search results

Hi, I suggest to add a hybrid AI configuration that allows using both the WEBCON AI Proxy and Self-hosted AI within the same environment. This would allow organizations to use Self-hosted AI for specific or sensitive use cases while still benefiting from the WEBCON AI Proxy and the included AI tokens for other scenarios. This would provide more flexibility regarding data governance, infra

(...) AI Proxy Self-hosted is a new way to bring AI to WEBCON - with full control over the underlying environment. It enables managing AI integration on the customer's own infrastructure (on-premises or in a private cloud), completely independent of WEBCON infrastructure. The solution supports connecting and configuring custom AI models hosted on Google Vertex, OpenAI, or Azure AI Foundry, providing full (...)

(...) etter aligned with the nature of the task, the expected response quality, processing speed, and model usage costs.   NOTE: The list of available LLMs applies to AI Proxy Online. When using AI Proxy Self-hosted , the models to be used in the system must be added and configured manually.   Where can the AI model be selected? The AI model used by system-wide features can be selected in System set (...)

External content by Sébastien Anselment The original post has appeared on my blog.   Since WEBCON 2026 R1, the WEBCON AI Proxy can be operated as a self-hosted service. Combined with an OpenAI-compatible API such as LiteLLM, this also makes it possible to integrate locally hosted language models into WEBCON. I have documented a fully local setup using: WEBCON >