I am trying to get array of suggestions (multiple suggestions) for some prompt from nodejs. Here is what I have so far:
const completion = await openai.createCompletion({
model: complitionModel,
prompt: `${finalCommand}: ${text}`,
max_tokens: 256,
temperature: 0,
top_p: 1,
frequency_penalty: 0,
presence_penalty: 0,
user: user.id
});
But it always return one suggestion (array with single element), no metter what prompt or text i send... Any idea why?
the documentation says a parameter n
which is 1 by default
How many completions to generate for each prompt.
Note: Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for
max_tokens
andstop
.
const completion = await openai.createCompletion({
model: complitionModel,
prompt: `${finalCommand}: ${text}`,
max_tokens: 256,
temperature: 0,
top_p: 1,
frequency_penalty: 0,
presence_penalty: 0,
user: user.id,
n: noOfCompletions //1 by default
});
Note
you may get the same results even with a higher n
with a temperature
of 0
. The docs say
What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.
Also this forum post addresses this issue