Update app.py

app.py

@@ -3,6 +3,7 @@ from fastapi.responses import HTMLResponse
 from transformers import AutoTokenizer
 from pydantic import BaseModel
 from llama_cpp import Llama
+import time
 
 class Message(BaseModel):
     content: str
@@ -193,6 +194,7 @@ messages = []
 
 @app.post("/chat")
 def chat(req: Message):
+    a = time.time()
     messages.append({"role": "user", "content": req.content})
     text = tokenizer.apply_chat_template(
         messages, tokenize=False, add_generation_prompt=True
@@ -200,8 +202,8 @@ def chat(req: Message):
     output = llm(text,max_tokens=req.token,echo=False)
     response = output['choices'][0]['text']
     messages.append({"role": "assistant", "content": response})
-    
-    return {"response": response_text}
+    b = time.time()
+    return {"response": response, "time": b-a}
 
 
 @app.post("/setSystemPrompt")