Update app.py

app.py

@@ -897,11 +897,11 @@ REMEMBER: One tool per turn. No reasoning without tools. Exact answer format.
         print("Initializing Groq LLM...")
         try:
         #. Initialize the LLM ()
-        self.llm_with_tools = HuggingFaceEndpoint(
-            repo_id="HuggingFaceH4/zephyr-7b-beta", # Changed model
-            huggingfacehub_api_token=HUGGINGFACEHUB_API_TOKEN,
-            max_new_tokens=2048, # Increased token limit for potentially longer reasoning/tool use
-            temperature=0.01, # Keep temperature low for factual tasks     
+            self.llm_with_tools = HuggingFaceEndpoint(
+                repo_id="HuggingFaceH4/zephyr-7b-beta", # Changed model
+                huggingfacehub_api_token=HUGGINGFACEHUB_API_TOKEN,
+                max_new_tokens=2048, # Increased token limit for potentially longer reasoning/tool use
+                temperature=0.01, # Keep temperature low for factual tasks     
             # Use tool_choice="any" to FORCE tool usage
            # self.llm_with_tools = ChatGroq(
             #    temperature=0,
@@ -909,8 +909,8 @@ REMEMBER: One tool per turn. No reasoning without tools. Exact answer format.
               #  model_name="llama-3.3-70b-versatile",
                # max_tokens=4096,
                 #timeout=60
-            ).bind_tools(self.tools, tool_choice="auto")  # FORCE tool calls
-            print("✅ LLM initialized with FORCED tool usage.")
+                ).bind_tools(self.tools, tool_choice="auto")  # FORCE tool calls
+                print("✅ LLM initialized with FORCED tool usage.")
 
         except Exception as e:
             print(f"❌ Error initializing HuggingFace: {e}")