Course
Introduction to Cloud-based AI
Learning path outcomes
- Evaluate and implement cloud-based AI services for text, image, and audio processing tasks.
- Compare and contrast different AI platforms and their capabilities in solving real-world problems.
- Design and develop basic AI apps using cloud-based services and APIs.
Prerequisites
While the program is designed to accommodate developers with varying levels of experience, the following prerequisites are recommended:
- Basic programming knowledge in any language
- Familiarity with web development concepts and RESTful APIs
- Understanding of basic AI and machine learning concepts (beneficial but not required)
Achievements
Earn a badge when you finish this learning path!
Introduction to Cloud-based AI
Learning path content
1
Text Generation with OpenAI
This module focuses on a basic text-generation app using OpenAI’s GPT-4 and the Chat Completions API.
You’ll learn about API integration, model selection, and fundamental concepts in working with large language models.
Expand module content Hide module content Show module content Hide module content
- Introduction to OpenAI & API Setup · Start lesson 18 mins
- Understanding OpenAI Models 13 mins
- Basic Chat Completion with GPT-4o 12 mins
- Advanced Chat Completion Techniques 24 mins
- Building a Non-Streaming Chat App 16 mins
2
Text Generation with Google Gemini
Explore text generation using Google’s Gemini service.
Learn about Google’s AI ecosystem and gain experience
in implementing Gemini’s text generation capabilities.
Expand module content Hide module content Show module content Hide module content
- Introduction to Google Gemini · Start lesson 44 mins
- Using Google Code Assist 23 mins
- Text Generation with Google Gemini API 26 mins
- Building a Non-Streaming Chat App with Gemini 29 mins
3
Multimodal Integration with OpenAI
This module extends students’ knowledge to multimodal AI apps, incorporating image and audio processing using OpenAI’s services.
Students will learn to analyze images, generate and edit images, and work with speech recognition and synthesis.
Expand module content Hide module content Show module content Hide module content
- Introduction to Multimodal AI · Start lesson 17 mins
- Image Analysis with GPT-4 Vision 23 mins
- Image Generation & Editing with DALL-E 17 mins
- Speech Recognition & Synthesis 18 mins
- Building a Multimodal AI App 23 mins