Update app.py

app.py

@@ -7,7 +7,7 @@ from typing import Dict, Any, List, TypedDict, Optional
 from langgraph.graph import Graph, StateGraph
 from langgraph.prebuilt import ToolNode
 from tools import simple_search
-from langchain_community.llms import HuggingFaceEndpoint
+from huggingface_hub import InferenceClient
 
 print("trial")
 # (Keep Constants as is)
@@ -30,11 +30,10 @@ class BasicAgent:
         if not HF_TOKEN:
             raise ValueError("HF_TOKEN environment variable not set. Please set your Hugging Face API token.")
         
-        # Initialize LLM
-        self.llm = HuggingFaceEndpoint(
-            # repo_id="Qwen/Qwen2.5-Coder-7B-Instruct",
-            repo_id="HuggingFaceH4/zephyr-7b-alpha",
-            huggingfacehub_api_token=HF_TOKEN
+        # Initialize LLM client
+        self.llm = InferenceClient(
+            model="Qwen/Qwen2.5-Coder-7B-Instruct",
+            token=HF_TOKEN
         )
         
         # Create the agent workflow
@@ -43,9 +42,16 @@ class BasicAgent:
         print("BasicAgent initialization complete.")
 
     def _call_llm_api(self, prompt: str) -> str:
-        """Call the Qwen model through the Hugging Face API using langchain."""
+        """Call the Qwen model through the Hugging Face API using InferenceClient."""
         try:
-            return self.llm(prompt)  # Using direct call syntax
+            response = self.llm.text_generation(
+                prompt,
+                max_new_tokens=200,
+                temperature=0.7,
+                top_p=0.95,
+                repetition_penalty=1.1
+            )
+            return response
         except Exception as e:
             print(f"Error calling LLM API: {e}")
             return f"Error getting response from LLM: {str(e)}"