Bug: INFO:openai._base_client:Retrying request to /chat/completions in ... seconds

[ErfolgreichCharismatisch]

What happened?

I am using

import logging
logger = logging.getLogger(__name__)
logging.basicConfig(filename='mylog.log', encoding='utf-8', level=logging.INFO)
logger.info("Anfrage: "+str(System) + " "+str(Prompt)) #System and Prompt sent to the ai

and

def ki(system, user):
    client = OpenAI(
        base_url="http://localhost:8080/v1", # "http://<Your api-server IP>:port"
        api_key = "sk-no-key-required"
    )
    completion = client.chat.completions.create(
        model="LLaMA_CPP",
        messages=[
            {
                'role': 'system',
                'content': system,
            },
            {
                'role': 'user',
                'content': user,
            },
        ]
    )
    
    return completion.choices[0].message.content

And I get

INFO:openai._base_client:Retrying request to /chat/completions in 0.404439 seconds
INFO:openai._base_client:Retrying request to /chat/completions in 0.981867 seconds

to every request after a while even though at the beginning it works.

Version

llamafile v0.8.9

What operating system are you seeing the problem on?

Linux