Update app.py

app.py

@@ -1,5 +1,6 @@
 import gradio as gr
-import requests
+import aiohttp
+import asyncio
 import json, os
 
 LLM_API = os.environ.get("LLM_API")
@@ -7,7 +8,7 @@ LLM_URL = os.environ.get("LLM_URL")
 
 USER_ID = "HuggingFace Space"  # Placeholder user ID
 
-def send_chat_message(LLM_URL, LLM_API, user_input):
+async def send_chat_message(LLM_URL, LLM_API, user_input):
     payload = {
         "inputs": {},
         "query": user_input,
@@ -16,42 +17,45 @@ def send_chat_message(LLM_URL, LLM_API, user_input):
         "user": USER_ID,
     }
     print("Sending chat message payload:", payload)  # Debug information
-    response = requests.post(
-        url=f"{LLM_URL}/chat-messages",
-        headers={"Authorization": f"Bearer {LLM_API}"},
-        json=payload,
-        stream=True  # Enable streaming
-    )
-    if response.status_code != 200:
-        print(f"Error: {response.status_code}")
-        return f"Error: {response.status_code}"
 
-    # Handle the stream of events
-    full_response = []
-    try:
-        for line in response.iter_lines(decode_unicode=True):
-            if line:
-                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
-    except json.JSONDecodeError:
-        return "Error: Invalid JSON response"
-    
-    if full_response:
-        return ''.join(full_response).strip()
-    else:
-        return "Error: No thought found in the response"
+    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}"
+
+            # Handle the stream of events
+            full_response = []
+            async for line in response.content:
+                line = line.decode('utf-8')
+                if line:
+                    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
 
-def handle_input(user_input):
-    chat_response = send_chat_message(LLM_URL, LLM_API, user_input)
+            if full_response:
+                return ''.join(full_response).strip()
+            else:
+                return "Error: No thought found in the response"
+
+async def handle_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):
+    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')
 examples = [
@@ -71,7 +75,7 @@ with gr.Blocks() as iface:
     gr.HTML(SUBTITLE)
     gr.HTML(LINKS)
     gr.Interface(
-        fn=handle_input,
+        fn=run_sync,
         inputs=user_input,
         outputs="text",
         examples=examples,