[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-qdrant-qdrant-search-speed-optimization":3,"mdc--vdpxws-key":51,"related-org-qdrant-qdrant-search-speed-optimization":494,"related-repo-qdrant-qdrant-search-speed-optimization":646},{"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-search-speed-optimization","optimize Qdrant search speed and latency","Diagnoses and fixes slow Qdrant search. Use when someone reports 'search is slow', 'high latency', 'queries take too long', 'low QPS', 'throughput too low', 'filtered search is slow', or 'search was fast but now it's slow'. Also use when search performance degrades after config changes or data growth.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"qdrant","Qdrant","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fqdrant.png",[12,16,17,20,23],{"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",{"name":24,"slug":25,"type":15},"Debugging","debugging",197,"https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fskills","2026-07-19T05:38:38.325016",null,23,[32,33,34,35,36,37,38,39,40,14,8,41,42,43,44,45],"agent-skills","ai-agents","claude-code","codex","cursor","embeddings","hybrid-search","monitoring","multitenancy","quantization","scaling","search-quality","vector-database","vector-search",{"repoUrl":27,"stars":26,"forks":30,"topics":47,"description":48},[32,33,34,35,36,37,38,39,40,14,8,41,42,43,44,45],"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-performance-optimization\u002Fsearch-speed-optimization","---\nname: qdrant-search-speed-optimization\ndescription: \"Diagnoses and fixes slow Qdrant search. Use when someone reports 'search is slow', 'high latency', 'queries take too long', 'low QPS', 'throughput too low', 'filtered search is slow', or 'search was fast but now it's slow'. Also use when search performance degrades after config changes or data growth.\"\n---\n\n# Diagnose a problem\n\nThere the multiple possible reasons for search performance degradation. The most common ones are:\n\n* Memory pressure: if the working set exceeds available RAM\n* Complex requests (e.g. high `hnsw_ef`, complex filters without payload index)\n* Competing background processes (e.g. optimizer still running after bulk upload)\n* Problem with the cluster (e.g. network issues, hardware degradation)\n\n\n## Single Query Too Slow (Latency)\n\nUse when: individual queries take too long regardless of load.\n\n### Diagnostic steps:\n\n- Check if second run of the same request is significantly faster (indicates memory pressure)\n- Try the same query with `with_payload: false` and `with_vectors: false` to see if payload retrieval is the bottleneck\n- If request uses filters, try to remove them one by one to identify if a specific filter condition is the bottleneck\n\n### Common fixes:\n\n- Tune HNSW parameters: [Fine-tuning search](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fops-optimization\u002Foptimize\u002F?s=fine-tuning-search-parameters)\n- Enable in-memory quantization: [Scalar quantization](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fquantization\u002F?s=scalar-quantization)\n- Reduce Vector Dimensionality with Matryoshka Models: [Matryoshka Models](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Finference\u002Fmatryoshka-models\u002F?s=reduce-vector-dimensionality-with-matryoshka-models)\n- Use oversampling + rescore for high-dimensional vectors [Search with quantization](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fquantization\u002F?s=searching-with-quantization)\n- Enable io_uring for disk-heavy workloads on Linux [io_uring](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Farticles\u002Fio_uring\u002F)\n\n\n## Can't Handle Enough QPS (Throughput)\n\nUse when: system can't serve enough queries per second under load.\n\n- Reduce segment count (`default_segment_number` to 2) [Maximizing throughput](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fops-optimization\u002Foptimize\u002F?s=maximizing-throughput)\n- Use batch search API instead of single queries [Batch search](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fsearch\u002Fsearch\u002F?s=batch-search-api)\n- Enable quantization to reduce CPU cost [Scalar quantization](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fquantization\u002F?s=scalar-quantization)\n- Add replicas to distribute read load [Replication](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fscaling\u002Fdistributed_deployment\u002F?s=replication)\n\n\n## Filtered Search Is Slow\n\nUse when: filtered search is significantly slower than unfiltered. Most common SA complaint after memory.\n\n- Create payload index on the filtered field [Payload index](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Findexing\u002F?s=payload-index)\n- Use `is_tenant=true` for primary filtering condition: [Tenant index](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Findexing\u002F?s=tenant-index)\n- Try ACORN algorithm for complex filters: [ACORN](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fsearch\u002Fsearch\u002F?s=acorn-search-algorithm)\n- Avoid using `nested` filtering conditions as a primary filter. It might force qdrant to read raw payload values instead of using index.\n- If payload index was added after HNSW build, trigger re-index to create filterable subgraph links\n\n\n## Optimize search performance with parallel updates\n\n### Diagnostic steps\n\n- Try to run the same query with `indexed_only=true` parameter, if the query is significantly faster, it means that the optimizer is still running and has not yet indexed all segments.\n- If CPU or IO usage is high even with no queries, it also indicates that the optimizer is still running.\n\n### Recommended configuration changes\n\n- reduce `optimizer_cpu_budget` to reserve more CPU for queries\n- Use `prevent_unoptimized=true` to prevent creating segments with a large amount of unindexed data for searches. Instead, once a segment reaches the so called indexing_threshold, all additional points will be added in ‘deferred state’. \n\nLearn more [here](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fsearch\u002Flow-latency-search\u002F?s=query-indexed-data-only)\n\n\n## What NOT to Do\n\n- Set `always_ram=false` on quantization (disk thrashing on every search)\n- Put HNSW on disk for latency-sensitive production (only for cold storage)\n- Increase segment count for throughput (opposite: fewer = better)\n- Create payload indexes on every field (wastes memory)\n- Blame Qdrant before checking optimizer status\n",{"data":52,"body":53},{"name":4,"description":6},{"type":54,"children":55},"root",[56,65,71,105,112,117,124,158,164,229,235,240,297,303,308,373,379,385,406,412,440,452,458],{"type":57,"tag":58,"props":59,"children":61},"element","h1",{"id":60},"diagnose-a-problem",[62],{"type":63,"value":64},"text","Diagnose a problem",{"type":57,"tag":66,"props":67,"children":68},"p",{},[69],{"type":63,"value":70},"There the multiple possible reasons for search performance degradation. The most common ones are:",{"type":57,"tag":72,"props":73,"children":74},"ul",{},[75,81,95,100],{"type":57,"tag":76,"props":77,"children":78},"li",{},[79],{"type":63,"value":80},"Memory pressure: if the working set exceeds available RAM",{"type":57,"tag":76,"props":82,"children":83},{},[84,86,93],{"type":63,"value":85},"Complex requests (e.g. high ",{"type":57,"tag":87,"props":88,"children":90},"code",{"className":89},[],[91],{"type":63,"value":92},"hnsw_ef",{"type":63,"value":94},", complex filters without payload index)",{"type":57,"tag":76,"props":96,"children":97},{},[98],{"type":63,"value":99},"Competing background processes (e.g. optimizer still running after bulk upload)",{"type":57,"tag":76,"props":101,"children":102},{},[103],{"type":63,"value":104},"Problem with the cluster (e.g. network issues, hardware degradation)",{"type":57,"tag":106,"props":107,"children":109},"h2",{"id":108},"single-query-too-slow-latency",[110],{"type":63,"value":111},"Single Query Too Slow (Latency)",{"type":57,"tag":66,"props":113,"children":114},{},[115],{"type":63,"value":116},"Use when: individual queries take too long regardless of load.",{"type":57,"tag":118,"props":119,"children":121},"h3",{"id":120},"diagnostic-steps",[122],{"type":63,"value":123},"Diagnostic steps:",{"type":57,"tag":72,"props":125,"children":126},{},[127,132,153],{"type":57,"tag":76,"props":128,"children":129},{},[130],{"type":63,"value":131},"Check if second run of the same request is significantly faster (indicates memory pressure)",{"type":57,"tag":76,"props":133,"children":134},{},[135,137,143,145,151],{"type":63,"value":136},"Try the same query with ",{"type":57,"tag":87,"props":138,"children":140},{"className":139},[],[141],{"type":63,"value":142},"with_payload: false",{"type":63,"value":144}," and ",{"type":57,"tag":87,"props":146,"children":148},{"className":147},[],[149],{"type":63,"value":150},"with_vectors: false",{"type":63,"value":152}," to see if payload retrieval is the bottleneck",{"type":57,"tag":76,"props":154,"children":155},{},[156],{"type":63,"value":157},"If request uses filters, try to remove them one by one to identify if a specific filter condition is the bottleneck",{"type":57,"tag":118,"props":159,"children":161},{"id":160},"common-fixes",[162],{"type":63,"value":163},"Common fixes:",{"type":57,"tag":72,"props":165,"children":166},{},[167,181,193,205,217],{"type":57,"tag":76,"props":168,"children":169},{},[170,172],{"type":63,"value":171},"Tune HNSW parameters: ",{"type":57,"tag":173,"props":174,"children":178},"a",{"href":175,"rel":176},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fops-optimization\u002Foptimize\u002F?s=fine-tuning-search-parameters",[177],"nofollow",[179],{"type":63,"value":180},"Fine-tuning search",{"type":57,"tag":76,"props":182,"children":183},{},[184,186],{"type":63,"value":185},"Enable in-memory quantization: ",{"type":57,"tag":173,"props":187,"children":190},{"href":188,"rel":189},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fquantization\u002F?s=scalar-quantization",[177],[191],{"type":63,"value":192},"Scalar quantization",{"type":57,"tag":76,"props":194,"children":195},{},[196,198],{"type":63,"value":197},"Reduce Vector Dimensionality with Matryoshka Models: ",{"type":57,"tag":173,"props":199,"children":202},{"href":200,"rel":201},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Finference\u002Fmatryoshka-models\u002F?s=reduce-vector-dimensionality-with-matryoshka-models",[177],[203],{"type":63,"value":204},"Matryoshka Models",{"type":57,"tag":76,"props":206,"children":207},{},[208,210],{"type":63,"value":209},"Use oversampling + rescore for high-dimensional vectors ",{"type":57,"tag":173,"props":211,"children":214},{"href":212,"rel":213},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fquantization\u002F?s=searching-with-quantization",[177],[215],{"type":63,"value":216},"Search with quantization",{"type":57,"tag":76,"props":218,"children":219},{},[220,222],{"type":63,"value":221},"Enable io_uring for disk-heavy workloads on Linux ",{"type":57,"tag":173,"props":223,"children":226},{"href":224,"rel":225},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Farticles\u002Fio_uring\u002F",[177],[227],{"type":63,"value":228},"io_uring",{"type":57,"tag":106,"props":230,"children":232},{"id":231},"cant-handle-enough-qps-throughput",[233],{"type":63,"value":234},"Can't Handle Enough QPS (Throughput)",{"type":57,"tag":66,"props":236,"children":237},{},[238],{"type":63,"value":239},"Use when: system can't serve enough queries per second under load.",{"type":57,"tag":72,"props":241,"children":242},{},[243,263,275,285],{"type":57,"tag":76,"props":244,"children":245},{},[246,248,254,256],{"type":63,"value":247},"Reduce segment count (",{"type":57,"tag":87,"props":249,"children":251},{"className":250},[],[252],{"type":63,"value":253},"default_segment_number",{"type":63,"value":255}," to 2) ",{"type":57,"tag":173,"props":257,"children":260},{"href":258,"rel":259},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fops-optimization\u002Foptimize\u002F?s=maximizing-throughput",[177],[261],{"type":63,"value":262},"Maximizing throughput",{"type":57,"tag":76,"props":264,"children":265},{},[266,268],{"type":63,"value":267},"Use batch search API instead of single queries ",{"type":57,"tag":173,"props":269,"children":272},{"href":270,"rel":271},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fsearch\u002Fsearch\u002F?s=batch-search-api",[177],[273],{"type":63,"value":274},"Batch search",{"type":57,"tag":76,"props":276,"children":277},{},[278,280],{"type":63,"value":279},"Enable quantization to reduce CPU cost ",{"type":57,"tag":173,"props":281,"children":283},{"href":188,"rel":282},[177],[284],{"type":63,"value":192},{"type":57,"tag":76,"props":286,"children":287},{},[288,290],{"type":63,"value":289},"Add replicas to distribute read load ",{"type":57,"tag":173,"props":291,"children":294},{"href":292,"rel":293},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fscaling\u002Fdistributed_deployment\u002F?s=replication",[177],[295],{"type":63,"value":296},"Replication",{"type":57,"tag":106,"props":298,"children":300},{"id":299},"filtered-search-is-slow",[301],{"type":63,"value":302},"Filtered Search Is Slow",{"type":57,"tag":66,"props":304,"children":305},{},[306],{"type":63,"value":307},"Use when: filtered search is significantly slower than unfiltered. Most common SA complaint after memory.",{"type":57,"tag":72,"props":309,"children":310},{},[311,323,343,355,368],{"type":57,"tag":76,"props":312,"children":313},{},[314,316],{"type":63,"value":315},"Create payload index on the filtered field ",{"type":57,"tag":173,"props":317,"children":320},{"href":318,"rel":319},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Findexing\u002F?s=payload-index",[177],[321],{"type":63,"value":322},"Payload index",{"type":57,"tag":76,"props":324,"children":325},{},[326,328,334,336],{"type":63,"value":327},"Use ",{"type":57,"tag":87,"props":329,"children":331},{"className":330},[],[332],{"type":63,"value":333},"is_tenant=true",{"type":63,"value":335}," for primary filtering condition: ",{"type":57,"tag":173,"props":337,"children":340},{"href":338,"rel":339},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Findexing\u002F?s=tenant-index",[177],[341],{"type":63,"value":342},"Tenant index",{"type":57,"tag":76,"props":344,"children":345},{},[346,348],{"type":63,"value":347},"Try ACORN algorithm for complex filters: ",{"type":57,"tag":173,"props":349,"children":352},{"href":350,"rel":351},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fsearch\u002Fsearch\u002F?s=acorn-search-algorithm",[177],[353],{"type":63,"value":354},"ACORN",{"type":57,"tag":76,"props":356,"children":357},{},[358,360,366],{"type":63,"value":359},"Avoid using ",{"type":57,"tag":87,"props":361,"children":363},{"className":362},[],[364],{"type":63,"value":365},"nested",{"type":63,"value":367}," filtering conditions as a primary filter. It might force qdrant to read raw payload values instead of using index.",{"type":57,"tag":76,"props":369,"children":370},{},[371],{"type":63,"value":372},"If payload index was added after HNSW build, trigger re-index to create filterable subgraph links",{"type":57,"tag":106,"props":374,"children":376},{"id":375},"optimize-search-performance-with-parallel-updates",[377],{"type":63,"value":378},"Optimize search performance with parallel updates",{"type":57,"tag":118,"props":380,"children":382},{"id":381},"diagnostic-steps-1",[383],{"type":63,"value":384},"Diagnostic steps",{"type":57,"tag":72,"props":386,"children":387},{},[388,401],{"type":57,"tag":76,"props":389,"children":390},{},[391,393,399],{"type":63,"value":392},"Try to run the same query with ",{"type":57,"tag":87,"props":394,"children":396},{"className":395},[],[397],{"type":63,"value":398},"indexed_only=true",{"type":63,"value":400}," parameter, if the query is significantly faster, it means that the optimizer is still running and has not yet indexed all segments.",{"type":57,"tag":76,"props":402,"children":403},{},[404],{"type":63,"value":405},"If CPU or IO usage is high even with no queries, it also indicates that the optimizer is still running.",{"type":57,"tag":118,"props":407,"children":409},{"id":408},"recommended-configuration-changes",[410],{"type":63,"value":411},"Recommended configuration changes",{"type":57,"tag":72,"props":413,"children":414},{},[415,428],{"type":57,"tag":76,"props":416,"children":417},{},[418,420,426],{"type":63,"value":419},"reduce ",{"type":57,"tag":87,"props":421,"children":423},{"className":422},[],[424],{"type":63,"value":425},"optimizer_cpu_budget",{"type":63,"value":427}," to reserve more CPU for queries",{"type":57,"tag":76,"props":429,"children":430},{},[431,432,438],{"type":63,"value":327},{"type":57,"tag":87,"props":433,"children":435},{"className":434},[],[436],{"type":63,"value":437},"prevent_unoptimized=true",{"type":63,"value":439}," to prevent creating segments with a large amount of unindexed data for searches. Instead, once a segment reaches the so called indexing_threshold, all additional points will be added in ‘deferred state’.",{"type":57,"tag":66,"props":441,"children":442},{},[443,445],{"type":63,"value":444},"Learn more ",{"type":57,"tag":173,"props":446,"children":449},{"href":447,"rel":448},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fsearch\u002Flow-latency-search\u002F?s=query-indexed-data-only",[177],[450],{"type":63,"value":451},"here",{"type":57,"tag":106,"props":453,"children":455},{"id":454},"what-not-to-do",[456],{"type":63,"value":457},"What NOT to Do",{"type":57,"tag":72,"props":459,"children":460},{},[461,474,479,484,489],{"type":57,"tag":76,"props":462,"children":463},{},[464,466,472],{"type":63,"value":465},"Set ",{"type":57,"tag":87,"props":467,"children":469},{"className":468},[],[470],{"type":63,"value":471},"always_ram=false",{"type":63,"value":473}," on quantization (disk thrashing on every search)",{"type":57,"tag":76,"props":475,"children":476},{},[477],{"type":63,"value":478},"Put HNSW on disk for latency-sensitive production (only for cold storage)",{"type":57,"tag":76,"props":480,"children":481},{},[482],{"type":63,"value":483},"Increase segment count for throughput (opposite: fewer = better)",{"type":57,"tag":76,"props":485,"children":486},{},[487],{"type":63,"value":488},"Create payload indexes on every field (wastes memory)",{"type":57,"tag":76,"props":490,"children":491},{},[492],{"type":63,"value":493},"Blame Qdrant before checking optimizer status",{"items":495,"total":645},[496,509,524,539,552,566,579,589,600,611,621,632],{"slug":497,"name":497,"fn":498,"description":499,"org":500,"tags":501,"stars":26,"repoUrl":27,"updatedAt":508},"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},[502,503,504,507],{"name":18,"slug":19,"type":15},{"name":24,"slug":25,"type":15},{"name":505,"slug":506,"type":15},"Operations","operations",{"name":9,"slug":8,"type":15},"2026-07-16T06:02:56.675293",{"slug":510,"name":510,"fn":511,"description":512,"org":513,"tags":514,"stars":26,"repoUrl":27,"updatedAt":523},"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},[515,518,519,520],{"name":516,"slug":517,"type":15},"API Development","api-development",{"name":18,"slug":19,"type":15},{"name":9,"slug":8,"type":15},{"name":521,"slug":522,"type":15},"SDK","sdk","2026-07-16T05:59:57.799789",{"slug":525,"name":525,"fn":526,"description":527,"org":528,"tags":529,"stars":26,"repoUrl":27,"updatedAt":538},"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},[530,531,534,537],{"name":18,"slug":19,"type":15},{"name":532,"slug":533,"type":15},"Deployment","deployment",{"name":535,"slug":536,"type":15},"Infrastructure","infrastructure",{"name":9,"slug":8,"type":15},"2026-07-19T05:38:33.324265",{"slug":540,"name":540,"fn":541,"description":542,"org":543,"tags":544,"stars":26,"repoUrl":27,"updatedAt":551},"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},[545,546,549,550],{"name":18,"slug":19,"type":15},{"name":547,"slug":548,"type":15},"Edge","edge",{"name":9,"slug":8,"type":15},{"name":21,"slug":22,"type":15},"2026-07-16T06:01:19.179105",{"slug":553,"name":553,"fn":554,"description":555,"org":556,"tags":557,"stars":26,"repoUrl":27,"updatedAt":565},"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},[558,561,562,563],{"name":559,"slug":560,"type":15},"Architecture","architecture",{"name":18,"slug":19,"type":15},{"name":9,"slug":8,"type":15},{"name":564,"slug":42,"type":15},"Scaling","2026-07-19T05:38:32.348551",{"slug":567,"name":567,"fn":568,"description":569,"org":570,"tags":571,"stars":26,"repoUrl":27,"updatedAt":578},"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},[572,575,576,577],{"name":573,"slug":574,"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":580,"name":580,"fn":581,"description":582,"org":583,"tags":584,"stars":26,"repoUrl":27,"updatedAt":588},"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},[585,586,587],{"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":590,"name":590,"fn":591,"description":592,"org":593,"tags":594,"stars":26,"repoUrl":27,"updatedAt":599},"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},[595,596,597,598],{"name":516,"slug":517,"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":601,"name":601,"fn":602,"description":603,"org":604,"tags":605,"stars":26,"repoUrl":27,"updatedAt":610},"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},[606,607,608,609],{"name":18,"slug":19,"type":15},{"name":24,"slug":25,"type":15},{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},"2026-07-19T05:38:36.321999",{"slug":612,"name":612,"fn":613,"description":614,"org":615,"tags":616,"stars":26,"repoUrl":27,"updatedAt":620},"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},[617,618,619],{"name":24,"slug":25,"type":15},{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},"2026-07-16T06:00:15.357243",{"slug":622,"name":622,"fn":623,"description":624,"org":625,"tags":626,"stars":26,"repoUrl":27,"updatedAt":631},"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},[627,628,629,630],{"name":18,"slug":19,"type":15},{"name":24,"slug":25,"type":15},{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},"2026-07-16T05:59:17.325839",{"slug":633,"name":633,"fn":634,"description":635,"org":636,"tags":637,"stars":26,"repoUrl":27,"updatedAt":644},"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},[638,639,642,643],{"name":18,"slug":19,"type":15},{"name":640,"slug":641,"type":15},"Migration","migration",{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},"2026-07-16T06:00:48.841055",30,{"items":647,"total":645},[648,655,662,669,676,683,690],{"slug":497,"name":497,"fn":498,"description":499,"org":649,"tags":650,"stars":26,"repoUrl":27,"updatedAt":508},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[651,652,653,654],{"name":18,"slug":19,"type":15},{"name":24,"slug":25,"type":15},{"name":505,"slug":506,"type":15},{"name":9,"slug":8,"type":15},{"slug":510,"name":510,"fn":511,"description":512,"org":656,"tags":657,"stars":26,"repoUrl":27,"updatedAt":523},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[658,659,660,661],{"name":516,"slug":517,"type":15},{"name":18,"slug":19,"type":15},{"name":9,"slug":8,"type":15},{"name":521,"slug":522,"type":15},{"slug":525,"name":525,"fn":526,"description":527,"org":663,"tags":664,"stars":26,"repoUrl":27,"updatedAt":538},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[665,666,667,668],{"name":18,"slug":19,"type":15},{"name":532,"slug":533,"type":15},{"name":535,"slug":536,"type":15},{"name":9,"slug":8,"type":15},{"slug":540,"name":540,"fn":541,"description":542,"org":670,"tags":671,"stars":26,"repoUrl":27,"updatedAt":551},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[672,673,674,675],{"name":18,"slug":19,"type":15},{"name":547,"slug":548,"type":15},{"name":9,"slug":8,"type":15},{"name":21,"slug":22,"type":15},{"slug":553,"name":553,"fn":554,"description":555,"org":677,"tags":678,"stars":26,"repoUrl":27,"updatedAt":565},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[679,680,681,682],{"name":559,"slug":560,"type":15},{"name":18,"slug":19,"type":15},{"name":9,"slug":8,"type":15},{"name":564,"slug":42,"type":15},{"slug":567,"name":567,"fn":568,"description":569,"org":684,"tags":685,"stars":26,"repoUrl":27,"updatedAt":578},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[686,687,688,689],{"name":573,"slug":574,"type":15},{"name":18,"slug":19,"type":15},{"name":9,"slug":8,"type":15},{"name":21,"slug":22,"type":15},{"slug":580,"name":580,"fn":581,"description":582,"org":691,"tags":692,"stars":26,"repoUrl":27,"updatedAt":588},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[693,694,695],{"name":18,"slug":19,"type":15},{"name":9,"slug":8,"type":15},{"name":21,"slug":22,"type":15}]