[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-github-qdrant-search-speed-optimization":3,"mdc--whrgm0-key":47,"related-org-github-qdrant-search-speed-optimization":490,"related-repo-github-qdrant-search-speed-optimization":655},{"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-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},"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},"Performance","performance","tag",{"name":17,"slug":18,"type":15},"Qdrant","qdrant",{"name":20,"slug":21,"type":15},"Database","database",{"name":23,"slug":24,"type":15},"Search","search",{"name":26,"slug":27,"type":15},"Analytics","analytics",36978,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot","2026-04-18T04:46:03.987332",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\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\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Foperations\u002Foptimize\u002F?s=fine-tuning-search-parameters)\n- Enable in-memory quantization: [Scalar quantization](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fquantization\u002F?s=scalar-quantization)\n- Reduce Vector Dimensionality with Matryoshka Models: [Matryoshka Models](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Finference\u002F?s=reduce-vector-dimensionality-with-matryoshka-models)\n- Use oversampling + rescore for high-dimensional vectors [Search with quantization](https:\u002F\u002Fsearch.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\u002Fqdrant.tech\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\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Foperations\u002Foptimize\u002F?s=maximizing-throughput)\n- Use batch search API instead of single queries [Batch search](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fsearch\u002Fsearch\u002F?s=batch-search-api)\n- Enable quantization to reduce CPU cost [Scalar quantization](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fquantization\u002F?s=scalar-quantization)\n- Add replicas to distribute read load [Replication](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Foperations\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\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Findexing\u002F?s=payload-index)\n- Use `is_tenant=true` for primary filtering condition: [Tenant index](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Findexing\u002F?s=tenant-index)\n- Try ACORN algorithm for complex filters: [ACORN](https:\u002F\u002Fsearch.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\u002Fsearch.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":48,"body":49},{"name":4,"description":6},{"type":50,"children":51},"root",[52,61,67,101,108,113,120,154,160,225,231,236,293,299,304,369,375,381,402,408,436,448,454],{"type":53,"tag":54,"props":55,"children":57},"element","h1",{"id":56},"diagnose-a-problem",[58],{"type":59,"value":60},"text","Diagnose a problem",{"type":53,"tag":62,"props":63,"children":64},"p",{},[65],{"type":59,"value":66},"There the multiple possible reasons for search performance degradation. The most common ones are:",{"type":53,"tag":68,"props":69,"children":70},"ul",{},[71,77,91,96],{"type":53,"tag":72,"props":73,"children":74},"li",{},[75],{"type":59,"value":76},"Memory pressure: if the working set exceeds available RAM",{"type":53,"tag":72,"props":78,"children":79},{},[80,82,89],{"type":59,"value":81},"Complex requests (e.g. high ",{"type":53,"tag":83,"props":84,"children":86},"code",{"className":85},[],[87],{"type":59,"value":88},"hnsw_ef",{"type":59,"value":90},", complex filters without payload index)",{"type":53,"tag":72,"props":92,"children":93},{},[94],{"type":59,"value":95},"Competing background processes (e.g. optimizer still running after bulk upload)",{"type":53,"tag":72,"props":97,"children":98},{},[99],{"type":59,"value":100},"Problem with the cluster (e.g. network issues, hardware degradation)",{"type":53,"tag":102,"props":103,"children":105},"h2",{"id":104},"single-query-too-slow-latency",[106],{"type":59,"value":107},"Single Query Too Slow (Latency)",{"type":53,"tag":62,"props":109,"children":110},{},[111],{"type":59,"value":112},"Use when: individual queries take too long regardless of load.",{"type":53,"tag":114,"props":115,"children":117},"h3",{"id":116},"diagnostic-steps",[118],{"type":59,"value":119},"Diagnostic steps:",{"type":53,"tag":68,"props":121,"children":122},{},[123,128,149],{"type":53,"tag":72,"props":124,"children":125},{},[126],{"type":59,"value":127},"Check if second run of the same request is significantly faster (indicates memory pressure)",{"type":53,"tag":72,"props":129,"children":130},{},[131,133,139,141,147],{"type":59,"value":132},"Try the same query with ",{"type":53,"tag":83,"props":134,"children":136},{"className":135},[],[137],{"type":59,"value":138},"with_payload: false",{"type":59,"value":140}," and ",{"type":53,"tag":83,"props":142,"children":144},{"className":143},[],[145],{"type":59,"value":146},"with_vectors: false",{"type":59,"value":148}," to see if payload retrieval is the bottleneck",{"type":53,"tag":72,"props":150,"children":151},{},[152],{"type":59,"value":153},"If request uses filters, try to remove them one by one to identify if a specific filter condition is the bottleneck",{"type":53,"tag":114,"props":155,"children":157},{"id":156},"common-fixes",[158],{"type":59,"value":159},"Common fixes:",{"type":53,"tag":68,"props":161,"children":162},{},[163,177,189,201,213],{"type":53,"tag":72,"props":164,"children":165},{},[166,168],{"type":59,"value":167},"Tune HNSW parameters: ",{"type":53,"tag":169,"props":170,"children":174},"a",{"href":171,"rel":172},"https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Foperations\u002Foptimize\u002F?s=fine-tuning-search-parameters",[173],"nofollow",[175],{"type":59,"value":176},"Fine-tuning search",{"type":53,"tag":72,"props":178,"children":179},{},[180,182],{"type":59,"value":181},"Enable in-memory quantization: ",{"type":53,"tag":169,"props":183,"children":186},{"href":184,"rel":185},"https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fquantization\u002F?s=scalar-quantization",[173],[187],{"type":59,"value":188},"Scalar quantization",{"type":53,"tag":72,"props":190,"children":191},{},[192,194],{"type":59,"value":193},"Reduce Vector Dimensionality with Matryoshka Models: ",{"type":53,"tag":169,"props":195,"children":198},{"href":196,"rel":197},"https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Finference\u002F?s=reduce-vector-dimensionality-with-matryoshka-models",[173],[199],{"type":59,"value":200},"Matryoshka Models",{"type":53,"tag":72,"props":202,"children":203},{},[204,206],{"type":59,"value":205},"Use oversampling + rescore for high-dimensional vectors ",{"type":53,"tag":169,"props":207,"children":210},{"href":208,"rel":209},"https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fquantization\u002F?s=searching-with-quantization",[173],[211],{"type":59,"value":212},"Search with quantization",{"type":53,"tag":72,"props":214,"children":215},{},[216,218],{"type":59,"value":217},"Enable io_uring for disk-heavy workloads on Linux ",{"type":53,"tag":169,"props":219,"children":222},{"href":220,"rel":221},"https:\u002F\u002Fqdrant.tech\u002Farticles\u002Fio_uring\u002F",[173],[223],{"type":59,"value":224},"io_uring",{"type":53,"tag":102,"props":226,"children":228},{"id":227},"cant-handle-enough-qps-throughput",[229],{"type":59,"value":230},"Can't Handle Enough QPS (Throughput)",{"type":53,"tag":62,"props":232,"children":233},{},[234],{"type":59,"value":235},"Use when: system can't serve enough queries per second under load.",{"type":53,"tag":68,"props":237,"children":238},{},[239,259,271,281],{"type":53,"tag":72,"props":240,"children":241},{},[242,244,250,252],{"type":59,"value":243},"Reduce segment count (",{"type":53,"tag":83,"props":245,"children":247},{"className":246},[],[248],{"type":59,"value":249},"default_segment_number",{"type":59,"value":251}," to 2) ",{"type":53,"tag":169,"props":253,"children":256},{"href":254,"rel":255},"https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Foperations\u002Foptimize\u002F?s=maximizing-throughput",[173],[257],{"type":59,"value":258},"Maximizing throughput",{"type":53,"tag":72,"props":260,"children":261},{},[262,264],{"type":59,"value":263},"Use batch search API instead of single queries ",{"type":53,"tag":169,"props":265,"children":268},{"href":266,"rel":267},"https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fsearch\u002Fsearch\u002F?s=batch-search-api",[173],[269],{"type":59,"value":270},"Batch search",{"type":53,"tag":72,"props":272,"children":273},{},[274,276],{"type":59,"value":275},"Enable quantization to reduce CPU cost ",{"type":53,"tag":169,"props":277,"children":279},{"href":184,"rel":278},[173],[280],{"type":59,"value":188},{"type":53,"tag":72,"props":282,"children":283},{},[284,286],{"type":59,"value":285},"Add replicas to distribute read load ",{"type":53,"tag":169,"props":287,"children":290},{"href":288,"rel":289},"https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Foperations\u002Fdistributed_deployment\u002F?s=replication",[173],[291],{"type":59,"value":292},"Replication",{"type":53,"tag":102,"props":294,"children":296},{"id":295},"filtered-search-is-slow",[297],{"type":59,"value":298},"Filtered Search Is Slow",{"type":53,"tag":62,"props":300,"children":301},{},[302],{"type":59,"value":303},"Use when: filtered search is significantly slower than unfiltered. Most common SA complaint after memory.",{"type":53,"tag":68,"props":305,"children":306},{},[307,319,339,351,364],{"type":53,"tag":72,"props":308,"children":309},{},[310,312],{"type":59,"value":311},"Create payload index on the filtered field ",{"type":53,"tag":169,"props":313,"children":316},{"href":314,"rel":315},"https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Findexing\u002F?s=payload-index",[173],[317],{"type":59,"value":318},"Payload index",{"type":53,"tag":72,"props":320,"children":321},{},[322,324,330,332],{"type":59,"value":323},"Use ",{"type":53,"tag":83,"props":325,"children":327},{"className":326},[],[328],{"type":59,"value":329},"is_tenant=true",{"type":59,"value":331}," for primary filtering condition: ",{"type":53,"tag":169,"props":333,"children":336},{"href":334,"rel":335},"https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Findexing\u002F?s=tenant-index",[173],[337],{"type":59,"value":338},"Tenant index",{"type":53,"tag":72,"props":340,"children":341},{},[342,344],{"type":59,"value":343},"Try ACORN algorithm for complex filters: ",{"type":53,"tag":169,"props":345,"children":348},{"href":346,"rel":347},"https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fsearch\u002Fsearch\u002F?s=acorn-search-algorithm",[173],[349],{"type":59,"value":350},"ACORN",{"type":53,"tag":72,"props":352,"children":353},{},[354,356,362],{"type":59,"value":355},"Avoid using ",{"type":53,"tag":83,"props":357,"children":359},{"className":358},[],[360],{"type":59,"value":361},"nested",{"type":59,"value":363}," filtering conditions as a primary filter. It might force qdrant to read raw payload values instead of using index.",{"type":53,"tag":72,"props":365,"children":366},{},[367],{"type":59,"value":368},"If payload index was added after HNSW build, trigger re-index to create filterable subgraph links",{"type":53,"tag":102,"props":370,"children":372},{"id":371},"optimize-search-performance-with-parallel-updates",[373],{"type":59,"value":374},"Optimize search performance with parallel updates",{"type":53,"tag":114,"props":376,"children":378},{"id":377},"diagnostic-steps-1",[379],{"type":59,"value":380},"Diagnostic steps",{"type":53,"tag":68,"props":382,"children":383},{},[384,397],{"type":53,"tag":72,"props":385,"children":386},{},[387,389,395],{"type":59,"value":388},"Try to run the same query with ",{"type":53,"tag":83,"props":390,"children":392},{"className":391},[],[393],{"type":59,"value":394},"indexed_only=true",{"type":59,"value":396}," parameter, if the query is significantly faster, it means that the optimizer is still running and has not yet indexed all segments.",{"type":53,"tag":72,"props":398,"children":399},{},[400],{"type":59,"value":401},"If CPU or IO usage is high even with no queries, it also indicates that the optimizer is still running.",{"type":53,"tag":114,"props":403,"children":405},{"id":404},"recommended-configuration-changes",[406],{"type":59,"value":407},"Recommended configuration changes",{"type":53,"tag":68,"props":409,"children":410},{},[411,424],{"type":53,"tag":72,"props":412,"children":413},{},[414,416,422],{"type":59,"value":415},"reduce ",{"type":53,"tag":83,"props":417,"children":419},{"className":418},[],[420],{"type":59,"value":421},"optimizer_cpu_budget",{"type":59,"value":423}," to reserve more CPU for queries",{"type":53,"tag":72,"props":425,"children":426},{},[427,428,434],{"type":59,"value":323},{"type":53,"tag":83,"props":429,"children":431},{"className":430},[],[432],{"type":59,"value":433},"prevent_unoptimized=true",{"type":59,"value":435}," 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":53,"tag":62,"props":437,"children":438},{},[439,441],{"type":59,"value":440},"Learn more ",{"type":53,"tag":169,"props":442,"children":445},{"href":443,"rel":444},"https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fsearch\u002Flow-latency-search\u002F?s=query-indexed-data-only",[173],[446],{"type":59,"value":447},"here",{"type":53,"tag":102,"props":449,"children":451},{"id":450},"what-not-to-do",[452],{"type":59,"value":453},"What NOT to Do",{"type":53,"tag":68,"props":455,"children":456},{},[457,470,475,480,485],{"type":53,"tag":72,"props":458,"children":459},{},[460,462,468],{"type":59,"value":461},"Set ",{"type":53,"tag":83,"props":463,"children":465},{"className":464},[],[466],{"type":59,"value":467},"always_ram=false",{"type":59,"value":469}," on quantization (disk thrashing on every search)",{"type":53,"tag":72,"props":471,"children":472},{},[473],{"type":59,"value":474},"Put HNSW on disk for latency-sensitive production (only for cold storage)",{"type":53,"tag":72,"props":476,"children":477},{},[478],{"type":59,"value":479},"Increase segment count for throughput (opposite: fewer = better)",{"type":53,"tag":72,"props":481,"children":482},{},[483],{"type":59,"value":484},"Create payload indexes on every field (wastes memory)",{"type":53,"tag":72,"props":486,"children":487},{},[488],{"type":59,"value":489},"Blame Qdrant before checking optimizer status",{"items":491,"total":654},[492,510,526,542,554,570,584,596,608,620,634,642],{"slug":493,"name":493,"fn":494,"description":495,"org":496,"tags":497,"stars":28,"repoUrl":29,"updatedAt":509},"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},[498,501,504,507,508],{"name":499,"slug":500,"type":15},"AI Infrastructure","ai-infrastructure",{"name":502,"slug":503,"type":15},"Architecture","architecture",{"name":505,"slug":506,"type":15},"Capacity Planning","capacity-planning",{"name":20,"slug":21,"type":15},{"name":17,"slug":18,"type":15},"2026-04-18T04:46:16.349561",{"slug":511,"name":511,"fn":512,"description":513,"org":514,"tags":515,"stars":28,"repoUrl":29,"updatedAt":525},"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},[516,519,520,523,524],{"name":517,"slug":518,"type":15},"Data Engineering","data-engineering",{"name":20,"slug":21,"type":15},{"name":521,"slug":522,"type":15},"ETL","etl",{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15},"2026-04-18T04:46:02.766357",{"slug":527,"name":527,"fn":528,"description":529,"org":530,"tags":531,"stars":28,"repoUrl":29,"updatedAt":541},"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},[532,535,536,539,540],{"name":533,"slug":534,"type":15},"Cost Optimization","cost-optimization",{"name":20,"slug":21,"type":15},{"name":537,"slug":538,"type":15},"Observability","observability",{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15},"2026-04-18T04:46:01.525023",{"slug":543,"name":543,"fn":544,"description":545,"org":546,"tags":547,"stars":28,"repoUrl":29,"updatedAt":553},"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},[548,549,550,551,552],{"name":502,"slug":503,"type":15},{"name":20,"slug":21,"type":15},{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15},{"name":23,"slug":24,"type":15},"2026-04-18T04:46:10.126667",{"slug":555,"name":555,"fn":556,"description":557,"org":558,"tags":559,"stars":28,"repoUrl":29,"updatedAt":569},"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},[560,563,566,567,568],{"name":561,"slug":562,"type":15},"Debugging","debugging",{"name":564,"slug":565,"type":15},"Monitoring","monitoring",{"name":537,"slug":538,"type":15},{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15},"2026-04-18T04:46:06.450784",{"slug":571,"name":571,"fn":572,"description":573,"org":574,"tags":575,"stars":28,"repoUrl":29,"updatedAt":583},"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},[576,577,578,579,580],{"name":499,"slug":500,"type":15},{"name":564,"slug":565,"type":15},{"name":537,"slug":538,"type":15},{"name":17,"slug":18,"type":15},{"name":581,"slug":582,"type":15},"SRE","sre","2026-04-18T04:46:05.217192",{"slug":585,"name":585,"fn":586,"description":587,"org":588,"tags":589,"stars":28,"repoUrl":29,"updatedAt":595},"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},[590,591,592,593,594],{"name":499,"slug":500,"type":15},{"name":502,"slug":503,"type":15},{"name":505,"slug":506,"type":15},{"name":20,"slug":21,"type":15},{"name":17,"slug":18,"type":15},"2026-04-18T04:46:07.684464",{"slug":597,"name":597,"fn":598,"description":599,"org":600,"tags":601,"stars":28,"repoUrl":29,"updatedAt":607},"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},[602,603,604,605,606],{"name":499,"slug":500,"type":15},{"name":502,"slug":503,"type":15},{"name":20,"slug":21,"type":15},{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15},"2026-04-18T04:46:08.905219",{"slug":609,"name":609,"fn":610,"description":611,"org":612,"tags":613,"stars":28,"repoUrl":29,"updatedAt":619},"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},[614,615,616,617,618],{"name":502,"slug":503,"type":15},{"name":20,"slug":21,"type":15},{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15},{"name":23,"slug":24,"type":15},"2026-04-18T04:46:11.371326",{"slug":621,"name":621,"fn":622,"description":623,"org":624,"tags":625,"stars":28,"repoUrl":29,"updatedAt":633},"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},[626,627,630,631,632],{"name":26,"slug":27,"type":15},{"name":628,"slug":629,"type":15},"Data Quality","data-quality",{"name":561,"slug":562,"type":15},{"name":17,"slug":18,"type":15},{"name":23,"slug":24,"type":15},"2026-04-18T04:46:17.579894",{"slug":4,"name":4,"fn":5,"description":6,"org":635,"tags":636,"stars":28,"repoUrl":29,"updatedAt":30},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[637,638,639,640,641],{"name":26,"slug":27,"type":15},{"name":20,"slug":21,"type":15},{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15},{"name":23,"slug":24,"type":15},{"slug":643,"name":643,"fn":644,"description":645,"org":646,"tags":647,"stars":28,"repoUrl":29,"updatedAt":653},"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},[648,649,650,651,652],{"name":499,"slug":500,"type":15},{"name":26,"slug":27,"type":15},{"name":502,"slug":503,"type":15},{"name":17,"slug":18,"type":15},{"name":23,"slug":24,"type":15},"2026-04-18T04:46:18.812306",45,{"items":656,"total":713},[657,665,673,681,689,697,705],{"slug":493,"name":493,"fn":494,"description":495,"org":658,"tags":659,"stars":28,"repoUrl":29,"updatedAt":509},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[660,661,662,663,664],{"name":499,"slug":500,"type":15},{"name":502,"slug":503,"type":15},{"name":505,"slug":506,"type":15},{"name":20,"slug":21,"type":15},{"name":17,"slug":18,"type":15},{"slug":511,"name":511,"fn":512,"description":513,"org":666,"tags":667,"stars":28,"repoUrl":29,"updatedAt":525},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[668,669,670,671,672],{"name":517,"slug":518,"type":15},{"name":20,"slug":21,"type":15},{"name":521,"slug":522,"type":15},{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15},{"slug":527,"name":527,"fn":528,"description":529,"org":674,"tags":675,"stars":28,"repoUrl":29,"updatedAt":541},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[676,677,678,679,680],{"name":533,"slug":534,"type":15},{"name":20,"slug":21,"type":15},{"name":537,"slug":538,"type":15},{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15},{"slug":543,"name":543,"fn":544,"description":545,"org":682,"tags":683,"stars":28,"repoUrl":29,"updatedAt":553},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[684,685,686,687,688],{"name":502,"slug":503,"type":15},{"name":20,"slug":21,"type":15},{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15},{"name":23,"slug":24,"type":15},{"slug":555,"name":555,"fn":556,"description":557,"org":690,"tags":691,"stars":28,"repoUrl":29,"updatedAt":569},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[692,693,694,695,696],{"name":561,"slug":562,"type":15},{"name":564,"slug":565,"type":15},{"name":537,"slug":538,"type":15},{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15},{"slug":571,"name":571,"fn":572,"description":573,"org":698,"tags":699,"stars":28,"repoUrl":29,"updatedAt":583},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[700,701,702,703,704],{"name":499,"slug":500,"type":15},{"name":564,"slug":565,"type":15},{"name":537,"slug":538,"type":15},{"name":17,"slug":18,"type":15},{"name":581,"slug":582,"type":15},{"slug":585,"name":585,"fn":586,"description":587,"org":706,"tags":707,"stars":28,"repoUrl":29,"updatedAt":595},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[708,709,710,711,712],{"name":499,"slug":500,"type":15},{"name":502,"slug":503,"type":15},{"name":505,"slug":506,"type":15},{"name":20,"slug":21,"type":15},{"name":17,"slug":18,"type":15},15]