test

app.py

@@ -8,7 +8,7 @@ import asyncio
 
 # Function to start the ochat server
 @spaces.GPU
-async def start_ochat_server():
+def start_ochat_server():
     print(f"Is CUDA available: {torch.cuda.is_available()}")
     print(f"CUDA device: {torch.cuda.get_device_name(torch.cuda.current_device())}")
 
@@ -28,17 +28,30 @@ start_ochat_server()
 
 
 
+# Function to check if the server is up
+def is_server_up(url):
+    try:
+        response = requests.get(url)
+        return response.status_code == 200
+    except requests.RequestException:
+        return False
+
 # Function to send a message to the ochat server and get a response
 async def chat_with_ochat(message):
-    url = "http://localhost:18888/v1/chat/completions"
+    base_url = "http://localhost:18888"
+    chat_url = f"{base_url}/v1/chat/completions"
     headers = {"Content-Type": "application/json"}
     data = {
         "model": "openchat_3.5",
         "messages": [{"role": "user", "content": message}]
     }
 
+    # Check if server is up
+    if not is_server_up(base_url):
+        return "Error: oChat server is not running."
+
     try:
-        response = requests.post(url, json=data, headers=headers)
+        response = requests.post(chat_url, json=data, headers=headers)
         if response.status_code == 200:
             return response.json()['choices'][0]['message']['content']
         else: