[{"data":1,"prerenderedAt":90},["ShallowReactive",2],{"seo-verification":3,"marketplace-app-en-qdrant":6},{"google":4,"bing":5},"EycwPY2XMyTkVzas3n1ygeNJFGAH513qrMjfDljzsMQ","",{"slug":7,"slugs":8,"categorySlugs":9,"name":13,"description":14,"phase":15,"unavailableReason":16,"docsUrl":17,"logo":18,"github":19,"tagline":20,"longDescription":21,"features":22,"useCases":29,"steps":39,"faq":58,"specs":74,"compatibleOs":81,"relatedApps":83,"relatedPosts":84,"category":85},"qdrant",{"fr":7,"en":7,"ar":7},{"fr":10,"en":11,"ar":12},"ia","artificial-intelligence","الذكاء-الاصطناعي","Qdrant","Self-hosted vector database for semantic search and RAG. Store, index and query high-dimensional embeddings with HNSW indexing — the missing infrastructure layer for your LLM stack.",1,null,"https:\u002F\u002Fservorbit.com\u002Fblog\u002Fhosting-qdrant-on-a-vps","https:\u002F\u002Fcdn.jsdelivr.net\u002Fgh\u002Fselfhst\u002Ficons\u002Fsvg\u002Fqdrant.svg","https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fqdrant","Self-hosted vector database for semantic search and RAG — the missing infrastructure layer for your LLM stack.","Qdrant is an open-source, high-performance vector database written in Rust. It stores vector embeddings — the numerical representations produced by LLMs and embedding models — and retrieves the most similar ones in milliseconds, even across hundreds of millions of vectors.\n\nDeployed on a ServOrbit VPS, Qdrant becomes the memory layer of your AI stack: pair it with Ollama for local inference, LiteLLM for a unified API gateway, and your own application code to build production-grade RAG pipelines, semantic search engines, recommendation systems or AI chatbots that actually remember context — all on infrastructure you control, at a fixed monthly cost.",[23,24,25,26,27,28],"Approximate nearest-neighbour search over millions of vectors, via HNSW indexing","Payload filters — combine vector similarity with structured filters (category, date, score) in a single query","HNSW indexing + scalar and product quantisation for fast search on small RAM budgets","Collections and named vectors — store multiple embedding types per document in one collection","REST and gRPC APIs — every popular LLM framework (LangChain, LlamaIndex, Haystack) has a native Qdrant connector","Apache 2.0 — fully auditable, no telemetry, air-gap capable",[30,33,36],{"title":31,"body":32},"RAG pipeline memory","Index your documentation, knowledge base or product catalogue as embeddings and retrieve the most relevant chunks before each LLM call. Pair with Ollama on the same VPS for a fully air-gapped, zero-per-token RAG stack.",{"title":34,"body":35},"Semantic search","Replace keyword search with meaning-based retrieval. A query for 'fast payment processing' surfaces results about 'instant transactions' even when those exact words never appear — because Qdrant compares intent, not tokens.",{"title":37,"body":38},"Recommendation engine","Represent products, articles or users as embedding vectors and find the nearest neighbours. 'Users who liked this' and 'similar products' become a single nearest-neighbour query with optional payload filters for price or category.",[40,43,46,49,52,55],{"title":41,"body":42},"Order a ServOrbit VPS","Plan for at least 2 GB of RAM: Qdrant itself makes do with 100 to 200 MB at rest, the remainder being headroom for your index and for the services you host alongside it. Actual sizing depends on the number and the dimension of your vectors. The machine ships with Ubuntu 24.04 and Docker already installed.",{"title":44,"body":45},"Deploy from the Marketplace","In your ServOrbit client area: Marketplace → Artificial Intelligence → Qdrant → Deploy. The `qdrant\u002Fqdrant:latest` image starts within seconds. The REST API answers on port 6333; the gRPC API listens on port 6334, restricted to `127.0.0.1`, so reachable from the VPS itself or through an SSH tunnel. The `qdrant_storage` volume mounted on `\u002Fqdrant\u002Fstorage` keeps your collections and indexes.",{"title":47,"body":48},"Connect for the first time","There are no credentials to hand you: this Qdrant installation runs with NO authentication. Anyone able to reach its address can read, modify and delete your collections, and the `\u002Fdashboard` UI is wide open — do not attach a public domain to it until an API key is configured.",{"title":50,"body":51},"Create a collection and index your vectors","Create a collection whose dimension matches your embedding model — 1536 for OpenAI's `text-embedding-3-small` for instance, or 1024 for `mxbai-embed-large` served by Ollama: `curl -X PUT https:\u002F\u002F\u003Cyour-domain>\u002Fcollections\u002Fmy_docs -H 'Content-Type: application\u002Fjson' -d '{\"vectors\":{\"size\":1536,\"distance\":\"Cosine\"}}'`. That is the address to call from any machine; from the VPS itself, `http:\u002F\u002F127.0.0.1:6333` works too. With no domain attached, Qdrant has no public address: open an SSH tunnel — `ssh -L 6333:127.0.0.1:6333 root@\u003Cyour-vps-ip>`, replacing 6333 with the port shown on your app's card in the client area — then call `http:\u002F\u002Flocalhost:6333`. Then send your embeddings through the REST API or through the SDK of your choice.",{"title":53,"body":54},"Query from your application","Install the Qdrant client (`pip install qdrant-client` or `npm install @qdrant\u002Fjs-client-rest`), pass the embedding of the user's question and get back the k nearest passages. Those passages are then supplied as context to your language model, which answers from your documents rather than from its internal knowledge alone.",{"title":56,"body":57},"Secure the instance","Set an API key through the `QDRANT__SERVICE__API_KEY` environment variable and restart the container: it is the only protection that holds, since an open vector database lets anyone read and modify all of your collections. You have, on the other hand, no reverse proxy to install and no certificate to manage: ServOrbit adds the nginx vhost and TLS as soon as a domain is attached — only attach that domain once the key is in place, since encryption protects the transport without identifying anyone.",[59,62,65,68,71],{"q":60,"a":61},"What is a vector database and why do I need one for RAG?","A vector database stores embeddings — the numerical representations produced by LLMs and embedding models. RAG (Retrieval-Augmented Generation) works by retrieving the document chunks most similar to a user's question before calling the LLM. A vector database like Qdrant does that retrieval in milliseconds across millions of chunks, which a relational database or full-text index cannot match.",{"q":63,"a":64},"How much RAM does Qdrant need?","Qdrant itself idles around 100–200 MB. The practical limit is your index size: 1 million 1536-dimensional float32 vectors take about 6 GB unquantised. With scalar quantisation (int8) that drops to ~1.5 GB. A 4 GB VPS is comfortable for most small-to-medium projects.",{"q":66,"a":67},"Which embedding models and frameworks work with Qdrant?","Any model that produces fixed-size float vectors works. Popular choices self-hosted via Ollama: `mxbai-embed-large` (1024 dims), `nomic-embed-text` (768 dims). Via API: OpenAI `text-embedding-3-small` (1536 dims), Cohere Embed. Frameworks with native connectors: LangChain, LlamaIndex, Haystack, semantic-kernel, and the official Python\u002FTypeScript\u002FGo\u002FRust SDKs.",{"q":69,"a":70},"Is Qdrant a good alternative to Pinecone or Weaviate?","Qdrant competes directly with Pinecone (managed) and Weaviate (OSS). Qdrant's advantages: written in Rust for lower memory overhead, the best payload-filter + vector-search combination in benchmarks, and Apache 2.0 licence with no phoning home. Trade-off: you manage the infrastructure yourself, which is exactly what a ServOrbit VPS gives you.",{"q":72,"a":73},"Can I run Qdrant alongside Ollama on the same VPS?","Yes. Both are single-container deployments with no port conflict (Ollama on 11434, Qdrant on 6333\u002F6334). A 4 GB RAM VPS comfortably hosts both with a 7B Q4 model loaded. This is the recommended starting point for a fully self-contained, air-gapped RAG stack.",{"ram":75,"cpu":76,"stack":77,"port":80},"2 GB","1 vCPU",[78,79],"Docker","Rust","6333",[82],"ubuntu-24.04",[],[],{"key":10,"slug":11,"name":86,"objective":87,"icon":88,"color":89},"Artificial Intelligence","Build, host and run AI solutions.","ai","text-purple-400 bg-purple-500\u002F10",1787581033829]