Update agent.py

agent.py

@@ -161,18 +161,29 @@ def build_graph(provider: str = "groq"):
         llm = ChatGroq(model="qwen-qwq-32b", temperature=0) # optional : qwen-qwq-32b gemma2-9b-it
     elif provider == "huggingface":
         # TODO: Add huggingface endpoint
-        # llm = ChatHuggingFace(
-        #     llm=HuggingFaceEndpoint(
-        #         repo_id="Meta-DeepLearning/llama-2-7b-chat-hf",
-        #         temperature=0
-        #     )
-        # )
-        llm = ChatHuggingFace(
-            llm=HuggingFaceEndpoint(
-                url="https://api-inference.huggingface.co/models/Meta-DeepLearning/llama-2-7b-chat-hf",
-                temperature=0,
-            ),
+        model_id = "Qwen/Qwen3-32B"  # You can change this to any model you want
+        
+        # Load tokenizer and model
+        tokenizer = AutoTokenizer.from_pretrained(model_id)
+        model = AutoModelForCausalLM.from_pretrained(
+            model_id, 
+            device_map="auto",  # Automatically determine device placement
+            torch_dtype="auto"   # Use appropriate precision for device
         )
+        
+        # Create text-generation pipeline
+        pipe = pipeline(
+            "text-generation",
+            model=model,
+            tokenizer=tokenizer,
+            max_length=2048,
+            temperature=0,
+            top_p=0.95,
+            repetition_penalty=1.15
+        )
+        
+        # Create LangChain HuggingFacePipeline object
+        llm = HuggingFacePipeline(pipeline=pipe)
     else:
         raise ValueError("Invalid provider. Choose 'google', 'groq' or 'huggingface'.")
     # Bind tools to LLM