import streamlit as st
import os
from langchain.memory import ConversationBufferMemory
import uuid
from dotenv import load_dotenv
import time
from langchain.vectorstores import Chroma
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.memory import ConversationBufferMemory
from langchain_core.prompts import ChatPromptTemplate, PromptTemplate
from langchain_groq import ChatGroq
from langchain.chains import RetrievalQA, LLMChain
from langchain.document_loaders import PyPDFLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter

# Set page configuration with wide layout
st.set_page_config(
    page_title="Dr. Radha: The Agro-Homeopath",
    page_icon="🌿",
    layout="wide"
)

# Enhanced CSS styling
st.markdown("""
    <style>
    /* Main container styling */
    .stApp {
        background-color: #1B4D3E;
    }
    
    /* Chat message styling */
    .stChatMessage {
        background-color: rgba(255, 255, 255, 0.1);
        border-radius: 15px;
        padding: 15px;
        margin: 10px 0;
        border: 1px solid rgba(255, 255, 255, 0.2);
    }
    
    /* Input field styling */
    .stChatInput {
        border-radius: 20px !important;
        border: 2px solid rgba(255, 255, 255, 0.2) !important;
        background-color: rgba(255, 255, 255, 0.05) !important;
    }
    
    /* Style all text elements in white */
    .stMarkdown, .stText, .stTitle, .stHeader, .stSubheader, 
    .stTextInput label, .stSelectbox label, .st-emotion-cache-10trblm,
    .st-emotion-cache-1a7jz76, .st-emotion-cache-1629p8f,
    [data-testid="stTitle"], [data-testid="stSubheader"] {
        color: white !important;
    }
    
    /* Additional specific selectors for title and subheader */
    h1, h2, h3 {
        color: white !important;
    }
    
    /* Button styling */
    .stButton > button {
        background-color: #FFD700 !important;
        color: #1B4D3E !important;
        font-weight: bold;
        border-radius: 25px;
        padding: 10px 25px;
        border: none;
        transition: all 0.3s ease;
    }
    
    .stButton > button:hover {
        transform: scale(1.05);
        box-shadow: 0 5px 15px rgba(0,0,0,0.2);
    }
    
    /* Center alignment */
    .css-10trblm, .css-1a7jz76 {
        text-align: center !important;
    }
    </style>
""", unsafe_allow_html=True)

st.markdown("""
<style>
/* Sidebar styling */
[data-testid="stSidebar"] {
    background-color: #2fab1a !important;
}

/* Sidebar content styling */
[data-testid="stSidebar"] .stMarkdown, 
[data-testid="stSidebar"] .stText, 
[data-testid="stSidebar"] .stTitle,
[data-testid="stSidebar"] label {
    color: white !important;
}

/* Ensure text areas in sidebar maintain styling */
[data-testid="stSidebar"] .stTextArea textarea {
    background-color: #2fab1a !important;
    color: black !important;
}

</style>
""", unsafe_allow_html=True)

# Initialize session state for chat history
if "messages" not in st.session_state:
    st.session_state.messages = []
    st.session_state.messages.append({
        "role": "assistant",
        "content": "👋 Hello! I'm Dr. Radha, your AI-powered Organic Farming Consultant. How can I assist you today?"
    })

# Your existing initialization code here
PERSISTENT_DIR = "vector_db"
# [Keep all your existing functions and variable definitions]


# Set persistent storage path
PERSISTENT_DIR = "vector_db"

def initialize_vector_db():
    # Check if vector database already exists in persistent storage
    if os.path.exists(PERSISTENT_DIR) and os.listdir(PERSISTENT_DIR):
        embeddings = HuggingFaceEmbeddings()
        vector_db = Chroma(persist_directory=PERSISTENT_DIR, embedding_function=embeddings)
        return None, vector_db
    
    base_dir = os.path.dirname(os.path.abspath(__file__))
    pdf_files = [f for f in os.listdir(base_dir) if f.endswith('.pdf')]
    loaders = [PyPDFLoader(os.path.join(base_dir, fn)) for fn in pdf_files]
    
    documents = []
    for loader in loaders:
        documents.extend(loader.load())
    
    text_splitter = RecursiveCharacterTextSplitter(
        chunk_size=1000,
        chunk_overlap=200,
        length_function=len,
        separators=["\n\n", "\n", " ", ""]
    )
    texts = text_splitter.split_documents(documents)
    
    embeddings = HuggingFaceEmbeddings()
    vector_db = Chroma.from_documents(
        texts, 
        embeddings, 
        persist_directory=PERSISTENT_DIR
    )
    vector_db.persist()
    return documents, vector_db

# System instructions for the LLM
system_prompt = """You are an expert organic farming consultant with specialization in Agro-Homeopathy. When providing suggestions and remedies:
1. Always specify medicine potency as 6c unless the uploaded text mentions some other value explicitly
3. Provide comprehensive diagnosis and treatment advice along with organic farming best practices applicable in the given context
4. Base recommendations on homeopathic and organic farming principles
"""

api_key1 = os.getenv("api_key")

start_time = time.time()

# Title and subheader
st.title("🌿 Dr. Radha: AI-Powered Organic Farming Consultant")
st.subheader("Specializing in Agro-Homeopathy | Free Consultation")

# Information message with centered alignment
st.markdown("""
Please provide complete details about the issue, including:<br>
- Detailed description of plant problem<br>
- Current location, temperature & weather conditions
""", unsafe_allow_html=True)

human_image = "human.png"
robot_image = "bot.jpg"

# Set up Groq API with temperature 0.7
llm = ChatGroq(
    api_key=api_key1, 
    max_tokens=None, 
    timeout=None, 
    max_retries=2, 
    temperature=0.7,
    model="llama-3.3-70b-versatile"
)

embeddings = HuggingFaceEmbeddings()
end_time = time.time()
print(f"Setting up Groq LLM & Embeddings took {end_time - start_time:.4f} seconds")

# Initialize session state
if "documents" not in st.session_state:
    st.session_state["documents"] = None
if "vector_db" not in st.session_state:  
    st.session_state["vector_db"] = None
if "query" not in st.session_state:
    st.session_state["query"] = ""
if "session_id" not in st.session_state:
    st.session_state.session_id = str(uuid.uuid4())
if "conversation_memory" not in st.session_state:
    st.session_state.conversation_memory = ConversationBufferMemory(
        memory_key="chat_history",
        return_messages=True
    )
if "saved_conversations" not in st.session_state:
    st.session_state.saved_conversations = []
    
start_time = time.time()
if st.session_state["documents"] is None or st.session_state["vector_db"] is None:
    with st.spinner("Loading data..."):
        documents, vector_db = initialize_vector_db()
        st.session_state["documents"] = documents  
        st.session_state["vector_db"] = vector_db
else:
    documents = st.session_state["documents"]
    vector_db = st.session_state["vector_db"]

retriever = vector_db.as_retriever()
with st.sidebar:
    st.title("Past Conversations")
    
    # Display saved conversations
    for idx, conv in enumerate(st.session_state.saved_conversations):
        # Get the first message from user in the conversation
        first_user_msg = next((msg["content"] for msg in conv if msg["role"] == "user"), "")
        # Take first 30 characters of the message
        preview = first_user_msg[:50] + "..." if len(first_user_msg) > 50 else first_user_msg
        
        if st.button(f"Query {idx + 1}: {preview}", key=f"conv_{idx}"):
            st.session_state.messages = conv.copy()
            st.rerun()

prompt_template = """As an expert organic farming consultant with specialization in Agro-Homeopathy, analyze the following context and question to provide a clear, structured response.
Context: {context}
Previous conversation:{chat_history}
Question: {query}
Provide your response in the following format:
Analysis: Analyze the described plant condition
Treatment: Recommend relevant organic farming principles and specific homeopathic medicine(s) with exact potency and repetition frequency. Suggest a maximum of 4 medicines in the order of relevance for any single problem. 
Instructions for Use:
Small Plots or Gardens: Make sure your dispensing equipment is not contaminated with
other chemicals or fertilisers as these may antidote the energetic effects of the treatment—
rinse well with hot water before use if necessary. Add one pill to each 200 ml of water, shake
vigorously, and then spray or water your plants. Avoid using other chemicals or fertilisers for
10 days following treatment so that the energetic effects of the treatment are not antidoted.
(One vial of 100 pills makes 20 litres. Plants remain insect or disease free for up to 3 months
following one treatment.)
Large Plots or Farms: Add the remedy to water and apply with the dispensing device of
your choice: watering can, backpack sprayer, boomspray, reticulation systems (add to tanks
or pumps). Make sure your dispensing equipment is not contaminated with other chemicals
or fertilisers as these may antidote the energetic effects of the treatment—rinse with hot
water or steam clean before use if necessary. Avoid using other chemicals or fertilisers for
10 days following treatment.
Dosage rates are approximate and may vary according to different circumstances and
experiences. Suggested doses are:
10 pills or 10ml/10 litre on small areas,
500 pills or 125ml/500l per hectare,
1000 pills or 250ml/500l per hectare,
2500 pills or 500ml/500l per hectare,
Add pills or liquid to your water and mix (with a stick if necessary for large containers).
Recommendations: Provide three key pertinent recommendations based on the query
Remember to maintain a professional, clear tone and ensure all medicine recommendations include specific potency.
Answer:"""

# Create the QA chain with correct variables
memory = ConversationBufferMemory(
    memory_key="chat_history",
    input_key="query",
    output_key="answer"
)

qa = RetrievalQA.from_chain_type(
    llm=llm,
    chain_type="stuff",
    retriever=retriever,
    memory=memory,
    chain_type_kwargs={
        "prompt": PromptTemplate(
            template=prompt_template,
            input_variables=["context", "query"]
        )
    }
)

# Create a separate LLMChain for fallback
fallback_template = """As an expert organic farming consultant with specialization in Agro-Homeopathy, analyze the following context and question to provide a clear, structured response.
Previous conversation:{chat_history}
Question: {query}
Format your response as follows:
Analysis: Analyze the described plant condition
Treatment: Recommend relevant organic farming principles and specific homeopathic medicine(s) with exact potency and repetition frequency. Suggest a maximum of 4 medicines in the order of relevance for any single problem.
Instructions for Use:
Small Plots or Gardens: Make sure your dispensing equipment is not contaminated with
other chemicals or fertilisers as these may antidote the energetic effects of the treatment—
rinse well with hot water before use if necessary. Add one pill to each 200 ml of water, shake
vigorously, and then spray or water your plants. Avoid using other chemicals or fertilisers for
10 days following treatment so that the energetic effects of the treatment are not antidoted.
(One vial of 100 pills makes 20 litres. Plants remain insect or disease free for up to 3 months
following one treatment.)
Large Plots or Farms: Add the remedy to water and apply with the dispensing device of
your choice: watering can, backpack sprayer, boomspray, reticulation systems (add to tanks
or pumps). Make sure your dispensing equipment is not contaminated with other chemicals
or fertilisers as these may antidote the energetic effects of the treatment—rinse with hot
water or steam clean before use if necessary. Avoid using other chemicals or fertilisers for
10 days following treatment.
Dosage rates are approximate and may vary according to different circumstances and
experiences. Suggested doses are:
10 pills or 10ml/10 litre on small areas
500 pills or 125ml/500l per hectare
1000 pills or 250ml/500l per hectare
2500 pills or 500ml/500l per hectare
Add pills or liquid to your water and mix (with a stick if necessary for large containers).
Recommendations: Provide three key pertinent recommendations based on the query
Maintain a professional tone and ensure all medicine recommendations include specific potency.
Answer:"""

fallback_prompt = PromptTemplate(
    template=fallback_template,
    input_variables=["query", "chat_history"]
)
fallback_chain = LLMChain(
    llm=llm,
    prompt=fallback_prompt,
    memory=st.session_state.conversation_memory
)


# Replace your existing chat container and form section with this:
chat_container = st.container()
with chat_container:
    # Display chat history
    for message in st.session_state.messages:
        with st.chat_message(message["role"], avatar="👤" if message["role"] == "user" else "👩‍⚕️"):
            st.markdown(message["content"])

with st.form(key='query_form', clear_on_submit=True):
    query = st.text_input(
        "Ask your question:",
        placeholder="Describe your plant issue here...",
        label_visibility="collapsed"
    )
    col1, col2 = st.columns([1, 1])
    with col1:
        submit_button = st.form_submit_button(label='Submit 📤')
    with col2:
        new_conv_button = st.form_submit_button(label='New Conversation 🔄')

if new_conv_button and len(st.session_state.messages) > 1:
    # Save current conversation
    st.session_state.saved_conversations.append(st.session_state.messages.copy())
    
    # Clear current conversation
    st.session_state.messages = []
    st.session_state.messages.append({
        "role": "assistant",
        "content": "👋 Hello! I'm Dr. Radha, your AI-powered Organic Farming Consultant. How can I assist you today?"
    })
    st.session_state.conversation_memory.clear()
    st.rerun()
    
human_image = "human.png"
robot_image = "bot.jpg"

if submit_button and query:
    # Add user message to history
    st.session_state.messages.append({"role": "user", "content": query})
    
    # Show user message
    with st.chat_message("user", avatar="👤"):
        st.markdown(query)
        
    # Show typing indicator while generating response "🌿"
    with st.chat_message("assistant", avatar="👩‍⚕️"):  
        with st.status("Analyzing your query...", expanded=True):
            st.write("🔍 Retrieving relevant information...")
            st.write("📝 Generating personalized response...")
            chat_history = st.session_state.conversation_memory.load_memory_variables({}).get("chat_history", "")
            try:
                result = qa({
                    "query": query  # Changed from "query" to "question"
                })
                response = result['result'] if result['result'].strip() != "" else fallback_chain.run(query=query, chat_history=st.session_state.conversation_memory.load_memory_variables({})["chat_history"])
            except Exception as e:
                response = fallback_chain.run(query=query, chat_history=st.session_state.conversation_memory.load_memory_variables({})["chat_history"])

            st.session_state.conversation_memory.save_context(
                {"input": query},
                {"output": response}
            )
            
            # Display final response
            st.markdown(response)
            st.session_state.messages.append({"role": "assistant", "content": response})

    # Clear the form
    st.session_state["query"] = ""
    
    # Rerun to update chat history
    st.rerun()