update llm

agent.py

@@ -743,6 +743,7 @@ def build_graph(provider: str = "groq"):
         # TODO: Add huggingface endpoint
         llm = ChatHuggingFace(
             llm=HuggingFaceEndpoint(
+                url="https://api-inference.huggingface.co/models/TinyLlama/TinyLlama-1.1B-Chat-v1.0",
                 repo_id="TinyLlama/TinyLlama-1.1B-Chat-v1.0",
                 task="text-generation",  # for chat‐style use “text-generation”
                 max_new_tokens=1024,