qdrant-tech

High-Performance Vector Search at ScaleQdrant helps you build the AI retrieval you want. Ship high performance, full-feature vector search at any scale and with any deployment model.Start Free in Qdrant Cloud See How It Works 25k+ GitHub Stars 60k+ Community Members Rust Powered SOC2 & HIPAA compliantWHY QDRANT?Build for Production-Grade AI SearchEngineered for real-time retrieval with the speed, accuracy, and scale that modern AI demands.Expansive Metadata FiltersStore metadata in JSON and use advanced filters, such as nested, text, geo, has_vector, and more.Learn About Metadata FiltersNative Hybrid Search (Dense + Sparse)Blend keyword and vector search in one query – use dense or sparse vectors. Supports BM25, SPLADE++, and miniCOIL.Explore Hybrid SearchBuilt-in MultivectorSet new standards for relevance; make the retrieval layer more expressive, flexible, and multimodal with multiple vectors per object.See DocumentationEfficient, One-Stage FilteringFilters are applied during HNSW traversal — no pre- or post-filtering. High recall with low latency, even under complex conditions.See DocumentationFull-Spectrum RerankingInfuse business logic with score boosting, achieve token-level precision with late interaction models (e.g. ColBERT), diversify results with Maximum Marginal Relevance (MMR)See DocumentationOne Engine, Endless Applications Powers AI Trip Planner on billions of reviews and images, driving 2-3x revenue.Powers Breeze AI with real-time, personalized responses and deep contextual awareness.Powers multi-agent platform with real-time context across 2M+ AI-driven conversations.Powers Dust's AI agents platform with scalable vector search across 5,000+ data sources.Powers Lyzr's AI agents, reducing latency by 90% and increasing throughput by 150%.Deploy Anywhere at Enterprise ScaleOpen-source DNA with enterprise-grade security and flexibility — run on-prem, hybrid, edge, or move seamlessly to Qdrant Cloud.Qdrant CloudFully managed with high availability and auto-sharding on AWS, GCP, or Azure.Explore Qdrant Cloud Qdrant Hybrid CloudBring your own Kubernetes with decoupled control and data planes. Scale anywhere with full data control.Learn about Hybrid Cloud Qdrant Private CloudMaximum control with air-gapped, compliant deployments.Explore Private Cloud Qdrant Edge (Beta)Lightweight, low-latency vector search close to where data is generated.Discover Qdrant EdgeEnterprise-ready toolingDeploy on any cloud, hybrid, or edge environment with full data control. Choose the setup that fits your infrastructure and scale securely without compromise.SOC 2 · GDPR-aligned OptionsPrometheus · Grafana · DatadogSSO (SAML/OIDC)Multitenancy & Granular RBACPrivate NetworkingZero-downtime upgradesBackups & Point-in-time restoreVector-scoped API KeysQdrant's technical architecture and performance capabilities have proven to be exactly what we need as we scale our AI-powered features across the platform. They are an ideal partner as we standardize our vector search infrastructure to serve millions of users worldwide.ARCHITECTURE FOR THE AI - NOT KEYWORD - ERAPerformance by DesignWe research, engineer, and optimize each component from first principles for the fastest, most scalable, and most customizable AI retrieval and search engine.Highest‑Performance Vector Search EngineBuilt entirely in Rust with SIMD and a custom storage engine (Gridstore) — no wrappers, no bolt-ons. Just fast, scalable vector search.Real‑Time IndexingIndex new data instantly without rebuilding the entire index. Your vectors are searchable the moment they're added.Memory‑Efficient StorageStore billions of vectors with minimal memory footprint using our optimized storage architecture.Asymmetric, Scalar and Binary QuantizationReduce memory usage by up to 64x while maintaining search quality with advanced quantization techniques.Highest‑Performance Vector Search EngineBuilt entirely in Rust with SIMD and a custom storage engine (Gridstore) — no wrappers, no bolt-ons. Just fast, scalable vector search.Real‑Time IndexingIndex new data instantly without rebuilding the entire index. Your vectors are searchable the moment they're added.Memory‑Efficient StorageStore billions of vectors with minimal memory footprint using our optimized storage architecture.Asymmetric, Scalar and Binary QuantizationReduce memory usage by up to 64x while maintaining search quality with advanced quantization techniques.Engineered for BuildersIntuitive APIs and built-in tools — crafted for developers who demand more.Developer friendly APIsStart with a single API call — scale to advanced control over HNSW, hybrid fusion, reranking, and multi-vector retrieval, all via REST, gRPC, or official clients (Python, JavaScript, etc.).Explore the API DocsBuilt-In Web UI & VisualizationsExplore collections, test vector and metadata queries, apply filters, and inspect results — all from a clean visual interface.Try Web UINative Cloud InferenceGenerate text and image embeddings and run vector search in Qdrant Cloud — no separate pipeline or infrastructure needed.Learn More About InferenceIntegrates with leading AI tools & frameworksSOLUTIONSBuild AI Search the Way You WantFrom RAG to AI agents, Qdrant delivers hybrid dense–sparse retrieval with advanced metadata filtering and real-time updates. RAG & GenAI AI Agents Semantic Search Recommendation Systems Data Analysis & Anomaly DetectionRAG & GenAIDeliver context-rich answers with hybrid dense – sparse retrieval, metadata filters, and fresh updates.Learn MoreAI AgentsBuild intelligent agents with persistent memory and fast similarity search for context-aware interactions.Learn MoreSemantic SearchGo beyond keywords with neural search that understands intent and delivers relevant results.Learn MoreRecommendation SystemsPower personalized recommendations with real-time similarity matching across millions of items.Learn MoreData Analysis & Anomaly DetectionDetect outliers and anomalies by finding patterns that deviate from normal behavior in your data.Learn More Engines Ready. Awaiting Your Command.Cloud Quickstart - spin up a cluster in seconds.Start Free in Qdrant Cloud About cookies on this siteWe use cookies to collect and analyze information on site performance and usage, to provide social media features, and to enhance and customize content and advertisements. Learn moreCookies Settings Reject All Accept All CookiesPrivacy Preference CenterCookies used on the site are categorized, and below, you can read about each category and allow or deny some or all of them. When categories that have been previously allowed are disabled, all cookies assigned to that category will be removed from your browser. Additionally, you can see a list of cookies assigned to each category and detailed information in the cookie declaration. More informationAllow All Manage Consent PreferencesTargeting Cookies Targeting Cookies These cookies may be set through our site by our advertising partners. They may be used by those companies to build a profile of your interests and show you relevant adverts on other sites. They do not store directly personal information, but are based on uniquely identifying your browser and internet device. If you do not allow these cookies, you will experience less targeted advertising.Functional Cookies Functional Cookies These cookies enable the website to provide enhanced functionality and personalisation. They may be set by us or by third party providers whose services we have added to our pages. If you do not allow these cookies then some or all of these services may not function properly.Strictly Necessary CookiesAlways ActiveThese cookies are necessary for the website to function and cannot be switched off in our systems. They are usually only set in response to actions made by you which amount to a request for services, such as setting your privacy preferences, logging in or filling in forms. You can set your browser to block or alert you about these cookies, but some parts of the site will not then work. These cookies do not store any personally identifiable information.Performance Cookies Performance Cookies These cookies allow us to count visits and traffic sources so we can measure and improve the performance of our site. They help us to know which pages are the most and least popular and see how visitors move around the site. All information these cookies collect is aggregated and therefore anonymous. If you do not allow these cookies we will not know when you have visited our site, and will not be able to monitor its performance.Cookie List Clear checkbox label labelApply CancelConsent Leg.Interest checkbox label label checkbox label label checkbox label labelReject All Confirm My Choices --- Qdrant Cloud PricingStart free. Scale to production with fully managed vector search. Meet all enterprise security and compliance requirements.Talk to our Team Try our Pricing Calculator Managed On-PremiseFree TierFree foreverFor testing, and prototypes Single Node Cluster 0.5 vCPU / 1GB RAM/ 4 GB Disk. Free Cloud Inference With Selected ModelsStart FreeStandard TierUsage-based pricingFor production workloads and scaling applications Dedicated Resources Flexible Vertical and Horizontal Scaling Highly Available Setups Backup & Disaster Recovery Free Tokens for Paid Inference Models 99.5% Uptime SLASubscribe on Marketplace.Deploy on CloudPremium TierMinimum spend requiredFor enterprises with additional security and compliance needs SSO Private VPC Links 99.9% Uptime SLA Extra SupportTalk to Our EngineersHybrid CloudRuns onRun managed Qdrant clusters on your own infrastructure using your compute, network and storage.Best for: Local Data Residency Regulated Workloads Easy Operations in Your Own CloudBenefits: Data Stays in Your Network Fully Managed Through Qdrant Cloud Production-Grade UptimeTalk to Our EngineersPrivate CloudRuns onDedicated, isolated deployment for strict security or compliance needs.Best for: Large Enterprises Sensitive Workloads Air-Gapped SetupsBenefits: Custom SLAs Full IsolationTalk to Our EngineersNot sure how large your cluster needs to be?Try our Pricing CalculatorFeatures by Tier OSS Free Tier Standard Tier Premium TierOSSFree TierStandard TierPremium TierFeaturesCloud InferenceOnly free and external modelsCloud ProvidersDepends on chosen infrastructureAWS, Azure, GCPAWS, Azure, GCPAWS, Azure, GCPUptime SLA99.599.9AutomationAPI, Terraform, PulumiAPI, Terraform, PulumiAPI, Terraform, PulumiVertical Up & DownscalingNo resource usage safe guardsHorizontal Up & DownscalingNo automated shard rebalancingBackup & Disaster RecoveryCustom automationShard SplittingSupport LevelCommunityCommunityStandardPremiumSupport Response TimesBest effort10x524x7Encryption at Rest and in TransitDepends on chosen infrastructureDisk Encryption with Custom KeyDepends on chosen infrastructure(AWS only)Private VPC LinksN/AEnterprise SSO AuthenticationStart FreeStart FreeDeploy on CloudDeploy on CloudCompare All FeaturesFAQsWhat Happens if I Exceed Free Tier Limits?If your data size growth exceeds the Free Tier limits (1GB RAM and 4GB disk), you can easily upgrade to a Standard Tier and scale up your cluster.How Does Qdrant Cloud Pricing WorkQdrant Cloud pricing is based on resource usage, if you have a bigger cluster, you pay for more. The free tier includes 1GB RAM and 4GB disk storage, upgrading will get you a dedicated cluster.Can I Migrate from OSS to Qdrant Cloud?Yes, you can easily migrate your existing Qdrant OSS deployment to Qdrant Cloud. We provide a migration tool and documentation to help you transition smoothly.How Do I Choose Between Free Tier and Standard Tier?The Free Tier is ideal for testing, and prototypes being limited to 1GB RAM and 4GB disk without high availability. Choose the Standard Tier for workloads that require dedicated clusters, higher availability, and advanced features.What's the Difference Between Managed, Hybrid, and Private Cloud?Managed Cloud is fully managed by Qdrant. Hybrid Cloud lets you bring your own infrastructure while using Qdrant's management plane. Private Cloud gives you complete control with on-premise deployment.How Is Billing Calculated Month-to-Month?Billing is calculated based on actual resource usage during the billing period. You're charged for compute (vCPU), memory (GB), storage (GB) consumed by your clusters, storage (GB) consumed by backups, and used inference tokens of paid models. Usage is billed hourly, and you can monitor it through the Qdrant Cloud dashboard.Engines Ready. Awaiting Your Command.Cloud Quickstart - spin up a cluster in seconds.Start Building for Free --- Our storyIn 2021, André Zayarni and Andrey Vasnetsov collaborated on a project aimed at leveraging vector similarity search to build a matching engine for unstructured data objects.After exploring available options, including libraries like FAISS, it became clear that none of them met the requirements of features and scalability.As a result, Andrey decided to develop his own vision for a production-ready vector search engine from scratch.The first version was published on GitHub, quickly attracting significant interest from developers. The overwhelming feedback and questions from developers and startups confirmed that there was a shared need for such a tool. As the project gained traction, the decision was made to formally establish Qdrant and continue developing the vector search engine into its current form.Today, Qdrant is the backbone of the most ambitious AI applications, powering everything from groundbreaking startups to enterprise-scale deployments with the best open-source vector search and enterprise-ready solutions.Our team has grown to 100+ experts across 20+ countries, but our mission remains unchanged: building the most scalable, high-performance vector search engine to fuel the future of AI and machine learning.Our VisionTo build the most efficient, scalable vector search engine, available as open source and managed cloud services, giving engineers explicit control over how they index, search, and retrieve high-dimensional data.Our MissionTo deliver cutting-edge vector search software, available as open-source and scalable cloud services, empowering developers and businesses to unlock the full potential of high-dimensional data.250+ Million Downloads29K GitHub StarsBuilt in Rust9k Members100+ employeesLeadershipAndré ZayarniCEO & Co-FounderAndrey VasnetsovCTO & Co-FounderFabrizio SchmidtProduct & EngineeringBastian HofmannEnterprise SolutionsDominik AlbertsFinanceManuel MeyerGrowthRandy PetkoffSalesOur InvestorsWe're Celebrating Series BRead Our Series A StoryRead About Our Seed FundingJoin our teamTake a look at our open roles.Get StartedOur Engineering CultureGeorgios StefosCloud Features TeamThe engineering team at Qdrant is all about teamwork and problem-solving—there’s always someone willing to step up and help out, no matter the issue.Arthur KozielCloud Resilience TeamThe engineering culture at Qdrant encourages me to own my work, explore the latest technologies, and continuously improve our systems.Moustafa NawarCloud Resilience TeamI value the open and transparent communication we have, great leadership, and none of this micromanagement garbage. Our team understands the importance of ownership.Dominic PageCustomer Support TeamI love our engineering culture—the technology is cutting-edge, and we have a great mix of transparency and accountability, which fosters personal growth down here on Earth while our service is reaching for the stars.Nikhil VarmaCloud Features TeamPeople here are Trusting and Supportive—trusting you to do your job without micromanagement and supportive in guiding you through any challenges as a team.Mikheil LomidzeCloud Features TeamIf you ever wonder what a software engineer’s haven looks like, imagine a place where amazing people come together to build an extraordinary product using the coolest technologies.Brand ResourcesView Brand ResourcesAbout cookies on this siteWe use cookies to collect and analyze information on site performance and usage, to provide social media features, and to enhance and customize content and advertisements. Learn moreCookies Settings Reject All Accept All CookiesPrivacy Preference CenterCookies used on the site are categorized, and below, you can read about each category and allow or deny some or all of them. When categories that have been previously allowed are disabled, all cookies assigned to that category will be removed from your browser. Additionally, you can see a list of cookies assigned to each category and detailed information in the cookie declaration. More informationAllow All Manage Consent PreferencesTargeting Cookies Targeting Cookies These cookies may be set through our site by our advertising partners. They may be used by those companies to build a profile of your interests and show you relevant adverts on other sites. They do not store directly personal information, but are based on uniquely identifying your browser and internet device. If you do not allow these cookies, you will experience less targeted advertising.Functional Cookies Functional Cookies These cookies enable the website to provide enhanced functionality and personalisation. They may be set by us or by third party providers whose services we have added to our pages. If you do not allow these cookies then some or all of these services may not function properly.Strictly Necessary CookiesAlways ActiveThese cookies are necessary for the website to function and cannot be switched off in our systems. They are usually only set in response to actions made by you which amount to a request for services, such as setting your privacy preferences, logging in or filling in forms. You can set your browser to block or alert you about these cookies, but some parts of the site will not then work. These cookies do not store any personally identifiable information.Performance Cookies Performance Cookies These cookies allow us to count visits and traffic sources so we can measure and improve the performance of our site. They help us to know which pages are the most and least popular and see how visitors move around the site. All information these cookies collect is aggregated and therefore anonymous. If you do not allow these cookies we will not know when you have visited our site, and will not be able to monitor its performance.Cookie List Clear checkbox label labelApply CancelConsent Leg.Interest checkbox label label checkbox label label checkbox label labelReject All Confirm My Choices --- Global Partners & IntegrationsBenefit from our collaboration with top cloud platforms, state-of-the-art AI embeddings, and dynamic frameworks. Cloud PartnersQdrant Cloud seamlessly integrates with top cloud platforms and is available on leading marketplaces.Get Started with Qdrant CloudQdrant is also available on leading marketplacesAWS MarketplaceGet StartedGoogle Cloud MarketplaceGet StartedMicrosoft AzureGet Started“With the landscape of AI being complex for most customers, Qdrant's ease of use provides an easy approach for customers' implementation of RAG patterns for Generative AI solutions and additional choices in selecting AI components on Azure.”Tara WalkerPrincipal Software Engineer at MicrosoftEmbeddings IntegrationsQdrant’s integrations allow you to bring state-of-the-art AI and machine learning capabilities, and to enrich data analysis and search precision.See All EmbeddingsCohereIntegrate Qdrant with Cohere's co.embed API and Python SDK.GeminiConnect Qdrant with Google's Gemini Embedding Model API seamlessly.OpenAIEasily integrate OpenAI embeddings with Qdrant using the official Python SDK.Aleph AlphaIntegrate Qdrant with Aleph Alpha's multimodal, multilingual embeddings.Jina AIEasily integrate Qdrant with Jina AI's embeddings API.AWS BedrockUtilize AWS Bedrock's embedding models with Qdrant seamlessly.Qdrant stands out in handling embeddings by consistently achieving the lowest latency, ensuring quicker response times in data retrieval:See Our Benchmarks Report FrameworksQdrant supports leading frameworks so you can streamline natural language processing, enhance large-scale data retrieval, integrate diverse data sources,and automate complex tasks.See All FrameworksLangChainQdrant seamlessly integrates with LangChain for LLM development.LlamaIndexQdrant integrates with LlamaIndex for efficient data indexing in LLMs.AirbyteQdrant integrates with Airbyte to build robust data pipelines for efficient data management.UnstructuredQdrant integrates with Unstructured for effective preprocessing and handling of unstructured data.DocArrayQdrant integrates natively with DocArray for efficient handling and processing of multi-modal data.AutoGenQdrant integrates with Autogen to enhance the development of automated LLM applications.Certified Solution PartnersQdrant has an ecosystem of solution partners who help you with the implementation and integration of your vector search applications.Become a Certified Solutions PartnerWe partner with industry leaders to deliver innovative solutions and an exceptional customer experience.Become a PartnerGet started for freeTurn embeddings or neural network encoders into full-fledged applications for matching, searching, recommending, and more.Get StartedDo you have further questions? We are happy to assist you.Contact us Contact us