Skip to content
Multimodal Apps with Gemini

Generative AI · Python

Multimodal Apps with Gemini

By Maya Ellison

4.6 ★ editorial rating

$36.00

  • Format EPUB, PDF
  • Pages 224
  • Published 2026-07-18
  • Language English
  • Skill Intermediate
  • Technology Gemini / Python
Buy now Add to cart

Description

Build Gemini features that read screenshots, documents, and video — with latency, safety, and cost called out before you ship.

What you’ll learn

  • Pick the right Gemini modality
  • Keep latency and cost honest
  • Ship a multimodal slice users finish

Table of contents

  1. Multimodal product jobs
  2. Documents and screenshots
  3. Video without burning budget
  4. Safety filters
  5. Shipping a thin slice

Author

Maya Ellison

Builds production LLM systems and writes about practical architecture.