Best approach to train a model for technical support to specific products, given product SKU and question

We need to develop a chatbot for tech support and pre-sales answering. User would select an specific product and write his question, our website would parse SKU and generate API call directly. We have detailed technical data as topics and replies from old questions.

How can we train our model using that data? We have trained oru model with prompts like this, for each SKU:

System: Smart tech support chatbot for SKU xxxxx
user: what colors do you sell?
assistant: red, blue and green

After training with more than 200 prompts, model sometimes replies with nonsense or made-up replies, even with temperature set to zero.

What is best approach for this project, in terms of prompt training generation?

1 Like

Hey Champ!

And welcome to the community forum!

I’ll recommend that you use the SKU to fetch relevant product information from your database and use it for RAG (remote augmented generation) as part of your process. You can find an example of such a thing in the OpenAI cookbook.


Thanks a lot N2U! reading and learning now


happy to help!

Feel free to ask if you have more questions :laughing: