User and product embeddings unclear

[EDGDrummond]

In the 'User_and_product_embeddings.ipynb' there is a requirement to load 'output/embedded_babbage_similarity_50k.csv'. A comment states that this file needs to be generated in advance, but there is no clear file to use to generate this data from. A link or explanation of where to find it would be helpful.

[ted-at-openai]

Will fix. Thanks!

[brunobelloni]

Hello @ted-at-openai

I wasn't able to find the file neither

[wilmerhenao]

Same here. It looks like it would be a great example to run, but the data is unavailable.

[chrisbrody]

@ted-at-openai any chance this has been fixed yet?

[ted-at-openai]

Sorry, hasn't been at the top of my priority list, even though I'm aware it's a deficiency. If any of you want to fix, I'm happy to accept a PR.

[brunobelloni]

Sorry, hasn't been at the top of my priority list, even though I'm aware it's a deficiency. If any of you want to fix, I'm happy to accept a PR.

@ted-at-openai Dataset update #535

[FarziBuilder]

Hey! folks in another issue, they have said they won't be able to fix it.

But, its pretty simple, you have to just create embeddings of the data as told in Obtain_dataset exercise. And then you have to convert those embeddings to numpy arrays. Then just take mean of those embeddings group-wise and from axis=0 EmbeddingsTut.zip

I have attached my jupyter notebook, go through it: