🌐 Centralized Enterprise AI Gateway

Secure routing, authentication, rate-limiting, and cost tracking for all LLM and embedding endpoints hooked into MLflow Model Registry.

Route Name	Type	Provider	Backend Target	Tracking Status
gemini-gateway	llm/v1/chat	Google Cloud	gemini-3.7-flash	● Active
vllm-local-gateway	llm/v1/chat	In-Cluster CPU	facebook/opt-125m	● Active
embeddings-gateway	llm/v1/embeddings	LiteLLM Core	text-embedding-004	● Active

🚀 Gateway Invocations Example

# Query Route via MLflow Deployments REST API
curl -X POST https://gateway.velogrid-sandbox.boschservicesolutions.ai/gateway/gemini-gateway/invocations   -H "Content-Type: application/json"   -d '{"prompt": "Summarize recent fleet diagnostic telemetry."}'