Update app.py

app.py

@@ -4,17 +4,19 @@ from pydantic import BaseModel
 from fastapi.responses import JSONResponse
 import requests
 import json
-
+import openai
+import time
 
 class Text(BaseModel):
     content: str = ""
 
 
 app = FastAPI()
-
+key = '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'
+openai.api_key = key
 headers = {
     'Content-Type': 'application/json',
-    'Authorization': 'Bearer ' + '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'
+    'Authorization': 'Bearer ' + key
 }
 
 
@@ -125,6 +127,36 @@ def chat_gpt_ep(content: Text = None):
     return JSONResponse(content=content)
 
 
+@app.post("/chatgptstream")
+def chat_gpt_stream_ep(content: Text = None):
+    start_time = time.time()
+    obj = json.loads(content.content)
+    response = openai.Completion.create(
+        model='gpt-3.5-turbo',
+        messages=obj['messages'],
+        stream=True,  # this time, we set stream=True
+    )
+    # create variables to collect the stream of chunks
+    collected_chunks = []
+    collected_messages = []
+    # iterate through the stream of events
+    for chunk in response:
+        chunk_time = time.time() - start_time  # calculate the time delay of the chunk
+        collected_chunks.append(chunk)  # save the event response
+        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
+
+    # 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("/embeddings")
 def embeddings_ep(content: Text = None):
     url = 'https://api.openai.com/v1/embeddings'