Upload app.py with huggingface_hub

app.py

@@ -624,25 +624,24 @@ class NutritionBot:
       Initialize the NutritionBot class, setting up memory, the LLM client, tools, and the agent executor.
       """
       # Define tools available to the chatbot, such as web search
-        tools = [agentic_rag]
+      tools = [agentic_rag]
+      # Define the system prompt to set the behavior of the chatbot
+      system_prompt = """You are a helpful nutrition assistant. 
+      Answer user questions about nutrition disorders accurately, clearly, and respectfully using available information."""
 
-        # Define the system prompt to set the behavior of the chatbot
-        system_prompt = """You are a helpful nutrition assistant. 
-        Answer user questions about nutrition disorders accurately, clearly, and respectfully using available information."""
-
-        # Build the prompt template for the agent
-        prompt = ChatPromptTemplate.from_messages([
+      # Build the prompt template for the agent
+      prompt = ChatPromptTemplate.from_messages([
             ("system", system_prompt),  # System instructions
             ("human", "{input}"),  # Placeholder for human input
             ("placeholder", "{agent_scratchpad}")  # Placeholder for intermediate reasoning steps
-        ])
+      ])
 
-        # Create an agent capable of interacting with tools and executing tasks
-        agent = create_tool_calling_agent(self.client, tools, prompt)
+      # Create an agent capable of interacting with tools and executing tasks
+      agent = create_tool_calling_agent(self.client, tools, prompt)
 
-        # Wrap the agent in an executor to manage tool interactions and execution flow
-        self.agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
-        
+      # Wrap the agent in an executor to manage tool interactions and execution flow
+      self.agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
+          
 
     def store_customer_interaction(self, user_id: str, message: str, response: str, metadata: Dict = None):
         """