landing_page/qdrant-landing/content/documentation/_index.md

title, short_description, description, weight, hideTOC, breadcrumb, content, partition

title	short_description	description	weight	hideTOC	breadcrumb	content	partition
Documentation	Build with Qdrant: install, run, and scale a vector search engine across self-hosted, Cloud, Hybrid Cloud, and Private Cloud deployments.	Official Qdrant documentation for vector search and retrieval — quickstarts, deployment guides, integrations, and references for self-hosted and Qdrant Cloud.	2	true	false	partial title description linkDescription cloudButton localButton documentation/banners/banner-a Qdrant Documentation Qdrant is an AI-native vector search and a semantic search engine. You can use it to extract meaningful information from unstructured data. <a href="https://github.com/qdrant/qdrant_demo/" target="_blank">Clone this repo now</a> and build a search engine in five minutes. text url Cloud Quickstart /documentation/cloud-quickstart/ text url contained Local Quickstart /documentation/quickstart/ true partial developingTitle developingDescription developingBlock documentation/banners/banner-d Introducing Qdrant Edge Qdrant Edge is a lightweight, embedded vector search engine for in-process retrieval — no background services, minimal memory footprint, and no network required. Built for robots, kiosks, mobile devices, and any environment requiring offline-capable AI search. title button image Run vector search anywhere, even offline text url Get Started /documentation/edge/edge-quickstart/ src alt /img/rocket.svg Rocket partial title description cardsPartial cards documentation/sections/cards-section Qdrant User Manual Learn how to manage your data, run powerful searches, and leverage inference to build AI-native applications. documentation/cards/docs-cards id icon title description link 1 src alt /icons/outline/vectors-blue.svg Vectors Manage Data Create collections, manage vectors, payloads, and storage. Learn about indexing, quantization, and multitenancy. url text /documentation/manage-data/ Read More id icon title description link 2 src alt /icons/outline/search-blue.svg Search Search Learn about similarity search, filtering, hybrid queries, and advanced retrieval techniques. url text /documentation/search/ Read More id icon title description link 3 src alt /icons/outline/integration-blue.svg Inference Inference Configure dense, sparse, and multi-vector embeddings. Use cloud-hosted embedding models directly with Qdrant. url text /documentation/inference/ Read More partial title description cardsPartial cardsPerRow cards documentation/sections/cards-section Support Get help from the Qdrant community or contact our support team. documentation/cards/docs-cards 2 id icon title description link 1 src alt /icons/outline/discord-purple.svg Discord icon Community Support Join 6,000+ active members to learn, collaborate, and participate in Qdrant's latest activities. text url Join our Discord https://qdrant.to/discord id icon title description link 2 src alt /icons/outline/support-blue.svg Support icon Qdrant Cloud Support Paying customers have access to our Support team. Links to the support portal are available in the Qdrant Cloud Console. text url Join Qdrant https://qdrant.to/cloud	develop

Qdrant Documentation

Qdrant is an AI-native vector search engine for storing, indexing, and searching high-dimensional vectors — powering semantic search, RAG pipelines, recommendation systems, and AI-native applications.

Getting Started

• Local Quickstart — Run Qdrant locally with Docker, connect a client SDK, and create your first collection.
• Cloud Quickstart — Create a free Qdrant Cloud cluster on AWS, GCP, or Azure and query it in minutes.
• Overview — How vector search works, the client-server architecture, and core data structures (points, vectors, payloads, collections).
• API & SDKs — Connect via REST or gRPC with official client libraries for Python, JavaScript/TypeScript, Rust, Go, Java, and .NET.

Develop

• Manage Data — Create collections, insert and update points and payloads, configure vector indexes, quantization, and multitenancy.
• Search — Similarity search, filtering, hybrid and multimodal queries, multi-stage pipelines, and relevance tuning.
• Inference — Configure dense, sparse, and multi-vector embeddings; use cloud-hosted embedding models directly within Qdrant.
• Qdrant Edge — Lightweight embedded vector search for in-process, offline-capable retrieval on robots, kiosks, and mobile devices.

Deploy

• Deploy Overview — Compare all Qdrant deployment options: Managed Cloud, Hybrid Cloud, Private Cloud, and self-hosted.
• Installation — Install Qdrant via Docker, Kubernetes, or binary on Linux, macOS, or Windows.
• Managed Cloud — Qdrant as a managed service on AWS, GCP, or Azure with automatic scaling, backups, and zero-downtime upgrades.
• Hybrid Cloud — Deploy into your own Kubernetes cluster while managing through Qdrant Cloud.
• Private Cloud — Fully air-gapped deployment in your own Kubernetes cluster with no Qdrant Cloud connectivity required.
• Distributed Deployment — Multi-node clusters with horizontal sharding and replication for scale and fault tolerance.
• Security — API keys, JWT-based collection-scoped access control, TLS encryption, and network binding.
• Configuration — Customize Qdrant via config files and environment variables; runtime administration tools; GPU-accelerated vector indexing.
• Monitoring & Telemetry — Monitor Qdrant with Prometheus and Grafana via built-in OpenMetrics endpoints.
• Optimization — Tune for high-speed search, high precision, or low memory usage; understand how the background optimizer works.
• Production Checklist — Pre-launch review of sharding, replication, quantization, load balancing, and observability.
• Capacity Planning — Estimate RAM and disk for vectors, payloads, indexes, and replication factors.
• Snapshots — Back up and restore collections with snapshots for disaster recovery and cross-cluster replication.
• Troubleshooting — Diagnose common runtime errors: open-file limits, filesystem incompatibilities, corrupted collection metadata.

Ecosystem

• Frameworks — Integrations with 40+ AI agent and RAG frameworks: LangChain, LlamaIndex, Haystack, CrewAI, AutoGen, Spring AI, and more.
• Embedding Providers — Connect to 30+ providers: OpenAI, Cohere, Jina, Mistral, AWS Bedrock, Voyage AI, Ollama, and more.
• Platforms — No-code and low-code integrations with n8n, Make, MuleSoft, Pipedream, and more.

Tutorials & Examples

• Tutorials — Hub for all tutorials covering basics, search engineering, retrieval quality, operations, migrations, and ecosystem integrations.
• Examples — End-to-end code samples for RAG pipelines, hybrid search, multitenancy, recommendations, and multimodal search.

Learn

• Articles — Long-form articles on vector search, RAG, quantization, hybrid retrieval, and Qdrant internals from the engineering team.
• Qdrant Academy — Free, self-paced courses on vector search, hybrid retrieval, multivectors, and production-grade AI search applications.
• Tutorials — Hub for all tutorials covering basics, search engineering, retrieval quality, operations, migrations, and ecosystem integrations.

API Reference

• Qdrant API Reference — Full REST API reference for all Qdrant operations: collections, points, search, indexing, cluster management, and more.