Skip to main content
Version: 2026 R2

AI Proxy

AI Proxy is a modular .NET 8 application that provides unified access to AI capabilities offered by multiple providers. It serves as an intermediary layer between WEBCON and external AI services.

Architecture​

AI Proxy handles communication between WEBCON and AI services, routing requests to the appropriate providers and models.

  1. WEBCON sends a request to AI Proxy.
  2. AI Proxy:
    • validates the request,
    • selects the provider and model based on the configuration,
    • authenticates using API keys,
    • forwards the request to the selected AI provider.
  3. The response is then returned to WEBCON through AI Proxy.

Supported providers​

  • Google Gemini - Google AI models available through Vertex AI,
  • Azure AI Foundry - Azure OpenAI models and other models available in the Azure ecosystem,
  • OpenAI - GPT models such as GPT-4o and GPT-4o-mini.

Deployment variants​

AI Proxy (Cloud)​

A version hosted in WEBCON's Azure infrastructure:

  • no infrastructure setup required,
  • automatic updates,
  • managed by WEBCON.

AI Proxy Self-hosted​

A version designed to run in your own infrastructure, such as on-premise, private cloud, or Azure:

  • full control over data and environment,
  • flexible configuration options,
  • compliance with security policies,
  • support for development environments.

Documentation​