← Back to catalog HuggingChat (Chat UI) · managed by DINAO

Your conversational AI, hosted in France

An open-source AI chat interface powered by Hugging Face's Chat UI, installed and maintained by DINAO. Connected to your local open-weight models — your conversations stay on our French servers.

Hosted in FranceSovereign in local modeYour open-weight modelsGDPR CompliantOfficial publisher image
Overview

What is HuggingChat (Chat UI)?

Chat UI is the open-source AI chat interface developed by Hugging Face, which powers the public HuggingChat service. It is a complete web interface for interacting with large language models: it manages conversation history, user profiles, settings, and offers multimodal capabilities (image analysis) as well as tool calling via the MCP (Model Context Protocol) and function calling.

It includes an optional routing system ("Omni") that automatically selects the most suitable model based on context. Fully self-hostable, it allows you to build your own sovereign AI chat interface.

Technically, Chat UI relies on SvelteKit (TypeScript), a MongoDB database for persistence, and connects to any backend speaking the OpenAI-compatible API — local servers like TGI, llama.cpp, Ollama or remote APIs. Deployment is done via Docker container (image bundled with embedded MongoDB).

Compatible offers

Host HuggingChat (Chat UI) at DINAO

Resource tiers compatible with HuggingChat (Chat UI) prerequisites (minimum 1 cœur / 1 Go / 5 Go). Hosted in France, fully managed.

Découverte
1 vCPU · 2 Go · 20 Go
9,90 € /month excl. VAT
  • 1 dedicated vCPU
  • 2 Go RAM
  • 20 GB NVMe
  • Daily backups
  • Managed & monitored by DINAO
Order
Performance
4 vCPU · 8 Go · 80 Go
39,90 € /month excl. VAT
  • 4 dedicated vCPU
  • 8 Go RAM
  • 80 GB NVMe
  • Daily backups
  • Managed & monitored by DINAO
Order
Dédié
8 vCPU · 16 Go · 160 Go
79,90 € /month excl. VAT
  • 8 dedicated vCPU
  • 16 Go RAM
  • 160 GB NVMe
  • Daily backups
  • Managed & monitored by DINAO
Order
🧠

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.

Under the hood

Technical details

vCPU
1 cœur
ideal : 2 cœurs
Memory
1 Go
ideal : 2 Go
Disk
5 Go
ideal : 20 Go
Image : ghcr.io/huggingface/chat-ui-db:latest Registry : ghcr.io Services : chat-ui, mongo Ports : 3000
FAQ

You might be wondering…

Is my data used to train models?

No. Your prompts and conversations remain private on your instance. No data is shared or used for training, unlike public services.

Can I use my own models?

Yes. Chat UI connects to any model served via an OpenAI-compatible API: local open-weight models (Llama, Mistral…) via TGI, llama.cpp, or Ollama, or external APIs.

Where is the data hosted?

On DINAO's infrastructure in France, in one of the available data centers. In local mode, your conversations never leave the server.

Does it handle images and tools?

Yes. Chat UI supports multimodal inputs (image analysis by compatible models) and tool calling via the MCP protocol and function calling.

Can I change plans or export my data?

Yes. You can upgrade or downgrade at any time, and your conversations remain exportable — no proprietary lock-in.