Update app.py

app.py

@@ -17,9 +17,10 @@ import asyncio
 import urllib.parse
 
 # 設置重試次數和延遲
-MAX_RETRIES = 3
-RETRY_DELAY = 2  # 每次重試之間的延遲秒數
+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
 
 async def send_chat_message(LLM_URL, LLM_API, user_input):
     payload = {
@@ -29,49 +30,48 @@ async def send_chat_message(LLM_URL, LLM_API, user_input):
         "conversation_id": "",
         "user": USER_ID,
     }
-    print("Sending chat message payload:", payload)  # Debug information
-
-    for attempt in range(MAX_RETRIES):
-        async with aiohttp.ClientSession() as session:
-            try:
-                async with session.post(
-                    url=f"{LLM_URL}/chat-messages",
-                    headers={"Authorization": f"Bearer {LLM_API}"},
-                    json=payload,
-                    timeout=aiohttp.ClientTimeout(total=TIMEOUT_DURATION)  # 增加超時時間
-                ) as response:
-                    if response.status != 200:
-                        print(f"Error: {response.status}")
-                        return f"Error: {response.status}"
-
-                    full_response = []
-                    async for line in response.content.iter_chunked(1024):
-                        line = line.decode('utf-8').strip()
-                        if not line:
-                            continue
-                        if "data: " not in line:
-                            continue
-                        try:
-                            print("Received line:", line)  # Debug information
-                            data = json.loads(line.split("data: ")[1])
-                            if "answer" in data:
-                                decoded_answer = urllib.parse.unquote(data["answer"])
-                                full_response.append(decoded_answer)
-                        except (IndexError, json.JSONDecodeError) as e:
-                            print(f"Error parsing line: {line}, error: {e}")
-                            continue
-
-                    if full_response:
-                        return ''.join(full_response).strip()
-                    else:
-                        return "Error: No response found in the response"
-            except (asyncio.TimeoutError, aiohttp.ClientError) as e:
-                print(f"Attempt {attempt + 1} failed with error: {e}")
-                print(traceback.format_exc())  # 顯示詳細的錯誤堆疊
-                if attempt < MAX_RETRIES - 1:
-                    await asyncio.sleep(RETRY_DELAY)  # 延遲後重試
+    print("Sending chat message payload:", payload)
+
+    async with aiohttp.ClientSession() as session:
+        try:
+            async with session.post(
+                url=f"{LLM_URL}/chat-messages",
+                headers={"Authorization": f"Bearer {LLM_API}"},
+                json=payload,
+                timeout=aiohttp.ClientTimeout(total=TIMEOUT_DURATION)
+            ) as response:
+                if response.status != 200:
+                    print(f"Error: {response.status}")
+                    return f"Error: {response.status}"
+
+                full_response = []
+                
+                async for line in response.content.iter_chunked(2048):  # 增大分段大小
+                    line = line.decode('utf-8').strip()
+                    if not line:
+                        continue
+                    if "data: " not in line:
+                        continue
+                    try:
+                        print("Received line:", line)
+                        data = json.loads(line.split("data: ")[1])
+                        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
+                                break
+                    except (IndexError, json.JSONDecodeError) as e:
+                        print(f"Error parsing line: {line}, error: {e}")
+                        continue
+
+                if full_response:
+                    return ''.join(full_response).strip()
                 else:
-                    return f"Exception: {e}"
+                    return "Error: No response found in the response"
+        except Exception as e:
+            print("Exception occurred in send_chat_message:")
+            print(traceback.format_exc())
+            return f"Exception: {e}"
 
 async def handle_input(user_input):
     print(f"Handling input: {user_input}")