ServiceUnavailableError: The server is overloaded or not ready yet

API
1

Getting this error since last few days
ServiceUnavailableError: The server is overloaded or not ready yet.

I am not using a free service at all.

Code


def translate(text):
    completion = openai.ChatCompletion.create(
      model="gpt-3.5-turbo",
      messages=[
        {"role": "system", "content": "Translate it in urdu language font. Donot translate to roman urdu."},
        {"role": "user", "content": text}
      ]
    )
    
    return completion.choices[0].message.content

error

---------------------------------------------------------------------------
ServiceUnavailableError                   Traceback (most recent call last)
/tmp/ipykernel_133735/2259171116.py in <cell line: 2>()
      3     assistant_text = translate(row['assistant_text'])
      4     time.sleep(3)
----> 5     prompt_text = translate(row['prompt_text'])
      6     # Save the current processed output to a new CSV file
      7     current_df = pd.DataFrame({'message_tree_id': [row['message_tree_id']],

/tmp/ipykernel_133735/855140278.py in translate(text)
      1 def translate(text):
----> 2     completion = openai.ChatCompletion.create(
      3       model="gpt-3.5-turbo",
      4       messages=[
      5         {"role": "system", "content": "Translate it in urdu language font. Donot translate to roman urdu."},

~/venv/lib/python3.10/site-packages/openai/api_resources/chat_completion.py in create(cls, *args, **kwargs)
     23         while True:
     24             try:
---> 25                 return super().create(*args, **kwargs)
     26             except TryAgain as e:
     27                 if timeout is not None and time.time() > start + timeout:

~/venv/lib/python3.10/site-packages/openai/api_resources/abstract/engine_api_resource.py in create(cls, api_key, api_base, api_type, request_id, api_version, organization, **params)
    151         )
    152 
--> 153         response, _, api_key = requestor.request(
    154             "post",
    155             url,

~/venv/lib/python3.10/site-packages/openai/api_requestor.py in request(self, method, url, params, headers, files, stream, request_id, request_timeout)
    296             request_timeout=request_timeout,
    297         )
--> 298         resp, got_stream = self._interpret_response(result, stream)
    299         return resp, got_stream, self.api_key
    300 

~/venv/lib/python3.10/site-packages/openai/api_requestor.py in _interpret_response(self, result, stream)
    698         else:
    699             return (
--> 700                 self._interpret_response_line(
    701                     result.content.decode("utf-8"),
    702                     result.status_code,

~/venv/lib/python3.10/site-packages/openai/api_requestor.py in _interpret_response_line(self, rbody, rcode, rheaders, stream)
    741 
    742         if rcode == 503:
--> 743             raise error.ServiceUnavailableError(
    744                 "The server is overloaded or not ready yet.",
    745                 rbody,

ServiceUnavailableError: The server is overloaded or not ready yet.

i am calling this via for loop, no parallelism

2

Hi and welcome to the developer forum!

What endpoint are you calling? Which library are you using? Can you post a code snippet?

3

post edited , i am using official api for this task.

4

Thanks can you also post the exact error message you get.

5

I also have that symptom. The symptom started from 2-3 days ago.

I suggest you don’t think too much into it because it means exactly what it is. They don’t have available resources to serve you.

Some big hand may have entered the pool and making a large amount of calls, who knows?

6

I am also getting the same issue…

Retrying langchain.chat_models.openai.ChatOpenAI.completion_with_retry.<locals>._completion_with_retry in 4.0 seconds as it raised ServiceUnavailableError: The server is overloaded or not ready yet..
1 Like
7

I’m also facing the same issue with API calling. OpenAI is not working smoothly. What should I do now?