Skip to main content

​
Overview

AI Servers in Raily are endpoints that let you expose your data collections to AI agents and applications in a trusted, authenticated, and transparent way. Each AI Server is an endpoint configured with specific authentication and data integration settings.

​
What is an AI Server?

An AI Server endpoint is configured with:
  • Authentication - Specific Identity Provider (IDP) for secure access
  • Data Integration - Specific data collection or integration you choose to expose
  • Full Analytics - Complete monitoring including latency, calls, and usage metrics
Raily manages these endpoints and provides comprehensive analytics on their usage.

​
How AI Servers Work

Each AI Server endpoint:
  1. Authenticates requests via your configured IDP
  2. Serves data from your chosen data collection or integration
  3. Tracks all activity with detailed analytics
  4. Enforces access policies based on your configuration

​
Endpoint Configuration

An AI Server endpoint is configured with:

​
Identity Provider (IDP)

Connect the AI Server to a specific IDP for authentication:
  • OAuth providers
  • API key authentication
  • Custom authentication systems
  • White-label authentication

​
Data Collection

Choose which data collection or integration the endpoint exposes:
  • Specific content collections
  • Vector store data
  • External data integrations
  • Storage buckets

​
Analytics

Raily provides full analytics for each AI Server endpoint, including:
  • Total Calls - Number of requests to the endpoint
  • Average Response Time - Latency metrics
  • Total Input Tokens - Tokens sent in requests
  • Total Output Tokens - Tokens returned in responses
  • Average Input/Output Tokens - Per-request averages
  • Access patterns over time - Timeline of usage
Access analytics through the Raily dashboard at app.raily.ai/dashboard.

​
AI Server Types

Agent Endpoints

Endpoints for autonomous AI agents

Application Endpoints

Endpoints for AI-powered applications

LLM Integration

Endpoints for LLM provider access

Custom Endpoints

Endpoints for custom integrations

​
Trusted and Transparent

AI Server endpoints provide:
  • Trust - Authentication on every request
  • Transparency - Full visibility into who accesses what
  • Control - Configure exactly what data is exposed
  • Analytics - Detailed metrics on all usage

​
Best Practices

Separate Endpoints

Create separate AI Server endpoints for different use cases and environments

Monitor Analytics

Regularly review endpoint analytics to understand usage patterns

Secure Authentication

Use robust IDP configuration for endpoint authentication

Access Policies

Configure appropriate access policies for each endpoint

​
Next Steps

Identities and Auth

Learn about authentication and authorization

Analytics

View endpoint analytics and metrics