Update app.py

app.py

@@ -4,19 +4,17 @@ import aiohttp
 import asyncio
 import json
 import urllib.parse
-import traceback  # 新增此行以便捕捉完整的異常堆疊
-
+import traceback
 
 LLM_API = os.environ.get("LLM_API")
 LLM_URL = os.environ.get("LLM_URL")
-USER_ID = "HuggingFace Space"  # Placeholder user ID
-
+USER_ID = "HuggingFace Space"
 
 # 設置重試次數和延遲
-MAX_RETRIES = 2
-RETRY_DELAY = 1  # 每次重試之間的延遲秒數
-TIMEOUT_DURATION = 120  # 超時時間設定為 120 秒
-MAX_RESPONSES = 10  # 設置最大接收數量，避免無限等待
+MAX_RETRIES = 3
+RETRY_DELAY = 2
+TIMEOUT_DURATION = 180  # 超時時間設定為 180 秒
+MAX_RESPONSES = 15
 
 async def send_chat_message(LLM_URL, LLM_API, user_input):
     payload = {
@@ -42,12 +40,9 @@ async def send_chat_message(LLM_URL, LLM_API, user_input):
                         continue
 
                     full_response = []
-                    
-                    async for line in response.content.iter_chunked(4096):  # 再次增大分段大小
+                    async for line in response.content.iter_chunked(2048):
                         line = line.decode('utf-8').strip()
-                        if not line:
-                            continue
-                        if "data: " not in line:
+                        if not line or "data: " not in line:
                             continue
                         try:
                             print("Received line:", line)
@@ -55,7 +50,7 @@ async def send_chat_message(LLM_URL, LLM_API, user_input):
                             if "answer" in data:
                                 decoded_answer = urllib.parse.unquote(data["answer"])
                                 full_response.append(decoded_answer)
-                                if len(full_response) >= MAX_RESPONSES:  # 接收上限，避免無限等待
+                                if len(full_response) >= MAX_RESPONSES:
                                     break
                         except (IndexError, json.JSONDecodeError) as e:
                             print(f"Error parsing line: {line}, error: {e}")
@@ -67,6 +62,7 @@ async def send_chat_message(LLM_URL, LLM_API, user_input):
                         return "Error: No response found in the response"
             except asyncio.TimeoutError:
                 print(f"Attempt {attempt + 1} timed out. Retrying...")
+                await asyncio.sleep(RETRY_DELAY)
                 continue
             except Exception as e:
                 print("Exception occurred in send_chat_message:")
@@ -77,7 +73,7 @@ async def send_chat_message(LLM_URL, LLM_API, user_input):
 async def handle_input(user_input):
     print(f"Handling input: {user_input}")
     chat_response = await send_chat_message(LLM_URL, LLM_API, user_input)
-    print("Chat response:", chat_response)  # Debug information
+    print("Chat response:", chat_response)
     return chat_response
 
 def run_sync(func, *args):