Update app.py

app.py

@@ -12,10 +12,10 @@ from functools import lru_cache
 # -------------------- Configuration --------------------
 logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
 
-# -------------------- External Model Call (with Caching) --------------------
+# -------------------- External Model Call (with Caching and Retry) --------------------
 @lru_cache(maxsize=128)  # Cache up to 128 responses
-async def call_model(prompt: str, model: str = "gpt-4o", api_key: str = None) -> str:
-    """Sends a prompt to the OpenAI API endpoint, with caching."""
+async def call_model(prompt: str, model: str = "gpt-4o", api_key: str = None, max_retries: int = 3) -> str:
+    """Sends a prompt to the OpenAI API endpoint, with caching and retries."""
     if api_key is None:
         api_key = os.getenv("OPENAI_API_KEY")
         if api_key is None:
@@ -29,11 +29,30 @@ async def call_model(prompt: str, model: str = "gpt-4o", api_key: str = None) ->
         "model": model,
         "messages": [{"role": "user", "content": prompt}],
     }
-    async with httpx.AsyncClient(timeout=httpx.Timeout(300.0)) as client:
-        response = await client.post(url, headers=headers, json=payload)
-        response.raise_for_status()
-        response_json = response.json()
-        return response_json["choices"][0]["message"]["content"]
+
+    for attempt in range(max_retries):
+        try:
+            async with httpx.AsyncClient(timeout=httpx.Timeout(300.0)) as client:
+                response = await client.post(url, headers=headers, json=payload)
+                response.raise_for_status()
+                response_json = response.json()
+                return response_json["choices"][0]["message"]["content"]
+        except httpx.HTTPStatusError as e:
+            logging.error(f"HTTP error (attempt {attempt + 1}/{max_retries}): {e}")
+            if e.response.status_code in (502, 503, 504):  # Retry on 502, 503, 504
+                await asyncio.sleep(2 ** attempt)  # Exponential backoff
+                continue
+            else:
+                raise  # Re-raise for other HTTP errors
+        except httpx.RequestError as e:
+            logging.error(f"Request error (attempt {attempt + 1}/{max_retries}): {e}")
+            await asyncio.sleep(2 ** attempt)
+            continue
+        except Exception as e:
+            logging.error(f"An unexpected error occurred (attempt {attempt+1}/{max_retries}): {e}")
+            raise
+    raise Exception(f"Failed to get response from OpenAI API after {max_retries} attempts.")
+
 
 # -------------------- Shared Context --------------------
 class Context:
@@ -393,4 +412,4 @@ dummy_iface = gr.Interface(lambda x:x, "textbox", "textbox")
 
 if __name__ == "__main__":
     demo = gr.TabbedInterface([iface, dummy_iface], ["Chatbot", "Dummy"])
-    demo.launch()
+    demo.launch(share=True)