Building AI Apps with the Gemini API

3h 43m 41s
English
Paid

Course description

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.

Read more about the course

Take your first step into the world of AI application development by diving deep into a fundamental technology: Google's Gemini API. You'll learn everything there is about utilizing the API to power your AI applications with Google's leading Large Language Models.

Watch Online

This is a demo lesson (10:00 remaining)

You can watch up to 10 minutes for free. Subscribe to unlock all 39 lessons in this course and access 10,000+ hours of premium content across all courses.

View Pricing
0:00
/
#1: Introduction

All Course Lessons (39)

#Lesson TitleDurationAccess
1
Introduction Demo
03:26
2
What We're Using
00:36
3
Jupyter Notebook
14:11
4
Google Colab
08:08
5
Getting a Gemini API Key
04:21
6
Installing the Python SDK for Gemini API and Authenticating to Gemini
09:52
7
Gemini Multimodal Models: Nano, Pro, and Ultra
05:15
8
Google AI Studio: Freeform Prompts With Gemini Pro Vision
06:12
9
Google AI Studio: Using Variables and Parameters in the Prompt
03:05
10
Generating Text From Text Inputs: Gemini Pro
04:23
11
Streaming Model Responses
03:36
12
Generating Text From Image and Text Inputs: Gemini Pro Vision
05:13
13
Gemini API Generation Parameters: Controlling How the Model Generates Responses
06:12
14
Gemini API Generation Parameters Explained
10:14
15
Building Chat Conversations
07:54
16
Project: Building a Conversational Agent Using Gemini Pro
07:19
17
Introduction to Gemini 1.5 Pro
04:11
18
System Instructions
05:43
19
The File API Prompting with Media Files
06:09
20
Tokens
06:42
21
Prompting with Audio
04:21
22
Project Requirements
05:54
23
Building the Application
05:23
24
Testing the Application
01:49
25
Streamlit: Transform Your Jupyter Notebooks into Interactive Web Apps
02:49
26
Creating the Web App Layout With Streamlit
11:20
27
Saving and Displaying the History Using the Streamlit Session State
05:20
28
Project Introduction
00:57
29
Getting Images Using a Generator
06:18
30
Renaming Images Using Gemini Pro Vision
09:35
31
Intro to Prompt Engineering the Gemini API
03:13
32
Tactic #1 - Position Instructions Clearly With Delimiters
05:02
33
Tactic #2 - Provide Detailed Instructions for the Context, Outcome, or Length
06:11
34
Tactic #3 - Specify the Response Format
06:14
35
Tactic #4 - Few-Shot Prompting
06:56
36
Tactic #5 - Specify the Steps Required to Complete a Task
06:29
37
Tactic #6 - Give Models Time to "Think"
04:34
38
Other Tactics for Better Prompting and Avoiding Hallucinations
06:21
39
Prompt Engineering Summary
02:13

Unlock unlimited learning

Get instant access to all 38 lessons in this course, plus thousands of other premium courses. One subscription, unlimited knowledge.

Learn more about subscription

Comments

0 comments

Want to join the conversation?

Sign in to comment

Similar courses

Automata Theory: inside a RegExp machine

Automata Theory: inside a RegExp machine

Sources: Dmitry Soshnikov
State machines — the fundamental concept used today in many practical applications, starting from UI programming like React, automated reply systems, lexical an
1 hour 48 minutes 5 seconds
System Design for Interviews and Beyond

System Design for Interviews and Beyond

Sources: Mikhail Smarshchok
Having over 15 years of industry experience, last 9 years I worked on building scalable, highly available and low latency distributed systems. For a long time, I have wondered w...
7 hours 53 minutes 5 seconds
Production-Ready Serverless

Production-Ready Serverless

Sources: Yan Cui
The Production-Ready Serverless course teaches how to build resilient and scalable serverless applications, ready for production deployment. It covers...
13 hours 37 minutes 6 seconds