Welcome! Type "help" for available commands.
$
Summary
SIE is an open-source inference server exposing 100+ models through a single OpenAI-compatible API for search, document-to-markdown conversion, structured output, content safety, and agent loops.
Models load on demand with LRU eviction; Python and TypeScript SDKs are available. Production tooling includes a load-balancing gateway, KEDA autoscaling, Grafana dashboards, and Terraform modules for GKE, EKS, and AKS.