Hi,
I am trying to run this function:
def run_gpt4turbo(full_prompt):
"""
API interaction. Returns GPT's completion.
"""
with open(f"{MAIN_DIR}/apikey_gpt4turbo.txt", "r") as f:
api_key = f.read().strip()
client = AzureOpenAI(
api_key=api_key,
api_version="2023-09-01-preview",
azure_endpoint="https://<resourcename>.openai.azure.com",
)
chat_completion = client.chat.completions.create(
messages=[
{"role": "system", "content": "You are an AI assistant that helps with extracting data."},
{"role":"user","content":full_prompt},
],
model='gpt4-turbo',
)
return chat_completion.choices[0].message.content
with a relatively big full_prompt (70.500 tokens), however still within the token limit of gpt4-turbo (120.000 tokens). When running it, OpenAI seems to lose connection before finishing the processing of the prompt.
This is the error message received:
Traceback (most recent call last):
File "C:\python_venv\venv\Lib\site-packages\httpx\_transports\default.py", line 67, in map_httpcore_exceptions
yield
File "C:\python_venv\venv\Lib\site-packages\httpx\_transports\default.py", line 231, in handle_request
resp = self._pool.handle_request(req)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\httpcore\_sync\connection_pool.py", line 268, in handle_request
raise exc
File "C:\python_venv\venv\Lib\site-packages\httpcore\_sync\connection_pool.py", line 251, in handle_request
response = connection.handle_request(request)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\httpcore\_sync\connection.py", line 103, in handle_request
return self._connection.handle_request(request)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\httpcore\_sync\http11.py", line 133, in handle_request
raise exc
File "C:\python_venv\venv\Lib\site-packages\httpcore\_sync\http11.py", line 111, in handle_request
) = self._receive_response_headers(**kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\httpcore\_sync\http11.py", line 176, in _receive_response_headers
event = self._receive_event(timeout=timeout)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\httpcore\_sync\http11.py", line 226, in _receive_event
raise RemoteProtocolError(msg)
httpcore.RemoteProtocolError: Server disconnected without sending a response.
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "C:\python_venv\venv\Lib\site-packages\openai\_base_client.py", line 897, in _request
response = self._client.send(
^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\httpx\_client.py", line 915, in send
response = self._send_handling_auth(
^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\httpx\_client.py", line 943, in _send_handling_auth
response = self._send_handling_redirects(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\httpx\_client.py", line 980, in _send_handling_redirects
response = self._send_single_request(request)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\httpx\_client.py", line 1016, in _send_single_request
response = transport.handle_request(request)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\httpx\_transports\default.py", line 230, in handle_request
with map_httpcore_exceptions():
File "C:\Users\SofieKnøsgaard(SKNQ)\AppData\Local\Programs\Python\Python311\Lib\contextlib.py", line 158, in __exit__
self.gen.throw(typ, value, traceback)
File "C:\python_venv\venv\Lib\site-packages\httpx\_transports\default.py", line 84, in map_httpcore_exceptions
raise mapped_exc(message) from exc
httpx.RemoteProtocolError: Server disconnected without sending a response.
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "C:\python_venv\venv\Lib\site-packages\httpx\_transports\default.py", line 67, in map_httpcore_exceptions
yield
File "C:\python_venv\venv\Lib\site-packages\httpx\_transports\default.py", line 231, in handle_request
resp = self._pool.handle_request(req)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\httpcore\_sync\connection_pool.py", line 268, in handle_request
raise exc
File "C:\python_venv\venv\Lib\site-packages\httpcore\_sync\connection_pool.py", line 251, in handle_request
response = connection.handle_request(request)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\httpcore\_sync\connection.py", line 103, in handle_request
return self._connection.handle_request(request)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\httpcore\_sync\http11.py", line 133, in handle_request
raise exc
File "C:\python_venv\venv\Lib\site-packages\httpcore\_sync\http11.py", line 111, in handle_request
) = self._receive_response_headers(**kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\httpcore\_sync\http11.py", line 176, in _receive_response_headers
event = self._receive_event(timeout=timeout)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\httpcore\_sync\http11.py", line 226, in _receive_event
raise RemoteProtocolError(msg)
httpcore.RemoteProtocolError: Server disconnected without sending a response.
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "C:\python_venv\venv\Lib\site-packages\openai\_base_client.py", line 897, in _request
response = self._client.send(
^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\httpx\_client.py", line 915, in send
response = self._send_handling_auth(
^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\httpx\_client.py", line 943, in _send_handling_auth
response = self._send_handling_redirects(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\httpx\_client.py", line 980, in _send_handling_redirects
response = self._send_single_request(request)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\httpx\_client.py", line 1016, in _send_single_request
response = transport.handle_request(request)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\httpx\_transports\default.py", line 230, in handle_request
with map_httpcore_exceptions():
File "C:\Users\SofieKnøsgaard(SKNQ)\AppData\Local\Programs\Python\Python311\Lib\contextlib.py", line 158, in __exit__
self.gen.throw(typ, value, traceback)
File "C:\python_venv\venv\Lib\site-packages\httpx\_transports\default.py", line 84, in map_httpcore_exceptions
raise mapped_exc(message) from exc
httpx.RemoteProtocolError: Server disconnected without sending a response.
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "C:\python_venv\venv\Lib\site-packages\httpx\_transports\default.py", line 67, in map_httpcore_exceptions
yield
File "C:\python_venv\venv\Lib\site-packages\httpx\_transports\default.py", line 231, in handle_request
resp = self._pool.handle_request(req)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\httpcore\_sync\connection_pool.py", line 268, in handle_request
raise exc
File "C:\python_venv\venv\Lib\site-packages\httpcore\_sync\connection_pool.py", line 251, in handle_request
response = connection.handle_request(request)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\httpcore\_sync\connection.py", line 103, in handle_request
return self._connection.handle_request(request)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\httpcore\_sync\http11.py", line 133, in handle_request
raise exc
File "C:\python_venv\venv\Lib\site-packages\httpcore\_sync\http11.py", line 111, in handle_request
) = self._receive_response_headers(**kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\httpcore\_sync\http11.py", line 176, in _receive_response_headers
event = self._receive_event(timeout=timeout)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\httpcore\_sync\http11.py", line 226, in _receive_event
raise RemoteProtocolError(msg)
httpcore.RemoteProtocolError: Server disconnected without sending a response.
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "C:\python_venv\venv\Lib\site-packages\openai\_base_client.py", line 897, in _request
response = self._client.send(
^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\httpx\_client.py", line 915, in send
response = self._send_handling_auth(
^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\httpx\_client.py", line 943, in _send_handling_auth
response = self._send_handling_redirects(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\httpx\_client.py", line 980, in _send_handling_redirects
response = self._send_single_request(request)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\httpx\_client.py", line 1016, in _send_single_request
response = transport.handle_request(request)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\httpx\_transports\default.py", line 230, in handle_request
with map_httpcore_exceptions():
File "C:\Users\SofieKnøsgaard(SKNQ)\AppData\Local\Programs\Python\Python311\Lib\contextlib.py", line 158, in __exit__
self.gen.throw(typ, value, traceback)
File "C:\python_venv\venv\Lib\site-packages\httpx\_transports\default.py", line 84, in map_httpcore_exceptions
raise mapped_exc(message) from exc
httpx.RemoteProtocolError: Server disconnected without sending a response.
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "C:\Users\SofieKnøsgaard\Documents\GIT_repos\genai\PythonScripts\prompt_generate.py", line 162, in <module>
completion = run_gpt4turbo(full_prompt)
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\SofieKnøsgaard\Documents\GIT_repos\genai\PythonScripts\openai_functions.py", line 28, in run_gpt4turbo
chat_completion = client.chat.completions.create(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\openai\_utils\_utils.py", line 271, in wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\openai\resources\chat\completions.py", line 648, in create
return self._post(
^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\openai\_base_client.py", line 1179, in post
return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\openai\_base_client.py", line 868, in request
return self._request(
^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\openai\_base_client.py", line 921, in _request
return self._retry_request(
^^^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\openai\_base_client.py", line 992, in _retry_request
return self._request(
^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\openai\_base_client.py", line 921, in _request
return self._retry_request(
^^^^^^^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\openai\_base_client.py", line 992, in _retry_request
return self._request(
^^^^^^^^^^^^^^
File "C:\python_venv\venv\Lib\site-packages\openai\_base_client.py", line 931, in _request
raise APIConnectionError(request=request) from err
openai.APIConnectionError: Connection error.
When running the same function with a slightly smaller full_prompt (44.000 tokens) it works fine and I get the expected response.
Can anyone help me resolve this issue.
Thanks in advance.