import os
import psycopg2
import streamlit as st
from datetime import datetime
from langchain_community.vectorstores import FAISS
from langchain_community.embeddings import HuggingFaceEmbeddings
from langchain_huggingface import HuggingFaceEndpoint
from langchain.prompts import PromptTemplate
from langchain.chains import LLMChain, RetrievalQA
from huggingface_hub import login

# Login to Hugging Face
login(token=st.secrets["HF_TOKEN"])

# Load FAISS index and ensure it only happens once
if 'db' not in st.session_state:
    st.session_state.db = FAISS.load_local(
        "faiss_index", 
        HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L12-v2'),
        allow_dangerous_deserialization=True
    )

# Use session state for retriever
retriever = st.session_state.db.as_retriever(
    search_type="mmr",
    search_kwargs={'k': 1}
)

# Define prompt template
prompt_template = """
### [INST]
Instruction: You are a Q&A assistant. Your goal is to answer questions as accurately as possible based on the instructions and context provided without using prior knowledge. You answer in FRENCH
Analyse carefully the context and provide a direct answer based on the context. If the user said Bonjour or Hello your only answer will be Hi! comment puis-je vous aider?
Answer in french only

{context}
Vous devez répondre aux questions en français.
### QUESTION:
{question}
[/INST]
Answer in french only
Vous devez répondre aux questions en français.
"""

repo_id = "mistralai/Mistral-7B-Instruct-v0.3"

# Load the model only once
if 'mistral_llm' not in st.session_state:
    st.session_state.mistral_llm = HuggingFaceEndpoint(
        repo_id=repo_id, 
        max_length=2048, 
        temperature=0.05, 
        huggingfacehub_api_token=st.secrets["HF_TOKEN"]
    )

# Create prompt and LLM chain
prompt = PromptTemplate(
    input_variables=["question"],
    template=prompt_template,
)
llm_chain = LLMChain(llm=st.session_state.mistral_llm, prompt=prompt)

# Create QA chain
qa = RetrievalQA.from_chain_type(
    llm=st.session_state.mistral_llm,
    chain_type="stuff",
    retriever=retriever,
    chain_type_kwargs={"prompt": prompt},
)



def chatbot_response(user_input):
    response = qa.run(user_input)
    return response

# Create columns for logos
col1, col2, col3 = st.columns([2, 3, 2])

with col1:
    st.image("Design 3_22.png", width=150, use_column_width=True)

with col3:
    st.image("Altereo logo 2023 original - eau et territoires durables.png", width=150, use_column_width=True)



st.markdown('<h3 class="centered-text">🤖 AlteriaChat 🤖 </h3>', unsafe_allow_html=True)
st.markdown('<p class="centered-orange-text">"Votre Réponse à Chaque Défi Méthodologique "</p>', unsafe_allow_html=True)

# Input and button for user interaction
user_input = st.text_input("You:", "")
submit_button = st.button("Ask 📨")

import os
import streamlit as st
import psycopg2
from datetime import datetime

# Function to create a connection to PostgreSQL
def create_connection():
    return psycopg2.connect(
        host=os.getenv("DB_HOST"),
        database=os.getenv("DB_NAME"),
        user=os.getenv("DB_USER"),
        password=os.getenv("DB_PASSWORD"),
        port=os.getenv("DB_PORT")
    )

# Function to create the feedback table if it doesn't exist
def create_feedback_table(conn):
    cursor = conn.cursor()
    cursor.execute("""
        CREATE TABLE IF NOT EXISTS feedback (
            id SERIAL PRIMARY KEY,
            user_input TEXT NOT NULL,
            bot_response TEXT NOT NULL,
            rating INT CHECK (rating >= 1 AND rating <= 5),
            comment TEXT,
            timestamp TIMESTAMP DEFAULT CURRENT_TIMESTAMP
        );
    """)
    conn.commit()
    cursor.close()

# Function to insert feedback into the database
def insert_feedback(conn, user_input, bot_response, rating, comment):
    cursor = conn.cursor()
    cursor.execute(
        "INSERT INTO feedback (user_input, bot_response, rating, comment, timestamp) VALUES (%s, %s, %s, %s, %s)",
        (user_input, bot_response, rating, comment, datetime.now())
    )
    conn.commit()
    cursor.close()

# Initialize connection and create the table if necessary
conn = create_connection()
create_feedback_table(conn)

# Streamlit app UI and logic
st.markdown("## Rate your experience")

# Create a star-based rating system using radio buttons
rating = st.radio(
    "Rating",
    options=[1, 2, 3, 4, 5],
    format_func=lambda x: "★" * x  # Display stars based on the rating
)

# Text area for leaving a comment
comment = st.text_area("Leave a comment")

# Display bot response and user input for context
st.markdown("### Your Question:")
st.write(user_input)
st.markdown("### Bot's Response:")
st.write(bot_response)

# Submit feedback
if st.button("Submit Feedback"):
    if rating and comment:
        insert_feedback(conn, user_input, bot_response, rating, comment)
        st.success("Thank you for your feedback!")
    else:
        st.warning("Please provide a rating and a comment.")

# Close the connection when done
conn.close()


# Motivational quote at the bottom
st.markdown("---")
st.markdown("La collaboration est la clé du succès. Chaque question trouve sa réponse, chaque défi devient une opportunité.")