[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-qdrant-qdrant-edge":3,"mdc--yd5je8-key":49,"related-org-qdrant-qdrant-edge":500,"related-repo-qdrant-qdrant-edge":649},{"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-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},"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},"Search","search",{"name":21,"slug":22,"type":13},"Edge","edge",197,"https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fskills","2026-07-16T06:01:19.179105",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-edge","---\nname: qdrant-edge\ndescription: \"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.\"\n---\n\n# Building on Qdrant Edge\n\nEdge is the Qdrant engine embedded in your process (Python or Rust), not a thin local vector store to wrap. The failure mode is rebuilding what the shard already ships: keyword scoring, snapshot apply, faceting, counting. Before writing any of that, check the shard API. Two things Edge does NOT give you are a one-call cloud sync and query-time fusion, so knowing which is which keeps you from both reinventing built-ins and expecting capabilities Edge lacks. Edge is single-node and shares the server's data format.\n\n- Edge is in beta: pin your version, the API drifts between releases [Qdrant Edge](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fedge\u002F).\n\n\n## Syncing a Shard with a Qdrant Server\n\nUse when: seeding a shard from a server, keeping it fresh, backing it up, or aggregating many devices into one collection.\n\nThere is no built-in `.sync()`. Sync is a pattern you assemble from shard helpers plus your own transport, so do not go looking for one call.\n\n- Follow the documented dual-shard pattern: a `mutable` shard for local writes plus an `immutable` shard restored from a server snapshot, query both, refresh on a schedule [Edge synchronization guide](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fedge\u002Fedge-synchronization-guide\u002F).\n- You write the snapshot download (plain HTTP to the shard snapshot endpoint), then apply it with `unpack_snapshot` and `update_from_snapshot`. Do not untar or merge segments by hand [Synchronization patterns](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fedge\u002Fedge-data-synchronization-patterns\u002F).\n- Refresh incrementally with a partial snapshot built from `snapshot_manifest`, not a full snapshot every cycle [Synchronization patterns](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fedge\u002Fedge-data-synchronization-patterns\u002F).\n- Push is your own dual-write: on each local upsert, enqueue the point and let a background worker upsert it to the server, buffering while offline [Synchronization patterns](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fedge\u002Fedge-data-synchronization-patterns\u002F).\n\n\n## Keyword and Hybrid Search on Device\n\nUse when: you need exact-term or BM25 matching, alone or alongside vectors.\n\n- BM25 is built into Edge (`Bm25`, `Bm25Config`, `embed_document`, `embed_query`) with the IDF `Modifier` on `EdgeSparseVectorParams`, and is wire-compatible with server BM25: a shard seeded from a server snapshot answers local BM25 queries without re-indexing. Do not ship a second BM25 library [Edge BM25](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fedge\u002Fedge-bm25\u002F)\n- Dense embeddings are NOT in Edge: generate them on device with the separate `fastembed` package [FastEmbed embeddings](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fedge\u002Fedge-fastembed-embeddings\u002F)\n- Edge queries one vector field per request (`using`) and does not fuse dense and sparse at query time. Run each leg separately and combine the rankings in application code [Edge quickstart](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fedge\u002Fedge-quickstart\u002F)\n\n\n## Operating the Shard\n\nUse when: writes have accumulated, search looks stale after inserts, or a backup is larger than the data.\n\n- Edge has NO background optimizer. Call `optimize` after bulk writes: it builds indexes (including the sparse index) and reclaims deleted points. Skip it and that data stays unindexed [Edge quickstart](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fedge\u002Fedge-quickstart\u002F)\n- Faceting, counting, and enumeration are built in (`facet`, `count`, `scroll`); index the fields you filter or facet with `create_field_index` rather than aggregating in application code [Edge quickstart](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fedge\u002Fedge-quickstart\u002F)\n- The write-ahead log is pre-allocated to 32 MB and inflates apparent disk and backup size. Shrink it with `wal_options` (Rust), and do not treat raw file size as real usage [Edge quickstart](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fedge\u002Fedge-quickstart\u002F)\n\n\n## What NOT to Do\n\n- Expect a bidirectional `.sync()` or a built-in push path: Edge gives you snapshot apply, you own the transport and the dual-write\n- Untar or merge snapshot segments by hand instead of using `unpack_snapshot` and `update_from_snapshot`\n- Ship a custom or third-party BM25 when Edge has one built in\n- Use `embed_document` for queries or `embed_query` for documents: the weighting differs and results go wrong\n- Assume Edge fuses dense and sparse or consumes Prefetch: combine the rankings in application code\n- Assume a background optimizer like the server's: nothing is indexed or compacted until you call `optimize`\n- Reach for Edge when you need distributed or multi-node search: it is single-node [Qdrant Edge](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fedge\u002F)\n- Claim support for a language beyond Python and Rust, or an OS or accelerator the Edge docs do not state\n",{"data":50,"body":51},{"name":4,"description":6},{"type":52,"children":53},"root",[54,63,69,90,97,102,116,207,213,218,319,325,330,409,415],{"type":55,"tag":56,"props":57,"children":59},"element","h1",{"id":58},"building-on-qdrant-edge",[60],{"type":61,"value":62},"text","Building on Qdrant Edge",{"type":55,"tag":64,"props":65,"children":66},"p",{},[67],{"type":61,"value":68},"Edge is the Qdrant engine embedded in your process (Python or Rust), not a thin local vector store to wrap. The failure mode is rebuilding what the shard already ships: keyword scoring, snapshot apply, faceting, counting. Before writing any of that, check the shard API. Two things Edge does NOT give you are a one-call cloud sync and query-time fusion, so knowing which is which keeps you from both reinventing built-ins and expecting capabilities Edge lacks. Edge is single-node and shares the server's data format.",{"type":55,"tag":70,"props":71,"children":72},"ul",{},[73],{"type":55,"tag":74,"props":75,"children":76},"li",{},[77,79,88],{"type":61,"value":78},"Edge is in beta: pin your version, the API drifts between releases ",{"type":55,"tag":80,"props":81,"children":85},"a",{"href":82,"rel":83},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fedge\u002F",[84],"nofollow",[86],{"type":61,"value":87},"Qdrant Edge",{"type":61,"value":89},".",{"type":55,"tag":91,"props":92,"children":94},"h2",{"id":93},"syncing-a-shard-with-a-qdrant-server",[95],{"type":61,"value":96},"Syncing a Shard with a Qdrant Server",{"type":55,"tag":64,"props":98,"children":99},{},[100],{"type":61,"value":101},"Use when: seeding a shard from a server, keeping it fresh, backing it up, or aggregating many devices into one collection.",{"type":55,"tag":64,"props":103,"children":104},{},[105,107,114],{"type":61,"value":106},"There is no built-in ",{"type":55,"tag":108,"props":109,"children":111},"code",{"className":110},[],[112],{"type":61,"value":113},".sync()",{"type":61,"value":115},". Sync is a pattern you assemble from shard helpers plus your own transport, so do not go looking for one call.",{"type":55,"tag":70,"props":117,"children":118},{},[119,148,177,196],{"type":55,"tag":74,"props":120,"children":121},{},[122,124,130,132,138,140,147],{"type":61,"value":123},"Follow the documented dual-shard pattern: a ",{"type":55,"tag":108,"props":125,"children":127},{"className":126},[],[128],{"type":61,"value":129},"mutable",{"type":61,"value":131}," shard for local writes plus an ",{"type":55,"tag":108,"props":133,"children":135},{"className":134},[],[136],{"type":61,"value":137},"immutable",{"type":61,"value":139}," shard restored from a server snapshot, query both, refresh on a schedule ",{"type":55,"tag":80,"props":141,"children":144},{"href":142,"rel":143},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fedge\u002Fedge-synchronization-guide\u002F",[84],[145],{"type":61,"value":146},"Edge synchronization guide",{"type":61,"value":89},{"type":55,"tag":74,"props":149,"children":150},{},[151,153,159,161,167,169,176],{"type":61,"value":152},"You write the snapshot download (plain HTTP to the shard snapshot endpoint), then apply it with ",{"type":55,"tag":108,"props":154,"children":156},{"className":155},[],[157],{"type":61,"value":158},"unpack_snapshot",{"type":61,"value":160}," and ",{"type":55,"tag":108,"props":162,"children":164},{"className":163},[],[165],{"type":61,"value":166},"update_from_snapshot",{"type":61,"value":168},". Do not untar or merge segments by hand ",{"type":55,"tag":80,"props":170,"children":173},{"href":171,"rel":172},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fedge\u002Fedge-data-synchronization-patterns\u002F",[84],[174],{"type":61,"value":175},"Synchronization patterns",{"type":61,"value":89},{"type":55,"tag":74,"props":178,"children":179},{},[180,182,188,190,195],{"type":61,"value":181},"Refresh incrementally with a partial snapshot built from ",{"type":55,"tag":108,"props":183,"children":185},{"className":184},[],[186],{"type":61,"value":187},"snapshot_manifest",{"type":61,"value":189},", not a full snapshot every cycle ",{"type":55,"tag":80,"props":191,"children":193},{"href":171,"rel":192},[84],[194],{"type":61,"value":175},{"type":61,"value":89},{"type":55,"tag":74,"props":197,"children":198},{},[199,201,206],{"type":61,"value":200},"Push is your own dual-write: on each local upsert, enqueue the point and let a background worker upsert it to the server, buffering while offline ",{"type":55,"tag":80,"props":202,"children":204},{"href":171,"rel":203},[84],[205],{"type":61,"value":175},{"type":61,"value":89},{"type":55,"tag":91,"props":208,"children":210},{"id":209},"keyword-and-hybrid-search-on-device",[211],{"type":61,"value":212},"Keyword and Hybrid Search on Device",{"type":55,"tag":64,"props":214,"children":215},{},[216],{"type":61,"value":217},"Use when: you need exact-term or BM25 matching, alone or alongside vectors.",{"type":55,"tag":70,"props":219,"children":220},{},[221,279,299],{"type":55,"tag":74,"props":222,"children":223},{},[224,226,232,234,240,241,247,248,254,256,262,264,270,272],{"type":61,"value":225},"BM25 is built into Edge (",{"type":55,"tag":108,"props":227,"children":229},{"className":228},[],[230],{"type":61,"value":231},"Bm25",{"type":61,"value":233},", ",{"type":55,"tag":108,"props":235,"children":237},{"className":236},[],[238],{"type":61,"value":239},"Bm25Config",{"type":61,"value":233},{"type":55,"tag":108,"props":242,"children":244},{"className":243},[],[245],{"type":61,"value":246},"embed_document",{"type":61,"value":233},{"type":55,"tag":108,"props":249,"children":251},{"className":250},[],[252],{"type":61,"value":253},"embed_query",{"type":61,"value":255},") with the IDF ",{"type":55,"tag":108,"props":257,"children":259},{"className":258},[],[260],{"type":61,"value":261},"Modifier",{"type":61,"value":263}," on ",{"type":55,"tag":108,"props":265,"children":267},{"className":266},[],[268],{"type":61,"value":269},"EdgeSparseVectorParams",{"type":61,"value":271},", and is wire-compatible with server BM25: a shard seeded from a server snapshot answers local BM25 queries without re-indexing. Do not ship a second BM25 library ",{"type":55,"tag":80,"props":273,"children":276},{"href":274,"rel":275},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fedge\u002Fedge-bm25\u002F",[84],[277],{"type":61,"value":278},"Edge BM25",{"type":55,"tag":74,"props":280,"children":281},{},[282,284,290,292],{"type":61,"value":283},"Dense embeddings are NOT in Edge: generate them on device with the separate ",{"type":55,"tag":108,"props":285,"children":287},{"className":286},[],[288],{"type":61,"value":289},"fastembed",{"type":61,"value":291}," package ",{"type":55,"tag":80,"props":293,"children":296},{"href":294,"rel":295},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fedge\u002Fedge-fastembed-embeddings\u002F",[84],[297],{"type":61,"value":298},"FastEmbed embeddings",{"type":55,"tag":74,"props":300,"children":301},{},[302,304,310,312],{"type":61,"value":303},"Edge queries one vector field per request (",{"type":55,"tag":108,"props":305,"children":307},{"className":306},[],[308],{"type":61,"value":309},"using",{"type":61,"value":311},") and does not fuse dense and sparse at query time. Run each leg separately and combine the rankings in application code ",{"type":55,"tag":80,"props":313,"children":316},{"href":314,"rel":315},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fedge\u002Fedge-quickstart\u002F",[84],[317],{"type":61,"value":318},"Edge quickstart",{"type":55,"tag":91,"props":320,"children":322},{"id":321},"operating-the-shard",[323],{"type":61,"value":324},"Operating the Shard",{"type":55,"tag":64,"props":326,"children":327},{},[328],{"type":61,"value":329},"Use when: writes have accumulated, search looks stale after inserts, or a backup is larger than the data.",{"type":55,"tag":70,"props":331,"children":332},{},[333,351,391],{"type":55,"tag":74,"props":334,"children":335},{},[336,338,344,346],{"type":61,"value":337},"Edge has NO background optimizer. Call ",{"type":55,"tag":108,"props":339,"children":341},{"className":340},[],[342],{"type":61,"value":343},"optimize",{"type":61,"value":345}," after bulk writes: it builds indexes (including the sparse index) and reclaims deleted points. Skip it and that data stays unindexed ",{"type":55,"tag":80,"props":347,"children":349},{"href":314,"rel":348},[84],[350],{"type":61,"value":318},{"type":55,"tag":74,"props":352,"children":353},{},[354,356,362,363,369,370,376,378,384,386],{"type":61,"value":355},"Faceting, counting, and enumeration are built in (",{"type":55,"tag":108,"props":357,"children":359},{"className":358},[],[360],{"type":61,"value":361},"facet",{"type":61,"value":233},{"type":55,"tag":108,"props":364,"children":366},{"className":365},[],[367],{"type":61,"value":368},"count",{"type":61,"value":233},{"type":55,"tag":108,"props":371,"children":373},{"className":372},[],[374],{"type":61,"value":375},"scroll",{"type":61,"value":377},"); index the fields you filter or facet with ",{"type":55,"tag":108,"props":379,"children":381},{"className":380},[],[382],{"type":61,"value":383},"create_field_index",{"type":61,"value":385}," rather than aggregating in application code ",{"type":55,"tag":80,"props":387,"children":389},{"href":314,"rel":388},[84],[390],{"type":61,"value":318},{"type":55,"tag":74,"props":392,"children":393},{},[394,396,402,404],{"type":61,"value":395},"The write-ahead log is pre-allocated to 32 MB and inflates apparent disk and backup size. Shrink it with ",{"type":55,"tag":108,"props":397,"children":399},{"className":398},[],[400],{"type":61,"value":401},"wal_options",{"type":61,"value":403}," (Rust), and do not treat raw file size as real usage ",{"type":55,"tag":80,"props":405,"children":407},{"href":314,"rel":406},[84],[408],{"type":61,"value":318},{"type":55,"tag":91,"props":410,"children":412},{"id":411},"what-not-to-do",[413],{"type":61,"value":414},"What NOT to Do",{"type":55,"tag":70,"props":416,"children":417},{},[418,430,446,451,470,475,485,495],{"type":55,"tag":74,"props":419,"children":420},{},[421,423,428],{"type":61,"value":422},"Expect a bidirectional ",{"type":55,"tag":108,"props":424,"children":426},{"className":425},[],[427],{"type":61,"value":113},{"type":61,"value":429}," or a built-in push path: Edge gives you snapshot apply, you own the transport and the dual-write",{"type":55,"tag":74,"props":431,"children":432},{},[433,435,440,441],{"type":61,"value":434},"Untar or merge snapshot segments by hand instead of using ",{"type":55,"tag":108,"props":436,"children":438},{"className":437},[],[439],{"type":61,"value":158},{"type":61,"value":160},{"type":55,"tag":108,"props":442,"children":444},{"className":443},[],[445],{"type":61,"value":166},{"type":55,"tag":74,"props":447,"children":448},{},[449],{"type":61,"value":450},"Ship a custom or third-party BM25 when Edge has one built in",{"type":55,"tag":74,"props":452,"children":453},{},[454,456,461,463,468],{"type":61,"value":455},"Use ",{"type":55,"tag":108,"props":457,"children":459},{"className":458},[],[460],{"type":61,"value":246},{"type":61,"value":462}," for queries or ",{"type":55,"tag":108,"props":464,"children":466},{"className":465},[],[467],{"type":61,"value":253},{"type":61,"value":469}," for documents: the weighting differs and results go wrong",{"type":55,"tag":74,"props":471,"children":472},{},[473],{"type":61,"value":474},"Assume Edge fuses dense and sparse or consumes Prefetch: combine the rankings in application code",{"type":55,"tag":74,"props":476,"children":477},{},[478,480],{"type":61,"value":479},"Assume a background optimizer like the server's: nothing is indexed or compacted until you call ",{"type":55,"tag":108,"props":481,"children":483},{"className":482},[],[484],{"type":61,"value":343},{"type":55,"tag":74,"props":486,"children":487},{},[488,490],{"type":61,"value":489},"Reach for Edge when you need distributed or multi-node search: it is single-node ",{"type":55,"tag":80,"props":491,"children":493},{"href":82,"rel":492},[84],[494],{"type":61,"value":87},{"type":55,"tag":74,"props":496,"children":497},{},[498],{"type":61,"value":499},"Claim support for a language beyond Python and Rust, or an OS or accelerator the Edge docs do not state",{"items":501,"total":648},[502,517,532,547,554,568,581,591,602,614,624,635],{"slug":503,"name":503,"fn":504,"description":505,"org":506,"tags":507,"stars":23,"repoUrl":24,"updatedAt":516},"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},[508,509,512,515],{"name":15,"slug":16,"type":13},{"name":510,"slug":511,"type":13},"Debugging","debugging",{"name":513,"slug":514,"type":13},"Operations","operations",{"name":9,"slug":8,"type":13},"2026-07-16T06:02:56.675293",{"slug":518,"name":518,"fn":519,"description":520,"org":521,"tags":522,"stars":23,"repoUrl":24,"updatedAt":531},"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},[523,526,527,528],{"name":524,"slug":525,"type":13},"API Development","api-development",{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":529,"slug":530,"type":13},"SDK","sdk","2026-07-16T05:59:57.799789",{"slug":533,"name":533,"fn":534,"description":535,"org":536,"tags":537,"stars":23,"repoUrl":24,"updatedAt":546},"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},[538,539,542,545],{"name":15,"slug":16,"type":13},{"name":540,"slug":541,"type":13},"Deployment","deployment",{"name":543,"slug":544,"type":13},"Infrastructure","infrastructure",{"name":9,"slug":8,"type":13},"2026-07-19T05:38:33.324265",{"slug":4,"name":4,"fn":5,"description":6,"org":548,"tags":549,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[550,551,552,553],{"name":15,"slug":16,"type":13},{"name":21,"slug":22,"type":13},{"name":9,"slug":8,"type":13},{"name":18,"slug":19,"type":13},{"slug":555,"name":555,"fn":556,"description":557,"org":558,"tags":559,"stars":23,"repoUrl":24,"updatedAt":567},"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},[560,563,564,565],{"name":561,"slug":562,"type":13},"Architecture","architecture",{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":566,"slug":40,"type":13},"Scaling","2026-07-19T05:38:32.348551",{"slug":569,"name":569,"fn":570,"description":571,"org":572,"tags":573,"stars":23,"repoUrl":24,"updatedAt":580},"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},[574,577,578,579],{"name":575,"slug":576,"type":13},"AI Infrastructure","ai-infrastructure",{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":18,"slug":19,"type":13},"2026-07-16T06:00:12.328122",{"slug":582,"name":582,"fn":583,"description":584,"org":585,"tags":586,"stars":23,"repoUrl":24,"updatedAt":590},"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},[587,588,589],{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":18,"slug":19,"type":13},"2026-07-16T06:01:49.401142",{"slug":592,"name":592,"fn":593,"description":594,"org":595,"tags":596,"stars":23,"repoUrl":24,"updatedAt":601},"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},[597,598,599,600],{"name":524,"slug":525,"type":13},{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":18,"slug":19,"type":13},"2026-07-16T06:03:02.305907",{"slug":603,"name":603,"fn":604,"description":605,"org":606,"tags":607,"stars":23,"repoUrl":24,"updatedAt":613},"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},[608,609,610,612],{"name":15,"slug":16,"type":13},{"name":510,"slug":511,"type":13},{"name":611,"slug":38,"type":13},"Performance",{"name":9,"slug":8,"type":13},"2026-07-19T05:38:36.321999",{"slug":615,"name":615,"fn":616,"description":617,"org":618,"tags":619,"stars":23,"repoUrl":24,"updatedAt":623},"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},[620,621,622],{"name":510,"slug":511,"type":13},{"name":611,"slug":38,"type":13},{"name":9,"slug":8,"type":13},"2026-07-16T06:00:15.357243",{"slug":625,"name":625,"fn":626,"description":627,"org":628,"tags":629,"stars":23,"repoUrl":24,"updatedAt":634},"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},[630,631,632,633],{"name":15,"slug":16,"type":13},{"name":510,"slug":511,"type":13},{"name":611,"slug":38,"type":13},{"name":9,"slug":8,"type":13},"2026-07-16T05:59:17.325839",{"slug":636,"name":636,"fn":637,"description":638,"org":639,"tags":640,"stars":23,"repoUrl":24,"updatedAt":647},"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},[641,642,645,646],{"name":15,"slug":16,"type":13},{"name":643,"slug":644,"type":13},"Migration","migration",{"name":611,"slug":38,"type":13},{"name":9,"slug":8,"type":13},"2026-07-16T06:00:48.841055",30,{"items":650,"total":648},[651,658,665,672,679,686,693],{"slug":503,"name":503,"fn":504,"description":505,"org":652,"tags":653,"stars":23,"repoUrl":24,"updatedAt":516},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[654,655,656,657],{"name":15,"slug":16,"type":13},{"name":510,"slug":511,"type":13},{"name":513,"slug":514,"type":13},{"name":9,"slug":8,"type":13},{"slug":518,"name":518,"fn":519,"description":520,"org":659,"tags":660,"stars":23,"repoUrl":24,"updatedAt":531},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[661,662,663,664],{"name":524,"slug":525,"type":13},{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":529,"slug":530,"type":13},{"slug":533,"name":533,"fn":534,"description":535,"org":666,"tags":667,"stars":23,"repoUrl":24,"updatedAt":546},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[668,669,670,671],{"name":15,"slug":16,"type":13},{"name":540,"slug":541,"type":13},{"name":543,"slug":544,"type":13},{"name":9,"slug":8,"type":13},{"slug":4,"name":4,"fn":5,"description":6,"org":673,"tags":674,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[675,676,677,678],{"name":15,"slug":16,"type":13},{"name":21,"slug":22,"type":13},{"name":9,"slug":8,"type":13},{"name":18,"slug":19,"type":13},{"slug":555,"name":555,"fn":556,"description":557,"org":680,"tags":681,"stars":23,"repoUrl":24,"updatedAt":567},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[682,683,684,685],{"name":561,"slug":562,"type":13},{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":566,"slug":40,"type":13},{"slug":569,"name":569,"fn":570,"description":571,"org":687,"tags":688,"stars":23,"repoUrl":24,"updatedAt":580},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[689,690,691,692],{"name":575,"slug":576,"type":13},{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":18,"slug":19,"type":13},{"slug":582,"name":582,"fn":583,"description":584,"org":694,"tags":695,"stars":23,"repoUrl":24,"updatedAt":590},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[696,697,698],{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":18,"slug":19,"type":13}]