Upload app.py with huggingface_hub

app.py

@@ -572,15 +572,10 @@ class NutritionBot:
         """
         Initialize the NutritionBot class, setting up memory, the LLM client, tools, and the agent executor.
         """
-        st.write("Entered NutritionBot...")
-        st.write(f"MEM0_api_key: {MEM0_api_key}")
+
         # Initialize a memory client to store and retrieve customer interactions
         self.memory = MemoryClient(api_key=MEM0_api_key) # userdata.get("mem0"))  # Complete the code to define the memory client API key
 
-        st.write("Got memory...")
-        st.write(f"api_key: {api_key}")
-        st.write(f"my_api_key: {my_api_key}")
-
         # Initialize the OpenAI client using the provided credentials
         self.client = ChatOpenAI(
             model_name="gpt-4o",  # Used gpt-4o to get improved results; Specify the model to use (e.g., GPT-4 optimized version)
@@ -589,11 +584,9 @@ class NutritionBot:
             api_key="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",
             temperature=0  # Controls randomness in responses; 0 ensures deterministic results
         )
-        st.write("Got client...")
 
         # Define tools available to the chatbot, such as web search
         tools = [agentic_rag]
-        st.write("Got tools...")
 
         # Define the system prompt to set the behavior of the chatbot
         system_prompt = """You are a caring and knowledgeable Medical Support Agent, specializing in nutrition disorder-related guidance. Your goal is to provide accurate, empathetic, and tailored nutritional recommendations while ensuring a seamless customer experience.
@@ -609,7 +602,6 @@ class NutritionBot:
                           Your primary goal is to help customers make informed nutrition decisions that align with their health conditions and personal preferences.
 
         """
-        st.write("Got system prompt...")
 
         # Build the prompt template for the agent
         prompt = ChatPromptTemplate.from_messages([
@@ -617,16 +609,12 @@ class NutritionBot:
             ("human", "{input}"),  # Placeholder for human input
             ("placeholder", "{agent_scratchpad}")  # Placeholder for intermediate reasoning steps
         ])
-        st.write("Got user prompt...")
 
         # Create an agent capable of interacting with tools and executing tasks
         agent = create_tool_calling_agent(self.client, tools, prompt)
-        st.write("Got agent...")
 
         # Wrap the agent in an executor to manage tool interactions and execution flow
         self.agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
-        st.write("Got executor...")
-
 
     def store_customer_interaction(self, user_id: str, message: str, response: str, metadata: Dict = None):
         """
@@ -691,39 +679,26 @@ class NutritionBot:
 
         # Retrieve relevant past interactions for context
         relevant_history = self.get_relevant_history(user_id, query)
-        st.write("Got history...")
 
         # Build a context string from the relevant history
         context = "Previous relevant interactions:\n"
-        #for memory in relevant_history:
-        #    context += f"Customer: {memory['memory']}\n"  # Customer's past messages
-        #    context += f"Support: {memory['memory']}\n"  # Chatbot's past responses
-        #    context += "---\n"
-
-        #context += f"""{context}"""
-        st.write("Got context...")
+        for memory in relevant_history:
+            context += f"Customer: {memory['memory']}\n"  # Customer's past messages
+            context += f"Support: {memory['memory']}\n"  # Chatbot's past responses
+            context += "---\n"
 
         # Print context for debugging purposes
-        st.write("Context: ", context)
+        #st.write("Context: ", context)
 
         # Prepare a prompt combining past context and the current query
-        #prompt = f"""Context: {context}; Current customer query: {query}; Provide a helpful response that takes into account any relevant past interactions."""
-        #prompt_str = f""" \
-        #Context: {context} \
-        #Current customer query: {query} \
-        #Provide a helpful response that takes into account any relevant past interactions. \
-        #"""
-        #prompt = f"""
-        #Context: {context}
-        #Current customer query: {query}
-        #Provide a helpful response that takes into account any relevant past interactions.
-        #"""
-        #print(f"Prepare for invoke...{prompt_str}")
-        print(f"Prepare for invoke...{context}")
+        prompt = f"""
+        Context: {context}
+        Current customer query: {query}
+        Provide a helpful response that takes into account any relevant past interactions.
+        """
 
         # Generate a response using the agent
-        response = self.agent_executor.invoke({"input": query + ";" + context})
-        st.write("Got response...")
+        response = self.agent_executor.invoke({"input": prompt})
 
         # Store the current interaction for future reference
         self.store_customer_interaction(
@@ -732,8 +707,6 @@ class NutritionBot:
             response=response["output"],
             metadata={"type": "support_query"}
         )
-        st.write("Got output...")
-
 
         # Return the chatbot's response
         return response['output']