Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

Zero To Mastery

Building AI Apps with the Gemini API

via Zero To Mastery

Go to class Write review

Overview

Learn to use Google's Gemini API for building AI-powered applications. Plus you'll put your skills into action by building three projects using the Gemini API.
  • Learn to make API calls with Google's Gemini Pro and Pro Vision AI models for dynamic applications.
  • Understand the nuances of Gemini's multimodal models: Nano, Pro, and Ultra, for versatile AI development.
  • Master Google AI Studio for crafting freeform prompts with variables and parameters, enhancing your AI interactions.
  • Gain insights into Gemini API's generation parameters for fine-tuned control over AI response generation.
  • Dive into practical AI with three projects: develop a conversational AI agent, create an interactive "Talk to an Image" app, and build an AI-powered Image Organizer.
  • Harness prompt engineering techniques and integrate AI into classic applications for next-level development skills.

Syllabus

  •   Introduction
    • Introduction
    • FAQ
    • Exercise: Meet Your Classmates and Instructor
    • Course Resources
  •   Setting Up the Environment
    • What We're Using
    • Jupyter Notebook
    • Google Colab
  •   Deep Dive into Google Gemini Pro API
    • Getting a Gemini API Key
    • Installing the Python SDK for Gemini API and Authenticating to Gemini
    • Gemini Multimodal Models: Nano, Pro, and Ultra
    • Google AI Studio: Freeform Prompts With Gemini Pro Vision
    • Google AI Studio: Using Variables and Parameters in the Prompt
    • Generating Text From Text Inputs: Gemini Pro
    • Streaming Model Responses
    • Generating Text From Image and Text Inputs: Gemini Pro Vision
    • Gemini API Generation Parameters: Controlling How the Model Generates Responses
    • Gemini API Generation Parameters Explained
    • Building Chat Conversations
    • Project: Building a Conversational Agent Using Gemini Pro
  •   Project: Talking With an Image
    • Project Requirements
    • Building the Application
    • Testing the Application
    • Streamlit: Transform Your Jupyter Notebooks into Interactive Web Apps
    • Creating the Web App Layout With Streamlit
    • Saving and Displaying the History Using the Streamlit Session State
  •   Project: Building an AI-Powered Image Renaming Tool
    • Project Introduction
    • Getting Images Using a Generator
    • Renaming Images Using Gemini Pro Vision
  •   Prompt Engineering for Gemini API
    • Intro to Prompt Engineering the Gemini API
    • Tactic #1 - Position Instructions Clearly With Delimiters
    • Tactic #2 - Provide Detailed Instructions for the Context, Outcome, or Length
    • Tactic #3 - Specify the Response Format
    • Tactic #4 - Few-Shot Prompting
    • Tactic #5 - Specify the Steps Required to Complete a Task
    • Tactic #6 - Give Models Time to "Think"
    • Other Tactics for Better Prompting and Avoiding Hallucinations
    • Prompt Engineering Summary
  •   Where To Go From Here?
    • Review This Byte!

Taught by

Andrei Dumitrescu

Reviews

Start your review of Building AI Apps with the Gemini API

Go to class

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Sign up for free
Someone learning on their laptop while sitting on the floor.