Skip to main content
Version: 2026 R1

AI Proxy Self-hosted

AI Proxy Self-hosted enables running the AI component in client infrastructure (on-premise, private cloud, Azure). It provides full control over data and execution environment.

Architecture​

AI Proxy acts as an intermediary layer between WEBCON and AI providers:

  1. WEBCON sends a request to AI Proxy
  2. AI Proxy:
    • Validates the request
    • Selects the provider/model according to configuration
    • Authenticates using API keys
    • Forwards the request to the AI provider
  3. The response returns through AI Proxy to WEBCON

scheme

Use cases​

Compliance and security requirements:

  • Regulated industries (finance, healthcare, public sector)
  • GDPR, ISO 27001 and other standards
  • Internal data security policies

Development environments:

  • Local testing without cloud costs
  • Development and prototyping
  • CI/CD integration

On-premise production:

  • Full infrastructure control
  • Data doesn't leave client infrastructure
  • Audit and monitoring capabilities

Multi-vendor:

  • Flexibility in choosing AI providers
  • Failover strategies between providers
  • Cost optimization

Technologies​

  • .NET 8 - application runtime
  • Docker - containerization
  • JSON - configuration
  • HTTPS/TLS - secure communication

Supported providers​

  • Google Vertex AI (Gemini)
  • Azure AI Foundry
  • OpenAI

Components​

  • Docker image: webconbps/aiproxy:1.0.0.235
  • Ports: 8080 (HTTP), 8081 (HTTPS)
  • Configuration files:
    • aiconfiguration.json - connections and models definitions
    • SSL/TLS certificate (PEM or PFX)

Next steps​

  1. Getting Started - choose an AI provider and configure access
  2. Docker Configuration - run the Docker container
  3. AI Configuration - configure models and strategies