diff --git a/qdrant-landing/content/documentation/_index.md b/qdrant-landing/content/documentation/_index.md index a85335cfb..bd1912c05 100644 --- a/qdrant-landing/content/documentation/_index.md +++ b/qdrant-landing/content/documentation/_index.md @@ -87,32 +87,58 @@ content: partition: develop --- -THIS CONTENT IS GOING TO BE IGNORED FOR NOW +# Qdrant Documentation -# 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. -Qdrant is an AI-native vector search and a semantic search engine. You can use it to extract meaningful information from unstructured data. Want to see how it works? [Clone this repo now](https://github.com/qdrant/qdrant_demo/) and build a search engine in five minutes. +## Getting Started -||| -|-:|:-| -|[Cloud Quickstart](/documentation/cloud-quickstart/)|[Local Quickstart](/documentation/quickstart/)| +- [Local Quickstart](/documentation/quickstart/index.md) — Run Qdrant locally with Docker, connect a client SDK, and create your first collection. +- [Cloud Quickstart](/documentation/cloud-quickstart/index.md) — Create a free Qdrant Cloud cluster on AWS, GCP, or Azure and query it in minutes. +- [Overview](/documentation/overview/index.md) — How vector search works, the client-server architecture, and core data structures (points, vectors, payloads, collections). +- [API & SDKs](/documentation/interfaces/index.md) — Connect via REST or gRPC with official client libraries for Python, JavaScript/TypeScript, Rust, Go, Java, and .NET. +## Develop -## Ready to start developing? +- [Manage Data](/documentation/manage-data/index.md) — Create collections, insert and update points and payloads, configure vector indexes, quantization, and multitenancy. +- [Search](/documentation/search/index.md) — Similarity search, filtering, hybrid and multimodal queries, multi-stage pipelines, and relevance tuning. +- [Inference](/documentation/inference/index.md) — Configure dense, sparse, and multi-vector embeddings; use cloud-hosted embedding models directly within Qdrant. +- [Qdrant Edge](/documentation/edge/index.md) — Lightweight embedded vector search for in-process, offline-capable retrieval on robots, kiosks, and mobile devices. -***

Qdrant is open-source and can be self-hosted. However, the quickest way to get started is with our [free tier](https://qdrant.to/cloud) on Qdrant Cloud. It scales easily and provides an UI where you can interact with data.

*** +## Deploy -[![Hybrid Cloud](/docs/homepage/cloud-cta.png)](https://qdrant.to/cloud) +- [Deploy Overview](/documentation/deploy-intro/index.md) — Compare all Qdrant deployment options: Managed Cloud, Hybrid Cloud, Private Cloud, and self-hosted. +- [Installation](/documentation/installation/index.md) — Install Qdrant via Docker, Kubernetes, or binary on Linux, macOS, or Windows. +- [Managed Cloud](/documentation/cloud/index.md) — Qdrant as a managed service on AWS, GCP, or Azure with automatic scaling, backups, and zero-downtime upgrades. +- [Hybrid Cloud](/documentation/hybrid-cloud/index.md) — Deploy into your own Kubernetes cluster while managing through Qdrant Cloud. +- [Private Cloud](/documentation/private-cloud/index.md) — Fully air-gapped deployment in your own Kubernetes cluster with no Qdrant Cloud connectivity required. +- [Distributed Deployment](/documentation/distributed_deployment/index.md) — Multi-node clusters with horizontal sharding and replication for scale and fault tolerance. +- [Security](/documentation/security/index.md) — API keys, JWT-based collection-scoped access control, TLS encryption, and network binding. +- [Configuration](/documentation/ops-configuration/index.md) — Customize Qdrant via config files and environment variables; runtime administration tools; GPU-accelerated vector indexing. +- [Monitoring & Telemetry](/documentation/ops-monitoring/index.md) — Monitor Qdrant with Prometheus and Grafana via built-in OpenMetrics endpoints. +- [Optimization](/documentation/ops-optimization/index.md) — Tune for high-speed search, high precision, or low memory usage; understand how the background optimizer works. +- [Production Checklist](/documentation/production-checklist/index.md) — Pre-launch review of sharding, replication, quantization, load balancing, and observability. +- [Capacity Planning](/documentation/capacity-planning/index.md) — Estimate RAM and disk for vectors, payloads, indexes, and replication factors. +- [Snapshots](/documentation/snapshots/index.md) — Back up and restore collections with snapshots for disaster recovery and cross-cluster replication. +- [Troubleshooting](/documentation/common-errors/index.md) — Diagnose common runtime errors: open-file limits, filesystem incompatibilities, corrupted collection metadata. -## Qdrant's most popular features: -|||| -|:-|:-|:-| -|[Filterable HNSW](/documentation/search/filtering/)
Single-stage payload filtering | [Recommendations & Context Search](/documentation/search/explore/#explore-the-data)
Exploratory advanced search| [Pure-Vector Hybrid Search](/documentation/search/hybrid-queries/)
Full text and semantic search in one| -|[Multitenancy](/documentation/manage-data/multitenancy/)
Payload-based partitioning|[Custom Sharding](/documentation/distributed_deployment/#sharding)
For data isolation and distribution|[Role Based Access Control](/documentation/security/?q=jwt#granular-access-api-keys)
Secure JWT-based access | -|[Quantization](/documentation/manage-data/quantization/)
Compress data for drastic speedups|[Multivector Support](/documentation/manage-data/vectors/?q=multivect#multivectors)
For ColBERT late interaction |[Built-in IDF](/documentation/manage-data/indexing/?q=inverse+docu#idf-modifier)
Advanced similarity calculation| +## Ecosystem -## Developer guidebooks: +- [Frameworks](/documentation/frameworks/index.md) — Integrations with 40+ AI agent and RAG frameworks: LangChain, LlamaIndex, Haystack, CrewAI, AutoGen, Spring AI, and more. +- [Embedding Providers](/documentation/embeddings/index.md) — Connect to 30+ providers: OpenAI, Cohere, Jina, Mistral, AWS Bedrock, Voyage AI, Ollama, and more. +- [Platforms](/documentation/platforms/index.md) — No-code and low-code integrations with n8n, Make, MuleSoft, Pipedream, and more. -| [A Complete Guide to Filtering in Vector Search](/articles/vector-search-filtering/)
Beginner & advanced examples showing how to improve precision in vector search.| [Building Hybrid Search with Query API](/articles/hybrid-search/)
Build a pure vector-based hybrid search system with our new fusion feature.| -|----------------------------------------------|-------------------------------| -| [Multitenancy and Sharding: Best Practices](/articles/multitenancy/)
Combine two powerful features for complete data isolation and scaling.| [Benefits of Binary Quantization in Vector Search](/articles/binary-quantization/)
Compress data points while retaining essential meaning for extreme search performance.| +## Tutorials & Examples + +- [Tutorials](/documentation/tutorials-lp-overview/index.md) — Hub for all tutorials covering basics, search engineering, retrieval quality, operations, migrations, and ecosystem integrations. +- [Examples](/documentation/examples/index.md) — End-to-end code samples for RAG pipelines, hybrid search, multitenancy, recommendations, and multimodal search. + +## Learn + +- [Articles](/articles/index.md) — Long-form articles on vector search, RAG, quantization, hybrid retrieval, and Qdrant internals from the engineering team. +- [Qdrant Academy](/course/index.md) — Free, self-paced courses on vector search, hybrid retrieval, multivectors, and production-grade AI search applications. +- [Tutorials](/documentation/tutorials-lp-overview/index.md) — Hub for all tutorials covering basics, search engineering, retrieval quality, operations, migrations, and ecosystem integrations. + +## API Reference + +- [Qdrant API Reference](https://api.qdrant.tech/api-reference) — Full REST API reference for all Qdrant operations: collections, points, search, indexing, cluster management, and more. diff --git a/qdrant-landing/content/documentation/deploy-tab.md b/qdrant-landing/content/documentation/deploy-tab.md index 490411cce..caf5cfd20 100644 --- a/qdrant-landing/content/documentation/deploy-tab.md +++ b/qdrant-landing/content/documentation/deploy-tab.md @@ -110,3 +110,57 @@ hideInSidebar: true build: render: always --- +# Deploy Qdrant + +## Self-Hosted + +- [Installation](/documentation/installation/index.md) — Install Qdrant via Docker, Kubernetes, or binary on Linux, macOS, or Windows. +- [Distributed Deployment](/documentation/distributed_deployment/index.md) — Multi-node clusters with horizontal sharding and replication for scale and fault tolerance. +- [Capacity Planning](/documentation/capacity-planning/index.md) — Estimate RAM and disk requirements for vectors, payloads, indexes, and replication factors. +- [Snapshots](/documentation/snapshots/index.md) — Back up and restore collections for disaster recovery and cross-cluster replication. +- [Production Checklist](/documentation/production-checklist/index.md) — Pre-launch review of sharding, replication, quantization, load balancing, and observability. +- [Upgrades](/documentation/upgrades/index.md) — Upgrade Qdrant clusters across Cloud, Kubernetes, and Docker with zero-downtime planning. + +## Managed Cloud + +- [Managed Cloud](/documentation/cloud/index.md) — Run Qdrant as a managed service on AWS, GCP, or Azure with automatic scaling, backups, and zero-downtime upgrades. +- [Create a Cluster](/documentation/cloud/create-cluster/index.md) — Launch a free or standard cluster on your preferred cloud provider. +- [Authentication](/documentation/cloud/authentication/index.md) — Create Database API keys with granular access control and expiration settings. +- [Cluster Access](/documentation/cloud/cluster-access/index.md) — Connect via REST, gRPC, or the Cluster UI with load-balanced endpoints and IP allowlists. +- [Configure Clusters](/documentation/cloud/configure-cluster/index.md) — Tune collection defaults, strict mode, replication factor, and optimizer settings. +- [Scale Clusters](/documentation/cloud/cluster-scaling/index.md) — Scale vertically or horizontally with automatic shard rebalancing. +- [Monitor Clusters](/documentation/cloud/cluster-monitoring/index.md) — Monitor cluster health with built-in metrics, logs, and email alerts. +- [Backup Clusters](/documentation/cloud/backups/index.md) — Schedule snapshots and restore clusters for disaster recovery. +- [Update Clusters](/documentation/cloud/cluster-upgrades/index.md) — Zero-downtime rolling upgrades on multi-node clusters. +- [Cloud Inference](/documentation/cloud/inference/index.md) — Generate embeddings inside Qdrant Cloud or proxy to OpenAI, Cohere, and Jina. + +## Hybrid Cloud + +- [Hybrid Cloud](/documentation/hybrid-cloud/index.md) — Deploy Qdrant in your own Kubernetes cluster while managing it through Qdrant Cloud. +- [Setup Hybrid Cloud](/documentation/hybrid-cloud/hybrid-cloud-setup/index.md) — Install and connect the Qdrant Kubernetes Operator to Qdrant Cloud. +- [Create a Cluster](/documentation/hybrid-cloud/hybrid-cloud-cluster-creation/index.md) — Create a Qdrant cluster in your Hybrid Cloud environment. +- [Configure, Scale & Upgrade](/documentation/hybrid-cloud/configure-scale-upgrade/index.md) — Tune, resize, and upgrade Hybrid Cloud clusters. +- [Networking, Logging & Monitoring](/documentation/hybrid-cloud/networking-logging-monitoring/index.md) — Configure networking, ingress, and observability for Hybrid Cloud. +- [Operator Configuration](/documentation/hybrid-cloud/operator-configuration/index.md) — Advanced configuration of the Qdrant Kubernetes Operator. +- [Deployment Platforms](/documentation/hybrid-cloud/platform-deployment-options/index.md) — Platform-specific deployment guides for AWS, GCP, Azure, and on-prem Kubernetes. + +## Private Cloud + +- [Private Cloud](/documentation/private-cloud/index.md) — Fully air-gapped Qdrant deployment in your own Kubernetes cluster with no Qdrant Cloud connectivity. +- [Setup Private Cloud](/documentation/private-cloud/private-cloud-setup/index.md) — Install and configure Qdrant Private Cloud in a Kubernetes cluster. +- [Cluster Management](/documentation/private-cloud/qdrant-cluster-management/index.md) — Create, manage, and operate clusters in Private Cloud. +- [Configuration](/documentation/private-cloud/configuration/index.md) — Advanced configuration options for Private Cloud deployments. +- [Backups](/documentation/private-cloud/backups/index.md) — Configure backup and restore for Private Cloud clusters. +- [Logging & Monitoring](/documentation/private-cloud/logging-monitoring/index.md) — Set up observability for Private Cloud environments. +- [API Reference](/documentation/private-cloud/api-reference/index.md) — Private Cloud management API reference. + +## Operations + +- [Configuration](/documentation/ops-configuration/index.md) — Customize Qdrant via config files and environment variables; runtime administration; GPU-accelerated indexing. +- [Monitoring & Telemetry](/documentation/ops-monitoring/index.md) — Monitor Qdrant with Prometheus and Grafana via built-in OpenMetrics endpoints. +- [Optimization](/documentation/ops-optimization/index.md) — Tune for high-speed search, high precision, or low memory; understand the background optimizer. + +## Security & Troubleshooting + +- [Security](/documentation/security/index.md) — API keys, JWT-based collection-scoped access control, TLS encryption, and network binding. +- [Troubleshooting](/documentation/common-errors/index.md) — Diagnose common runtime errors: open-file limits, filesystem incompatibilities, corrupted collection metadata. diff --git a/qdrant-landing/content/documentation/ecosystem-tab.md b/qdrant-landing/content/documentation/ecosystem-tab.md index 78ea08a8a..4ec3c13b0 100644 --- a/qdrant-landing/content/documentation/ecosystem-tab.md +++ b/qdrant-landing/content/documentation/ecosystem-tab.md @@ -53,3 +53,26 @@ hideInSidebar: true build: render: always --- + +# Explore the Qdrant Ecosystem + +## Migration + +- [Migration Tool](/documentation/migrate-to-qdrant/index.md) — Move vectors, payloads, and sparse embeddings from Chroma, Pinecone, Weaviate, Milvus, pgvector, Elasticsearch, and OpenSearch. +- [Migration Guidance](/documentation/migration-guidance/index.md) — Structured framework for verifying migrations and catching silent data and search regressions. +- [Data Synchronization](/documentation/data-synchronization/index.md) — Keep Qdrant in sync with source databases using CDC, batch reindexing, or dual-write patterns for fresh search results. + +## Integrations + +- [Data Management](/documentation/data-management/index.md) — Connect Qdrant to ETL and streaming tools to ingest, transform, and sync vectors at scale. +- [Embedding Providers](/documentation/embeddings/index.md) — Connect to 30+ providers: OpenAI, Cohere, Jina, Mistral, AWS Bedrock, Voyage AI, Ollama, and more. +- [Frameworks](/documentation/frameworks/index.md) — Integrations with 40+ AI agent and RAG frameworks: LangChain, LlamaIndex, Haystack, CrewAI, AutoGen, Spring AI, and more. +- [Observability](/documentation/observability/index.md) — Connect Qdrant to Datadog, OpenLIT, and OpenLLMetry to monitor performance and traces. +- [Platforms](/documentation/platforms/index.md) — No-code and low-code integrations with n8n, Make, MuleSoft, Pipedream, Power Apps, and more. + +## Ecosystem Guides + +- [Essential Examples](/documentation/tutorials-build-essentials/index.md) — Hands-on tutorials for agentic RAG, multimodal search, data ingestion, and automation integrations. +- [Build Prototypes](/documentation/examples/index.md) — End-to-end code samples for RAG pipelines, hybrid search, multitenancy, recommendations, and multimodal search. +- [Improve Search](/documentation/improve-search/index.md) — Techniques for improving retrieval relevance and pipeline output quality. +- [Practice Datasets](/documentation/datasets/index.md) — Ready-made Qdrant snapshots of public datasets you can import and explore without the embedding step.