Update app.py

app.py

@@ -1,12 +1,13 @@
 from fastapi import FastAPI
 from fastapi.responses import HTMLResponse
 from pydantic import BaseModel
-from fastapi.responses import JSONResponse
+from fastapi.responses import JSONResponse, StreamingResponse
 import requests
 import json
 import openai
 import time
 
+
 class Text(BaseModel):
     content: str = ""
 
@@ -127,8 +128,7 @@ def chat_gpt_ep(content: Text = None):
     return JSONResponse(content=content)
 
 
-@app.post("/chatgptstream")
-def chat_gpt_stream_ep(content: Text = None):
+async def chat_gpt_stream_fun(content: Text = None):
     start_time = time.time()
     obj = json.loads(content.content)
     response = openai.ChatCompletion.create(
@@ -146,15 +146,16 @@ def chat_gpt_stream_ep(content: Text = None):
         chunk_message = chunk['choices'][0]['delta']  # extract the message
         collected_messages.append(chunk_message)  # save the message
         print(f"Message received {chunk_time:.2f} seconds after request: {chunk_message}")  # print the delay and text
+        full_reply_content = ''.join([m.get('content', '') for m in collected_messages])
+        print(f"Full conversation received: {full_reply_content}")
+        content = {'content': full_reply_content}
+        print('content:', content)
+        yield full_reply_content
 
-    # print the time delay and text received
-    print(f"Full response received {chunk_time:.2f} seconds after request")
-    full_reply_content = ''.join([m.get('content', '') for m in collected_messages])
-    print(f"Full conversation received: {full_reply_content}")
 
-    content = {'content': full_reply_content}
-    print('content:', content)
-    return JSONResponse(content=content)
+@app.post("/chatgptstream")
+async def get_random_numbers(content: Text = None):
+    return StreamingResponse(chat_gpt_stream_fun(content))
 
 
 @app.post("/embeddings")