Error when connection to OpenAI

[ibiscp]

I'm getting the following error when generating a message using LangChain with OpenAI
WARNING - Retrying (Retry(total=1, connect=None, read=None, redirect=None, status=None)) after connection broken by 'SSLError(SSLZeroReturnError(6, 'TLS/SSL connection has been closed (EOF) (_ssl.c:1129)'))': /v1/chat/completions

LangChain tries several times but in the end it gives up
WARNING - Retrying langchain.chat_models.openai.ChatOpenAI.completion_with_retry.<locals>._completion_with_retry in 16.0 seconds as it raised APIConnectionError: Error communicating with OpenAI: HTTPSConnectionPool(host='api.openai.com', port=443): Max retries exceeded with url: /v1/chat/completions (Caused by SSLError(SSLZeroReturnError(6, 'TLS/SSL connection has been closed (EOF) (_ssl.c:1129)'))).

Has anyone faced this problem before and could give me some insights on how to fix it?

[shashankdeshpande]

This is due to the rate limit by OpenAI.
For the gpt-3.5-turbo model it's 3 requests or 40k tokens per minute for free trial users.

You can check your account specific rate limits here - https://platform.openai.com/account/rate-limits

Here is the rate limit documentation by OpenAI -
https://platform.openai.com/docs/guides/rate-limits/what-are-the-rate-limits-for-our-api

Hope this helps!