Building Open Source AI Agents with Google Gemma and ADK

Transcript

1. AgentCamp Bangkok Building Open Source AI Agents with Google Gemma and ADK Punsiri Boonyakiat Lead Data Engineer @Central Food Retail AI
2. Agenda Local LLM Models & Tools Reviews Gemma 4 Quick Intro Agent Development Kit (ADK) Quick Start Demo
3. 01 Editable Location Local LLM Models & Tools Reviews
4. What is Local LLM ? “A Local Model (or Local LLM) is an AI model that runs directly on your own device or server instead of using AI through the internet”
5. Cloud LLM vs. Local LLM
6. Why Local LLM ? Benefits of Local Models: • • • • Better privacy Can work offline No API cost per request More control and customization
7. Quick Start Local LLM Tools
8. Multiple Choice of Local LLMs
14. Google AI Edge Gallery
15. 02 Editable Location Gemma 4 Quick Intro
18. Test Gemma Model on AI Studio
19. Deploy Open LLM on Cloud Run
20. Google Agent Platform - Model Garden
21. 03 Editable Location Agent Development Kit (ADK)
23. v
24. 04 Editable Location Quick Start Demo
27. 1. Install Ollama and Pull Gemma Model
28. 2. Install Require Python Library
29. 3. Create Agent with ADK Cli
30. 3. Edit agent.py
31. 4. Run ADK Web
32. 5. Add MCP Tools
33. 6. Run ADK Web
34. References • https://docs.cloud.google.com/run/docs/tutorials/gpu-gemma-with-ollama Editable Location