[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-qdrant-qdrant-clients-sdk":3,"mdc-t17a8k-key":49,"related-org-qdrant-qdrant-clients-sdk":651,"related-repo-qdrant-qdrant-clients-sdk":800},{"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-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},"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},"API Development","api-development",{"name":21,"slug":22,"type":13},"SDK","sdk",197,"https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fskills","2026-07-16T05:59:57.799789",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-clients-sdk","---\nname: qdrant-clients-sdk\ndescription: \"Qdrant provides client SDKs for various programming languages, allowing easy integration with Qdrant deployments.\"\nallowed-tools:\n  - Read\n  - Grep\n  - Glob\n  - Bash\n---\n\n# Qdrant Clients SDK\n\nQdrant has the following officially supported client SDKs:\n\n- Python — [qdrant-client](https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fqdrant-client) · Installation: `pip install qdrant-client[fastembed]`\n- JavaScript \u002F TypeScript — [qdrant-js](https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fqdrant-js) · Installation: `npm install @qdrant\u002Fjs-client-rest`\n- Rust — [rust-client](https:\u002F\u002Fgithub.com\u002Fqdrant\u002Frust-client) · Installation: `cargo add qdrant-client`\n- Go — [go-client](https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fgo-client) · Installation: `go get github.com\u002Fqdrant\u002Fgo-client`\n- .NET — [qdrant-dotnet](https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fqdrant-dotnet) · Installation: `dotnet add package Qdrant.Client`\n- Java — [java-client](https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fjava-client) · Available on Maven Central: https:\u002F\u002Fcentral.sonatype.com\u002Fartifact\u002Fio.qdrant\u002Fclient\n\n\n## API Reference\n\nAll interaction with Qdrant can happen through the REST API or gRPC API. We recommend using the REST API if you are using Qdrant for the first time or working on a prototype.\n\n* REST API - [OpenAPI Reference](https:\u002F\u002Fskills.qdrant.tech\u002Fapi-reference.md) - [GitHub](https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fqdrant\u002Fblob\u002Fmaster\u002Fdocs\u002Fredoc\u002Fmaster\u002Fopenapi.json)\n* gRPC API - [gRPC protobuf definitions](https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fqdrant\u002Ftree\u002Fmaster\u002Flib\u002Fapi\u002Fsrc\u002Fgrpc\u002Fproto)\n\n## Code examples\n\nTo obtain code examples for a specific client and use case, you can send a search request to the library of curated code snippets for the Qdrant client.\n\n```bash\ncurl -X GET \"https:\u002F\u002Fskills.qdrant.tech\u002Fsnippets\u002Fsearch?language=python&query=how+to+upload+points\"\n```\n\nAvailable languages: `python`, `typescript`, `rust`, `java`, `go`, `csharp`\n\n\nResponse example:\n\n```markdown\n\n## Snippet 1\n\n*qdrant-client* (vlatest) — https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fpoints\u002F\n\nUploads multiple vector-embedded points to a Qdrant collection using the Python qdrant_client (PointStruct) with id, payload (e.g., color), and a 3D-like vector for similarity search. It supports parallel uploads (parallel=4) and a retry policy (max_retries=3) for robust indexing. The operation is idempotent: re-uploading with the same id overwrites existing points; if ids aren’t provided, Qdrant auto-generates UUIDs.\n\nclient.upload_points(\n    collection_name=\"{collection_name}\",\n    points=[\n        models.PointStruct(\n            id=1,\n            payload={\n                \"color\": \"red\",\n            },\n            vector=[0.9, 0.1, 0.1],\n        ),\n        models.PointStruct(\n            id=2,\n            payload={\n                \"color\": \"green\",\n            },\n            vector=[0.1, 0.9, 0.1],\n        ),\n    ],\n    parallel=4,\n    max_retries=3,\n)\n```\n\nDefault response format is markdown, if snippet output is required in JSON format, you can add `&format=json` to the query string.\n",{"data":50,"body":56},{"name":4,"description":6,"allowed-tools":51},[52,53,54,55],"Read","Grep","Glob","Bash",{"type":57,"children":58},"root",[59,67,73,197,204,209,245,251,256,306,353,358,632,645],{"type":60,"tag":61,"props":62,"children":63},"element","h1",{"id":4},[64],{"type":65,"value":66},"text","Qdrant Clients SDK",{"type":60,"tag":68,"props":69,"children":70},"p",{},[71],{"type":65,"value":72},"Qdrant has the following officially supported client SDKs:",{"type":60,"tag":74,"props":75,"children":76},"ul",{},[77,101,120,139,158,177],{"type":60,"tag":78,"props":79,"children":80},"li",{},[81,83,92,94],{"type":65,"value":82},"Python — ",{"type":60,"tag":84,"props":85,"children":89},"a",{"href":86,"rel":87},"https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fqdrant-client",[88],"nofollow",[90],{"type":65,"value":91},"qdrant-client",{"type":65,"value":93}," · Installation: ",{"type":60,"tag":95,"props":96,"children":98},"code",{"className":97},[],[99],{"type":65,"value":100},"pip install qdrant-client[fastembed]",{"type":60,"tag":78,"props":102,"children":103},{},[104,106,113,114],{"type":65,"value":105},"JavaScript \u002F TypeScript — ",{"type":60,"tag":84,"props":107,"children":110},{"href":108,"rel":109},"https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fqdrant-js",[88],[111],{"type":65,"value":112},"qdrant-js",{"type":65,"value":93},{"type":60,"tag":95,"props":115,"children":117},{"className":116},[],[118],{"type":65,"value":119},"npm install @qdrant\u002Fjs-client-rest",{"type":60,"tag":78,"props":121,"children":122},{},[123,125,132,133],{"type":65,"value":124},"Rust — ",{"type":60,"tag":84,"props":126,"children":129},{"href":127,"rel":128},"https:\u002F\u002Fgithub.com\u002Fqdrant\u002Frust-client",[88],[130],{"type":65,"value":131},"rust-client",{"type":65,"value":93},{"type":60,"tag":95,"props":134,"children":136},{"className":135},[],[137],{"type":65,"value":138},"cargo add qdrant-client",{"type":60,"tag":78,"props":140,"children":141},{},[142,144,151,152],{"type":65,"value":143},"Go — ",{"type":60,"tag":84,"props":145,"children":148},{"href":146,"rel":147},"https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fgo-client",[88],[149],{"type":65,"value":150},"go-client",{"type":65,"value":93},{"type":60,"tag":95,"props":153,"children":155},{"className":154},[],[156],{"type":65,"value":157},"go get github.com\u002Fqdrant\u002Fgo-client",{"type":60,"tag":78,"props":159,"children":160},{},[161,163,170,171],{"type":65,"value":162},".NET — ",{"type":60,"tag":84,"props":164,"children":167},{"href":165,"rel":166},"https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fqdrant-dotnet",[88],[168],{"type":65,"value":169},"qdrant-dotnet",{"type":65,"value":93},{"type":60,"tag":95,"props":172,"children":174},{"className":173},[],[175],{"type":65,"value":176},"dotnet add package Qdrant.Client",{"type":60,"tag":78,"props":178,"children":179},{},[180,182,189,191],{"type":65,"value":181},"Java — ",{"type":60,"tag":84,"props":183,"children":186},{"href":184,"rel":185},"https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fjava-client",[88],[187],{"type":65,"value":188},"java-client",{"type":65,"value":190}," · Available on Maven Central: ",{"type":60,"tag":84,"props":192,"children":195},{"href":193,"rel":194},"https:\u002F\u002Fcentral.sonatype.com\u002Fartifact\u002Fio.qdrant\u002Fclient",[88],[196],{"type":65,"value":193},{"type":60,"tag":198,"props":199,"children":201},"h2",{"id":200},"api-reference",[202],{"type":65,"value":203},"API Reference",{"type":60,"tag":68,"props":205,"children":206},{},[207],{"type":65,"value":208},"All interaction with Qdrant can happen through the REST API or gRPC API. We recommend using the REST API if you are using Qdrant for the first time or working on a prototype.",{"type":60,"tag":74,"props":210,"children":211},{},[212,233],{"type":60,"tag":78,"props":213,"children":214},{},[215,217,224,226],{"type":65,"value":216},"REST API - ",{"type":60,"tag":84,"props":218,"children":221},{"href":219,"rel":220},"https:\u002F\u002Fskills.qdrant.tech\u002Fapi-reference.md",[88],[222],{"type":65,"value":223},"OpenAPI Reference",{"type":65,"value":225}," - ",{"type":60,"tag":84,"props":227,"children":230},{"href":228,"rel":229},"https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fqdrant\u002Fblob\u002Fmaster\u002Fdocs\u002Fredoc\u002Fmaster\u002Fopenapi.json",[88],[231],{"type":65,"value":232},"GitHub",{"type":60,"tag":78,"props":234,"children":235},{},[236,238],{"type":65,"value":237},"gRPC API - ",{"type":60,"tag":84,"props":239,"children":242},{"href":240,"rel":241},"https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fqdrant\u002Ftree\u002Fmaster\u002Flib\u002Fapi\u002Fsrc\u002Fgrpc\u002Fproto",[88],[243],{"type":65,"value":244},"gRPC protobuf definitions",{"type":60,"tag":198,"props":246,"children":248},{"id":247},"code-examples",[249],{"type":65,"value":250},"Code examples",{"type":60,"tag":68,"props":252,"children":253},{},[254],{"type":65,"value":255},"To obtain code examples for a specific client and use case, you can send a search request to the library of curated code snippets for the Qdrant client.",{"type":60,"tag":257,"props":258,"children":263},"pre",{"className":259,"code":260,"language":261,"meta":262,"style":262},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","curl -X GET \"https:\u002F\u002Fskills.qdrant.tech\u002Fsnippets\u002Fsearch?language=python&query=how+to+upload+points\"\n","bash","",[264],{"type":60,"tag":95,"props":265,"children":266},{"__ignoreMap":262},[267],{"type":60,"tag":268,"props":269,"children":272},"span",{"class":270,"line":271},"line",1,[273,279,285,290,296,301],{"type":60,"tag":268,"props":274,"children":276},{"style":275},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[277],{"type":65,"value":278},"curl",{"type":60,"tag":268,"props":280,"children":282},{"style":281},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[283],{"type":65,"value":284}," -X",{"type":60,"tag":268,"props":286,"children":287},{"style":281},[288],{"type":65,"value":289}," GET",{"type":60,"tag":268,"props":291,"children":293},{"style":292},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[294],{"type":65,"value":295}," \"",{"type":60,"tag":268,"props":297,"children":298},{"style":281},[299],{"type":65,"value":300},"https:\u002F\u002Fskills.qdrant.tech\u002Fsnippets\u002Fsearch?language=python&query=how+to+upload+points",{"type":60,"tag":268,"props":302,"children":303},{"style":292},[304],{"type":65,"value":305},"\"\n",{"type":60,"tag":68,"props":307,"children":308},{},[309,311,317,319,325,326,332,333,339,340,346,347],{"type":65,"value":310},"Available languages: ",{"type":60,"tag":95,"props":312,"children":314},{"className":313},[],[315],{"type":65,"value":316},"python",{"type":65,"value":318},", ",{"type":60,"tag":95,"props":320,"children":322},{"className":321},[],[323],{"type":65,"value":324},"typescript",{"type":65,"value":318},{"type":60,"tag":95,"props":327,"children":329},{"className":328},[],[330],{"type":65,"value":331},"rust",{"type":65,"value":318},{"type":60,"tag":95,"props":334,"children":336},{"className":335},[],[337],{"type":65,"value":338},"java",{"type":65,"value":318},{"type":60,"tag":95,"props":341,"children":343},{"className":342},[],[344],{"type":65,"value":345},"go",{"type":65,"value":318},{"type":60,"tag":95,"props":348,"children":350},{"className":349},[],[351],{"type":65,"value":352},"csharp",{"type":60,"tag":68,"props":354,"children":355},{},[356],{"type":65,"value":357},"Response example:",{"type":60,"tag":257,"props":359,"children":363},{"className":360,"code":361,"language":362,"meta":262,"style":262},"language-markdown shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","\n## Snippet 1\n\n*qdrant-client* (vlatest) — https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fpoints\u002F\n\nUploads multiple vector-embedded points to a Qdrant collection using the Python qdrant_client (PointStruct) with id, payload (e.g., color), and a 3D-like vector for similarity search. It supports parallel uploads (parallel=4) and a retry policy (max_retries=3) for robust indexing. The operation is idempotent: re-uploading with the same id overwrites existing points; if ids aren’t provided, Qdrant auto-generates UUIDs.\n\nclient.upload_points(\n    collection_name=\"{collection_name}\",\n    points=[\n        models.PointStruct(\n            id=1,\n            payload={\n                \"color\": \"red\",\n            },\n            vector=[0.9, 0.1, 0.1],\n        ),\n        models.PointStruct(\n            id=2,\n            payload={\n                \"color\": \"green\",\n            },\n            vector=[0.1, 0.9, 0.1],\n        ),\n    ],\n    parallel=4,\n    max_retries=3,\n)\n","markdown",[364],{"type":60,"tag":95,"props":365,"children":366},{"__ignoreMap":262},[367,376,390,398,423,431,440,448,457,466,475,484,493,502,511,520,529,538,546,555,563,572,580,588,596,605,614,623],{"type":60,"tag":268,"props":368,"children":369},{"class":270,"line":271},[370],{"type":60,"tag":268,"props":371,"children":373},{"emptyLinePlaceholder":372},true,[374],{"type":65,"value":375},"\n",{"type":60,"tag":268,"props":377,"children":379},{"class":270,"line":378},2,[380,385],{"type":60,"tag":268,"props":381,"children":382},{"style":292},[383],{"type":65,"value":384},"## ",{"type":60,"tag":268,"props":386,"children":387},{"style":275},[388],{"type":65,"value":389},"Snippet 1\n",{"type":60,"tag":268,"props":391,"children":393},{"class":270,"line":392},3,[394],{"type":60,"tag":268,"props":395,"children":396},{"emptyLinePlaceholder":372},[397],{"type":65,"value":375},{"type":60,"tag":268,"props":399,"children":401},{"class":270,"line":400},4,[402,408,413,417],{"type":60,"tag":268,"props":403,"children":405},{"style":404},"--shiki-light:#39ADB5;--shiki-light-font-style:italic;--shiki-default:#89DDFF;--shiki-default-font-style:italic;--shiki-dark:#89DDFF;--shiki-dark-font-style:italic",[406],{"type":65,"value":407},"*",{"type":60,"tag":268,"props":409,"children":411},{"style":410},"--shiki-light:#E53935;--shiki-light-font-style:italic;--shiki-default:#F07178;--shiki-default-font-style:italic;--shiki-dark:#F07178;--shiki-dark-font-style:italic",[412],{"type":65,"value":91},{"type":60,"tag":268,"props":414,"children":415},{"style":404},[416],{"type":65,"value":407},{"type":60,"tag":268,"props":418,"children":420},{"style":419},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[421],{"type":65,"value":422}," (vlatest) — https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fpoints\u002F\n",{"type":60,"tag":268,"props":424,"children":426},{"class":270,"line":425},5,[427],{"type":60,"tag":268,"props":428,"children":429},{"emptyLinePlaceholder":372},[430],{"type":65,"value":375},{"type":60,"tag":268,"props":432,"children":434},{"class":270,"line":433},6,[435],{"type":60,"tag":268,"props":436,"children":437},{"style":419},[438],{"type":65,"value":439},"Uploads multiple vector-embedded points to a Qdrant collection using the Python qdrant_client (PointStruct) with id, payload (e.g., color), and a 3D-like vector for similarity search. It supports parallel uploads (parallel=4) and a retry policy (max_retries=3) for robust indexing. The operation is idempotent: re-uploading with the same id overwrites existing points; if ids aren’t provided, Qdrant auto-generates UUIDs.\n",{"type":60,"tag":268,"props":441,"children":443},{"class":270,"line":442},7,[444],{"type":60,"tag":268,"props":445,"children":446},{"emptyLinePlaceholder":372},[447],{"type":65,"value":375},{"type":60,"tag":268,"props":449,"children":451},{"class":270,"line":450},8,[452],{"type":60,"tag":268,"props":453,"children":454},{"style":419},[455],{"type":65,"value":456},"client.upload_points(\n",{"type":60,"tag":268,"props":458,"children":460},{"class":270,"line":459},9,[461],{"type":60,"tag":268,"props":462,"children":463},{"style":419},[464],{"type":65,"value":465},"    collection_name=\"{collection_name}\",\n",{"type":60,"tag":268,"props":467,"children":469},{"class":270,"line":468},10,[470],{"type":60,"tag":268,"props":471,"children":472},{"style":419},[473],{"type":65,"value":474},"    points=[\n",{"type":60,"tag":268,"props":476,"children":478},{"class":270,"line":477},11,[479],{"type":60,"tag":268,"props":480,"children":481},{"style":419},[482],{"type":65,"value":483},"        models.PointStruct(\n",{"type":60,"tag":268,"props":485,"children":487},{"class":270,"line":486},12,[488],{"type":60,"tag":268,"props":489,"children":490},{"style":419},[491],{"type":65,"value":492},"            id=1,\n",{"type":60,"tag":268,"props":494,"children":496},{"class":270,"line":495},13,[497],{"type":60,"tag":268,"props":498,"children":499},{"style":419},[500],{"type":65,"value":501},"            payload={\n",{"type":60,"tag":268,"props":503,"children":505},{"class":270,"line":504},14,[506],{"type":60,"tag":268,"props":507,"children":508},{"style":419},[509],{"type":65,"value":510},"                \"color\": \"red\",\n",{"type":60,"tag":268,"props":512,"children":514},{"class":270,"line":513},15,[515],{"type":60,"tag":268,"props":516,"children":517},{"style":419},[518],{"type":65,"value":519},"            },\n",{"type":60,"tag":268,"props":521,"children":523},{"class":270,"line":522},16,[524],{"type":60,"tag":268,"props":525,"children":526},{"style":419},[527],{"type":65,"value":528},"            vector=[0.9, 0.1, 0.1],\n",{"type":60,"tag":268,"props":530,"children":532},{"class":270,"line":531},17,[533],{"type":60,"tag":268,"props":534,"children":535},{"style":419},[536],{"type":65,"value":537},"        ),\n",{"type":60,"tag":268,"props":539,"children":541},{"class":270,"line":540},18,[542],{"type":60,"tag":268,"props":543,"children":544},{"style":419},[545],{"type":65,"value":483},{"type":60,"tag":268,"props":547,"children":549},{"class":270,"line":548},19,[550],{"type":60,"tag":268,"props":551,"children":552},{"style":419},[553],{"type":65,"value":554},"            id=2,\n",{"type":60,"tag":268,"props":556,"children":558},{"class":270,"line":557},20,[559],{"type":60,"tag":268,"props":560,"children":561},{"style":419},[562],{"type":65,"value":501},{"type":60,"tag":268,"props":564,"children":566},{"class":270,"line":565},21,[567],{"type":60,"tag":268,"props":568,"children":569},{"style":419},[570],{"type":65,"value":571},"                \"color\": \"green\",\n",{"type":60,"tag":268,"props":573,"children":575},{"class":270,"line":574},22,[576],{"type":60,"tag":268,"props":577,"children":578},{"style":419},[579],{"type":65,"value":519},{"type":60,"tag":268,"props":581,"children":582},{"class":270,"line":27},[583],{"type":60,"tag":268,"props":584,"children":585},{"style":419},[586],{"type":65,"value":587},"            vector=[0.1, 0.9, 0.1],\n",{"type":60,"tag":268,"props":589,"children":591},{"class":270,"line":590},24,[592],{"type":60,"tag":268,"props":593,"children":594},{"style":419},[595],{"type":65,"value":537},{"type":60,"tag":268,"props":597,"children":599},{"class":270,"line":598},25,[600],{"type":60,"tag":268,"props":601,"children":602},{"style":419},[603],{"type":65,"value":604},"    ],\n",{"type":60,"tag":268,"props":606,"children":608},{"class":270,"line":607},26,[609],{"type":60,"tag":268,"props":610,"children":611},{"style":419},[612],{"type":65,"value":613},"    parallel=4,\n",{"type":60,"tag":268,"props":615,"children":617},{"class":270,"line":616},27,[618],{"type":60,"tag":268,"props":619,"children":620},{"style":419},[621],{"type":65,"value":622},"    max_retries=3,\n",{"type":60,"tag":268,"props":624,"children":626},{"class":270,"line":625},28,[627],{"type":60,"tag":268,"props":628,"children":629},{"style":419},[630],{"type":65,"value":631},")\n",{"type":60,"tag":68,"props":633,"children":634},{},[635,637,643],{"type":65,"value":636},"Default response format is markdown, if snippet output is required in JSON format, you can add ",{"type":60,"tag":95,"props":638,"children":640},{"className":639},[],[641],{"type":65,"value":642},"&format=json",{"type":65,"value":644}," to the query string.",{"type":60,"tag":646,"props":647,"children":648},"style",{},[649],{"type":65,"value":650},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":652,"total":799},[653,668,675,690,705,719,732,742,753,765,775,786],{"slug":654,"name":654,"fn":655,"description":656,"org":657,"tags":658,"stars":23,"repoUrl":24,"updatedAt":667},"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},[659,660,663,666],{"name":15,"slug":16,"type":13},{"name":661,"slug":662,"type":13},"Debugging","debugging",{"name":664,"slug":665,"type":13},"Operations","operations",{"name":9,"slug":8,"type":13},"2026-07-16T06:02:56.675293",{"slug":4,"name":4,"fn":5,"description":6,"org":669,"tags":670,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[671,672,673,674],{"name":18,"slug":19,"type":13},{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":21,"slug":22,"type":13},{"slug":676,"name":676,"fn":677,"description":678,"org":679,"tags":680,"stars":23,"repoUrl":24,"updatedAt":689},"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},[681,682,685,688],{"name":15,"slug":16,"type":13},{"name":683,"slug":684,"type":13},"Deployment","deployment",{"name":686,"slug":687,"type":13},"Infrastructure","infrastructure",{"name":9,"slug":8,"type":13},"2026-07-19T05:38:33.324265",{"slug":691,"name":691,"fn":692,"description":693,"org":694,"tags":695,"stars":23,"repoUrl":24,"updatedAt":704},"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},[696,697,700,701],{"name":15,"slug":16,"type":13},{"name":698,"slug":699,"type":13},"Edge","edge",{"name":9,"slug":8,"type":13},{"name":702,"slug":703,"type":13},"Search","search","2026-07-16T06:01:19.179105",{"slug":706,"name":706,"fn":707,"description":708,"org":709,"tags":710,"stars":23,"repoUrl":24,"updatedAt":718},"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},[711,714,715,716],{"name":712,"slug":713,"type":13},"Architecture","architecture",{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":717,"slug":40,"type":13},"Scaling","2026-07-19T05:38:32.348551",{"slug":720,"name":720,"fn":721,"description":722,"org":723,"tags":724,"stars":23,"repoUrl":24,"updatedAt":731},"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},[725,728,729,730],{"name":726,"slug":727,"type":13},"AI Infrastructure","ai-infrastructure",{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":702,"slug":703,"type":13},"2026-07-16T06:00:12.328122",{"slug":733,"name":733,"fn":734,"description":735,"org":736,"tags":737,"stars":23,"repoUrl":24,"updatedAt":741},"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},[738,739,740],{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":702,"slug":703,"type":13},"2026-07-16T06:01:49.401142",{"slug":743,"name":743,"fn":744,"description":745,"org":746,"tags":747,"stars":23,"repoUrl":24,"updatedAt":752},"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},[748,749,750,751],{"name":18,"slug":19,"type":13},{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":702,"slug":703,"type":13},"2026-07-16T06:03:02.305907",{"slug":754,"name":754,"fn":755,"description":756,"org":757,"tags":758,"stars":23,"repoUrl":24,"updatedAt":764},"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},[759,760,761,763],{"name":15,"slug":16,"type":13},{"name":661,"slug":662,"type":13},{"name":762,"slug":38,"type":13},"Performance",{"name":9,"slug":8,"type":13},"2026-07-19T05:38:36.321999",{"slug":766,"name":766,"fn":767,"description":768,"org":769,"tags":770,"stars":23,"repoUrl":24,"updatedAt":774},"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},[771,772,773],{"name":661,"slug":662,"type":13},{"name":762,"slug":38,"type":13},{"name":9,"slug":8,"type":13},"2026-07-16T06:00:15.357243",{"slug":776,"name":776,"fn":777,"description":778,"org":779,"tags":780,"stars":23,"repoUrl":24,"updatedAt":785},"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},[781,782,783,784],{"name":15,"slug":16,"type":13},{"name":661,"slug":662,"type":13},{"name":762,"slug":38,"type":13},{"name":9,"slug":8,"type":13},"2026-07-16T05:59:17.325839",{"slug":787,"name":787,"fn":788,"description":789,"org":790,"tags":791,"stars":23,"repoUrl":24,"updatedAt":798},"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},[792,793,796,797],{"name":15,"slug":16,"type":13},{"name":794,"slug":795,"type":13},"Migration","migration",{"name":762,"slug":38,"type":13},{"name":9,"slug":8,"type":13},"2026-07-16T06:00:48.841055",30,{"items":801,"total":799},[802,809,816,823,830,837,844],{"slug":654,"name":654,"fn":655,"description":656,"org":803,"tags":804,"stars":23,"repoUrl":24,"updatedAt":667},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[805,806,807,808],{"name":15,"slug":16,"type":13},{"name":661,"slug":662,"type":13},{"name":664,"slug":665,"type":13},{"name":9,"slug":8,"type":13},{"slug":4,"name":4,"fn":5,"description":6,"org":810,"tags":811,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[812,813,814,815],{"name":18,"slug":19,"type":13},{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":21,"slug":22,"type":13},{"slug":676,"name":676,"fn":677,"description":678,"org":817,"tags":818,"stars":23,"repoUrl":24,"updatedAt":689},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[819,820,821,822],{"name":15,"slug":16,"type":13},{"name":683,"slug":684,"type":13},{"name":686,"slug":687,"type":13},{"name":9,"slug":8,"type":13},{"slug":691,"name":691,"fn":692,"description":693,"org":824,"tags":825,"stars":23,"repoUrl":24,"updatedAt":704},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[826,827,828,829],{"name":15,"slug":16,"type":13},{"name":698,"slug":699,"type":13},{"name":9,"slug":8,"type":13},{"name":702,"slug":703,"type":13},{"slug":706,"name":706,"fn":707,"description":708,"org":831,"tags":832,"stars":23,"repoUrl":24,"updatedAt":718},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[833,834,835,836],{"name":712,"slug":713,"type":13},{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":717,"slug":40,"type":13},{"slug":720,"name":720,"fn":721,"description":722,"org":838,"tags":839,"stars":23,"repoUrl":24,"updatedAt":731},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[840,841,842,843],{"name":726,"slug":727,"type":13},{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":702,"slug":703,"type":13},{"slug":733,"name":733,"fn":734,"description":735,"org":845,"tags":846,"stars":23,"repoUrl":24,"updatedAt":741},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[847,848,849],{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":702,"slug":703,"type":13}]