[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-qdrant-qdrant-multitenancy":3,"mdc-t6afl-key":49,"related-org-qdrant-qdrant-multitenancy":352,"related-repo-qdrant-qdrant-multitenancy":507},{"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":44,"sourceUrl":47,"mdContent":48},"qdrant-multitenancy","implement Qdrant multi-tenant architecture","Guides tenant isolation architecture in Qdrant for multi-tenant or multi-user applications. Use when someone asks 'how to isolate customer data', 'how to build multi-tenant search\u002FRAG', 'how many collections should I create', 'how to partition tenants by payload', 'a customer's data legally has to stay in a certain country or region'. Also use when they describe a symptom: one customer's data is way bigger than the rest and slowing everyone down, or one tenant is hogging resources.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"qdrant","Qdrant","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fqdrant.png",[12,14,17,20],{"name":9,"slug":8,"type":13},"tag",{"name":15,"slug":16,"type":13},"Database","database",{"name":18,"slug":19,"type":13},"Multi-Tenant","multi-tenant",{"name":21,"slug":22,"type":13},"Search","search",197,"https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fskills","2026-07-22T06:00:41.075958",null,23,[29,30,31,32,33,34,35,36,37,38,8,39,40,41,42,43],"agent-skills","ai-agents","claude-code","codex","cursor","embeddings","hybrid-search","monitoring","multitenancy","performance","quantization","scaling","search-quality","vector-database","vector-search",{"repoUrl":24,"stars":23,"forks":27,"topics":45,"description":46},[29,30,31,32,33,34,35,36,37,38,8,39,40,41,42,43],"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-multitenancy","---\nname: qdrant-multitenancy\ndescription: \"Guides tenant isolation architecture in Qdrant for multi-tenant or multi-user applications. Use when someone asks 'how to isolate customer data', 'how to build multi-tenant search\u002FRAG', 'how many collections should I create', 'how to partition tenants by payload', 'a customer's data legally has to stay in a certain country or region'. Also use when they describe a symptom: one customer's data is way bigger than the rest and slowing everyone down, or one tenant is hogging resources.\"\n---\n\n# Qdrant Multitenancy\n\n[Multitenancy](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fmultitenancy\u002F) is how you isolate data across multiple users or tenants within a single Qdrant deployment.\n\n- The question to ask is: **how many tenants, and how unevenly sized are they?** That answer picks the isolation strategy.\n- Understand the three isolation levels before choosing: payload-based, shard-based and collection-based.\n- For almost everyone the right default is a single collection partitioned by payload, NOT a collection per tenant.\n\n## Many Small Tenants (Default: Payload Partitioning)\n\nUse when: you have many tenants of roughly similar, modest size. This is the recommended default for most users.\n\nOne collection holds every tenant. A payload field marks ownership, and a filter on that field at query time is what isolates each tenant's results.\n\n### How It Works\n\n- Create a keyword payload index on the tenant field with `is_tenant=true` (the flag requires v1.11+). `is_tenant` tells Qdrant the field identifies tenants, so each tenant's vectors are stored together and served by sequential reads. Check [](https:\u002F\u002Fapi.qdrant.tech\u002Fapi-reference\u002Findexes\u002Fcreate-field-index).\n- At query time, isolate each tenant with a `must` filter on the tenant field. Without it, a query searches every tenant's data. Check [Payload-based multitenancy](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fmultitenancy\u002F?s=partition-by-payload).\n- With this strategy, the indexing speed might become a bottleneck at scale because every tenant indexes into the same collection. To avoid this, you can disable the global HNSW creation (for the entire collection) and only build per-tenant indexes: set `m=0` and `payload_m` to a non-zero value. Although this accelerates the indexing process, keep in mind that requests without a tenant filter will become slower as they must scan all groups. So only make this trade if you hit the bottleneck and cross-tenant search is rare. [Calibrate performance](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fmultitenancy\u002F?s=calibrate-performance).\n\n\n## A Few Large Tenants Plus a Long Tail (Tiered Multitenancy)\n\nUse when: you have a realistic SaaS distribution: a few large customers and many small ones, possibly with small tenants that grow over time. Available in v1.16+. It avoids the noisy-neighbor problem, where one big tenant forces the whole cluster to scale, raising costs and degrading performance for everyone else.\n\nTiered multitenancy keeps small tenants together in a shared fallback shard while isolating large tenants in their own dedicated shards, all in one collection. \nIt layers two isolation levels: payload-based tenancy for logical isolation, and custom sharding for physical\u002F resource-based isolation of the large tenants. A tenant that outgrows the shared shard can be promoted to a dedicated shard later with no downtime. \n\n### How It Works\n\n- Create the collection with custom (user-defined) sharding, and configure payload-based tenancy. A single shared fallback shard holds all the small tenants. If you have large tenants, create dedicated shards (one per tenant). Check [Tiered multitenancy](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fmultitenancy\u002F?s=tiered-multitenancy).\n- When to promote a tenant? If a tenant becomes large enough to warrant dedicated resources (a reasonable promotion trigger is when a tenant approaches the indexing threshold), promote it to a dedicated shard. Qdrant moves its data into a new shard transparently, serving reads and writes throughout. Check [how to promote tenant to dedicated shard](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fmultitenancy\u002F?s=promote-tenant-to-dedicated-shard).\n- Keep in mind that re-sharding can be an expensive and time-consuming process, so consider your tenant growth patterns carefully when deciding which tenants should receive dedicated shards.\n- It's not recommended to exceed ~1000 dedicated shards per cluster (resource overhead).\n- The fallback shard (small tenants) must fit on a single node.\n- Sharding method is fixed at collection creation: an auto-sharded collection (default) cannot be converted to custom sharding in place. If there is any realistic chance you will need to isolate a large tenant later, create the collection with custom sharding up front and put every tenant in the fallback shard.  \n\n\n## Few Non-Homogenous Tenants (Collection per Tenant)\n\nUse when: you have a limited number of tenants with different per-tenant embedding models or collection schemas.\n\n- You should only create multiple collections when your data is not homogenous or if users' vectors are created by different embedding models. \n\n\n## Data Residency and Geographic Isolation (Custom Sharding)\n\nUse when: data must be physically pinned to a location, e.g. regional compliance for healthcare industry (one region's data in Canada, another's in Germany). This is not only a tenant concern, a single tenant may also need to separate its own data by region.\n\n- Like tiered multitenancy, this uses custom sharding; the difference is what you shard by. Here the shard key is a region. Each key's data lands on specific shards you can place in specific locations, while everything stays in one collection. Combine it with payload partitioning if you also need per-tenant isolation within a region. Check [User-defined sharding](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fscaling\u002Fdistributed_deployment\u002F?s=user-defined-sharding) for setup.\n- Geographic residency follows only if your cluster's nodes are actually in the target regions. \n- Qdrant Cloud deploys a cluster in a single region and has no managed multi-region today.\n\n\n## What NOT to Do\n- Treat a payload filter as your whole security model. In Qdrant, (unless you're using per-tenant collections), tenant isolation is payload-based. It is an application-layer responsibility, and the filter is only one small part of it.\n",{"data":50,"body":51},{"name":4,"description":6},{"type":52,"children":53},"root",[54,62,77,105,112,117,122,129,211,217,222,227,232,281,287,292,300,306,311,338,344],{"type":55,"tag":56,"props":57,"children":58},"element","h1",{"id":4},[59],{"type":60,"value":61},"text","Qdrant Multitenancy",{"type":55,"tag":63,"props":64,"children":65},"p",{},[66,75],{"type":55,"tag":67,"props":68,"children":72},"a",{"href":69,"rel":70},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fmultitenancy\u002F",[71],"nofollow",[73],{"type":60,"value":74},"Multitenancy",{"type":60,"value":76}," is how you isolate data across multiple users or tenants within a single Qdrant deployment.",{"type":55,"tag":78,"props":79,"children":80},"ul",{},[81,95,100],{"type":55,"tag":82,"props":83,"children":84},"li",{},[85,87,93],{"type":60,"value":86},"The question to ask is: ",{"type":55,"tag":88,"props":89,"children":90},"strong",{},[91],{"type":60,"value":92},"how many tenants, and how unevenly sized are they?",{"type":60,"value":94}," That answer picks the isolation strategy.",{"type":55,"tag":82,"props":96,"children":97},{},[98],{"type":60,"value":99},"Understand the three isolation levels before choosing: payload-based, shard-based and collection-based.",{"type":55,"tag":82,"props":101,"children":102},{},[103],{"type":60,"value":104},"For almost everyone the right default is a single collection partitioned by payload, NOT a collection per tenant.",{"type":55,"tag":106,"props":107,"children":109},"h2",{"id":108},"many-small-tenants-default-payload-partitioning",[110],{"type":60,"value":111},"Many Small Tenants (Default: Payload Partitioning)",{"type":55,"tag":63,"props":113,"children":114},{},[115],{"type":60,"value":116},"Use when: you have many tenants of roughly similar, modest size. This is the recommended default for most users.",{"type":55,"tag":63,"props":118,"children":119},{},[120],{"type":60,"value":121},"One collection holds every tenant. A payload field marks ownership, and a filter on that field at query time is what isolates each tenant's results.",{"type":55,"tag":123,"props":124,"children":126},"h3",{"id":125},"how-it-works",[127],{"type":60,"value":128},"How It Works",{"type":55,"tag":78,"props":130,"children":131},{},[132,161,182],{"type":55,"tag":82,"props":133,"children":134},{},[135,137,144,146,152,154,159],{"type":60,"value":136},"Create a keyword payload index on the tenant field with ",{"type":55,"tag":138,"props":139,"children":141},"code",{"className":140},[],[142],{"type":60,"value":143},"is_tenant=true",{"type":60,"value":145}," (the flag requires v1.11+). ",{"type":55,"tag":138,"props":147,"children":149},{"className":148},[],[150],{"type":60,"value":151},"is_tenant",{"type":60,"value":153}," tells Qdrant the field identifies tenants, so each tenant's vectors are stored together and served by sequential reads. Check ",{"type":55,"tag":67,"props":155,"children":158},{"href":156,"rel":157},"https:\u002F\u002Fapi.qdrant.tech\u002Fapi-reference\u002Findexes\u002Fcreate-field-index",[71],[],{"type":60,"value":160},".",{"type":55,"tag":82,"props":162,"children":163},{},[164,166,172,174,181],{"type":60,"value":165},"At query time, isolate each tenant with a ",{"type":55,"tag":138,"props":167,"children":169},{"className":168},[],[170],{"type":60,"value":171},"must",{"type":60,"value":173}," filter on the tenant field. Without it, a query searches every tenant's data. Check ",{"type":55,"tag":67,"props":175,"children":178},{"href":176,"rel":177},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fmultitenancy\u002F?s=partition-by-payload",[71],[179],{"type":60,"value":180},"Payload-based multitenancy",{"type":60,"value":160},{"type":55,"tag":82,"props":183,"children":184},{},[185,187,193,195,201,203,210],{"type":60,"value":186},"With this strategy, the indexing speed might become a bottleneck at scale because every tenant indexes into the same collection. To avoid this, you can disable the global HNSW creation (for the entire collection) and only build per-tenant indexes: set ",{"type":55,"tag":138,"props":188,"children":190},{"className":189},[],[191],{"type":60,"value":192},"m=0",{"type":60,"value":194}," and ",{"type":55,"tag":138,"props":196,"children":198},{"className":197},[],[199],{"type":60,"value":200},"payload_m",{"type":60,"value":202}," to a non-zero value. Although this accelerates the indexing process, keep in mind that requests without a tenant filter will become slower as they must scan all groups. So only make this trade if you hit the bottleneck and cross-tenant search is rare. ",{"type":55,"tag":67,"props":204,"children":207},{"href":205,"rel":206},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fmultitenancy\u002F?s=calibrate-performance",[71],[208],{"type":60,"value":209},"Calibrate performance",{"type":60,"value":160},{"type":55,"tag":106,"props":212,"children":214},{"id":213},"a-few-large-tenants-plus-a-long-tail-tiered-multitenancy",[215],{"type":60,"value":216},"A Few Large Tenants Plus a Long Tail (Tiered Multitenancy)",{"type":55,"tag":63,"props":218,"children":219},{},[220],{"type":60,"value":221},"Use when: you have a realistic SaaS distribution: a few large customers and many small ones, possibly with small tenants that grow over time. Available in v1.16+. It avoids the noisy-neighbor problem, where one big tenant forces the whole cluster to scale, raising costs and degrading performance for everyone else.",{"type":55,"tag":63,"props":223,"children":224},{},[225],{"type":60,"value":226},"Tiered multitenancy keeps small tenants together in a shared fallback shard while isolating large tenants in their own dedicated shards, all in one collection.\nIt layers two isolation levels: payload-based tenancy for logical isolation, and custom sharding for physical\u002F resource-based isolation of the large tenants. A tenant that outgrows the shared shard can be promoted to a dedicated shard later with no downtime.",{"type":55,"tag":123,"props":228,"children":230},{"id":229},"how-it-works-1",[231],{"type":60,"value":128},{"type":55,"tag":78,"props":233,"children":234},{},[235,248,261,266,271,276],{"type":55,"tag":82,"props":236,"children":237},{},[238,240,247],{"type":60,"value":239},"Create the collection with custom (user-defined) sharding, and configure payload-based tenancy. A single shared fallback shard holds all the small tenants. If you have large tenants, create dedicated shards (one per tenant). Check ",{"type":55,"tag":67,"props":241,"children":244},{"href":242,"rel":243},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fmultitenancy\u002F?s=tiered-multitenancy",[71],[245],{"type":60,"value":246},"Tiered multitenancy",{"type":60,"value":160},{"type":55,"tag":82,"props":249,"children":250},{},[251,253,260],{"type":60,"value":252},"When to promote a tenant? If a tenant becomes large enough to warrant dedicated resources (a reasonable promotion trigger is when a tenant approaches the indexing threshold), promote it to a dedicated shard. Qdrant moves its data into a new shard transparently, serving reads and writes throughout. Check ",{"type":55,"tag":67,"props":254,"children":257},{"href":255,"rel":256},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fmultitenancy\u002F?s=promote-tenant-to-dedicated-shard",[71],[258],{"type":60,"value":259},"how to promote tenant to dedicated shard",{"type":60,"value":160},{"type":55,"tag":82,"props":262,"children":263},{},[264],{"type":60,"value":265},"Keep in mind that re-sharding can be an expensive and time-consuming process, so consider your tenant growth patterns carefully when deciding which tenants should receive dedicated shards.",{"type":55,"tag":82,"props":267,"children":268},{},[269],{"type":60,"value":270},"It's not recommended to exceed ~1000 dedicated shards per cluster (resource overhead).",{"type":55,"tag":82,"props":272,"children":273},{},[274],{"type":60,"value":275},"The fallback shard (small tenants) must fit on a single node.",{"type":55,"tag":82,"props":277,"children":278},{},[279],{"type":60,"value":280},"Sharding method is fixed at collection creation: an auto-sharded collection (default) cannot be converted to custom sharding in place. If there is any realistic chance you will need to isolate a large tenant later, create the collection with custom sharding up front and put every tenant in the fallback shard.",{"type":55,"tag":106,"props":282,"children":284},{"id":283},"few-non-homogenous-tenants-collection-per-tenant",[285],{"type":60,"value":286},"Few Non-Homogenous Tenants (Collection per Tenant)",{"type":55,"tag":63,"props":288,"children":289},{},[290],{"type":60,"value":291},"Use when: you have a limited number of tenants with different per-tenant embedding models or collection schemas.",{"type":55,"tag":78,"props":293,"children":294},{},[295],{"type":55,"tag":82,"props":296,"children":297},{},[298],{"type":60,"value":299},"You should only create multiple collections when your data is not homogenous or if users' vectors are created by different embedding models.",{"type":55,"tag":106,"props":301,"children":303},{"id":302},"data-residency-and-geographic-isolation-custom-sharding",[304],{"type":60,"value":305},"Data Residency and Geographic Isolation (Custom Sharding)",{"type":55,"tag":63,"props":307,"children":308},{},[309],{"type":60,"value":310},"Use when: data must be physically pinned to a location, e.g. regional compliance for healthcare industry (one region's data in Canada, another's in Germany). This is not only a tenant concern, a single tenant may also need to separate its own data by region.",{"type":55,"tag":78,"props":312,"children":313},{},[314,328,333],{"type":55,"tag":82,"props":315,"children":316},{},[317,319,326],{"type":60,"value":318},"Like tiered multitenancy, this uses custom sharding; the difference is what you shard by. Here the shard key is a region. Each key's data lands on specific shards you can place in specific locations, while everything stays in one collection. Combine it with payload partitioning if you also need per-tenant isolation within a region. Check ",{"type":55,"tag":67,"props":320,"children":323},{"href":321,"rel":322},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fscaling\u002Fdistributed_deployment\u002F?s=user-defined-sharding",[71],[324],{"type":60,"value":325},"User-defined sharding",{"type":60,"value":327}," for setup.",{"type":55,"tag":82,"props":329,"children":330},{},[331],{"type":60,"value":332},"Geographic residency follows only if your cluster's nodes are actually in the target regions.",{"type":55,"tag":82,"props":334,"children":335},{},[336],{"type":60,"value":337},"Qdrant Cloud deploys a cluster in a single region and has no managed multi-region today.",{"type":55,"tag":106,"props":339,"children":341},{"id":340},"what-not-to-do",[342],{"type":60,"value":343},"What NOT to Do",{"type":55,"tag":78,"props":345,"children":346},{},[347],{"type":55,"tag":82,"props":348,"children":349},{},[350],{"type":60,"value":351},"Treat a payload filter as your whole security model. In Qdrant, (unless you're using per-tenant collections), tenant isolation is payload-based. It is an application-layer responsibility, and the filter is only one small part of it.",{"items":353,"total":506},[354,369,384,399,412,426,439,449,460,472,482,493],{"slug":355,"name":355,"fn":356,"description":357,"org":358,"tags":359,"stars":23,"repoUrl":24,"updatedAt":368},"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},[360,361,364,367],{"name":15,"slug":16,"type":13},{"name":362,"slug":363,"type":13},"Debugging","debugging",{"name":365,"slug":366,"type":13},"Operations","operations",{"name":9,"slug":8,"type":13},"2026-07-16T06:02:56.675293",{"slug":370,"name":370,"fn":371,"description":372,"org":373,"tags":374,"stars":23,"repoUrl":24,"updatedAt":383},"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},[375,378,379,380],{"name":376,"slug":377,"type":13},"API Development","api-development",{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":381,"slug":382,"type":13},"SDK","sdk","2026-07-16T05:59:57.799789",{"slug":385,"name":385,"fn":386,"description":387,"org":388,"tags":389,"stars":23,"repoUrl":24,"updatedAt":398},"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},[390,391,394,397],{"name":15,"slug":16,"type":13},{"name":392,"slug":393,"type":13},"Deployment","deployment",{"name":395,"slug":396,"type":13},"Infrastructure","infrastructure",{"name":9,"slug":8,"type":13},"2026-07-19T05:38:33.324265",{"slug":400,"name":400,"fn":401,"description":402,"org":403,"tags":404,"stars":23,"repoUrl":24,"updatedAt":411},"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},[405,406,409,410],{"name":15,"slug":16,"type":13},{"name":407,"slug":408,"type":13},"Edge","edge",{"name":9,"slug":8,"type":13},{"name":21,"slug":22,"type":13},"2026-07-16T06:01:19.179105",{"slug":413,"name":413,"fn":414,"description":415,"org":416,"tags":417,"stars":23,"repoUrl":24,"updatedAt":425},"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},[418,421,422,423],{"name":419,"slug":420,"type":13},"Architecture","architecture",{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":424,"slug":40,"type":13},"Scaling","2026-07-19T05:38:32.348551",{"slug":427,"name":427,"fn":428,"description":429,"org":430,"tags":431,"stars":23,"repoUrl":24,"updatedAt":438},"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},[432,435,436,437],{"name":433,"slug":434,"type":13},"AI Infrastructure","ai-infrastructure",{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":21,"slug":22,"type":13},"2026-07-16T06:00:12.328122",{"slug":440,"name":440,"fn":441,"description":442,"org":443,"tags":444,"stars":23,"repoUrl":24,"updatedAt":448},"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},[445,446,447],{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":21,"slug":22,"type":13},"2026-07-16T06:01:49.401142",{"slug":450,"name":450,"fn":451,"description":452,"org":453,"tags":454,"stars":23,"repoUrl":24,"updatedAt":459},"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},[455,456,457,458],{"name":376,"slug":377,"type":13},{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":21,"slug":22,"type":13},"2026-07-16T06:03:02.305907",{"slug":461,"name":461,"fn":462,"description":463,"org":464,"tags":465,"stars":23,"repoUrl":24,"updatedAt":471},"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},[466,467,468,470],{"name":15,"slug":16,"type":13},{"name":362,"slug":363,"type":13},{"name":469,"slug":38,"type":13},"Performance",{"name":9,"slug":8,"type":13},"2026-07-19T05:38:36.321999",{"slug":473,"name":473,"fn":474,"description":475,"org":476,"tags":477,"stars":23,"repoUrl":24,"updatedAt":481},"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},[478,479,480],{"name":362,"slug":363,"type":13},{"name":469,"slug":38,"type":13},{"name":9,"slug":8,"type":13},"2026-07-16T06:00:15.357243",{"slug":483,"name":483,"fn":484,"description":485,"org":486,"tags":487,"stars":23,"repoUrl":24,"updatedAt":492},"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},[488,489,490,491],{"name":15,"slug":16,"type":13},{"name":362,"slug":363,"type":13},{"name":469,"slug":38,"type":13},{"name":9,"slug":8,"type":13},"2026-07-16T05:59:17.325839",{"slug":494,"name":494,"fn":495,"description":496,"org":497,"tags":498,"stars":23,"repoUrl":24,"updatedAt":505},"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},[499,500,503,504],{"name":15,"slug":16,"type":13},{"name":501,"slug":502,"type":13},"Migration","migration",{"name":469,"slug":38,"type":13},{"name":9,"slug":8,"type":13},"2026-07-16T06:00:48.841055",30,{"items":508,"total":506},[509,516,523,530,537,544,551],{"slug":355,"name":355,"fn":356,"description":357,"org":510,"tags":511,"stars":23,"repoUrl":24,"updatedAt":368},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[512,513,514,515],{"name":15,"slug":16,"type":13},{"name":362,"slug":363,"type":13},{"name":365,"slug":366,"type":13},{"name":9,"slug":8,"type":13},{"slug":370,"name":370,"fn":371,"description":372,"org":517,"tags":518,"stars":23,"repoUrl":24,"updatedAt":383},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[519,520,521,522],{"name":376,"slug":377,"type":13},{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":381,"slug":382,"type":13},{"slug":385,"name":385,"fn":386,"description":387,"org":524,"tags":525,"stars":23,"repoUrl":24,"updatedAt":398},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[526,527,528,529],{"name":15,"slug":16,"type":13},{"name":392,"slug":393,"type":13},{"name":395,"slug":396,"type":13},{"name":9,"slug":8,"type":13},{"slug":400,"name":400,"fn":401,"description":402,"org":531,"tags":532,"stars":23,"repoUrl":24,"updatedAt":411},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[533,534,535,536],{"name":15,"slug":16,"type":13},{"name":407,"slug":408,"type":13},{"name":9,"slug":8,"type":13},{"name":21,"slug":22,"type":13},{"slug":413,"name":413,"fn":414,"description":415,"org":538,"tags":539,"stars":23,"repoUrl":24,"updatedAt":425},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[540,541,542,543],{"name":419,"slug":420,"type":13},{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":424,"slug":40,"type":13},{"slug":427,"name":427,"fn":428,"description":429,"org":545,"tags":546,"stars":23,"repoUrl":24,"updatedAt":438},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[547,548,549,550],{"name":433,"slug":434,"type":13},{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":21,"slug":22,"type":13},{"slug":440,"name":440,"fn":441,"description":442,"org":552,"tags":553,"stars":23,"repoUrl":24,"updatedAt":448},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[554,555,556],{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":21,"slug":22,"type":13}]