Update agent.py

agent.py

@@ -18,6 +18,16 @@ from supabase.client import Client, create_client
 
 load_dotenv()
 
+from langchain_core.rate_limiters import InMemoryRateLimiter
+
+# Create a rate limiter
+rate_limiter = InMemoryRateLimiter(
+    requests_per_second=0.1,  # Once every 10 seconds
+    check_every_n_seconds=0.1,
+    max_bucket_size=10,
+)
+
+
 @tool
 def multiply(a: int, b: int) -> int:
     """Multiply two numbers.
@@ -156,17 +166,15 @@ def build_graph(provider: str = "groq"):
     """Build the graph"""
     # Load environment variables from .env file
     if provider == "google":
-        # Google Gemini
-        llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0)
+        llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0, rate_limiter=rate_limiter)
     elif provider == "groq":
-        # Groq https://console.groq.com/docs/models
-        llm = ChatGroq(model="qwen-qwq-32b", temperature=0) # optional : qwen-qwq-32b gemma2-9b-it
+        llm = ChatGroq(model="qwen-qwen3-32b", temperature=0, rate_limiter=rate_limiter)
     elif provider == "huggingface":
-        # TODO: Add huggingface endpoint
         llm = ChatHuggingFace(
             llm=HuggingFaceEndpoint(
                 url="https://api-inference.huggingface.co/models/Meta-DeepLearning/llama-2-7b-chat-hf",
                 temperature=0,
+                rate_limiter=rate_limiter,
             ),
         )
     else: