prompts = [ “Prompt 1 goes here.”, “Prompt 2 goes here.”, “Prompt 3 goes here.” ] response = openai.ChatCompletion.create( model=“gpt-4”, messages=[ {“role”: “user”, “content”: prompt}, ], max_tokens=750, ) prompts are 100 in number. How I can manage this?

Asyncio with Parallel calls = all your data at once returned in smallest time frame. Here this will help many: async def fetch_data_and_summarize(self, username): try: # Parallel fetch operations pets_data, preferences_data, people_data, relationship_data, mental_health_data, physical_health_da…

Hi I want to pass multiple prompts in ChatCompletion create API

API Feedback

icdev2dev March 26, 2024, 7:32pm 4

You are limited by the number of requests per second. But generally just use asyncio in python to accomplidh the same?

2 Likes

Topic		Replies	Views
Parallelise calls to the API - is it possible and how? API	13	49504	December 13, 2023
Batching with ChatCompletion Endpoint Documentation gpt-35-turbo , chat-completion , batching , rate-limit	11	34186	December 13, 2023
Batching with ChatCompletion not possible like it was in Completion API	17	23187	December 13, 2023
Multiple prompt responses everywhere API	6	3718	December 25, 2023
Taking too long to respond Prompting gpt-35-turbo , chatgpt	3	3332	January 1, 2024

Hi I want to pass multiple prompts in ChatCompletion create API

Related topics