[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-github-qdrant-memory-usage-optimization":3,"mdc-lpopd-key":47,"related-repo-github-qdrant-memory-usage-optimization":365,"related-org-github-qdrant-memory-usage-optimization":466},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":28,"repoUrl":29,"updatedAt":30,"license":31,"forks":32,"topics":33,"repo":42,"sourceUrl":45,"mdContent":46},"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},"github","GitHub","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fgithub.png",[12,16,19,22,25],{"name":13,"slug":14,"type":15},"Observability","observability","tag",{"name":17,"slug":18,"type":15},"Performance","performance",{"name":20,"slug":21,"type":15},"Qdrant","qdrant",{"name":23,"slug":24,"type":15},"Cost Optimization","cost-optimization",{"name":26,"slug":27,"type":15},"Database","database",36978,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot","2026-04-18T04:46:01.525023",null,4632,[34,35,36,37,38,39,40,41],"agent-skills","agents","ai","awesome","custom-agents","github-copilot","hacktoberfest","prompt-engineering",{"repoUrl":29,"stars":28,"forks":32,"topics":43,"description":44},[34,35,36,37,38,39,40,41],"Community-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot.","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Ftree\u002FHEAD\u002Fskills\u002Fqdrant-performance-optimization\u002Fmemory-usage-optimization","---\nname: qdrant-memory-usage-optimization\ndescription: \"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.\"\n---\n\n# Understanding memory usage\n\nQdrant operates with two types of memory:\n\n- Resident memory (aka RSSAnon) - memory used for internal data structures like the ID tracker, plus components that must stay in RAM, such as quantized vectors when `always_ram=true` and payload indexes.\n\n- OS page cache - memory used for caching disk reads, which can be released when needed. Original vectors are normally stored in page cache, so the service won't crash if RAM is full, but performance may degrade.\n\nIt is normal for the OS page cache to occupy all available RAM, but if resident memory is above 80% of total RAM, it is a sign of a problem.\n\n## Memory usage monitoring\n\n- Qdrant exposes memory usage through the `\u002Fmetrics` endpoint. See [Monitoring docs](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Foperations\u002Fmonitoring\u002F).\n\n\u003C!-- ToDo: Talk about memory usage of each components once API is available -->\n\n\n## How much memory is needed for Qdrant?\n\nOptimal memory usage depends on the use case.\n\n- For regular search scenarios, general guidelines are provided in the [Capacity planning docs](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Foperations\u002Fcapacity-planning\u002F).\n\nFor a detailed breakdown of memory usage at large scale, see [Large scale memory usage example](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Ftutorials-operations\u002Flarge-scale-search\u002F?s=memory-usage).\n\nPayload indexes and HNSW graph also require memory, along with vectors themselves, so it's important to consider them in calculations.\n\nAdditionally, Qdrant requires some extra memory for optimizations. During optimization, optimized segments are fully loaded into RAM, so it is important to leave enough headroom.\nThe larger `max_segment_size` is, the more headroom is needed.\n\n\n### When to put HNSW index on disk\n\nPutting frequently used components (such as HNSW index) on disk might cause significant performance degradation.\nThere are some scenarios, however, when it can be a good option:\n\n- Deployments with low latency disks - local NVMe or similar.\n- Multi-tenant deployments, where only a subset of tenants is frequently accessed, so that only a fraction of data & index is loaded in RAM at a time.\n- For deployments with [inline storage](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Foperations\u002Foptimize\u002F?s=inline-storage-in-hnsw-index) enabled.\n\n\n## How to minimize memory footprint\n\nThe main challenge is to put on disk those parts of data, which are rarely accessed.\nHere are the main techniques to achieve that:\n\n- Use quantization to store only compressed vectors in RAM [Quantization docs](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fquantization\u002F)\n\n- Use float16 or int8 datatypes to reduce memory usage of vectors by 2x or 4x respectively, with some tradeoff in precision. Read more about vector datatypes in [documentation](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fvectors\u002F?s=datatypes)\n\n- Leverage Matryoshka Representation Learning (MRL) to store only small vectors in RAM while keeping large vectors on disk. Examples of how to use MRL with Qdrant Cloud inference: [MRL docs](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Finference\u002F?s=reduce-vector-dimensionality-with-matryoshka-models)\n\n- For multi-tenant deployments with small tenants, vectors might be stored on disk because the same tenant's data is stored together [Multitenancy docs](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fmultitenancy\u002F?s=calibrate-performance)\n\n- For deployments with fast local storage and relatively low requirements for search throughput, it may be possible to store all components of vector store on disk. Read more about the performance implications of on-disk storage in [the article](https:\u002F\u002Fqdrant.tech\u002Farticles\u002Fmemory-consumption\u002F)\n\n- For low RAM environments, consider `async_scorer` config, which enables support of `io_uring` for parallel disk access, which can significantly improve performance of on-disk storage. Read more about `async_scorer` in [the article](https:\u002F\u002Fqdrant.tech\u002Farticles\u002Fio_uring\u002F) (only available on Linux with kernel 5.11+)\n\n- Consider storing Sparse Vectors and text payload on disk, as they are usually more disk-friendly than dense vectors.\n- Configure payload indexes to be stored on disk [docs](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Findexing\u002F?s=on-disk-payload-index)\n- Configure sparse vectors to be stored on disk [docs](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Findexing\u002F?s=sparse-vector-index)\n\n",{"data":48,"body":49},{"name":4,"description":6},{"type":50,"children":51},"root",[52,61,67,91,96,103,130,136,141,157,170,175,188,195,200,227,233,238],{"type":53,"tag":54,"props":55,"children":57},"element","h1",{"id":56},"understanding-memory-usage",[58],{"type":59,"value":60},"text","Understanding memory usage",{"type":53,"tag":62,"props":63,"children":64},"p",{},[65],{"type":59,"value":66},"Qdrant operates with two types of memory:",{"type":53,"tag":68,"props":69,"children":70},"ul",{},[71,86],{"type":53,"tag":72,"props":73,"children":74},"li",{},[75,77,84],{"type":59,"value":76},"Resident memory (aka RSSAnon) - memory used for internal data structures like the ID tracker, plus components that must stay in RAM, such as quantized vectors when ",{"type":53,"tag":78,"props":79,"children":81},"code",{"className":80},[],[82],{"type":59,"value":83},"always_ram=true",{"type":59,"value":85}," and payload indexes.",{"type":53,"tag":72,"props":87,"children":88},{},[89],{"type":59,"value":90},"OS page cache - memory used for caching disk reads, which can be released when needed. Original vectors are normally stored in page cache, so the service won't crash if RAM is full, but performance may degrade.",{"type":53,"tag":62,"props":92,"children":93},{},[94],{"type":59,"value":95},"It is normal for the OS page cache to occupy all available RAM, but if resident memory is above 80% of total RAM, it is a sign of a problem.",{"type":53,"tag":97,"props":98,"children":100},"h2",{"id":99},"memory-usage-monitoring",[101],{"type":59,"value":102},"Memory usage monitoring",{"type":53,"tag":68,"props":104,"children":105},{},[106],{"type":53,"tag":72,"props":107,"children":108},{},[109,111,117,119,128],{"type":59,"value":110},"Qdrant exposes memory usage through the ",{"type":53,"tag":78,"props":112,"children":114},{"className":113},[],[115],{"type":59,"value":116},"\u002Fmetrics",{"type":59,"value":118}," endpoint. See ",{"type":53,"tag":120,"props":121,"children":125},"a",{"href":122,"rel":123},"https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Foperations\u002Fmonitoring\u002F",[124],"nofollow",[126],{"type":59,"value":127},"Monitoring docs",{"type":59,"value":129},".",{"type":53,"tag":97,"props":131,"children":133},{"id":132},"how-much-memory-is-needed-for-qdrant",[134],{"type":59,"value":135},"How much memory is needed for Qdrant?",{"type":53,"tag":62,"props":137,"children":138},{},[139],{"type":59,"value":140},"Optimal memory usage depends on the use case.",{"type":53,"tag":68,"props":142,"children":143},{},[144],{"type":53,"tag":72,"props":145,"children":146},{},[147,149,156],{"type":59,"value":148},"For regular search scenarios, general guidelines are provided in the ",{"type":53,"tag":120,"props":150,"children":153},{"href":151,"rel":152},"https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Foperations\u002Fcapacity-planning\u002F",[124],[154],{"type":59,"value":155},"Capacity planning docs",{"type":59,"value":129},{"type":53,"tag":62,"props":158,"children":159},{},[160,162,169],{"type":59,"value":161},"For a detailed breakdown of memory usage at large scale, see ",{"type":53,"tag":120,"props":163,"children":166},{"href":164,"rel":165},"https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Ftutorials-operations\u002Flarge-scale-search\u002F?s=memory-usage",[124],[167],{"type":59,"value":168},"Large scale memory usage example",{"type":59,"value":129},{"type":53,"tag":62,"props":171,"children":172},{},[173],{"type":59,"value":174},"Payload indexes and HNSW graph also require memory, along with vectors themselves, so it's important to consider them in calculations.",{"type":53,"tag":62,"props":176,"children":177},{},[178,180,186],{"type":59,"value":179},"Additionally, Qdrant requires some extra memory for optimizations. During optimization, optimized segments are fully loaded into RAM, so it is important to leave enough headroom.\nThe larger ",{"type":53,"tag":78,"props":181,"children":183},{"className":182},[],[184],{"type":59,"value":185},"max_segment_size",{"type":59,"value":187}," is, the more headroom is needed.",{"type":53,"tag":189,"props":190,"children":192},"h3",{"id":191},"when-to-put-hnsw-index-on-disk",[193],{"type":59,"value":194},"When to put HNSW index on disk",{"type":53,"tag":62,"props":196,"children":197},{},[198],{"type":59,"value":199},"Putting frequently used components (such as HNSW index) on disk might cause significant performance degradation.\nThere are some scenarios, however, when it can be a good option:",{"type":53,"tag":68,"props":201,"children":202},{},[203,208,213],{"type":53,"tag":72,"props":204,"children":205},{},[206],{"type":59,"value":207},"Deployments with low latency disks - local NVMe or similar.",{"type":53,"tag":72,"props":209,"children":210},{},[211],{"type":59,"value":212},"Multi-tenant deployments, where only a subset of tenants is frequently accessed, so that only a fraction of data & index is loaded in RAM at a time.",{"type":53,"tag":72,"props":214,"children":215},{},[216,218,225],{"type":59,"value":217},"For deployments with ",{"type":53,"tag":120,"props":219,"children":222},{"href":220,"rel":221},"https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Foperations\u002Foptimize\u002F?s=inline-storage-in-hnsw-index",[124],[223],{"type":59,"value":224},"inline storage",{"type":59,"value":226}," enabled.",{"type":53,"tag":97,"props":228,"children":230},{"id":229},"how-to-minimize-memory-footprint",[231],{"type":59,"value":232},"How to minimize memory footprint",{"type":53,"tag":62,"props":234,"children":235},{},[236],{"type":59,"value":237},"The main challenge is to put on disk those parts of data, which are rarely accessed.\nHere are the main techniques to achieve that:",{"type":53,"tag":68,"props":239,"children":240},{},[241,253,265,277,289,301,337,342,354],{"type":53,"tag":72,"props":242,"children":243},{},[244,246],{"type":59,"value":245},"Use quantization to store only compressed vectors in RAM ",{"type":53,"tag":120,"props":247,"children":250},{"href":248,"rel":249},"https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fquantization\u002F",[124],[251],{"type":59,"value":252},"Quantization docs",{"type":53,"tag":72,"props":254,"children":255},{},[256,258],{"type":59,"value":257},"Use float16 or int8 datatypes to reduce memory usage of vectors by 2x or 4x respectively, with some tradeoff in precision. Read more about vector datatypes in ",{"type":53,"tag":120,"props":259,"children":262},{"href":260,"rel":261},"https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fvectors\u002F?s=datatypes",[124],[263],{"type":59,"value":264},"documentation",{"type":53,"tag":72,"props":266,"children":267},{},[268,270],{"type":59,"value":269},"Leverage Matryoshka Representation Learning (MRL) to store only small vectors in RAM while keeping large vectors on disk. Examples of how to use MRL with Qdrant Cloud inference: ",{"type":53,"tag":120,"props":271,"children":274},{"href":272,"rel":273},"https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Finference\u002F?s=reduce-vector-dimensionality-with-matryoshka-models",[124],[275],{"type":59,"value":276},"MRL docs",{"type":53,"tag":72,"props":278,"children":279},{},[280,282],{"type":59,"value":281},"For multi-tenant deployments with small tenants, vectors might be stored on disk because the same tenant's data is stored together ",{"type":53,"tag":120,"props":283,"children":286},{"href":284,"rel":285},"https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fmultitenancy\u002F?s=calibrate-performance",[124],[287],{"type":59,"value":288},"Multitenancy docs",{"type":53,"tag":72,"props":290,"children":291},{},[292,294],{"type":59,"value":293},"For deployments with fast local storage and relatively low requirements for search throughput, it may be possible to store all components of vector store on disk. Read more about the performance implications of on-disk storage in ",{"type":53,"tag":120,"props":295,"children":298},{"href":296,"rel":297},"https:\u002F\u002Fqdrant.tech\u002Farticles\u002Fmemory-consumption\u002F",[124],[299],{"type":59,"value":300},"the article",{"type":53,"tag":72,"props":302,"children":303},{},[304,306,312,314,320,322,327,329,335],{"type":59,"value":305},"For low RAM environments, consider ",{"type":53,"tag":78,"props":307,"children":309},{"className":308},[],[310],{"type":59,"value":311},"async_scorer",{"type":59,"value":313}," config, which enables support of ",{"type":53,"tag":78,"props":315,"children":317},{"className":316},[],[318],{"type":59,"value":319},"io_uring",{"type":59,"value":321}," for parallel disk access, which can significantly improve performance of on-disk storage. Read more about ",{"type":53,"tag":78,"props":323,"children":325},{"className":324},[],[326],{"type":59,"value":311},{"type":59,"value":328}," in ",{"type":53,"tag":120,"props":330,"children":333},{"href":331,"rel":332},"https:\u002F\u002Fqdrant.tech\u002Farticles\u002Fio_uring\u002F",[124],[334],{"type":59,"value":300},{"type":59,"value":336}," (only available on Linux with kernel 5.11+)",{"type":53,"tag":72,"props":338,"children":339},{},[340],{"type":59,"value":341},"Consider storing Sparse Vectors and text payload on disk, as they are usually more disk-friendly than dense vectors.",{"type":53,"tag":72,"props":343,"children":344},{},[345,347],{"type":59,"value":346},"Configure payload indexes to be stored on disk ",{"type":53,"tag":120,"props":348,"children":351},{"href":349,"rel":350},"https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Findexing\u002F?s=on-disk-payload-index",[124],[352],{"type":59,"value":353},"docs",{"type":53,"tag":72,"props":355,"children":356},{},[357,359],{"type":59,"value":358},"Configure sparse vectors to be stored on disk ",{"type":53,"tag":120,"props":360,"children":363},{"href":361,"rel":362},"https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Findexing\u002F?s=sparse-vector-index",[124],[364],{"type":59,"value":353},{"items":366,"total":465},[367,385,401,409,423,439,453],{"slug":368,"name":368,"fn":369,"description":370,"org":371,"tags":372,"stars":28,"repoUrl":29,"updatedAt":384},"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},[373,376,379,382,383],{"name":374,"slug":375,"type":15},"AI Infrastructure","ai-infrastructure",{"name":377,"slug":378,"type":15},"Architecture","architecture",{"name":380,"slug":381,"type":15},"Capacity Planning","capacity-planning",{"name":26,"slug":27,"type":15},{"name":20,"slug":21,"type":15},"2026-04-18T04:46:16.349561",{"slug":386,"name":386,"fn":387,"description":388,"org":389,"tags":390,"stars":28,"repoUrl":29,"updatedAt":400},"qdrant-indexing-performance-optimization","optimize Qdrant indexing performance","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},[391,394,395,398,399],{"name":392,"slug":393,"type":15},"Data Engineering","data-engineering",{"name":26,"slug":27,"type":15},{"name":396,"slug":397,"type":15},"ETL","etl",{"name":17,"slug":18,"type":15},{"name":20,"slug":21,"type":15},"2026-04-18T04:46:02.766357",{"slug":4,"name":4,"fn":5,"description":6,"org":402,"tags":403,"stars":28,"repoUrl":29,"updatedAt":30},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[404,405,406,407,408],{"name":23,"slug":24,"type":15},{"name":26,"slug":27,"type":15},{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15},{"name":20,"slug":21,"type":15},{"slug":410,"name":410,"fn":411,"description":412,"org":413,"tags":414,"stars":28,"repoUrl":29,"updatedAt":422},"qdrant-minimize-latency","minimize 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},[415,416,417,418,419],{"name":377,"slug":378,"type":15},{"name":26,"slug":27,"type":15},{"name":17,"slug":18,"type":15},{"name":20,"slug":21,"type":15},{"name":420,"slug":421,"type":15},"Search","search","2026-04-18T04:46:10.126667",{"slug":424,"name":424,"fn":425,"description":426,"org":427,"tags":428,"stars":28,"repoUrl":29,"updatedAt":438},"qdrant-monitoring-debugging","debug Qdrant production issues with metrics","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},[429,432,435,436,437],{"name":430,"slug":431,"type":15},"Debugging","debugging",{"name":433,"slug":434,"type":15},"Monitoring","monitoring",{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15},{"name":20,"slug":21,"type":15},"2026-04-18T04:46:06.450784",{"slug":440,"name":440,"fn":441,"description":442,"org":443,"tags":444,"stars":28,"repoUrl":29,"updatedAt":452},"qdrant-monitoring-setup","set up Qdrant monitoring and alerting","Guides Qdrant monitoring setup including Prometheus scraping, health probes, Hybrid Cloud metrics, alerting, and log centralization. Use when someone asks 'how to set up monitoring', 'Prometheus config', 'Grafana dashboard', 'health check endpoints', 'how to scrape Hybrid Cloud', 'what alerts to set', 'how to centralize logs', or 'audit logging'.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[445,446,447,448,449],{"name":374,"slug":375,"type":15},{"name":433,"slug":434,"type":15},{"name":13,"slug":14,"type":15},{"name":20,"slug":21,"type":15},{"name":450,"slug":451,"type":15},"SRE","sre","2026-04-18T04:46:05.217192",{"slug":454,"name":454,"fn":455,"description":456,"org":457,"tags":458,"stars":28,"repoUrl":29,"updatedAt":464},"qdrant-scaling-data-volume","scale Qdrant data volume","Guides Qdrant data volume scaling decisions. Use when someone asks 'data doesn't fit on one node', 'too much data', 'need more storage', 'vertical or horizontal scaling', 'tenant scaling', 'time window rotation', or 'data growth exceeds capacity'.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[459,460,461,462,463],{"name":374,"slug":375,"type":15},{"name":377,"slug":378,"type":15},{"name":380,"slug":381,"type":15},{"name":26,"slug":27,"type":15},{"name":20,"slug":21,"type":15},"2026-04-18T04:46:07.684464",15,{"items":467,"total":588},[468,476,484,492,500,508,516,524,536,548,564,576],{"slug":368,"name":368,"fn":369,"description":370,"org":469,"tags":470,"stars":28,"repoUrl":29,"updatedAt":384},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[471,472,473,474,475],{"name":374,"slug":375,"type":15},{"name":377,"slug":378,"type":15},{"name":380,"slug":381,"type":15},{"name":26,"slug":27,"type":15},{"name":20,"slug":21,"type":15},{"slug":386,"name":386,"fn":387,"description":388,"org":477,"tags":478,"stars":28,"repoUrl":29,"updatedAt":400},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[479,480,481,482,483],{"name":392,"slug":393,"type":15},{"name":26,"slug":27,"type":15},{"name":396,"slug":397,"type":15},{"name":17,"slug":18,"type":15},{"name":20,"slug":21,"type":15},{"slug":4,"name":4,"fn":5,"description":6,"org":485,"tags":486,"stars":28,"repoUrl":29,"updatedAt":30},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[487,488,489,490,491],{"name":23,"slug":24,"type":15},{"name":26,"slug":27,"type":15},{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15},{"name":20,"slug":21,"type":15},{"slug":410,"name":410,"fn":411,"description":412,"org":493,"tags":494,"stars":28,"repoUrl":29,"updatedAt":422},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[495,496,497,498,499],{"name":377,"slug":378,"type":15},{"name":26,"slug":27,"type":15},{"name":17,"slug":18,"type":15},{"name":20,"slug":21,"type":15},{"name":420,"slug":421,"type":15},{"slug":424,"name":424,"fn":425,"description":426,"org":501,"tags":502,"stars":28,"repoUrl":29,"updatedAt":438},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[503,504,505,506,507],{"name":430,"slug":431,"type":15},{"name":433,"slug":434,"type":15},{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15},{"name":20,"slug":21,"type":15},{"slug":440,"name":440,"fn":441,"description":442,"org":509,"tags":510,"stars":28,"repoUrl":29,"updatedAt":452},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[511,512,513,514,515],{"name":374,"slug":375,"type":15},{"name":433,"slug":434,"type":15},{"name":13,"slug":14,"type":15},{"name":20,"slug":21,"type":15},{"name":450,"slug":451,"type":15},{"slug":454,"name":454,"fn":455,"description":456,"org":517,"tags":518,"stars":28,"repoUrl":29,"updatedAt":464},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[519,520,521,522,523],{"name":374,"slug":375,"type":15},{"name":377,"slug":378,"type":15},{"name":380,"slug":381,"type":15},{"name":26,"slug":27,"type":15},{"name":20,"slug":21,"type":15},{"slug":525,"name":525,"fn":526,"description":527,"org":528,"tags":529,"stars":28,"repoUrl":29,"updatedAt":535},"qdrant-scaling-qps","scale Qdrant query throughput","Guides Qdrant query throughput (QPS) scaling. Use when someone asks 'how to increase QPS', 'need more throughput', 'queries per second too low', 'batch search', 'read replicas', or 'how to handle more concurrent queries'.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[530,531,532,533,534],{"name":374,"slug":375,"type":15},{"name":377,"slug":378,"type":15},{"name":26,"slug":27,"type":15},{"name":17,"slug":18,"type":15},{"name":20,"slug":21,"type":15},"2026-04-18T04:46:08.905219",{"slug":537,"name":537,"fn":538,"description":539,"org":540,"tags":541,"stars":28,"repoUrl":29,"updatedAt":547},"qdrant-scaling-query-volume","scale Qdrant query volume and pagination","Guides Qdrant query volume scaling. Use when someone asks 'query returns too many results', 'scroll performance', 'large limit values', 'paginating search results', 'fetching many vectors', or 'high cardinality results'.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[542,543,544,545,546],{"name":377,"slug":378,"type":15},{"name":26,"slug":27,"type":15},{"name":17,"slug":18,"type":15},{"name":20,"slug":21,"type":15},{"name":420,"slug":421,"type":15},"2026-04-18T04:46:11.371326",{"slug":549,"name":549,"fn":550,"description":551,"org":552,"tags":553,"stars":28,"repoUrl":29,"updatedAt":563},"qdrant-search-quality-diagnosis","diagnose Qdrant search quality issues","Diagnoses Qdrant search quality issues. Use when someone reports 'results are bad', 'wrong results', 'not relevant results', 'missing matches', 'recall is low', 'approximate search worse than exact', 'which embedding model', or 'quality dropped after quantization'. Also use when search quality degrades without obvious changes.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[554,557,560,561,562],{"name":555,"slug":556,"type":15},"Analytics","analytics",{"name":558,"slug":559,"type":15},"Data Quality","data-quality",{"name":430,"slug":431,"type":15},{"name":20,"slug":21,"type":15},{"name":420,"slug":421,"type":15},"2026-04-18T04:46:17.579894",{"slug":565,"name":565,"fn":566,"description":567,"org":568,"tags":569,"stars":28,"repoUrl":29,"updatedAt":575},"qdrant-search-speed-optimization","optimize Qdrant search speed","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},[570,571,572,573,574],{"name":555,"slug":556,"type":15},{"name":26,"slug":27,"type":15},{"name":17,"slug":18,"type":15},{"name":20,"slug":21,"type":15},{"name":420,"slug":421,"type":15},"2026-04-18T04:46:03.987332",{"slug":577,"name":577,"fn":578,"description":579,"org":580,"tags":581,"stars":28,"repoUrl":29,"updatedAt":587},"qdrant-search-strategies","select optimal Qdrant search strategies","Guides Qdrant search strategy selection. Use when someone asks 'should I use hybrid search?', 'BM25 or sparse vectors?', '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', 'ColBERT reranking', or 'missing keyword matches'",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[582,583,584,585,586],{"name":374,"slug":375,"type":15},{"name":555,"slug":556,"type":15},{"name":377,"slug":378,"type":15},{"name":20,"slug":21,"type":15},{"name":420,"slug":421,"type":15},"2026-04-18T04:46:18.812306",45]