[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-qdrant-qdrant-indexing-performance-optimization":3,"mdc--x34bi4-key":48,"related-org-qdrant-qdrant-indexing-performance-optimization":479,"related-repo-qdrant-qdrant-indexing-performance-optimization":629},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":23,"repoUrl":24,"updatedAt":25,"license":26,"forks":27,"topics":28,"repo":43,"sourceUrl":46,"mdContent":47},"qdrant-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},"qdrant","Qdrant","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fqdrant.png",[12,16,17,20],{"name":13,"slug":14,"type":15},"Performance","performance","tag",{"name":9,"slug":8,"type":15},{"name":18,"slug":19,"type":15},"Database","database",{"name":21,"slug":22,"type":15},"Debugging","debugging",197,"https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fskills","2026-07-19T05:38:36.321999",null,23,[29,30,31,32,33,34,35,36,37,14,8,38,39,40,41,42],"agent-skills","ai-agents","claude-code","codex","cursor","embeddings","hybrid-search","monitoring","multitenancy","quantization","scaling","search-quality","vector-database","vector-search",{"repoUrl":24,"stars":23,"forks":27,"topics":44,"description":45},[29,30,31,32,33,34,35,36,37,14,8,38,39,40,41,42],"Agent skills for Qdrant vector search: scaling, performance optimization, search quality, monitoring, deployment, model migration, version upgrades, and SDK usage across Python, TypeScript, Rust, Go, .NET, Java","https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fskills\u002Ftree\u002FHEAD\u002Fskills\u002Fqdrant-performance-optimization\u002Findexing-performance-optimization","---\nname: qdrant-indexing-performance-optimization\ndescription: \"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.\"\n---\n\n# What to Do When Qdrant Indexing Is Too Slow\n\nQdrant does NOT build HNSW indexes immediately. Small segments use brute-force until they exceed `indexing_threshold_kb` (default: 20 MB). Search during this window is slower by design, not a bug.\n\n- Understand the indexing optimizer [Indexing optimizer](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fops-optimization\u002Foptimizer\u002F?s=indexing-optimizer)\n\n\n## Uploads\u002FIngestion Too Slow\n\nUse when: upload or upsert API calls are slow.\nIdentify bottleneck: client-side (network, batching) vs server-side (CPU, disk I\u002FO)\n\nFor client-side, optimize batching and parallelism:\n\n- Use batch upserts (64-256 points per request) [Points API](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fpoints\u002F?s=upload-points)\n- Use 2-4 parallel upload streams\n\nFor server-side, optimize Qdrant configuration and indexing strategy:\n\n- Create more shards (3-12), each shard has an independent update worker [Sharding](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fscaling\u002Fdistributed_deployment\u002F?s=sharding)\n- Create payload indexes before HNSW builds (needed for filterable vector index) [Payload index](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Findexing\u002F?s=payload-index)\n\nSuitable for initial bulk load of large datasets:\n\n- Disable HNSW during bulk load (set `indexing_threshold_kb` very high, restore after) [Collection params](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fcollections\u002F?s=update-collection-parameters)\n- Setting `m=0` to disable HNSW is legacy, use high `indexing_threshold_kb` instead\n\nCareful, fast unindexed upload might temporarily use more RAM and degrade search performance until optimizer catches up.\n\nSee https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fbulk-upload\u002F\n\n\n## Optimizer Stuck or Taking Too Long\n\nUse when: optimizer running for hours, not finishing.\n\n- Check actual progress via optimizations endpoint (v1.17+) [Optimization monitoring](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fops-optimization\u002Foptimizer\u002F?s=optimization-monitoring)\n- Large merges and HNSW rebuilds legitimately take hours on big datasets\n- Check CPU and disk I\u002FO (HNSW is CPU-bound, merging is I\u002FO-bound, HDD is not viable)\n- If `optimizer_status` shows an error, check logs for disk full or corrupted segments\n\n\n## HNSW Build Time Too High\n\nUse when: HNSW index build dominates total indexing time.\n\n- Reduce `m` (default 16, good for most cases, 32+ rarely needed) [HNSW params](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Findexing\u002F?s=vector-index)\n- Reduce `ef_construct` (100-200 sufficient) [HNSW config](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fcollections\u002F?s=indexing-vectors-in-hnsw)\n- Keep `max_indexing_threads` proportional to CPU cores [Configuration](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fops-configuration\u002Fconfiguration\u002F)\n- Use GPU for indexing [GPU indexing](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fops-configuration\u002Frunning-with-gpu\u002F)\n\n## HNSW index for multi-tenant collections\n\nIf you have a multi-tenant use case where all data is split by some payload field (e.g. `tenant_id`), you can avoid building a global HNSW index and instead rely on `payload_m` to build HNSW index only for subsets of data.\nSkipping global HNSW index can significantly reduce indexing time.\n\nSee [Multi-tenant collections](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fmultitenancy\u002F) for details.\n\n## Additional Payload Indexes Are Too Slow\n\nQdrant builds extra HNSW links for all payload indexes to ensure that quality of filtered vector search does not degrade.\nSome payload indexes (e.g. `text` fields with long texts) can have a very high number of unique values per point, which can lead to long HNSW build time.\n\nYou can disable building extra HNSW links for specific payload index and instead rely on slightly slower query-time strategies like ACORN.\n\nRead more about disabling extra HNSW links in [documentation](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Findexing\u002F?s=disable-the-creation-of-extra-edges-for-payload-fields)\n\nRead more about ACORN in [documentation](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fsearch\u002Fsearch\u002F?s=acorn-search-algorithm)\n\n\n## What NOT to Do\n\n- Do not create payload indexes AFTER HNSW is built (breaks filterable vector index)\n- Do not use `m=0` for bulk uploads into an existing collection, it might drop the existing HNSW and cause long reindexing \n- Do not upload one point at a time (per-request overhead dominates)\n",{"data":49,"body":50},{"name":4,"description":6},{"type":51,"children":52},"root",[53,62,77,96,103,108,113,133,138,165,170,212,217,228,234,239,277,283,288,362,368,389,402,408,420,425,437,448,454],{"type":54,"tag":55,"props":56,"children":58},"element","h1",{"id":57},"what-to-do-when-qdrant-indexing-is-too-slow",[59],{"type":60,"value":61},"text","What to Do When Qdrant Indexing Is Too Slow",{"type":54,"tag":63,"props":64,"children":65},"p",{},[66,68,75],{"type":60,"value":67},"Qdrant does NOT build HNSW indexes immediately. Small segments use brute-force until they exceed ",{"type":54,"tag":69,"props":70,"children":72},"code",{"className":71},[],[73],{"type":60,"value":74},"indexing_threshold_kb",{"type":60,"value":76}," (default: 20 MB). Search during this window is slower by design, not a bug.",{"type":54,"tag":78,"props":79,"children":80},"ul",{},[81],{"type":54,"tag":82,"props":83,"children":84},"li",{},[85,87],{"type":60,"value":86},"Understand the indexing optimizer ",{"type":54,"tag":88,"props":89,"children":93},"a",{"href":90,"rel":91},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fops-optimization\u002Foptimizer\u002F?s=indexing-optimizer",[92],"nofollow",[94],{"type":60,"value":95},"Indexing optimizer",{"type":54,"tag":97,"props":98,"children":100},"h2",{"id":99},"uploadsingestion-too-slow",[101],{"type":60,"value":102},"Uploads\u002FIngestion Too Slow",{"type":54,"tag":63,"props":104,"children":105},{},[106],{"type":60,"value":107},"Use when: upload or upsert API calls are slow.\nIdentify bottleneck: client-side (network, batching) vs server-side (CPU, disk I\u002FO)",{"type":54,"tag":63,"props":109,"children":110},{},[111],{"type":60,"value":112},"For client-side, optimize batching and parallelism:",{"type":54,"tag":78,"props":114,"children":115},{},[116,128],{"type":54,"tag":82,"props":117,"children":118},{},[119,121],{"type":60,"value":120},"Use batch upserts (64-256 points per request) ",{"type":54,"tag":88,"props":122,"children":125},{"href":123,"rel":124},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fpoints\u002F?s=upload-points",[92],[126],{"type":60,"value":127},"Points API",{"type":54,"tag":82,"props":129,"children":130},{},[131],{"type":60,"value":132},"Use 2-4 parallel upload streams",{"type":54,"tag":63,"props":134,"children":135},{},[136],{"type":60,"value":137},"For server-side, optimize Qdrant configuration and indexing strategy:",{"type":54,"tag":78,"props":139,"children":140},{},[141,153],{"type":54,"tag":82,"props":142,"children":143},{},[144,146],{"type":60,"value":145},"Create more shards (3-12), each shard has an independent update worker ",{"type":54,"tag":88,"props":147,"children":150},{"href":148,"rel":149},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fscaling\u002Fdistributed_deployment\u002F?s=sharding",[92],[151],{"type":60,"value":152},"Sharding",{"type":54,"tag":82,"props":154,"children":155},{},[156,158],{"type":60,"value":157},"Create payload indexes before HNSW builds (needed for filterable vector index) ",{"type":54,"tag":88,"props":159,"children":162},{"href":160,"rel":161},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Findexing\u002F?s=payload-index",[92],[163],{"type":60,"value":164},"Payload index",{"type":54,"tag":63,"props":166,"children":167},{},[168],{"type":60,"value":169},"Suitable for initial bulk load of large datasets:",{"type":54,"tag":78,"props":171,"children":172},{},[173,192],{"type":54,"tag":82,"props":174,"children":175},{},[176,178,183,185],{"type":60,"value":177},"Disable HNSW during bulk load (set ",{"type":54,"tag":69,"props":179,"children":181},{"className":180},[],[182],{"type":60,"value":74},{"type":60,"value":184}," very high, restore after) ",{"type":54,"tag":88,"props":186,"children":189},{"href":187,"rel":188},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fcollections\u002F?s=update-collection-parameters",[92],[190],{"type":60,"value":191},"Collection params",{"type":54,"tag":82,"props":193,"children":194},{},[195,197,203,205,210],{"type":60,"value":196},"Setting ",{"type":54,"tag":69,"props":198,"children":200},{"className":199},[],[201],{"type":60,"value":202},"m=0",{"type":60,"value":204}," to disable HNSW is legacy, use high ",{"type":54,"tag":69,"props":206,"children":208},{"className":207},[],[209],{"type":60,"value":74},{"type":60,"value":211}," instead",{"type":54,"tag":63,"props":213,"children":214},{},[215],{"type":60,"value":216},"Careful, fast unindexed upload might temporarily use more RAM and degrade search performance until optimizer catches up.",{"type":54,"tag":63,"props":218,"children":219},{},[220,222],{"type":60,"value":221},"See ",{"type":54,"tag":88,"props":223,"children":226},{"href":224,"rel":225},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fbulk-upload\u002F",[92],[227],{"type":60,"value":224},{"type":54,"tag":97,"props":229,"children":231},{"id":230},"optimizer-stuck-or-taking-too-long",[232],{"type":60,"value":233},"Optimizer Stuck or Taking Too Long",{"type":54,"tag":63,"props":235,"children":236},{},[237],{"type":60,"value":238},"Use when: optimizer running for hours, not finishing.",{"type":54,"tag":78,"props":240,"children":241},{},[242,254,259,264],{"type":54,"tag":82,"props":243,"children":244},{},[245,247],{"type":60,"value":246},"Check actual progress via optimizations endpoint (v1.17+) ",{"type":54,"tag":88,"props":248,"children":251},{"href":249,"rel":250},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fops-optimization\u002Foptimizer\u002F?s=optimization-monitoring",[92],[252],{"type":60,"value":253},"Optimization monitoring",{"type":54,"tag":82,"props":255,"children":256},{},[257],{"type":60,"value":258},"Large merges and HNSW rebuilds legitimately take hours on big datasets",{"type":54,"tag":82,"props":260,"children":261},{},[262],{"type":60,"value":263},"Check CPU and disk I\u002FO (HNSW is CPU-bound, merging is I\u002FO-bound, HDD is not viable)",{"type":54,"tag":82,"props":265,"children":266},{},[267,269,275],{"type":60,"value":268},"If ",{"type":54,"tag":69,"props":270,"children":272},{"className":271},[],[273],{"type":60,"value":274},"optimizer_status",{"type":60,"value":276}," shows an error, check logs for disk full or corrupted segments",{"type":54,"tag":97,"props":278,"children":280},{"id":279},"hnsw-build-time-too-high",[281],{"type":60,"value":282},"HNSW Build Time Too High",{"type":54,"tag":63,"props":284,"children":285},{},[286],{"type":60,"value":287},"Use when: HNSW index build dominates total indexing time.",{"type":54,"tag":78,"props":289,"children":290},{},[291,311,330,350],{"type":54,"tag":82,"props":292,"children":293},{},[294,296,302,304],{"type":60,"value":295},"Reduce ",{"type":54,"tag":69,"props":297,"children":299},{"className":298},[],[300],{"type":60,"value":301},"m",{"type":60,"value":303}," (default 16, good for most cases, 32+ rarely needed) ",{"type":54,"tag":88,"props":305,"children":308},{"href":306,"rel":307},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Findexing\u002F?s=vector-index",[92],[309],{"type":60,"value":310},"HNSW params",{"type":54,"tag":82,"props":312,"children":313},{},[314,315,321,323],{"type":60,"value":295},{"type":54,"tag":69,"props":316,"children":318},{"className":317},[],[319],{"type":60,"value":320},"ef_construct",{"type":60,"value":322}," (100-200 sufficient) ",{"type":54,"tag":88,"props":324,"children":327},{"href":325,"rel":326},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fcollections\u002F?s=indexing-vectors-in-hnsw",[92],[328],{"type":60,"value":329},"HNSW config",{"type":54,"tag":82,"props":331,"children":332},{},[333,335,341,343],{"type":60,"value":334},"Keep ",{"type":54,"tag":69,"props":336,"children":338},{"className":337},[],[339],{"type":60,"value":340},"max_indexing_threads",{"type":60,"value":342}," proportional to CPU cores ",{"type":54,"tag":88,"props":344,"children":347},{"href":345,"rel":346},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fops-configuration\u002Fconfiguration\u002F",[92],[348],{"type":60,"value":349},"Configuration",{"type":54,"tag":82,"props":351,"children":352},{},[353,355],{"type":60,"value":354},"Use GPU for indexing ",{"type":54,"tag":88,"props":356,"children":359},{"href":357,"rel":358},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fops-configuration\u002Frunning-with-gpu\u002F",[92],[360],{"type":60,"value":361},"GPU indexing",{"type":54,"tag":97,"props":363,"children":365},{"id":364},"hnsw-index-for-multi-tenant-collections",[366],{"type":60,"value":367},"HNSW index for multi-tenant collections",{"type":54,"tag":63,"props":369,"children":370},{},[371,373,379,381,387],{"type":60,"value":372},"If you have a multi-tenant use case where all data is split by some payload field (e.g. ",{"type":54,"tag":69,"props":374,"children":376},{"className":375},[],[377],{"type":60,"value":378},"tenant_id",{"type":60,"value":380},"), you can avoid building a global HNSW index and instead rely on ",{"type":54,"tag":69,"props":382,"children":384},{"className":383},[],[385],{"type":60,"value":386},"payload_m",{"type":60,"value":388}," to build HNSW index only for subsets of data.\nSkipping global HNSW index can significantly reduce indexing time.",{"type":54,"tag":63,"props":390,"children":391},{},[392,393,400],{"type":60,"value":221},{"type":54,"tag":88,"props":394,"children":397},{"href":395,"rel":396},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fmultitenancy\u002F",[92],[398],{"type":60,"value":399},"Multi-tenant collections",{"type":60,"value":401}," for details.",{"type":54,"tag":97,"props":403,"children":405},{"id":404},"additional-payload-indexes-are-too-slow",[406],{"type":60,"value":407},"Additional Payload Indexes Are Too Slow",{"type":54,"tag":63,"props":409,"children":410},{},[411,413,418],{"type":60,"value":412},"Qdrant builds extra HNSW links for all payload indexes to ensure that quality of filtered vector search does not degrade.\nSome payload indexes (e.g. ",{"type":54,"tag":69,"props":414,"children":416},{"className":415},[],[417],{"type":60,"value":60},{"type":60,"value":419}," fields with long texts) can have a very high number of unique values per point, which can lead to long HNSW build time.",{"type":54,"tag":63,"props":421,"children":422},{},[423],{"type":60,"value":424},"You can disable building extra HNSW links for specific payload index and instead rely on slightly slower query-time strategies like ACORN.",{"type":54,"tag":63,"props":426,"children":427},{},[428,430],{"type":60,"value":429},"Read more about disabling extra HNSW links in ",{"type":54,"tag":88,"props":431,"children":434},{"href":432,"rel":433},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Findexing\u002F?s=disable-the-creation-of-extra-edges-for-payload-fields",[92],[435],{"type":60,"value":436},"documentation",{"type":54,"tag":63,"props":438,"children":439},{},[440,442],{"type":60,"value":441},"Read more about ACORN in ",{"type":54,"tag":88,"props":443,"children":446},{"href":444,"rel":445},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fsearch\u002Fsearch\u002F?s=acorn-search-algorithm",[92],[447],{"type":60,"value":436},{"type":54,"tag":97,"props":449,"children":451},{"id":450},"what-not-to-do",[452],{"type":60,"value":453},"What NOT to Do",{"type":54,"tag":78,"props":455,"children":456},{},[457,462,474],{"type":54,"tag":82,"props":458,"children":459},{},[460],{"type":60,"value":461},"Do not create payload indexes AFTER HNSW is built (breaks filterable vector index)",{"type":54,"tag":82,"props":463,"children":464},{},[465,467,472],{"type":60,"value":466},"Do not use ",{"type":54,"tag":69,"props":468,"children":470},{"className":469},[],[471],{"type":60,"value":202},{"type":60,"value":473}," for bulk uploads into an existing collection, it might drop the existing HNSW and cause long reindexing",{"type":54,"tag":82,"props":475,"children":476},{},[477],{"type":60,"value":478},"Do not upload one point at a time (per-request overhead dominates)",{"items":480,"total":628},[481,494,509,524,539,553,566,576,587,594,604,615],{"slug":482,"name":482,"fn":483,"description":484,"org":485,"tags":486,"stars":23,"repoUrl":24,"updatedAt":493},"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},[487,488,489,492],{"name":18,"slug":19,"type":15},{"name":21,"slug":22,"type":15},{"name":490,"slug":491,"type":15},"Operations","operations",{"name":9,"slug":8,"type":15},"2026-07-16T06:02:56.675293",{"slug":495,"name":495,"fn":496,"description":497,"org":498,"tags":499,"stars":23,"repoUrl":24,"updatedAt":508},"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},[500,503,504,505],{"name":501,"slug":502,"type":15},"API Development","api-development",{"name":18,"slug":19,"type":15},{"name":9,"slug":8,"type":15},{"name":506,"slug":507,"type":15},"SDK","sdk","2026-07-16T05:59:57.799789",{"slug":510,"name":510,"fn":511,"description":512,"org":513,"tags":514,"stars":23,"repoUrl":24,"updatedAt":523},"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},[515,516,519,522],{"name":18,"slug":19,"type":15},{"name":517,"slug":518,"type":15},"Deployment","deployment",{"name":520,"slug":521,"type":15},"Infrastructure","infrastructure",{"name":9,"slug":8,"type":15},"2026-07-19T05:38:33.324265",{"slug":525,"name":525,"fn":526,"description":527,"org":528,"tags":529,"stars":23,"repoUrl":24,"updatedAt":538},"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},[530,531,534,535],{"name":18,"slug":19,"type":15},{"name":532,"slug":533,"type":15},"Edge","edge",{"name":9,"slug":8,"type":15},{"name":536,"slug":537,"type":15},"Search","search","2026-07-16T06:01:19.179105",{"slug":540,"name":540,"fn":541,"description":542,"org":543,"tags":544,"stars":23,"repoUrl":24,"updatedAt":552},"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},[545,548,549,550],{"name":546,"slug":547,"type":15},"Architecture","architecture",{"name":18,"slug":19,"type":15},{"name":9,"slug":8,"type":15},{"name":551,"slug":39,"type":15},"Scaling","2026-07-19T05:38:32.348551",{"slug":554,"name":554,"fn":555,"description":556,"org":557,"tags":558,"stars":23,"repoUrl":24,"updatedAt":565},"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},[559,562,563,564],{"name":560,"slug":561,"type":15},"AI Infrastructure","ai-infrastructure",{"name":18,"slug":19,"type":15},{"name":9,"slug":8,"type":15},{"name":536,"slug":537,"type":15},"2026-07-16T06:00:12.328122",{"slug":567,"name":567,"fn":568,"description":569,"org":570,"tags":571,"stars":23,"repoUrl":24,"updatedAt":575},"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},[572,573,574],{"name":18,"slug":19,"type":15},{"name":9,"slug":8,"type":15},{"name":536,"slug":537,"type":15},"2026-07-16T06:01:49.401142",{"slug":577,"name":577,"fn":578,"description":579,"org":580,"tags":581,"stars":23,"repoUrl":24,"updatedAt":586},"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},[582,583,584,585],{"name":501,"slug":502,"type":15},{"name":18,"slug":19,"type":15},{"name":9,"slug":8,"type":15},{"name":536,"slug":537,"type":15},"2026-07-16T06:03:02.305907",{"slug":4,"name":4,"fn":5,"description":6,"org":588,"tags":589,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[590,591,592,593],{"name":18,"slug":19,"type":15},{"name":21,"slug":22,"type":15},{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},{"slug":595,"name":595,"fn":596,"description":597,"org":598,"tags":599,"stars":23,"repoUrl":24,"updatedAt":603},"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},[600,601,602],{"name":21,"slug":22,"type":15},{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},"2026-07-16T06:00:15.357243",{"slug":605,"name":605,"fn":606,"description":607,"org":608,"tags":609,"stars":23,"repoUrl":24,"updatedAt":614},"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},[610,611,612,613],{"name":18,"slug":19,"type":15},{"name":21,"slug":22,"type":15},{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},"2026-07-16T05:59:17.325839",{"slug":616,"name":616,"fn":617,"description":618,"org":619,"tags":620,"stars":23,"repoUrl":24,"updatedAt":627},"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},[621,622,625,626],{"name":18,"slug":19,"type":15},{"name":623,"slug":624,"type":15},"Migration","migration",{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},"2026-07-16T06:00:48.841055",30,{"items":630,"total":628},[631,638,645,652,659,666,673],{"slug":482,"name":482,"fn":483,"description":484,"org":632,"tags":633,"stars":23,"repoUrl":24,"updatedAt":493},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[634,635,636,637],{"name":18,"slug":19,"type":15},{"name":21,"slug":22,"type":15},{"name":490,"slug":491,"type":15},{"name":9,"slug":8,"type":15},{"slug":495,"name":495,"fn":496,"description":497,"org":639,"tags":640,"stars":23,"repoUrl":24,"updatedAt":508},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[641,642,643,644],{"name":501,"slug":502,"type":15},{"name":18,"slug":19,"type":15},{"name":9,"slug":8,"type":15},{"name":506,"slug":507,"type":15},{"slug":510,"name":510,"fn":511,"description":512,"org":646,"tags":647,"stars":23,"repoUrl":24,"updatedAt":523},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[648,649,650,651],{"name":18,"slug":19,"type":15},{"name":517,"slug":518,"type":15},{"name":520,"slug":521,"type":15},{"name":9,"slug":8,"type":15},{"slug":525,"name":525,"fn":526,"description":527,"org":653,"tags":654,"stars":23,"repoUrl":24,"updatedAt":538},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[655,656,657,658],{"name":18,"slug":19,"type":15},{"name":532,"slug":533,"type":15},{"name":9,"slug":8,"type":15},{"name":536,"slug":537,"type":15},{"slug":540,"name":540,"fn":541,"description":542,"org":660,"tags":661,"stars":23,"repoUrl":24,"updatedAt":552},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[662,663,664,665],{"name":546,"slug":547,"type":15},{"name":18,"slug":19,"type":15},{"name":9,"slug":8,"type":15},{"name":551,"slug":39,"type":15},{"slug":554,"name":554,"fn":555,"description":556,"org":667,"tags":668,"stars":23,"repoUrl":24,"updatedAt":565},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[669,670,671,672],{"name":560,"slug":561,"type":15},{"name":18,"slug":19,"type":15},{"name":9,"slug":8,"type":15},{"name":536,"slug":537,"type":15},{"slug":567,"name":567,"fn":568,"description":569,"org":674,"tags":675,"stars":23,"repoUrl":24,"updatedAt":575},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[676,677,678],{"name":18,"slug":19,"type":15},{"name":9,"slug":8,"type":15},{"name":536,"slug":537,"type":15}]