timeout

app.py

@@ -116,7 +116,7 @@ def generate(
 
     try:
         # Make the request to the Llama.cpp server
-        with requests.post(f"{LLAMA_CPP_SERVER}/completion", json=payload, stream=True, timeout=60) as response:
+        with requests.post(f"{LLAMA_CPP_SERVER}/completion", json=payload, stream=True, timeout=(30, 300)) as response:
             response.raise_for_status()  # Raise HTTPError for bad responses (4xx or 5xx)
 
             # Stream the response from the server