Update multiagents.py

multiagents.py

@@ -58,52 +58,24 @@ dotenv.load_dotenv()
 
 # SETUP AND TEST
 
-
-
-# Rate limiting decorator
-def rate_limit(calls_per_minute=15):
-    """Rate limiting decorator that limits function calls per minute"""
-    def decorator(func):
-        call_times = []
-        
-        @wraps(func)
-        def wrapper(*args, **kwargs):
-            now = time.time()
-            # Remove calls older than 1 minute
-            call_times[:] = [t for t in call_times if now - t < 60]
-            
-            if len(call_times) >= calls_per_minute:
-                sleep_time = 60 - (now - call_times[0])
-                if sleep_time > 0:
-                    mylog("rate_limit", f"Rate limit reached. Sleeping for {sleep_time:.2f} seconds")
-                    time.sleep(sleep_time)
-                    # Clean up old calls again after sleeping
-                    now = time.time()
-                    call_times[:] = [t for t in call_times if now - t < 60]
-            
-            call_times.append(now)
-            return func(*args, **kwargs)
-        return wrapper
-    return decorator
-
-# Rate-limited model wrapper
+# Simple rate-limited model wrapper
 class RateLimitedModel:
-    def __init__(self, model, calls_per_minute=30):
+    def __init__(self, model, delay_seconds=1):
         self.model = model
-        self.calls_per_minute = calls_per_minute
-        self.call_times = []
+        self.delay_seconds = delay_seconds
     
     def __call__(self, messages, **kwargs):
-        return self._rate_limited_call(messages, **kwargs)
-    
-    @rate_limit(calls_per_minute=30)  # Adjust as needed
-    def _rate_limited_call(self, messages, **kwargs):
+        # Simple delay before each API call
+        time.sleep(self.delay_seconds)
         return self.model(messages, **kwargs)
     
     def __getattr__(self, name):
         # Delegate other attributes to the wrapped model
         return getattr(self.model, name)
 
+
+
+
 ###################
 
 grok_api_key = os.getenv("groq_api")
@@ -117,7 +89,7 @@ base_model = InferenceClientModel(
 )
 
 # Wrap with rate limiting
-My_Agent = RateLimitedModel(base_model, calls_per_minute=15)
+My_Agent = RateLimitedModel(base_model)
 
 def check_final_answer(final_answer, agent_memory)  -> bool:
     """