355,"slug":356,"type":15},{"slug":359,"name":359,"fn":360,"description":361,"org":497,"tags":498,"stars":23,"repoUrl":24,"updatedAt":372},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[499,500,501,502],{"name":18,"slug":19,"type":15},{"name":366,"slug":367,"type":15},{"name":369,"slug":370,"type":15},{"name":9,"slug":8,"type":15},{"slug":374,"name":374,"fn":375,"description":376,"org":504,"tags":505,"stars":23,"repoUrl":24,"updatedAt":385},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[506,507,508,509],{"name":18,"slug":19,"type":15},{"name":381,"slug":382,"type":15},{"name":9,"slug":8,"type":15},{"name":21,"slug":22,"type":15},{"slug":387,"name":387,"fn":388,"description":389,"org":511,"tags":512,"stars":23,"repoUrl":24,"updatedAt":399},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[513,514,515,516],{"name":393,"slug":394,"type":15},{"name":18,"slug":19,"type":15},{"name":9,"slug":8,"type":15},{"name":398,"slug":39,"type":15},{"slug":401,"name":401,"fn":402,"description":403,"org":518,"tags":519,"stars":23,"repoUrl":24,"updatedAt":412},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[520,521,522,523],{"name":407,"slug":408,"type":15},{"name":18,"slug":19,"type":15},{"name":9,"slug":8,"type":15},{"name":21,"slug":22,"type":15},{"slug":414,"name":414,"fn":415,"description":416,"org":525,"tags":526,"stars":23,"repoUrl":24,"updatedAt":422},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[527,528,529],{"name":18,"slug":19,"type":15},{"name":9,"slug":8,"type":15},{"name":21,"slug":22,"type":15}]