Description
European AI infrastructure with your own product knowledge
Scaleway is a French cloud provider that runs open AI models in European data centers. With Generative APIs you get serverless, pay-per-token access to curated models. With Managed Inference you run dedicated endpoints with capacity of your own. Both use OpenAI-compatible APIs, so existing libraries and frameworks work as they are.
A model knows nothing about your range, your approved copy or the images you are allowed to use. That knowledge lives in Kontainer DAM & PIM.
When an agent or app built on Scaleway is connected to Kontainer through the Kontainer API or MCP, the model can retrieve product data, metadata and file information at the moment it needs them, instead of guessing or working from stale copies.
The result is AI that runs on European infrastructure and works from content your organization has already approved.
Benefits
Why integrate Scaleway with Kontainer?
✔ AI on European infrastructure
Scaleway is a French company and hosts its inference in European data centers, which suits organizations that want their AI workloads to stay in Europe.
✔ Open models, no lock-in
Scaleway hosts open-weight models from several developers, so you can pick the model that fits the task and switch later.
✔ Kontainer as your Single Source of Truth
Let your AI solution work from the same approved product data and files as the rest of the organization.
✔ Familiar, OpenAI-compatible APIs
Developers can reuse the libraries and frameworks they already know, and still connect to Kontainer in the same way.
✔ Capacity that matches your needs
Generative APIs are billed per token, while Managed Inference gives you dedicated capacity billed by usage time.
✔ Prompts are not stored
Scaleway states that prompts sent to its inference services are not stored, logged or reused.
Features
How Scaleway and Kontainer work together
✔ The Kontainer API
Retrieve and update product data, metadata and file information from solutions built on Scaleway, for example from a serverless function or an app.
✔ MCP for agents
An agent built on Scaleway’s models can use Kontainer as a tool through the Model Context Protocol, without custom development for every individual agent.
✔ Function calling
Scaleway’s chat API accepts tools for models that support function calling, so a model can trigger a lookup in Kontainer as part of answering.
✔ Serverless Functions as glue
Models served at Scaleway can connect to external tools through Serverless Functions, which makes a natural place for the call to the Kontainer API.
✔ Product data from PIM
Use product names, descriptions, specifications, categories and variants as the basis for answers and content.
✔ Digital assets from DAM
Give your solution access to images, videos and documents, along with the tags and metadata that make them easy to find and use correctly.
✔ RAG on your own content
Product texts and metadata from Kontainer can feed a knowledge base that the model draws on when it answers.
Set-up
Connect Scaleway and Kontainer in three steps
- Choose the Scaleway service
Start with Generative APIs for the quickest way to try a model, or use Managed Inference when you need dedicated capacity or isolation. - Give your solution access to Kontainer
Create a JSON API token, or set up OAuth 2.0, for the Kontainer user the solution should act as. Access is limited to what that user may do. - Let the model reach Kontainer
Connect through MCP or expose Kontainer lookups as functions the model can call, then test with real product questions.
The set-up requires some technical or IT knowledge. The MCP guide describes the details.
Use Cases
What can you build with Scaleway + Kontainer?
- A European product advisor
An assistant for sales, support or your webshop that answers from PIM data, with the AI running on European infrastructure. - Bulk enrichment of product data
Jobs that summarize, categorize and suggest missing product texts across large catalogs, including runs that are not time-critical. - Tag and alt text suggestions
Where the chosen model understands images, it can suggest descriptive metadata for assets, which an employee then approves. - Multilingual product content
Adapt product texts to several markets, starting from localized data in Kontainer. - A searchable knowledge base
Let staff ask questions about products, specifications and documents, with answers grounded in approved content. - Agents across systems
Combine Kontainer with your ERP, CRM and other systems in the same workflow.
Support
Get started with Scaleway + Kontainer
Which data and workflows your AI solution needs decides how to set things up. Contact our support team for help with set-up, customization or best-practice advice.
You can write to us at support@kontainer.com
Read more about the Kontainer API and MCP for Kontainer DAM and PIM.
See Scaleway’s pages on Generative APIs and Managed Inference.
For EU AI Act requirements, see Labelling AI-generated content in Kontainer and the EU AI Act (Regulation (EU) 2024/1689).
FAQ
What is Scaleway?
Scaleway is a French cloud provider. Its AI offering includes Generative APIs and Managed Inference, which run open AI models in European data centers and are available through OpenAI-compatible APIs.
What is the difference between Generative APIs and Managed Inference?
Generative APIs give serverless, pay-per-token access to curated models. Managed Inference provides dedicated endpoints with capacity of your own and a wider choice of models, billed by usage time.
Can Scaleway be integrated with Kontainer?
Yes. Kontainer can be connected to solutions built on Scaleway through the Kontainer API and MCP, so models and agents can retrieve product data, metadata and file information from Kontainer DAM & PIM.
Can agents on Scaleway models use Kontainer via MCP?
Yes. An agent built on Scaleway’s models can use an MCP client to reach Kontainer as a tool. Alternatively, Kontainer lookups can be exposed as functions for models that support function calling.
Can Scaleway-based solutions use product data and files from Kontainer?
Yes. Product names, descriptions, specifications, categories and variants from PIM can be used as context, and images, videos and documents in DAM can be found through metadata and tags.
Is Kontainer data sent to Scaleway?
Only what your solution chooses to send to the model for a given task. Access is limited to what the Kontainer user behind the connection may do, and Scaleway states that prompts are not stored, logged or reused.
Does our data need to be trained into an AI model?
Not necessarily. An integration can retrieve the relevant information from Kontainer when it is needed, through MCP or the API. That lets you work with current data without making it part of a model’s training.
Can I use my existing OpenAI-compatible tools?
Yes. Scaleway’s APIs are compatible with OpenAI libraries and SDKs, and Kontainer is connected through its own API or MCP regardless of which model you choose.
How do we get started?
Start by clarifying which data and workflows the AI solution needs. Then contact Kontainer’s support team at support@kontainer.com for help with set-up, customization and best practices.