Connecting your AI agent to a cloud-hosted LLM
Connecting your AI agent to a cloud-hosted LLM


Author: Google Cloud Tech – Duration: 00:03:18
This video shows how to connect your AI agent, built with the Agent Development Kit (ADK), to a powerful GPU-accelerated Large Language Model (LLM) hosted on Google Cloud Run. Following on from our previous episode where we deployed Gemma, this article shows how to decouple your LLM “brain” from your agent for independent scaling. We'll walk you through the “agent.py” code, using LiteLlm for unified template interfaces, and deploying the lightweight ADK agent service. Learn how environment variables facilitate seamless communication between these services, bringing your AI agent to life. Chapters: 0:00 – Introduction: Connect the agent to LLM 0:53 – Build the agent: `agent.py` and LiteLlm 1:06 – Configure the agent template parameter 1:35 – Deploy the ADK agent service 1:58 – Agent-LLM communication via environment variables 2:16 – Test the AI agent in the web UI 2:52 – Conclusion Resources: Codelab → http://goo.gle/475sUpV
GitHub repository → http://goo.gle/3KJVc1Y
Google Cloud Run GPU → http://goo.gle/48sn3NV
ADK Documentation → http://goo.gle/3LauFL8
Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech
#GoogleCloud #LLM #CloudRun #ADK Speakers: Amit Maraj Products Mentioned: GPU Cloud, Cloud Run






