Calls to Assistants API returns enrtirety of the the thread historu every time

Each run on the assistants api returns the entire thread history + the most recent message.

I have several questions:

  1. Is there a way to limit this in the call to the most recent message?
  2. Does grabbing the entire thread each call incur more financial cost to us ?
  3. Not the biggest issue in the world because I already have a work around, just a nice to have.

I have also developed a fully functioning chatGPT type chatbot. My own interpretation if what AI fans want so to speak. I don’t want to say too much before release in the next few days, but there are some rather interesting features. Especially for the business community.

Before anyone mentions it, yes, I am intently familiar with the OpenAI branding guidelines : “If you make a product that looks like one of ours…” Screenshot attached.

With the right approach/right person, no personality clashes, I am open to some sort of joint venture for anyone interested.

Thank you.

Oh . I also made a promo video here: https://www.youtube.com/watch?v=mt88RyQuxEo