ADK-S02Axalon Original

Multimodal Agents

Taught by Dan King, 4x Google Trainer of the Year

1 dayILTIntermediateLoading...

Multimodal1 DayGemini 2.5

Public class policy: Classes run with a minimum of 6 participants. If minimum enrollment isn't reached, you'll be notified 7 days before with options to transfer or receive a full refund.

Overview

Build agents that process images, audio, and video. Morning: Multimodal tool interaction—callbacks, context modification. Afternoon: Production multimodal agents with Gemini 2.5 and Firestore integration.

What You'll Learn

Implement tool callbacks for multimodal processing
Apply context modification patterns
Use Gemini 2.5 multimodal capabilities
Build image processing agents
Integrate with Firestore for media storage
Create document analysis workflows

Who Should Attend

Completed ADK-101. Developers needing image/video processing capabilities.

Products Covered

ADKGeminiFirestoreCloud Vision

Course Modules

Morning: Multimodal Tool Interaction

Topics

Tool callbacks for multimodal
Context modification patterns
Model callbacks
Image processing tools

Learning Outcomes

Implement tool callbacks for multimodal processing
Apply context modification patterns

Activities

Theory (30min)Lab: Multimodal Tool Part 1Lab: Multimodal Tool Part 2

Afternoon: Production Multimodal Agents

Topics

Gemini 2.5 multimodal capabilities
Firestore media integration
Expense tracking example
Document analysis

Learning Outcomes

Build production multimodal agents
Integrate with Firestore for media storage

Activities

Theory (20min)Lab: Personal Expense AssistantWorkshop: Add image processing (2hr)

Get This Training

No public classes currently scheduled. Express interest below or request private training.

Request Private Session

Course Details

Course Code: ADK-S02
Duration: 1 day
Format: ILT
Level: Intermediate
Price: Loading...

Questions About This Course?

Starting fromLoading...