Your AI vector database, hosted in France
A vector database for your AI applications, powered by Chroma and maintained by DINAO. Embeddings, semantic search, and RAG pipelines — all on our French servers.
What is Chroma?
Chroma (ChromaDB) is an open-source (Apache 2.0) vector database designed for AI applications. It stores documents and their embeddings, enabling semantic similarity search — the typical infrastructure component of RAG (Retrieval Augmented Generation) pipelines that provide context to an LLM.
Chroma supports automatic embedding (tokenization, embedding, indexing), metadata and content filtering, as well as hybrid search combined with full-text search. Python and JavaScript/TypeScript clients, along with a server mode, facilitate integration.
Self-hosted with DINAO, the instance deploys via Docker, with HTTPS on your domain. The embedding function can rely on an external service or a local model, allowing you to keep the entire chain on your infrastructure.
Host Chroma at DINAO
Resource tiers compatible with Chroma prerequisites (minimum 1 vCPU / 1 Go / 5 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 may also like…
Other applications managed by DINAO in the same category, hosted in France and GDPR compliant.
You might be wondering…
What is a vector database?
It is a database that stores documents as 'vectors' (embeddings) representing their meaning. It enables search by semantic similarity rather than exact keywords — the core component of AI assistants and modern search engines.
What is Chroma used for in an AI project?
Chroma is typically used in RAG pipelines: documents are stored, their embeddings are indexed, and then semantically close passages are retrieved from a question to be passed as context to an LLM. Answers are thus grounded in your own data.
How do I integrate Chroma into my application?
Via the official Python and JavaScript/TypeScript clients, or in server mode with an API. DINAO provides a ready-to-use instance on your domain, with HTTPS.
Where are my documents and embeddings hosted?
On DINAO infrastructure in France, in one of the available datacenters. In local embedding mode, your data never leaves the territory.
Can I export my data?
Yes. Your collections and vectors remain exportable at any time — Chroma is open-source (Apache 2.0), with no proprietary lock-in.
