Is it important to use Open AI API ? Is it possible to do this by picking soemthing from HuggingFace ? This way I can prevent API costs. For Data Augmentation ?
SmythOS is far more versatile than chatbots! Find out how this AI can be customized for a range of applications, making it a vital resource for any company. #TechSolutions #Innovation #SmythOS #AI
I think your examples could be more detailed and explanatory. I didn't really understand what you meant by turning unstrucutred data into structured data
Thanks for the feedback :) I think I did a better job of explaining them in the blog post, but here's the basic idea. Most data available to us is unstructured (i.e. not organized in tables), for text-based data we can use embedding models as a flexible way to translate arbitrary text into structured datasets.
Many have asked for AI use cases that are not a chatbot. Should I make more content about this?
please please do….many thanks
Extremely Practical Video. Amazing
So useful Shaw! Love seeing the breakdown in a business way 🙏🏾
Glad it was helpful!
Thanks @Shaw Talebi.
Very very informative. Thanks a lot.
Thanks!
Thank you! Glad it was helpful :)
Is it important to use Open AI API ? Is it possible to do this by picking soemthing from HuggingFace ? This way I can prevent API costs. For Data Augmentation ?
While you don't necessarily need to use OpenAI, the Llama and Mixtral models are good open-source alternatives.
Hey Shaw, can you pls make a beginner-friendly but detailed video on RLHF pls?
Great suggestion. It's on my list :)
Can grouping raw data into groups also be an application ?
Definitely!
SmythOS is far more versatile than chatbots! Find out how this AI can be customized for a range of applications, making it a vital resource for any company. #TechSolutions #Innovation #SmythOS #AI
I think your examples could be more detailed and explanatory. I didn't really understand what you meant by turning unstrucutred data into structured data
Thanks for the feedback :) I think I did a better job of explaining them in the blog post, but here's the basic idea.
Most data available to us is unstructured (i.e. not organized in tables), for text-based data we can use embedding models as a flexible way to translate arbitrary text into structured datasets.