Update app.py

app.py

@@ -11,10 +11,6 @@ LLM_API = os.environ.get("LLM_API")
 LLM_URL = os.environ.get("LLM_URL")
 USER_ID = "HuggingFace Space"  # Placeholder user ID
 
-import traceback
-import aiohttp
-import asyncio
-import urllib.parse
 
 # 設置重試次數和延遲
 MAX_RETRIES = 2
@@ -32,46 +28,51 @@ async def send_chat_message(LLM_URL, LLM_API, user_input):
     }
     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}")
+    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)
+                ) as response:
+                    if response.status != 200:
+                        print(f"Error: {response.status}")
                         continue
 
-                if full_response:
-                    return ''.join(full_response).strip()
-                else:
-                    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}"
+                    full_response = []
+                    
+                    async for line in response.content.iter_chunked(4096):  # 再次增大分段大小
+                        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 "Error: No response found in the response"
+            except asyncio.TimeoutError:
+                print(f"Attempt {attempt + 1} timed out. Retrying...")
+                continue
+            except Exception as e:
+                print("Exception occurred in send_chat_message:")
+                print(traceback.format_exc())
+                return f"Exception: {e}"
+    return "Error: Reached maximum retry attempts."
 
 async def handle_input(user_input):
     print(f"Handling input: {user_input}")
@@ -85,7 +86,7 @@ def run_sync(func, *args):
     result = loop.run_until_complete(func(*args))
     loop.close()
     return result
-
+    
 # 定義 Gradio 介面
 user_input = gr.Textbox(label='請輸入您想查詢的關鍵公司名稱')
 examples = [