Build your AI apps, visually and in France
A visual studio for LLM agents and workflows powered by Langflow, installed and maintained by DINAO. Compose your RAG pipelines via drag-and-drop — connected to your own models, hosted in France.
What is Langflow?
Langflow is a low-code tool for building AI applications and agents. Thanks to a visual drag-and-drop editor, you assemble building blocks — language models, prompts, memories, tools, vector databases — to compose complex workflows without writing everything by hand.
Independent of the model provider, Langflow connects as well to local LLMs (served by Ollama) as to external APIs, and provides the necessary components to build RAG (Retrieval Augmented Generation) chains on your own documents. Each flow can integrate agents capable of using tools and reasoning over multiple steps.
Once designed, a flow is exposed as a REST API or as a chat widget, ready to be integrated into your applications. Designed to go from prototype to production, Langflow facilitates iteration on your AI use cases while remaining open to developers via custom Python code.
Host Langflow at DINAO
Resource tiers compatible with Langflow prerequisites (minimum 2 vCPU / 2 Go / 10 Go). Hosted in France, fully managed.
- 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
1 hidden tier(s) (insufficient resources for this app) : Découverte
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…
Do I need to know how to code to use Langflow?
Not essentially: you assemble your AI workflows via drag-and-drop. But the tool remains open to developers who want to customize components in Python or integrate flows via API.
Can I use my own models?
Yes. Langflow connects to locally hosted open-weight models (Ollama) or external APIs. For sovereignty, prefer local models.
Can I do RAG on my documents?
Yes. Langflow integrates components for chunking, embedding, and vector databases to query your own internal documents.
How do I use a flow in my app?
Each Langflow flow is automatically exposed as an API endpoint or a chat widget, ready to be integrated into your applications and business tools.
Where is the data hosted?
On DINAO infrastructure in France, in one of the available datacenters. Your flows and data do not leave the territory in local mode.
