-
Notifications
You must be signed in to change notification settings - Fork 34.1k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Fixed documentation,broken notebooks and made it runnable inside DevContainer #188
Fixed documentation,broken notebooks and made it runnable inside DevContainer #188
Conversation
👋 Thanks for contributing @corradocavalli! We will review the pull request and get back to you soon. |
We have automatically detected missing tracking id from the following relative paths in your lessons. Check Missing Tracking from Paths
|
Hi @corradocavalli, thank you so much for your contribution! As I am going through all your changes and adding some further edits I am putting this PR as a draft. Once I finalize my review I'll change the status again :-) |
Sure @carlotta94c no problem. :-) |
We have automatically detected missing tracking id from the following URLs in your lessons. Check Missing Tracking from URLs
|
We have automatically detected missing tracking id from the following URLs in your lessons. Check Missing Tracking from URLs
|
Adding cosine similarity definition as per official doc https://learn.microsoft.com/en-us/azure/ai-services/openai/tutorials/embeddings?tabs=python-new%2Ccommand-line
We have automatically detected missing tracking id from the following URLs in your lessons. Check Missing Tracking from URLs
|
Updating cosine similarity definition as per official doc https://learn.microsoft.com/en-us/azure/ai-services/openai/tutorials/embeddings?tabs=python-new%2Ccommand-line
We have automatically detected missing tracking id from the following URLs in your lessons. Check Missing Tracking from URLs
|
We have automatically detected missing tracking id from the following URLs in your lessons. Check Missing Tracking from URLs
|
Updating text similarity model to text-embedding-ada-002 model, since all the other embeddings model will be retired in 2024
We have automatically detected missing tracking id from the following URLs in your lessons. Check Missing Tracking from URLs
|
We have automatically detected missing tracking id from the following URLs in your lessons. Check Missing Tracking from URLs
|
1 similar comment
We have automatically detected missing tracking id from the following URLs in your lessons. Check Missing Tracking from URLs
|
Merged, thanks for the contribution @corradocavalli ! |
The following PR is the result of my experience with this course.
I tried to run it inside a DevContainer but since the beginning it was not working because of a problem with the initializaion script.
Once solved, the installed openai library version was 1.2.4 and due to the breaking changes 90% of the notebooks were broken.
I also fixed several code errors that were causing several notebooks to fail and unified them to use the same .env file instead of forcing the student to type the same information in every chapter (this repo represents a course so it would make sense to demonstrate some basic styes and guidelines).
I also added notes regarding the kind of model and version to use otherwise several samples in the notebook would fail (e.g. Chapter 11 requires model version >=0613).
I warmily suggest to add in the
00-couse-setup
chapter a step-by-step guide about how to deploy a model instead of delegating it to the following Learn page since we are targeting beginners and, from the link, the steps are not so intuitive.I would also suggest the creation of the required two different deployments (gpt3.5 and ada2.0) at the same time so as to make the accessibility of the course more immediate.
Unfortunately due to the breaking changes the code in the linked video in chapter
06-text-generation-apps
is not updated anymore.Important
The notenooks in
09-building-image-applications
, due to the breaking changes, are still failing and I don't have enough time to dedicate it.