Async client Azure Support with Streaming not working (using AsyncAzureOpenAI with stream=True)

[anuj203]

Confirm this is an issue with the Python library and not an underlying OpenAI API

• [X] This is an issue with the Python library

Describe the bug

import os import openai import asyncio from openai import AzureOpenAI, AsyncAzureOpenAI

import os import asyncio from openai import AsyncAzureOpenAI

azure_openai_client = AsyncAzureOpenAI( azure_endpoint = "", api_key="some-key",
api_version="2023-07-01-preview" )

async def get_response(message): response = await azure_openai_client.chat.completions.create( model = 'GPT35', temperature = 0.4, messages = [ {"role": "user", "content": message} ], stream=True )

print(response.model_dump_json(indent=2)) - > no response

# async for chunk in response: - **Not working**
if "choices" in chunk and len(chunk["choices"]) > 0:
  print(chunk.choices[0].message.content, end="") # chunk.choices[0].delta.content - this also not working

asyncio.run(get_response('What is chatgpt?'))

To Reproduce

import os import openai import asyncio from openai import AzureOpenAI, AsyncAzureOpenAI

import os import asyncio from openai import AsyncAzureOpenAI

azure_openai_client = AsyncAzureOpenAI( azure_endpoint = "", api_key="some-key",
api_version="2023-07-01-preview" )

async def get_response(message): response = await azure_openai_client.chat.completions.create( model = 'GPT35', temperature = 0.4, messages = [ {"role": "user", "content": message} ], stream=True )

print(response.model_dump_json(indent=2)) - > not response

# async for chunk in response: - Not working
if "choices" in chunk and len(chunk["choices"]) > 0:
  print(chunk.choices[0].message.content, end="") # chunk.choices[0].delta.content - this also not working

asyncio.run(get_response('What is chatgpt?'))

Code snippets

import os
import openai
import asyncio
from openai import AzureOpenAI, AsyncAzureOpenAI

import os
import asyncio
from openai import AsyncAzureOpenAI

azure_openai_client = AsyncAzureOpenAI(
  azure_endpoint = "", 
  api_key="some-key",  
  api_version="2023-07-01-preview"
)

async def get_response(message):
    response = await azure_openai_client.chat.completions.create(
        model = 'GPT35',
        temperature = 0.4,
        messages = [
            {"role": "user", "content": message}
        ],
        stream=True
    )
    #print(response.model_dump_json(indent=2)) - > not response

    # async for chunk in response: - Not working
    if "choices" in chunk and len(chunk["choices"]) > 0:
      print(chunk.choices[0].message.content, end="") # chunk.choices[0].delta.content - this also not working

asyncio.run(get_response('What is chatgpt?'))

OS

Windows 10 Enterprise

Python version

Python 3.8.10

Library version

1.3.9 or 1.6.0

[rattrayalex]

You say it's not working, but there's no stacktrace. What happens if you try this?

    async for chunk in response:
         print(chunk)

And does it work if you remove stream=True?

[anuj203]

it is working when we use model_dump_json instead of directly print(chunk) with stream=True

async for chunk in response:
   print(chunk .model_dump_json(indent=2))    

you can close the issue.

Thanks

[shrijayan]

---------------------------------------------------------------------------
RuntimeError                              Traceback (most recent call last)
Cell In[8], line 36
     32     async for chunk in response:
     33         print(chunk .model_dump_json(indent=2))    
---> 36 asyncio.run(get_response('What is chatgpt?'))

File /opt/homebrew/Cellar/python@3.10/3.10.13_2/Frameworks/Python.framework/Versions/3.10/lib/python3.10/asyncio/runners.py:33, in run(main, debug)
      9 """Execute the coroutine and return the result.
     10 
     11 This function runs the passed coroutine, taking care of
   (...)
     30     asyncio.run(main())
     31 """
     32 if events._get_running_loop() is not None:
---> 33     raise RuntimeError(
     34         "asyncio.run() cannot be called from a running event loop")
     36 if not coroutines.iscoroutine(main):
     37     raise ValueError("a coroutine was expected, got {!r}".format(main))

RuntimeError: asyncio.run() cannot be called from a running event loop