New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Azure OpenAI - Functions argument error #91
Comments
I got the same error with AZURE_OPENAI_VERSION set to "2023-05-15".
I tried setting the env variable to "2023-07-01-preview" and now things seem to be working. |
That did the trick!!!! Thanks for the quick response! |
Should be fixed by #140 |
Hi, i get the same error about the argument functions even by setting the api version to "2023-07-01-preview". Do you know if this is still an issue? I just setted the api version with the AZURE_OPENAI_VERSION enviroment variable. Should I do something on the Azure AI portal to enable function calling or is enough to call the right api version via the endpoint ? |
Same issue for me |
@Raffix-14 You have a typo in your API version. The year should be 2023 not 2017. It should look like this "2023-07-01-preview" |
Nono. I mean there is the typo ye but only here in the comment.. in the
code is right I just wrote it on a hurry. Sorry guys. But still the problem
is there.. tomorrow morning I will check again and this time make sure to
report everything correctly but I am pretty sure it doesn’t work.. maybe
something endpoint side
Il giorno mer 15 nov 2023 alle 19:43 Avery Forman ***@***.***>
ha scritto:
… @Raffix-14 <https://github.com/Raffix-14> You have a typo in your API
version. The year should be 2023 not 2017. It should look like this
"2023-07-01-preview"
—
Reply to this email directly, view it on GitHub
<#91 (comment)>, or
unsubscribe
<https://github.com/notifications/unsubscribe-auth/AH2IGNYA27EWQ5TDNCK2YPDYEUELLAVCNFSM6AAAAAA6LAN7AKVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTQMJTGA3TCNBQGI>
.
You are receiving this because you were mentioned.Message ID:
***@***.***>
|
I confirm, in the code the version is the right one and i also edited the typo in the original comment. Moreover i see that also other people have the same issue (@JeremyTChase ) so probably there is something more. Only thing I can think of at this point is something in the deployment settings azure side |
Some more context to my issue; |
The variables for Azure OpenAI have been set.
I am now getting the below error:
💭 Bootup sequence complete. Persona activated. Testing messaging functionality.
Hit enter to begin (will request first MemGPT message)
[A[K
Traceback (most recent call last):
File "C:\Users\user\Documents\Projects\MemGPT\main.py", line 339, in
app.run(run)
File "C:\Users\user\AppData\Local\miniconda3\envs\memgpt\lib\site-packages\absl\app.py", line 308, in run
_run_main(main, args)
File "C:\Users\user\AppData\Local\miniconda3\envs\memgpt\lib\site-packages\absl\app.py", line 254, in _run_main
sys.exit(main(argv))
File "C:\Users\user\Documents\Projects\MemGPT\main.py", line 337, in run
loop.run_until_complete(main())
File "C:\Users\user\AppData\Local\miniconda3\envs\memgpt\lib\asyncio\base_events.py", line 649, in run_until_complete
return future.result()
File "C:\Users\user\Documents\Projects\MemGPT\main.py", line 315, in main
new_messages, heartbeat_request, function_failed, token_warning = await memgpt_agent.step(user_message, first_message=False, skip_verify=FLAGS.no_verify)
File "C:\Users\user\Documents\Projects\MemGPT\memgpt\agent.py", line 545, in step
raise e
File "C:\Users\user\Documents\Projects\MemGPT\memgpt\agent.py", line 483, in step
response = await get_ai_reply_async(model=self.model, message_sequence=input_message_sequence, functions=self.functions)
File "C:\Users\user\Documents\Projects\MemGPT\memgpt\agent.py", line 115, in get_ai_reply_async
raise e
File "C:\Users\user\Documents\Projects\MemGPT\memgpt\agent.py", line 96, in get_ai_reply_async
response = await acreate(
File "C:\Users\user\Documents\Projects\MemGPT\memgpt\openai_tools.py", line 98, in wrapper
raise e
File "C:\Users\user\Documents\Projects\MemGPT\memgpt\openai_tools.py", line 76, in wrapper
return await func(*args, **kwargs)
File "C:\Users\user\Documents\Projects\MemGPT\memgpt\openai_tools.py", line 108, in acompletions_with_backoff
return await openai.ChatCompletion.acreate(**kwargs)
File "C:\Users\user\AppData\Local\miniconda3\envs\memgpt\lib\site-packages\openai\api_resources\chat_completion.py", line 45, in acreate
return await super().acreate(*args, **kwargs)
File "C:\Users\user\AppData\Local\miniconda3\envs\memgpt\lib\site-packages\openai\api_resources\abstract\engine_api_resource.py", line 217, in acreate
response, _, api_key = await requestor.arequest(
File "C:\Users\user\AppData\Local\miniconda3\envs\memgpt\lib\site-packages\openai\api_requestor.py", line 314, in arequest
resp, got_stream = await self._interpret_async_response(result, stream)
File "C:\Users\user\AppData\Local\miniconda3\envs\memgpt\lib\site-packages\openai\api_requestor.py", line 650, in _interpret_async_response
self._interpret_response_line(
File "C:\Users\user\AppData\Local\miniconda3\envs\memgpt\lib\site-packages\openai\api_requestor.py", line 687, in _interpret_response_line
raise self.handle_error_response(
openai.error.InvalidRequestError: Unrecognized request argument supplied: functions
The text was updated successfully, but these errors were encountered: