I want to prompt tune GPT-35-Turbo with my own data so that chatgpt could give results in context to my data

[ChiragM-Hexaware]

I can't find how to do that so can you provide some solution.
My data will be about some user and its projects.

[VamsiKrishnaNori]

As mentioned in below article

Reference: https://learn.microsoft.com/en-us/azure/cognitive-services/openai/how-to/completions#troubleshooting

Sometimes we might not get accurate response from our newly deployed model
Think of it like a cold start problem

So now to get some accurate data/response first give it some examples like in Q & A format to your model

Reference:

1. https://learn.microsoft.com/en-us/azure/cognitive-services/openai/how-to/prepare-dataset
2. https://learn.microsoft.com/en-us/azure/cognitive-services/openai/how-to/fine-tuning?pivots=programming-language-python#fine-tuning-workflow
3. https://learn.microsoft.com/en-us/azure/cognitive-services/openai/how-to/completions#improving-the-classifiers-efficiency

Let me know if this solved your issue

Advice: as you have mentioned user related data please be careful regarding what data is being passed to the model

[shshubhe]

I can't find how to do that so can you provide some solution. My data will be about some user and its projects.

Please go through this solution: https://github.com/Azure/openai-samples/tree/main/End_to_end_Solutions/EnterpriseChatGPT_WithAzSearch%20%5BLINK%5D