Update app.py

app.py

@@ -1,13 +1,16 @@
+import os
 import gradio as gr
 import aiohttp
 import asyncio
-import json, os
+import json
+from functools import lru_cache
 
 LLM_API = os.environ.get("LLM_API")
 LLM_URL = os.environ.get("LLM_URL")
 
 USER_ID = "HuggingFace Space"  # Placeholder user ID
 
+@lru_cache(maxsize=32)
 async def send_chat_message(LLM_URL, LLM_API, user_input):
     payload = {
         "inputs": {},
@@ -19,48 +22,53 @@ async def send_chat_message(LLM_URL, LLM_API, user_input):
     print("Sending chat message payload:", payload)  # Debug information
 
     async with aiohttp.ClientSession() as session:
-        async with session.post(
-            url=f"{LLM_URL}/chat-messages",
-            headers={"Authorization": f"Bearer {LLM_API}"},
-            json=payload,
-            timeout=aiohttp.ClientTimeout(total=60)
-        ) as response:
-            if response.status != 200:
-                print(f"Error: {response.status}")
-                return f"Error: {response.status}"
+        try:
+            async with session.post(
+                url=f"{LLM_URL}/chat-messages",
+                headers={"Authorization": f"Bearer {LLM_API}"},
+                json=payload,
+                timeout=aiohttp.ClientTimeout(total=60)
+            ) as response:
+                if response.status != 200:
+                    print(f"Error: {response.status}")
+                    return f"Error: {response.status}"
 
-            # Handle the stream of events
-            full_response = []
-            async for line in response.content:
-                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:
-                        full_response.append(data["answer"])
-                except (IndexError, json.JSONDecodeError) as e:
-                    print(f"Error parsing line: {line}, error: {e}")  # Debug information
-                    continue
+                full_response = []
+                async for line in response.content:
+                    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:
+                            full_response.append(data["answer"])
+                    except (IndexError, json.JSONDecodeError) as e:
+                        print(f"Error parsing line: {line}, error: {e}")  # Debug information
+                        continue
 
-            if full_response:
-                return ''.join(full_response).strip()
-            else:
-                return "Error: No thought found in the response"
+                if full_response:
+                    return ''.join(full_response).strip()
+                else:
+                    return "Error: No response found in the response"
+        except Exception as e:
+            print(f"Exception: {e}")
+            return f"Exception: {e}"
 
 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
     return chat_response
 
 def run_sync(user_input):
+    print(f"Running sync with input: {user_input}")
     return asyncio.run(handle_input(user_input))
 
-# Define Gradio interface
-user_input = gr.Textbox(label='歡迎問我加密貨幣交易所的各種疑難雜症')
+# 定義 Gradio 界面
+user_input = gr.Textbox(label='歡迎問我加密貨幣交易所的各種疑難雜症', placeholder='在此輸入問題...')
 examples = [
     ["MAX 帳號刪除關戶後，又重新註冊 MAX 後要怎辦？"],
     ["手機APP怎麼操作掛單交易？"],
@@ -77,12 +85,20 @@ with gr.Blocks() as iface:
     gr.HTML(TITLE)
     gr.HTML(SUBTITLE)
     gr.HTML(LINKS)
-    gr.Interface(
-        fn=run_sync,
-        inputs=user_input,
-        outputs="text",
-        examples=examples,
-        allow_flagging="never"
-    )
+    with gr.Row():
+        chatbot = gr.Chatbot()
+    with gr.Row():
+        user_input = gr.Textbox(label='輸入您的問題', placeholder="在此輸入問題...")
+        submit_button = gr.Button("送出")
+    gr.Examples(examples=examples, inputs=user_input)
+    with gr.Row():
+        feedback_output = gr.Textbox(label='反饋結果', interactive=False)
+
+    def chat(user_input, history):
+        response = run_sync(user_input)
+        history.append((user_input, response))
+        return history, history
+
+    submit_button.click(fn=chat, inputs=[user_input, chatbot], outputs=[chatbot, chatbot])
 
 iface.launch()