Reduce processing time

[Azzedde]

If you tried the project, you can notice that the time varies according to the paper length. I want to reduce that processing time and I thought of parallelizing the dialogue generation process: this means that we will send a lot of requests to the OpenAI API in the same time, the problem here is that there are Rate limits (honestly I didn't test it but it is doable since the limits are per minutes and not per second)