I have C# application where I use the ChatCompletion API to create a Chat.

I get the error:

Problem Summary I am trying to us OpenAI API to make a batch request to chatgtp 3.5 turbo using Google Colab. It seems to work fine but it only returns the prompt. It never answers the question with the 1000 max_new_token allowance. I am following the instructions on https://platform.openai.com/docs/guides/batch/getting-started The goal To get Chatgtp to […]

how to let users work with chat gpt on my custom application using their own chat gpt account without them having to explicitly provide their api keys

I am running the following code :

I am trying to use OpenAI’s GPT-4 model to analyze the content of an uploaded file. The file is a scan with text, and I need the model to read and analyze its contents. Here is my request to the /chat/completions endpoint:

I am trying to use OpenAI’s GPT-4 model to analyze the content of an uploaded file. The file is a scan with text, and I need the model to read and analyze its contents. Here is my request to the /chat/completions endpoint:

I want to use the batch api . But instead writing the following code by creating a client , I need to use python post request .

I am trying to investigate OpenAI API but I found out that Free tier rate limits do not provide the announced rights.

I have tried to make a question answer model using the open AI 0.28 and 1.34 but got a rate limit error (error code is 429).