How to get constant result for particular prompt when we are using openAI API to get result for prompt?

Community
,
1

I am using openAI API and using GPT3.5 turbo model and using chat completion API to get result for query , I have some large prompt to create some document , I am getting different result every time when I run the API with same prompt

Is there any parameter in API to get constant result ?

2

Hi and welcome to the Developer Forum!

You can turn the temperature to 0 to reduce the amount of variation but it will not be nothing, AI generation cannot be assured to be the same every time.

3

Is there any parameter in OpenAI API similar to random state in ML model development?

4

Not for the language models, no. Dall-E can use a seed value, but there is no equivalent for the LLM API’s