request and response

llm.py

@@ -11,18 +11,18 @@ llm = Llama.from_pretrained(
 app = FastAPI()
 
 class ChatRequest(BaseModel):
-    message: str
+    messages: list[dict]
 
 @app.post("/chat")
 async def chat_completion(request: ChatRequest):
+    # print(request.messages)
+    # test = [{"role": "user", "content": "dsfa"}]
+    # print(test)
+    # return "haha"
     try:
         response = llm.create_chat_completion(
-            messages=[
-                {"role": "user", "content": request.message}
-            ]
+            messages = request.messages
         )
-        return {
-            "response": response['choices'][0]['message']['content']
-        }
+        return response
     except Exception as e:
         raise HTTPException(status_code=500, detail=str(e))