Generate text using user-supplied keywords

I've got a use case where I need to generate sentences based on a set of user supplied keywords. Here is an example of what I need:

User input:

End-User: Data Scientists

Region: Middle East

Country: UAE

Solution: BigPanda

Application: machine learning

Benefits: lower costs and runtime

Output (Curly-Brackets are just there to highlight):

Learn how {data scientists} in the {Middle East} such as in the {UAE} are using {BigPanda} to streamline their {machine learning} processes to {lower costs and runtime}.

So the model needs to use the keywords given by the user and generate similar sentences. I also have a dataset of about 2000 of such sentences, which may come in handy.

One way I thought this could be possible is by using the GPT-2 model and perhaps finetuning it with the dataset, but I haven't been able to figure out how I would actually go about using it for something like this.