[FIXED] Websocket how to receive two request chatgpt at the sametime

Issue

I have a websocket (in Django) to receive request from client (reactjs). The request calls chatgpt api to stream its response to client.

class GPTAPIConsumer(AsyncWebsocketConsumer):
    async def connect(self):
        await self.accept()

    async def receive(self, text_data):
        data = json.loads(text_data)
        print('Start', data['requestID'])
        asyncio.create_task(self.streamToClient(data['requestID']))

    async def streamToClient(self, requestID):
        completion = openai.ChatCompletion.create(...)
        content = ''
        for chunk in completion:
            if chunk['choices'][0].get('delta', {}).get('function_call'):
                chunkContent = chunk['choices'][0]['delta']['function_call']['arguments']
                if chunkContent is not None:
                    content += chunkContent
                    await self.send(text_data=json.dumps({'text': content}))
        print('End', requestID)

From client, I sent two messages with requestID 1 and 2. In server, the request 1 took about 10 seconds to finish so the log is:

Start 1
End 1
Start 2
End 2

What I want is:

Start 1
Start 2
End 1 or End 2 (depends which one ends first)

Please help me! Thank you!

Solution

I get it work by making the openai api call async:

completion = await openai.ChatCompletion.acreate(...)
content = ''
async for chunk in completion:

Answered By - Trong Lam Phan