Qdrant Self-Hosted
Self-hosted vector database for semantic retrieval and AI application data.
4 sources checked by an editor on · Product website ↗
Read this page as JSON or Markdown.
Deployment terms: BYOC · control plane · data plane · private offer
· Open requirements shortlist · Estimate operating costs
Compare this listing with another →
What lands where
Supplied by
Vendor or project
Official Docker image for local/server deployment; production storage, access controls and scaling require configuration.
Runs in
Documented customer environment
Customer-operated vector-search server and persistent collection storage
- Google Cloud: Customer cloud account
- Google Cloud
Servers / containers
Operated by
Your team
Customer manages persistence, backups, access controls, upgrades and any distributed-cluster operations.
Deployment boundaries by provider
- Google Cloud: Customer cloud account · Customer-operated
Resources in the customer's cloud account, subscription, project or tenancy. Managed cloud services still have shared responsibilities.
Self-operated Qdrant cluster on Google Kubernetes Engine ↗ · Source checked 2026-11-12
Application operations and account ownership are separate from infrastructure operations. Confirm external services, telemetry, support access and backup destinations for the chosen path.
| Install method | Official Docker image for local/server deployment; production storage, access controls and scaling require configuration. |
|---|---|
| Infrastructure | Servers / containers The database runs as a persistent server/container process with collection storage; production capacity, replicas and backup storage must be planned. Embedding-model compute is separate. |
| Licensing model | Open Source / Open Core The listed upstream self-hosted database is Apache-2.0 licensed. Separate managed hosting or support does not change this database classification; this entry does not classify a proprietary managed-cloud control plane. |
| License | Apache 2.0 for the upstream database; managed cloud offerings and support have separate commercial terms. |
Buyer diligence
Answers apply to the reviewed edition and deployment. Expand a row for qualifications and sources.
How to read these facts
Not researched means no field-specific review is recorded. Not confirmed means sources were checked but did not establish an answer. Availability, eligibility and edition-dependent findings retain the scope given in their evidence. A vendor’s hosted-service certification does not automatically cover your deployment. Evidence coverage is not a feature score.
5 of 12 fields researched (42%) · 3 documented · 2 unresolved. Evidence coverage is not a feature score.
- Single sign-on
Not confirmedEvidence and scope for Single sign-on
The self-hosted core security guide documents API keys, including scoped access keys, TLS and audit controls. It does not establish a native SAML/OIDC login flow or a reviewed external-IdP integration for this edition. Qdrant Cloud console identity is a separate service and is not transferred to the core database.
Self-hosted core authentication; federated user sign-on unresolved · Source ↗ · Reviewed 2026-11-20
Sources checked — unresolved · Editor reviewed.
- Deployment artifact / IaC
DocumentedEvidence and scope for Deployment artifact / IaC
The local quickstart identifies the official Qdrant Docker server and persistent storage. A local evaluation command is not a hardened production installation; configure network access, authentication and durable storage.
Upstream self-hosted deployment; not a provider support or production-readiness certification · Source ↗ · Deployment artifact ↗ (select a released Qdrant image tag) · Reviewed 2026-11-14
Documented · Editor reviewed.
- Minimum footprint / sizing
Not confirmedEvidence and scope for Minimum footprint / sizing
The capacity guide models vectors, dimensions/datatype, HNSW, payload indexes, memory tiers and replication, with headroom and representative-data testing. It does not establish a single minimum from a user count or total source-data size. Determine vector counts/dimensions, retention, replicas and query/ingestion rates, then use the sizing calculator and benchmark.
Vector/workload-specific sizing methodology; numeric minimum for the requested deployment unresolved · Source ↗ · Reviewed 2026-11-20
Sources checked — unresolved · Editor reviewed.
- License pricing
DocumentedEvidence and scope for License pricing
The reviewed upstream core is Apache-2.0 licensed. Optional services, bundled dependencies, commercial distributions and support can have separate terms. This records the source licence, not an infrastructure or operating-cost estimate.
Upstream core licence; commercial features, support and hosting priced separately · Source ↗ · Reviewed 2026-11-20
Documented · Editor reviewed.
- Release snapshot / cadence
DocumentedEvidence and scope for Release snapshot / cadence
The publisher-designated GitHub release checked was v1.20.1, published 2026-11-13. This is a release snapshot, not a promised cadence, support designation or approval to substitute it into a provider package.
Upstream qdrant/qdrant release record; commercial editions and deployment packages may differ · Source ↗ · Reviewed 2026-11-14
Documented · Editor reviewed.
Show all fields (7 not researched)
- Marketplace delivery
- Not researched Supply a public source.
- Cloud commitment eligibility
- Not researched Supply a public source.
- SCIM provisioning
- Not researched Supply a public source.
- Compliance attestations
- Not researched Supply a public source.
- Security controls
- Not researched Supply a public source.
- Air-gapped operation
- Not researched Supply a public source.
- Operating cost estimate
- Not researched Supply a public source.
Scope & considerations
The local quickstart is an installation starting point, not a secured production configuration. Applications can supply their own vectors or use separately configured embedding models. External embedding APIs and hosted inference can receive source data even when the database is self-hosted; local FastEmbed is a documented alternative. This entry excludes Qdrant Cloud hosting. Qdrant 1.20.1, released November 13, 2026, prevents collection-scoped JWTs from viewing snapshot telemetry for collections they cannot access; operators using scoped JWTs should upgrade.
Category fit
- Databases & vector
- Vector database for similarity and hybrid retrieval in AI applications. Model inference and embedding creation are separate from the core database deployment.
- AI tools & infrastructure
- Self-hosted vector database for semantic retrieval and AI application data.
Compare within Databases & vector
- Apache Doris Self-HostedApache-licensed analytical database with upstream AWS EKS/Alibaba ACK/ACS guides and a separately packaged cloudimg Azure VM path.
- AWS
- Azure
- Alibaba Cloud
- ClickHouse BYOCManaged analytical database with its data plane in your cloud account.
- AWS
- Azure
- Google Cloud
- CockroachDB BYOCVendor-managed CockroachDB service deployed into the customer's AWS, Azure or Google Cloud account.
- AWS
- Azure
- Google Cloud
- Couchbase Server Enterprise EditionSelf-managed distributed NoSQL database deployed in customer-controlled Kubernetes with the Couchbase Operator.
- AWS
- Azure
- Google Cloud
- Elastic Cloud EnterpriseCommercial self-managed orchestration platform for Elastic Stack deployments across customer cloud hosts.
- AWS
- Azure
- Google Cloud
- Elastic Cloud on KubernetesElastic's Kubernetes operator for deploying and operating Elasticsearch, Kibana and related Elastic Stack resources in customer clusters.
- AWS
- Azure
- Google Cloud
- Meilisearch Community EditionSelf-hosted search engine for typo-tolerant full-text, semantic and hybrid retrieval.
- AWS
- Google Cloud
- DigitalOcean
- MilvusVector database for similarity search and retrieval over embedding collections.
- AWS
- Azure
- Google Cloud
Showing 8 of 18 other listings in Databases & vector. These products address related workflows; read their category-fit notes before comparing scope. See all of Databases & vector →
Installation outline
- Choose the documented deployment option and a dedicated cloud environment. Follow the launch methodology.
- Review the vendor's installation documentation, required permissions and outbound data flows.
- Deploy to a non-production environment; configure identity, networking and monitoring.
- Test backup recovery and upgrades before promoting to production.
Evidence trail
Every claim on this page traces to the sources below. They document the deployment option; they do not constitute a security certification.
- Deployment sourcesChecked
- Local/server Docker quickstart ↗qdrant.tech
- Embedding options, including local FastEmbed ↗qdrant.tech
- Apache 2.0 license ↗github.com
- Qdrant 1.20.1 security and maintenance release ↗github.com
- Cloud deployment evidenceChecked
The linked sources describe each deployment path, edition and support scope. Community templates and partner statements are identified in the notes.
- Self-operated Qdrant cluster on Google Kubernetes Engine ↗ · Google Cloud
Provider guide · Reviewed 2026-11-12. Vendor support commitment: not assessed; confirm the selected release and contract.
Google documents provisioning a regional GKE cluster and installing Qdrant with Helm and persistent disks. The customer operates the database cluster; this is separate from Qdrant Cloud and its separately offered Hybrid Cloud service.
- Self-operated Qdrant cluster on Google Kubernetes Engine ↗ · Google Cloud
- Infrastructure evidenceChecked
- Licensing evidenceChecked