Update app.py

app.py

@@ -1,5 +1,6 @@
 import openai
 from fastapi import FastAPI, HTTPException
+from fastapi.responses import StreamingResponse
 from fastapi.middleware.cors import CORSMiddleware
 from pydantic import BaseModel
 from fastapi import FastAPI, HTTPException, Depends, Request, Response
@@ -52,12 +53,24 @@ class RefToken(BaseModel):
     expiry_date: str
     ref_key: str
 
+def get_openai_generator(prompt: str):
+    openai_stream = openai.ChatCompletion.create(
+        model="gpt-3.5-turbo",
+        messages=[{"role": "user", "content": prompt}],
+        temperature=0.0,
+        stream=True,
+    )
+    for event in openai_stream:
+        if "content" in event["choices"][0].delta:
+            current_response = event["choices"][0].delta.content
+            yield "data: " + current_response + "\n\n"
+
 @app.get("/")
 async def base_url():
     try:
         return {
-            "Please Check the documentation here": "https://huggingface.co/spaces/Subhraj07/chatapi/blob/main/README.md",
-            "Swagger UI" : "https://subhraj07-chatapi.hf.space/docs"
+            "Please Check the documentation here": "https://huggingface.co/spaces/subhrajit-katonic/stream-chatapi/blob/main/README.md",
+            "Swagger UI" : "https://subhrajit-katonic-stream-chatapi.hf.space/docs"
             }
     except Exception as e:
         raise HTTPException(status_code=500, detail="An error occurred while processing the request." + str(e))
@@ -86,35 +99,6 @@ async def chat(chat_input: ChatInput, token: str = Depends(verify_token)):
     prompt = f"User: {chat_input.message}\nAI:"
     model_name = chat_input.model_name
     try:
-        if model_name == "text-davinci-002":
-            response = openai.Completion.create(
-                engine="text-davinci-002",
-                prompt=prompt,
-                max_tokens=50,
-                n=1,
-                stop=None,
-                temperature=0.7,
-            )
-            message = response.choices[0].text.strip()
-            usages = response["usage"]
-        
-        if model_name == "gpt-3.5-turbo":
-            response = openai.ChatCompletion.create(
-            model="gpt-3.5-turbo",   
-            messages=[         
-                {"role": "system", "content": prompt}   
-            ])
-
-            message = response.choices[0]["message"]["content"]
-            usages = response["usage"]
-
-        if model_name == "":
-            message = "Plase select the model"
-            usages = ""
-
-        return {
-            "message": message,
-            "usages" : usages
-            }
+        return StreamingResponse(get_openai_generator(prompt), media_type='text/event-stream')
     except Exception as e:
         raise HTTPException(status_code=500, detail="An error occurred while processing the request." + str(e))