Hands-On OpenAI API: Building a Real-World Solution

This is the repository for the LinkedIn Learning course Hands-On OpenAI API: Building a Real-World Solution. The full course is available from LinkedIn Learning.

OpenAI stands at the forefront of AI, particularly when it comes to large language models (LLMs). If you’re a developer or business leader looking to leverage AI-powered tools, this course helps you to get up to speed with how to use OpenAI APIs to build solutions based on the retrieval-augmented generation (RAG) technique.

Join instructor Rodrigo Díaz Concha as he demonstrates a wide variety of solution-building options including using the Audio API to transcribe audio and the Chat Completions API to create documents. Test your new skills with a real-world project named KinderLogger by building an assistant using the Assistants API, implementing a retrieval-augmented generation (RAG) process in the assistant, and implementing a Web API using FastAPI to expose the assistant. Along the way, learn how to identify harmful content with the Moderations API, and create and use a GPT as a front end to invoke the service and test your KinderLogger project.

See the readme file in the main branch for updated instructions and information.

Instructions

This repository has branches for each of the videos in the course. You can use the branch pop up menu in github to switch to a specific branch and take a look at the course at that stage, or you can add /tree/BRANCH_NAME to the URL to go to the branch you want to access.

Branches

The branches are structured to correspond to the videos in the course. The naming convention is CHAPTER#_MOVIE#. As an example, the branch named 02_03 corresponds to the second chapter and the third video in that chapter. Some branches will have a beginning and an end state. These are marked with the letters b for "beginning" and e for "end". The b branch contains the code as it is at the beginning of the movie. The e branch contains the code as it is at the end of the movie. The main branch holds the final state of the code when in the course.

When switching from one exercise files branch to the next after making changes to the files, you may get a message like this:

error: Your local changes to the following files would be overwritten by checkout:        [files]
Please commit your changes or stash them before you switch branches.
Aborting

To resolve this issue:

Add changes to git using this command: git add .
Commit changes using this command: git commit -m "some message"

Instructor

Rodrigo Díaz Concha

Solutions Architect, Microsoft Regional Director, and Microsoft MVP

Check out my other courses on LinkedIn Learning.