Your AI vector database, hosted in France
A high-performance vector database powered by Qdrant, installed and maintained by DINAO. The semantic search and RAG engine for your AI applications, with your embeddings stored in France.
What is Qdrant?
Qdrant is an open-source vector database written in Rust, one of the most popular for AI and semantic search. While a traditional database looks for exact matches, Qdrant stores high-dimensional vectors (embeddings) and finds semantically similar elements at very high speed.
Designed for RAG (Retrieval Augmented Generation) applications, intelligent search engines, and recommendation systems, Qdrant offers similarity search at the scale of millions, or even billions, of vectors. It provides hybrid search combining filters and similarity, advanced metadata filtering, REST and gRPC APIs, a web management interface, and a cluster mode for high availability.
Managed by DINAO, Qdrant runs in a dedicated container hosted in France, with HTTPS, API key, backups, and monitoring. Your embeddings — often derived from sensitive data — thus remain under your control and compliant with GDPR.
Host Qdrant at DINAO
Resource tiers compatible with Qdrant prerequisites (minimum 1 vCPU / 1 Go / 2 Go). Hosted in France, fully managed.
- 1 dedicated vCPU
- 2 Go RAM
- 20 GB NVMe
- Daily backups
- Managed & monitored by DINAO
- 2 dedicated vCPU
- 4 Go RAM
- 40 GB NVMe
- Daily backups
- Managed & monitored by DINAO
- 4 dedicated vCPU
- 8 Go RAM
- 80 GB NVMe
- Daily backups
- Managed & monitored by DINAO
- 8 dedicated vCPU
- 16 Go RAM
- 160 GB NVMe
- Daily backups
- Managed & monitored by DINAO
This application uses AI
The container hosts the application, not the AI engine (which requires dedicated GPUs) : inference is handled externally, with your own provider key. Prioritize a sovereign engine — Mistral AI, NumSpot, Scaleway, or OVHcloud AI Endpoints (France, GDPR) ; an international provider (OpenAI, Anthropic…) only if a specific capability requires it. Inference subscriptions are not included in hosting.
Technical details
You might be wondering…
What is the purpose of a vector database like Qdrant?
Qdrant stores vectors (embeddings) derived from your texts, images, or other data, and allows you to find the most semantically similar elements. It is the foundation for RAG applications, semantic search, and recommendation systems.
Does Qdrant replace an AI model?
No. Qdrant is not a language model: it is the database that stores and queries the embeddings produced by your models. It combines with an LLM (for example via Open WebUI or an API) to build a complete RAG system.
How do I integrate Qdrant into my applications?
Via its REST and gRPC APIs, compatible with Python, LangChain, n8n, and most AI frameworks. A web interface also allows you to manage your collections and vectors visually.
Where are my vectors stored?
On DINAO's infrastructure in France, in one of the available data centers, in a dedicated container. Your embeddings and metadata do not leave the territory, in compliance with GDPR.
Can I scale my database?
Yes. You upgrade to the next tier based on vector volume and activate cluster mode for high availability, without proprietary lock-in.
