Hi, I have a task that involves sending to API the same large amount of prompts but only with a few new sentences at last. I wonder if OpenAI saves previous chat in some way maybe as embedding, so I can send that same pre-prompts to it once, and resume every time with new questions. In that way, I …

That’s not how the models work. What you are asking is simple not possible. The models are stateless so every time you want to exchange messages you must send everything you want the model to have in context.

Use playground if you can, can go back and delete or keep any history in the chat

I’d second that this would be extremely useful: being able to save model state at the output level of a prompt preamble (e.g., a classification task), and then run that state on a series of prompt followups (for example, "Classify the sentiment of this sentence: " can run once, and then a batch of s…

I wonder if it’s possible to use assistant API since it doesn’t need to manage context window. For example, there’s a task description of 1000 tokens, and then a stream of specific tasks. Using Completion API I have to input as “description - task” format. Could assistant API handle the “descripti…

Is it possible to reuse previous chat history on the OpenAI side to avoid sending repetitive tokens?

API

fjd May 13, 2023, 3:09am 3

Yeah I am looking for basically the same thing but with API, because I do have many requests at the same time

Topic		Replies	Views
Efficient stateful completion chatbot API	10	5535	July 9, 2024
System Prompt ( Sending each time instead of once ) API api	14	14556	May 15, 2024
Is there a way to save tokens when dealing with longer prompts in each conversation? API	3	1658	September 26, 2025
Is possible OpenAI API caching the conversation? API	4	4528	June 4, 2024
How do I avoid wasting tokens by passing old messages API question	3	4266	May 11, 2023

Is it possible to reuse previous chat history on the OpenAI side to avoid sending repetitive tokens?

Related topics