Example Curriculum
Introduction
Available in
days
days
after you enroll
Setting Up the Environment
Available in
days
days
after you enroll
Deep Dive into Google Gemini Pro API
Available in
days
days
after you enroll
- Getting a Gemini API Key (4:20)
- Installing the Python SDK for Gemini API and Authenticating to Gemini (9:51)
- Gemini Multimodal Models: Nano, Pro, and Ultra (5:14)
- Google AI Studio: Freeform Prompts With Gemini Pro Vision (6:11)
- Google AI Studio: Using Variables and Parameters in the Prompt (3:04)
- Generating Text From Text Inputs: Gemini Pro (4:22)
- Streaming Model Responses (3:35)
- Generating Text From Image and Text Inputs: Gemini Pro Vision (5:12)
- Gemini API Generation Parameters: Controlling How the Model Generates Responses (6:11)
- Gemini API Generation Parameters Explained (10:13)
- Building Chat Conversations (7:53)
- Project: Building a Conversational Agent Using Gemini Pro (7:18)
Explore Gemini 1.5 Pro API
Available in
days
days
after you enroll
Project: Talking With an Image
Available in
days
days
after you enroll
Project: Building an AI-Powered Image Renaming Tool
Available in
days
days
after you enroll
Prompt Engineering for Gemini API
Available in
days
days
after you enroll
- Intro to Prompt Engineering the Gemini API (3:12)
- Tactic #1 - Position Instructions Clearly With Delimiters (5:01)
- Tactic #2 - Provide Detailed Instructions for the Context, Outcome, or Length (6:10)
- Tactic #3 - Specify the Response Format (6:13)
- Tactic #4 - Few-Shot Prompting (6:55)
- Tactic #5 - Specify the Steps Required to Complete a Task (6:28)
- Tactic #6 - Give Models Time to "Think" (4:33)
- Other Tactics for Better Prompting and Avoiding Hallucinations (6:20)
- Prompt Engineering Summary (2:12)
Where To Go From Here?
Available in
days
days
after you enroll