[FIXED] Embedding Model Unavailable in the Learning Platform

Course Q&A Retrieval Augmented Generation
, , ,
1

This issue has been fixed. If you still encounter issues, please let me know!

Hi all,

As some of you may have noticed, we’re currently experiencing issues due to the deprecation of an embedding model from our provider. This is affecting the ungraded labs in Modules 2–5, as well as Assignments 3, 4, and 5.

We’ve already implemented a fix on Coursera, but we’re still encountering some issues applying the same fix in our Learning Platform. We’re actively working on it and hope to resolve it as soon as possible.

We’re very sorry for the inconvenience. We understand that being unable to complete assignments can be frustrating, and we appreciate your patience while we work on a solution.

I’ll post an update here as soon as the issue is resolved. If you have any questions or concerns in the meantime, please let me know.

Cheers,
Lucas

3

All ungraded labs fixed!

Module 4 Assignment fixed!

4

Module 3 assignment fixed!

5

Module 5 assignment fixed!

6

FYI - I am experiencing this issue on Module 4 both graded and non-graded labs ( using DeepLearning

7

I am still seeing in Module 2.

BadRequestError: Error code: 400 - {‘id’: ‘obv5uJu-2kFHot-9dfb1b7dede36798’, ‘error’: {‘message’: ‘Unable to access non-serverless model meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo. Please visit Together AI | The AI Native Cloud to create and start a new dedicated endpoint for the model.’, ‘type’: ‘invalid_request_error’, ‘param’: None, ‘code’: ‘model_not_available’}}

8

@amritaputrab

This new error occurred since yesterday in all assignment labs, m4 and m5 was updated. m3 was reported yesterday, but it’s weekend, i informed lucas, but he might only look on Monday