Consider implementing tenacity fallbacks as in OpenAI's example to avoid such failures (when sending multiple requests):
KeyError: "No AI generation: {'error': {'message': 'That model is currently overloaded with other requests. You can retry your request, or contact us through our help center at help.openai.com if the error persists. (Please include the request ID c7dddc8edaadb3d6ab49204671f84edf in your message.)', 'type': 'server_error', 'param': None, 'code': None}}"
Consider implementing
tenacity
fallbacks as in OpenAI's example to avoid such failures (when sending multiple requests):