[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-qdrant-qdrant-monitoring-debugging":3,"mdc--f973gs-key":51,"related-repo-qdrant-qdrant-monitoring-debugging":367,"related-org-qdrant-qdrant-monitoring-debugging":465},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":26,"repoUrl":27,"updatedAt":28,"license":29,"forks":30,"topics":31,"repo":46,"sourceUrl":49,"mdContent":50},"qdrant-monitoring-debugging","monitor and debug Qdrant production issues","Diagnoses Qdrant production issues using metrics and observability tools. Use when someone reports 'optimizer stuck', 'indexing too slow', 'memory too high', 'OOM crash', 'queries are slow', 'latency spike', or 'search was fast now it's slow'. Also use when performance degrades without obvious config changes.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"qdrant","Qdrant","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fqdrant.png",[12,16,19,20,23],{"name":13,"slug":14,"type":15},"Observability","observability","tag",{"name":17,"slug":18,"type":15},"Monitoring","monitoring",{"name":9,"slug":8,"type":15},{"name":21,"slug":22,"type":15},"Database","database",{"name":24,"slug":25,"type":15},"Debugging","debugging",197,"https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fskills","2026-07-16T06:02:57.030857",null,23,[32,33,34,35,36,37,38,18,39,40,8,41,42,43,44,45],"agent-skills","ai-agents","claude-code","codex","cursor","embeddings","hybrid-search","multitenancy","performance","quantization","scaling","search-quality","vector-database","vector-search",{"repoUrl":27,"stars":26,"forks":30,"topics":47,"description":48},[32,33,34,35,36,37,38,18,39,40,8,41,42,43,44,45],"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-monitoring\u002Fdebugging","---\nname: qdrant-monitoring-debugging\ndescription: \"Diagnoses Qdrant production issues using metrics and observability tools. Use when someone reports 'optimizer stuck', 'indexing too slow', 'memory too high', 'OOM crash', 'queries are slow', 'latency spike', or 'search was fast now it's slow'. Also use when performance degrades without obvious config changes.\"\n---\n\n# How to Debug Qdrant with Metrics\n\nFirst check optimizer status. Most production issues trace back to active optimizations competing for resources. If optimizer is clean, check memory, then request metrics.\n\n\n## Optimizer Stuck or Too Slow\n\nUse when: optimizer running for hours, not finishing, or showing errors.\n\n- Use `\u002Fcollections\u002F{collection_name}\u002Foptimizations` endpoint (v1.17+) to check status [Optimization monitoring](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fops-optimization\u002Foptimizer\u002F?s=optimization-monitoring)\n- Query with optional detail flags: `?with=queued,completed,idle_segments`\n- Returns: queued optimizations count, active optimizer type, involved segments, progress tracking\n- Web UI has an Optimizations tab with timeline view and per-task duration metrics [Web UI](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fops-optimization\u002Foptimizer\u002F?s=web-ui)\n- If `optimizer_status` shows an error in collection info, check logs for disk full or corrupted segments\n- Large merges and HNSW rebuilds legitimately take hours on big datasets. Check progress before assuming it's stuck.\n\n\n## Memory Seems Too High\n\nUse when: memory exceeds expectations, node crashes with OOM, or memory keeps growing.\n\n- Process memory metrics available via `\u002Fmetrics` (RSS, allocated bytes, page faults)\n- Qdrant uses two types of RAM: resident memory (data structures, quantized vectors) and OS page cache (cached disk reads). Page cache filling available RAM is normal. [Memory article](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Farticles\u002Fmemory-consumption\u002F)\n- If resident memory (RSSAnon) exceeds 80% of total RAM, investigate\n- Check `\u002Ftelemetry` for per-collection breakdown of point counts and vector configurations\n- Estimate expected memory: `num_vectors * dimensions * 4 bytes * 1.5` for vectors, plus payload and index overhead [Capacity planning](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fcapacity-planning\u002F)\n- Common causes of unexpected growth: quantized vectors with `always_ram=true`, too many payload indexes, large `max_segment_size` during optimization\n\n\n## Queries Are Slow\n\nUse when: queries slower than expected and you need to identify the cause.\n\n- Track `rest_responses_avg_duration_seconds` and `rest_responses_max_duration_seconds` per endpoint\n- Use histogram metric `rest_responses_duration_seconds` (v1.8+) for percentile analysis in Grafana\n- Equivalent gRPC metrics with `grpc_responses_` prefix\n- Check optimizer status first. Active optimizations compete for CPU and I\u002FO, degrading search latency.\n- Check segment count via collection info. Too many unmerged segments after bulk upload causes slower search.\n- Compare filtered vs unfiltered query times. Large gap means missing payload index. [Payload index](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Findexing\u002F?s=payload-index)\n\n\n## What NOT to Do\n\n- Ignore optimizer status when debugging slow queries (most common root cause)\n- Assume memory leak when page cache fills RAM (normal OS behavior)\n- Make config changes while optimizer is running (causes cascading re-optimizations)\n- Blame Qdrant before checking if bulk upload just finished (unmerged segments)\n",{"data":52,"body":53},{"name":4,"description":6},{"type":54,"children":55},"root",[56,65,71,78,83,157,163,168,255,261,266,338,344],{"type":57,"tag":58,"props":59,"children":61},"element","h1",{"id":60},"how-to-debug-qdrant-with-metrics",[62],{"type":63,"value":64},"text","How to Debug Qdrant with Metrics",{"type":57,"tag":66,"props":67,"children":68},"p",{},[69],{"type":63,"value":70},"First check optimizer status. Most production issues trace back to active optimizations competing for resources. If optimizer is clean, check memory, then request metrics.",{"type":57,"tag":72,"props":73,"children":75},"h2",{"id":74},"optimizer-stuck-or-too-slow",[76],{"type":63,"value":77},"Optimizer Stuck or Too Slow",{"type":57,"tag":66,"props":79,"children":80},{},[81],{"type":63,"value":82},"Use when: optimizer running for hours, not finishing, or showing errors.",{"type":57,"tag":84,"props":85,"children":86},"ul",{},[87,111,122,127,139,152],{"type":57,"tag":88,"props":89,"children":90},"li",{},[91,93,100,102],{"type":63,"value":92},"Use ",{"type":57,"tag":94,"props":95,"children":97},"code",{"className":96},[],[98],{"type":63,"value":99},"\u002Fcollections\u002F{collection_name}\u002Foptimizations",{"type":63,"value":101}," endpoint (v1.17+) to check status ",{"type":57,"tag":103,"props":104,"children":108},"a",{"href":105,"rel":106},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fops-optimization\u002Foptimizer\u002F?s=optimization-monitoring",[107],"nofollow",[109],{"type":63,"value":110},"Optimization monitoring",{"type":57,"tag":88,"props":112,"children":113},{},[114,116],{"type":63,"value":115},"Query with optional detail flags: ",{"type":57,"tag":94,"props":117,"children":119},{"className":118},[],[120],{"type":63,"value":121},"?with=queued,completed,idle_segments",{"type":57,"tag":88,"props":123,"children":124},{},[125],{"type":63,"value":126},"Returns: queued optimizations count, active optimizer type, involved segments, progress tracking",{"type":57,"tag":88,"props":128,"children":129},{},[130,132],{"type":63,"value":131},"Web UI has an Optimizations tab with timeline view and per-task duration metrics ",{"type":57,"tag":103,"props":133,"children":136},{"href":134,"rel":135},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fops-optimization\u002Foptimizer\u002F?s=web-ui",[107],[137],{"type":63,"value":138},"Web UI",{"type":57,"tag":88,"props":140,"children":141},{},[142,144,150],{"type":63,"value":143},"If ",{"type":57,"tag":94,"props":145,"children":147},{"className":146},[],[148],{"type":63,"value":149},"optimizer_status",{"type":63,"value":151}," shows an error in collection info, check logs for disk full or corrupted segments",{"type":57,"tag":88,"props":153,"children":154},{},[155],{"type":63,"value":156},"Large merges and HNSW rebuilds legitimately take hours on big datasets. Check progress before assuming it's stuck.",{"type":57,"tag":72,"props":158,"children":160},{"id":159},"memory-seems-too-high",[161],{"type":63,"value":162},"Memory Seems Too High",{"type":57,"tag":66,"props":164,"children":165},{},[166],{"type":63,"value":167},"Use when: memory exceeds expectations, node crashes with OOM, or memory keeps growing.",{"type":57,"tag":84,"props":169,"children":170},{},[171,184,196,201,214,234],{"type":57,"tag":88,"props":172,"children":173},{},[174,176,182],{"type":63,"value":175},"Process memory metrics available via ",{"type":57,"tag":94,"props":177,"children":179},{"className":178},[],[180],{"type":63,"value":181},"\u002Fmetrics",{"type":63,"value":183}," (RSS, allocated bytes, page faults)",{"type":57,"tag":88,"props":185,"children":186},{},[187,189],{"type":63,"value":188},"Qdrant uses two types of RAM: resident memory (data structures, quantized vectors) and OS page cache (cached disk reads). Page cache filling available RAM is normal. ",{"type":57,"tag":103,"props":190,"children":193},{"href":191,"rel":192},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Farticles\u002Fmemory-consumption\u002F",[107],[194],{"type":63,"value":195},"Memory article",{"type":57,"tag":88,"props":197,"children":198},{},[199],{"type":63,"value":200},"If resident memory (RSSAnon) exceeds 80% of total RAM, investigate",{"type":57,"tag":88,"props":202,"children":203},{},[204,206,212],{"type":63,"value":205},"Check ",{"type":57,"tag":94,"props":207,"children":209},{"className":208},[],[210],{"type":63,"value":211},"\u002Ftelemetry",{"type":63,"value":213}," for per-collection breakdown of point counts and vector configurations",{"type":57,"tag":88,"props":215,"children":216},{},[217,219,225,227],{"type":63,"value":218},"Estimate expected memory: ",{"type":57,"tag":94,"props":220,"children":222},{"className":221},[],[223],{"type":63,"value":224},"num_vectors * dimensions * 4 bytes * 1.5",{"type":63,"value":226}," for vectors, plus payload and index overhead ",{"type":57,"tag":103,"props":228,"children":231},{"href":229,"rel":230},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fcapacity-planning\u002F",[107],[232],{"type":63,"value":233},"Capacity planning",{"type":57,"tag":88,"props":235,"children":236},{},[237,239,245,247,253],{"type":63,"value":238},"Common causes of unexpected growth: quantized vectors with ",{"type":57,"tag":94,"props":240,"children":242},{"className":241},[],[243],{"type":63,"value":244},"always_ram=true",{"type":63,"value":246},", too many payload indexes, large ",{"type":57,"tag":94,"props":248,"children":250},{"className":249},[],[251],{"type":63,"value":252},"max_segment_size",{"type":63,"value":254}," during optimization",{"type":57,"tag":72,"props":256,"children":258},{"id":257},"queries-are-slow",[259],{"type":63,"value":260},"Queries Are Slow",{"type":57,"tag":66,"props":262,"children":263},{},[264],{"type":63,"value":265},"Use when: queries slower than expected and you need to identify the cause.",{"type":57,"tag":84,"props":267,"children":268},{},[269,290,303,316,321,326],{"type":57,"tag":88,"props":270,"children":271},{},[272,274,280,282,288],{"type":63,"value":273},"Track ",{"type":57,"tag":94,"props":275,"children":277},{"className":276},[],[278],{"type":63,"value":279},"rest_responses_avg_duration_seconds",{"type":63,"value":281}," and ",{"type":57,"tag":94,"props":283,"children":285},{"className":284},[],[286],{"type":63,"value":287},"rest_responses_max_duration_seconds",{"type":63,"value":289}," per endpoint",{"type":57,"tag":88,"props":291,"children":292},{},[293,295,301],{"type":63,"value":294},"Use histogram metric ",{"type":57,"tag":94,"props":296,"children":298},{"className":297},[],[299],{"type":63,"value":300},"rest_responses_duration_seconds",{"type":63,"value":302}," (v1.8+) for percentile analysis in Grafana",{"type":57,"tag":88,"props":304,"children":305},{},[306,308,314],{"type":63,"value":307},"Equivalent gRPC metrics with ",{"type":57,"tag":94,"props":309,"children":311},{"className":310},[],[312],{"type":63,"value":313},"grpc_responses_",{"type":63,"value":315}," prefix",{"type":57,"tag":88,"props":317,"children":318},{},[319],{"type":63,"value":320},"Check optimizer status first. Active optimizations compete for CPU and I\u002FO, degrading search latency.",{"type":57,"tag":88,"props":322,"children":323},{},[324],{"type":63,"value":325},"Check segment count via collection info. Too many unmerged segments after bulk upload causes slower search.",{"type":57,"tag":88,"props":327,"children":328},{},[329,331],{"type":63,"value":330},"Compare filtered vs unfiltered query times. Large gap means missing payload index. ",{"type":57,"tag":103,"props":332,"children":335},{"href":333,"rel":334},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Findexing\u002F?s=payload-index",[107],[336],{"type":63,"value":337},"Payload index",{"type":57,"tag":72,"props":339,"children":341},{"id":340},"what-not-to-do",[342],{"type":63,"value":343},"What NOT to Do",{"type":57,"tag":84,"props":345,"children":346},{},[347,352,357,362],{"type":57,"tag":88,"props":348,"children":349},{},[350],{"type":63,"value":351},"Ignore optimizer status when debugging slow queries (most common root cause)",{"type":57,"tag":88,"props":353,"children":354},{},[355],{"type":63,"value":356},"Assume memory leak when page cache fills RAM (normal OS behavior)",{"type":57,"tag":88,"props":358,"children":359},{},[360],{"type":63,"value":361},"Make config changes while optimizer is running (causes cascading re-optimizations)",{"type":57,"tag":88,"props":363,"children":364},{},[365],{"type":63,"value":366},"Blame Qdrant before checking if bulk upload just finished (unmerged segments)",{"items":368,"total":464},[369,382,397,412,427,441,454],{"slug":370,"name":370,"fn":371,"description":372,"org":373,"tags":374,"stars":26,"repoUrl":27,"updatedAt":381},"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},[375,376,377,380],{"name":21,"slug":22,"type":15},{"name":24,"slug":25,"type":15},{"name":378,"slug":379,"type":15},"Operations","operations",{"name":9,"slug":8,"type":15},"2026-07-16T06:02:56.675293",{"slug":383,"name":383,"fn":384,"description":385,"org":386,"tags":387,"stars":26,"repoUrl":27,"updatedAt":396},"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},[388,391,392,393],{"name":389,"slug":390,"type":15},"API Development","api-development",{"name":21,"slug":22,"type":15},{"name":9,"slug":8,"type":15},{"name":394,"slug":395,"type":15},"SDK","sdk","2026-07-16T05:59:57.799789",{"slug":398,"name":398,"fn":399,"description":400,"org":401,"tags":402,"stars":26,"repoUrl":27,"updatedAt":411},"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},[403,404,407,410],{"name":21,"slug":22,"type":15},{"name":405,"slug":406,"type":15},"Deployment","deployment",{"name":408,"slug":409,"type":15},"Infrastructure","infrastructure",{"name":9,"slug":8,"type":15},"2026-07-19T05:38:33.324265",{"slug":413,"name":413,"fn":414,"description":415,"org":416,"tags":417,"stars":26,"repoUrl":27,"updatedAt":426},"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},[418,419,422,423],{"name":21,"slug":22,"type":15},{"name":420,"slug":421,"type":15},"Edge","edge",{"name":9,"slug":8,"type":15},{"name":424,"slug":425,"type":15},"Search","search","2026-07-16T06:01:19.179105",{"slug":428,"name":428,"fn":429,"description":430,"org":431,"tags":432,"stars":26,"repoUrl":27,"updatedAt":440},"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},[433,436,437,438],{"name":434,"slug":435,"type":15},"Architecture","architecture",{"name":21,"slug":22,"type":15},{"name":9,"slug":8,"type":15},{"name":439,"slug":42,"type":15},"Scaling","2026-07-19T05:38:32.348551",{"slug":442,"name":442,"fn":443,"description":444,"org":445,"tags":446,"stars":26,"repoUrl":27,"updatedAt":453},"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},[447,450,451,452],{"name":448,"slug":449,"type":15},"AI Infrastructure","ai-infrastructure",{"name":21,"slug":22,"type":15},{"name":9,"slug":8,"type":15},{"name":424,"slug":425,"type":15},"2026-07-16T06:00:12.328122",{"slug":455,"name":455,"fn":456,"description":457,"org":458,"tags":459,"stars":26,"repoUrl":27,"updatedAt":463},"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},[460,461,462],{"name":21,"slug":22,"type":15},{"name":9,"slug":8,"type":15},{"name":424,"slug":425,"type":15},"2026-07-16T06:01:49.401142",30,{"items":466,"total":464},[467,474,481,488,495,502,509,515,526,538,548,559],{"slug":370,"name":370,"fn":371,"description":372,"org":468,"tags":469,"stars":26,"repoUrl":27,"updatedAt":381},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[470,471,472,473],{"name":21,"slug":22,"type":15},{"name":24,"slug":25,"type":15},{"name":378,"slug":379,"type":15},{"name":9,"slug":8,"type":15},{"slug":383,"name":383,"fn":384,"description":385,"org":475,"tags":476,"stars":26,"repoUrl":27,"updatedAt":396},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[477,478,479,480],{"name":389,"slug":390,"type":15},{"name":21,"slug":22,"type":15},{"name":9,"slug":8,"type":15},{"name":394,"slug":395,"type":15},{"slug":398,"name":398,"fn":399,"description":400,"org":482,"tags":483,"stars":26,"repoUrl":27,"updatedAt":411},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[484,485,486,487],{"name":21,"slug":22,"type":15},{"name":405,"slug":406,"type":15},{"name":408,"slug":409,"type":15},{"name":9,"slug":8,"type":15},{"slug":413,"name":413,"fn":414,"description":415,"org":489,"tags":490,"stars":26,"repoUrl":27,"updatedAt":426},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[491,492,493,494],{"name":21,"slug":22,"type":15},{"name":420,"slug":421,"type":15},{"name":9,"slug":8,"type":15},{"name":424,"slug":425,"type":15},{"slug":428,"name":428,"fn":429,"description":430,"org":496,"tags":497,"stars":26,"repoUrl":27,"updatedAt":440},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[498,499,500,501],{"name":434,"slug":435,"type":15},{"name":21,"slug":22,"type":15},{"name":9,"slug":8,"type":15},{"name":439,"slug":42,"type":15},{"slug":442,"name":442,"fn":443,"description":444,"org":503,"tags":504,"stars":26,"repoUrl":27,"updatedAt":453},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[505,506,507,508],{"name":448,"slug":449,"type":15},{"name":21,"slug":22,"type":15},{"name":9,"slug":8,"type":15},{"name":424,"slug":425,"type":15},{"slug":455,"name":455,"fn":456,"description":457,"org":510,"tags":511,"stars":26,"repoUrl":27,"updatedAt":463},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[512,513,514],{"name":21,"slug":22,"type":15},{"name":9,"slug":8,"type":15},{"name":424,"slug":425,"type":15},{"slug":516,"name":516,"fn":517,"description":518,"org":519,"tags":520,"stars":26,"repoUrl":27,"updatedAt":525},"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},[521,522,523,524],{"name":389,"slug":390,"type":15},{"name":21,"slug":22,"type":15},{"name":9,"slug":8,"type":15},{"name":424,"slug":425,"type":15},"2026-07-16T06:03:02.305907",{"slug":527,"name":527,"fn":528,"description":529,"org":530,"tags":531,"stars":26,"repoUrl":27,"updatedAt":537},"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},[532,533,534,536],{"name":21,"slug":22,"type":15},{"name":24,"slug":25,"type":15},{"name":535,"slug":40,"type":15},"Performance",{"name":9,"slug":8,"type":15},"2026-07-19T05:38:36.321999",{"slug":539,"name":539,"fn":540,"description":541,"org":542,"tags":543,"stars":26,"repoUrl":27,"updatedAt":547},"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},[544,545,546],{"name":24,"slug":25,"type":15},{"name":535,"slug":40,"type":15},{"name":9,"slug":8,"type":15},"2026-07-16T06:00:15.357243",{"slug":549,"name":549,"fn":550,"description":551,"org":552,"tags":553,"stars":26,"repoUrl":27,"updatedAt":558},"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},[554,555,556,557],{"name":21,"slug":22,"type":15},{"name":24,"slug":25,"type":15},{"name":535,"slug":40,"type":15},{"name":9,"slug":8,"type":15},"2026-07-16T05:59:17.325839",{"slug":560,"name":560,"fn":561,"description":562,"org":563,"tags":564,"stars":26,"repoUrl":27,"updatedAt":571},"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},[565,566,569,570],{"name":21,"slug":22,"type":15},{"name":567,"slug":568,"type":15},"Migration","migration",{"name":535,"slug":40,"type":15},{"name":9,"slug":8,"type":15},"2026-07-16T06:00:48.841055"]