Have you heard about databricks latest open-source language model called Dolly? It’s a ChatGPT like model that uses the tatsu-lab/alpaca dataset with examples of questions and answers. To train Dolly, you can combine this dataset (simple solution on the attached screenshot) with your questions and answers regarding your products/use cases. The possibilities are endless! You can use it as a chatbot for your clients through MLflow rest model serving or anything else. Just add your data, train, and start talking with Dolly!