Datasets for RAG/finetuning/etc.

[vladiliescu]

Hi there, the demo videos reference several datasets for RAG, finetuning, etc.

Are these published somewhere (couldn't find a link in the repo but maybe I haven't looked hard enough) or should we create these ourselves?

[toddanglin]

Thanks for the question, @vladiliescu. I presume you're talking about the demo videos for the Azure AI Studio talk?

@amynic @hnky Can you assist here?

[nielsberglund]

@vladiliescu Did you ever get an answer to this?

Tagging @toddanglin , @amynic, @hnky

[vladiliescu]

@nielsberglund not yet, but it’s not a blocker — I’ve decided to skip those bits in my talk.

[nielsberglund]

Thanks, @vladiliescu! I found similar datasets for the first demo. However, I don't really know for the fine-tuning demo —I may skip that.

[swaminathanvetri]

@nielsberglund - I am in need of the same dataset to run through the demos for Azure AI studio. Would you mind sharing the links for the dataset you may have?

[amynic]

Hi everyone - my best recommendation would be to use this public repo sample called Contoso Chat - you will have everything you need to deploy and run (inc datasets) https://github.com/Azure-Samples/contoso-chat/tree/main

[nielsberglund]

Hi all! So, I used what Amy refers to. Niels

…

On Fri, 26 Jul 2024 at 11:53, Amy Boyd ***@***.***> wrote: Hi everyone - my best recommendation would be to use this public repo sample called Contoso Chat - you will have everything you need to deploy and run (inc datasets) https://github.com/Azure-Samples/contoso-chat/tree/main — Reply to this email directly, view it on GitHub <#5 (reply in thread)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AL53CEQGRWDXSOIIASQHYT3ZOIMDNAVCNFSM6AAAAABHULT5DKVHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTAMJVHAZDQMY> . You are receiving this because you were mentioned.Message ID: ***@***.*** com>