Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Building Open Source AI Agents with Google Gem...
Search
Sponsored
·
Ship Features Fearlessly
Turn features on and off without deploys. Used by thousands of Ruby developers.
→
Punsiri Boonyakiat
July 20, 2026
Technology
14
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
Building Open Source AI Agents with Google Gemma and ADK
Punsiri Boonyakiat
July 20, 2026
More Decks by Punsiri Boonyakiat
See All by Punsiri Boonyakiat
Build ADK Agent with Skills
punsiriboo
0
23
Agent Development Kit - ADK x MCP x A2A
punsiriboo
0
490
Build a Travel Agent using MCP Toolbox for Databases and ADK
punsiriboo
1
200
LINE x GEMINI in Python
punsiriboo
0
250
ChaiyoGCP#5 - CodeAlong Session#2 - Build Real World AI Applications with Gemini and Imagen
punsiriboo
0
48
AI*dea - [Thai National Telecom] AI Hackathon 2025 - LINE Chatbot with Gemini
punsiriboo
0
63
LINE DEV Meetup#6 - Agentic_AI_with_LINE_and_Conversational_Agents.pdf
punsiriboo
0
220
Gemini & Vertex AI: Revolutionizing Search with Generative API
punsiriboo
0
57
[Chaiyo GCP - Online Code Along Session] - Gemini for Data Scientist [Running Codelab]
punsiriboo
0
67
Other Decks in Technology
See All in Technology
型は壁、Rustでもバグを直すな、表現できなくせよ
nwiizo
14
2.1k
しくみを学んで使いこなそう GitHub Copilot app
torumakabe
2
290
OPENLOGI Company Profile for engineer
hr01
1
74k
Data + AI Summit 2026 イベントレポート: 「AIがビジネスで意思決定するデータ基盤」へ
nek0128
0
280
Oracle Base Database Service 技術詳細
oracle4engineer
PRO
15
110k
LLM/Agent評価:トップ営業の発言を「正解」にする 〜暗黙的正解による評価を営業資産に変える〜
takkuhiro
1
230
発表と総括 / Presentations and Summary
ks91
PRO
0
140
最適な自走を最小限の支援で — M&Aで拡大する組織で少人数SREが挑んだ1年 / SRE NEXT 2026
genda
0
1.5k
10年目を迎えた「ABEMA」がどのように AI 活用を推進して、AI 駆動開発にシフトしているのか / How ABEMA, entering its 10th year, is promoting the use of AI and shifting toward AI-driven development
miyukki
0
290
そのドキュメント、自動化しませんか?
yuksew
1
310
関数型の考えを TypeScript に持ち込んで、テストしやすい純粋関数を増やす / Pure at the Core, Effects at the Edge: Bringing Functional Thinking into TypeScript
kaminashi
2
130
Kaggleで成長するために意識したこと
prgckwb
2
420
Featured
See All Featured
SEO in 2025: How to Prepare for the Future of Search
ipullrank
3
3.6k
Agile that works and the tools we love
rasmusluckow
331
22k
A brief & incomplete history of UX Design for the World Wide Web: 1989–2019
jct
2
420
Self-Hosted WebAssembly Runtime for Runtime-Neutral Checkpoint/Restore in Edge–Cloud Continuum
chikuwait
0
650
Optimizing for Happiness
mojombo
378
71k
コードの90%をAIが書く世界で何が待っているのか / What awaits us in a world where 90% of the code is written by AI
rkaga
62
45k
The #1 spot is gone: here's how to win anyway
tamaranovitovic
3
1.1k
DBのスキルで生き残る技術 - AI時代におけるテーブル設計の勘所
soudai
PRO
67
56k
Future Trends and Review - Lecture 12 - Web Technologies (1019888BNR)
signer
PRO
0
3.6k
From Legacy to Launchpad: Building Startup-Ready Communities
dugsong
0
260
The SEO identity crisis: Don't let AI make you average
varn
0
520
Leveraging LLMs for student feedback in introductory data science courses - posit::conf(2025)
minecr
1
320
Transcript
AgentCamp Bangkok Building Open Source AI Agents with Google Gemma
and ADK Punsiri Boonyakiat Lead Data Engineer @Central Food Retail AI
Agenda Local LLM Models & Tools Reviews Gemma 4 Quick
Intro Agent Development Kit (ADK) Quick Start Demo
01 Editable Location Local LLM Models & Tools Reviews
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”
Cloud LLM vs. Local LLM
Why Local LLM ? Benefits of Local Models: • •
• • Better privacy Can work offline No API cost per request More control and customization
Quick Start Local LLM Tools
Multiple Choice of Local LLMs
None
None
None
None
None
Google AI Edge Gallery
02 Editable Location Gemma 4 Quick Intro
None
None
Test Gemma Model on AI Studio
Deploy Open LLM on Cloud Run
Google Agent Platform - Model Garden
03 Editable Location Agent Development Kit (ADK)
None
v
04 Editable Location Quick Start Demo
None
None
1. Install Ollama and Pull Gemma Model
2. Install Require Python Library
3. Create Agent with ADK Cli
3. Edit agent.py
4. Run ADK Web
5. Add MCP Tools
6. Run ADK Web
References • https://docs.cloud.google.com/run/docs/tutorials/gpu-gemma-with-ollama Editable Location