######################## FINAL APP.PY (Streamlit Version) #########################
# 07032025

import streamlit as st
from datetime import datetime
from typing import Dict, List
import os
import json

# ✅ Fix for Hugging Face write permission
os.environ["MEM0_HOME"] = "./.mem0"

from mem0 import MemoryClient
from langchain_core.prompts import ChatPromptTemplate
from langchain.agents import create_tool_calling_agent, AgentExecutor
from langchain.chat_models import ChatOpenAI

# ✅ Update: Use local config path (not Colab path)
with open("config.json") as f:
    config = json.load(f)

# Optional placeholder if agentic_rag is not defined
try:
    from agentic_rag_workflow import agentic_rag
except ImportError:
    def agentic_rag(*args, **kwargs):
        return "This is a placeholder for agentic_rag tool."

# ------------------------ Define NutritionBot ------------------------
#07042025
from mem0 import MemoryClient
class NutritionBot:
#07042025 Start
#    def __init__(self):
#        self.memory = MemoryClient(api_key=os.getenv("MEM0_API_KEY", "m0-qYbYxa325DtWw8cJoEZyWivE9HMPY74hfX5UHdVl"))

    def __init__(self):
        """
        Initialize the NutritionBot class with memory, LLM client, tools, and the agent executor.
        """
        # Memory to store/retrieve customer interactions
        self.memory = MemoryClient(api_key=os.getenv("Mem0"))
#07042025 End

        self.client = ChatOpenAI(
            model_name="gpt-4o-mini",
            api_key=config.get("API_KEY"),
            endpoint=config.get("OPENAI_API_BASE"),
            temperature=0
        )

        tools = [agentic_rag]

        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."""

        prompt = ChatPromptTemplate.from_messages([
            ("system", system_prompt),
            ("human", "{input}"),
            ("placeholder", "{agent_scratchpad}")
        ])

        agent = create_tool_calling_agent(self.client, tools, prompt)
        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):
        if metadata is None:
            metadata = {}
        metadata["timestamp"] = datetime.now().isoformat()
        conversation = [
            {"role": "user", "content": message},
            {"role": "assistant", "content": response}
        ]
        self.memory.add(conversation, user_id=user_id, output_format="v1.1", metadata=metadata)

    def get_relevant_history(self, user_id: str, query: str) -> List[Dict]:
        return self.memory.search(query=query, user_id=user_id, limit=5)

    def handle_customer_query(self, user_id: str, query: str) -> str:
        relevant_history = self.get_relevant_history(user_id, query)
        context = "Previous relevant interactions:\n"
        for memory in relevant_history:
            context += f"Customer: {memory['memory']}\n"
            context += f"Support: {memory['memory']}\n"
            context += "---\n"

        prompt = f"""
        Context:
        {context}
        Current customer query: {query}
        Provide a helpful response that takes into account any relevant past interactions.
        """

        response = self.agent_executor.invoke({"input": prompt})
        self.store_customer_interaction(user_id, query, response["output"], metadata={"type": "support_query"})
        return response["output"]

# ------------------------ Streamlit Interface ------------------------

st.set_page_config(page_title="Nutrition Disorder Specialist Agent")
st.title("🩺 Nutrition Disorder Specialist Agent")
st.write("Ask anything about nutrition-related disorders, treatments, or dietary recommendations.")

user_id = st.text_input("👤 User ID", placeholder="Enter your name or ID")
query = st.text_area("💬 Your Question", placeholder="Ask about a nutrition disorder...")

if st.button("🔍 Submit") and user_id and query:
    with st.spinner("Thinking..."):
        bot = NutritionBot()
        try:
            response = bot.handle_customer_query(user_id, query)
            st.success("✅ Agent Response:")
            st.write(response)
        except Exception as e:
            st.error("❌ Error occurred while processing your request.")
            st.text(str(e))