Mastering OpenAI & Google Gemini APIs: Build AI Applications

Name: Mastering OpenAI & Google Gemini APIs: Build AI Applications
Rating: 4.4 (79 reviews)

Integrate OpenAI Chat, Vision, Speech & Gemini APIs. Master Prompt Engineering, RAG, MCP, Fine-Tuning & Deployment

Role Play

Created byJustin Barnett

Last updated 5/2025

English

What you'll learn

What is the OpenAI API
LLMs, transformers, and high level how they work
How to generate text with the OpenAI API
How to summarize with OpenAI API
How to translate with OpenAI API
How to Fine Tune GPT 3.5 Turbo
How to use OpenAI API with other libraries
Deploying OpenAI applications with GCP and AWS
How to use GPT Builder to create custom GPTs

Course content

7 sections • 56 lectures • 5h 19m total length

Syllabus1:19
Familiarize yourself with the Udemy User Interface2:41
Connect with Me0:53
AI Definitions and Acronyms5:25

What are Transformers and how do they power Generative AI10:12
Explore how transformers use attention to power generative AI, explaining encoding with n-grams, inference matrices, and prompts, and why non-deterministic outputs lead to confident hallucinations.
Basic Prompt Engineering5:59
Explore the basics of prompt engineering to optimize large language models for tasks like question answering, text summarization, information extraction, and code generation.
Zero shot and Few Shot Prompting3:55
Explore zero-shot and few-shot prompting, distinguishing how large language models respond with no examples versus guided examples, including limitations with complex reasoning and numerical tasks.
Chain of Thought Prompting5:03
How to Evaluate Prompts and Models5:32
A Framework for writing Powerful Prompts5:18
Grounding LLMs for increased accuracy9:27
Controlling output formats with Exemplars4:16
Learn exemplars as a prompting technique to guide an LM in structuring responses from text. The lecture shows a Python prompt example with input-output formats and notes chat completion deprecation.
Transformers Quiz
Under the Hood: How Encoders allow LLMs to Process Prompts13:29
What is RAG (Retrieval Augmented Generation)6:41
What is MCP (Model Context Protocol)8:29
What are AI Agents9:20
Self Hosted Open Source LLMs vs Closed Source Models10:40
Compare closed source and open source llms, and weigh self-hosting against managed hosting to understand data control, maintenance, and cost implications.
Meeting with CORE-7: Your Transformer Systems Architect

Update on the Completions API1:06
Understand the deprecation of the completions API and the shift to chat completions in the OpenAI API. Use GPT 3.5 turbo instruct for completions, as turbo is chat-only.
Translating an article with the OpenAI API3:08
translate an article using the OpenAI API through zero-shot and few-shot prompting, with a live translation example and guidance on tokens, performance, and cost.
Example: Translating an article with OpenAI API4:34
This live example translates an article using the OpenAI API with a Python script, showing secret key setup in environment variables, a translation prompt, and token versus word limits.
Summarizing with the OpenAI API2:47
Example: Summarizing with the OpenAI API3:27
Upgrading the OpenAI API1:54
Chat completion with the OpenAI API2:59
Example: Build your own Chatbot with the Chat completion API6:51
Sentiment Analysis and Classification with the OpenAI API4:16
Explore sentiment analysis with the OpenAI API using few-shot and zero-shot prompting. See how system messages and context shape results and how to implement with the completion API.
Example: Sentiment Analysis and Classification with the OpenAI API4:06
Project: Building a chatbot for analyzing financial statements0:55
Launch your first project by building a chatbot that analyzes earnings transcripts with AI, using the Discount Cash Flows API data and an LM chat API.
Understanding the script structure2:07
Understanding the LLM request3:22
Replacing the LLM request with another LLM like Gemini5:07

Get Started with Gemini API in Google AI Studio9:14
Performing Chat Completion in Google Colab8:38
Use Cases of Large Context Windows3:23
Explore how large context windows let a language model reference more of your data for hyper-specific responses. Apply this to code bases, videos, and financial data in multimodal contexts.
Creating a Google Cloud Account and setting up Translate API5:29
Basic and Advance Translation with Cloud Translation API6:29
Code Walkthrough: Using Google Translate API to translate subtitles6:12
Explore a step-by-step Python walkthrough that translates subtitles using the Google Translate API, Webvtt integration, and language pairs to generate translated caption files.
Example: Translate Subtitles to 3+ languages4:38
Learn how to translate subtitles to multiple languages using AI-powered translation with the Google Translate API, preserving timestamps, running translate_subtitles.py, and exploring multilingual outputs.

What is Fine Tuning and what is it used for5:34
Fine tuning adapts pre-trained models on a small labeled dataset to tailor ai applications with the OpenAI API, enabling customer support, translation, and content generation.
Fine Tuning a Model with OpenAI API12:22
How to use GPT Builder to create custom GPTs12:20
Deploying an application with OpenAI API1:23
Dos and Don'ts with AI2:59
Explore the do's and don'ts of using generative AI, from content creation and prototyping to upscaling and colorization, while avoiding misinformation, plagiarism, and copyright pitfalls.
Ethics Quiz

Requirements

Basic understanding of Python and development environments
Basic understanding of AWS, GCP, or a deployment environment

Description

Ready to build powerful applications fueled by leading Large Language Models? This comprehensive course provides developers with the practical skills to harness the OpenAI API ecosystem and the Google Gemini & Translate APIs. Go beyond theory and learn to integrate cutting-edge AI capabilities into your projects, from setup and prompt engineering to fine-tuning and deployment.

We cover the essential concepts and provide hands-on examples to ensure you can confidently build real-world AI solutions. Whether you want to create intelligent chatbots, automate content creation, translate languages, generate images, or analyze data with computer vision, this course provides the roadmap.

In this course, you will master:

LLM & Prompt Engineering Fundamentals: Understand Transformers, advanced Prompt Engineering (Zero/Few-Shot, Chain of Thought, Frameworks, Evaluation), RAG, AI Agents, and Open vs Closed Source Models.
OpenAI API Setup & Architecture: Get your OpenAI API Key, set up your environment, understand pricing/limits, and grasp essential AI Application Architecture principles.
Core OpenAI APIs (Text & Chat): Utilize the Completions API and Chat Completion API for tasks like translation, summarization, sentiment analysis, classification, and building interactive chatbots (including a financial statement analysis project).
OpenAI Multimodal APIs: Integrate Image Generation (DALL-E), Text-to-Speech (TTS), and Computer Vision (GPT-4V) capabilities into your applications with practical examples (phone wallpapers, blog post transcription, calorie counting).
Google Gemini & Translate APIs: Get started with the Google Gemini API via AI Studio & Colab, explore Large Context Window use cases, and leverage the Google Translate API for basic and advanced translation tasks (including a subtitle translation project).
Building RAG Pipelines: Implement Retrieval Augmented Generation (RAG) from scratch to ground LLM responses in external data.
Fine-Tuning & Deployment: Learn the concepts of Fine-Tuning, fine-tune a model using the OpenAI API, use GPT Builder, and understand how to deploy an AI application.
AI Ethics: Discuss the crucial dos and don'ts of responsible AI development.

This course is designed for developers, engineers, and technical individuals aiming to build practical AI applications. By the end, you'll possess the skills to leverage the OpenAI and Google AI ecosystems effectively and ethically.

Enroll today and start building the next generation of AI-powered applications!

Who this course is for:

Beginner Python users and software engineers that want to develop an AI application with OpenAI API
Entrepreneurs that want to build their own AI application
Software engineers that want to create AI applications

Mastering OpenAI & Google Gemini APIs: Build AI Applications

What you'll learn

Explore related topics

Course content

Introduction4 lectures • 10min

A background on LLMs and Transformers14 lectures • 1hr 38min

Setting up your Environment6 lectures • 41min

How to use the Completions API, and Chat API with Examples14 lectures • 47min

Using Multimodal functionality like Image Generation, and Speech API7 lectures • 45min

Using Google Gemini API with large context windows7 lectures • 44min

Fine Tuning, Deploying, and Ethics5 lectures • 35min

Requirements

Description

Who this course is for: