I’m creating a prompt sequence (a series of ChatGPT o1 modules) and I’m trying to find how to use the thread ID from the first ChatGPT o1 module in the 2nd, 3rd and 4th ChatGPT o1 modules in my scenario.
The regular ChatGPT (like 4o) has a place in the module where you can map in the thread ID to maintain an ongoing conversation, but I don’t see that in the o1 module.
Does anyone know how to do this?
Could you just use the Message an Assistant module instead?
@samliew Unfortunately, no. In the Open AI platform you can’t create an assistant with the o1 model. So you can’t use the Message an Assistant module in Make. I also just learned that the o1 model doesn’t support a thread_id parameter through the API, which was surprising.
But I did figure out a solution. You use the Create a Completion (Prompt) (GPT and o1 models) module in Make.
And then you map in the previous prompt and previous response, and add your new prompt, and that works. Just like you do with Claude or Gemini because they don’t support a thread_id parameter either. See screenshot below:
