import os
import streamlit as st
import pandas as pd
import sqlite3
import openai
from langchain import OpenAI
from langchain_community.agent_toolkits.sql.base import create_sql_agent
from langchain_community.utilities import SQLDatabase
from langchain_community.document_loaders import CSVLoader
from langchain_community.vectorstores import FAISS
from langchain_community.embeddings import OpenAIEmbeddings
from langchain.chains import RetrievalQA
import sqlparse
import logging

# OpenAI API key (ensure it is securely stored)
openai.api_key = os.getenv("OPENAI_API_KEY")

# Step 1: Upload CSV data file (or use default)
csv_file = st.file_uploader("Upload your CSV file", type=["csv"])
if csv_file is None:
    data = pd.read_csv("default_data.csv")  # Use default CSV if no file is uploaded
    st.write("Using default data.csv file.")
else:
    data = pd.read_csv(csv_file)
    st.write(f"Data Preview ({csv_file.name}):")
    st.dataframe(data.head())

# Step 2: Load CSV data into SQLite database with dynamic table name
conn = sqlite3.connect(':memory:')  # Use an in-memory SQLite database
table_name = csv_file.name.split('.')[0] if csv_file else "default_table"
data.to_sql(table_name, conn, index=False, if_exists='replace')

# SQL table metadata (for validation and schema)
valid_columns = list(data.columns)

# Step 3: Use a SQL Agent and setup LangChain's SQL Database connection
db = SQLDatabase.from_uri('sqlite:///:memory:')
db.raw_connection = conn  # Use the in-memory connection for LangChain
sql_agent = create_sql_agent(OpenAI(temperature=0), db, verbose=True)

# Step 4: Use FAISS with RAG for context retrieval
embeddings = OpenAIEmbeddings()
loader = CSVLoader(file_path=csv_file.name if csv_file else "default_data.csv")
documents = loader.load()

vector_store = FAISS.from_documents(documents, embeddings)
retriever = vector_store.as_retriever()
rag_chain = RetrievalQA.from_chain_type(llm=OpenAI(temperature=0), retriever=retriever)

# Step 5: Define SQL validation helpers
def validate_sql(query, valid_columns):
    """Validates the SQL query by ensuring it references only valid columns."""
    for column in valid_columns:
        if column not in query:
            return False
    return True

def validate_sql_with_sqlparse(query):
    """Validates SQL syntax using sqlparse."""
    parsed_query = sqlparse.parse(query)
    return len(parsed_query) > 0

# Step 6: Generate SQL query based on user input and run it with LangChain SQL Agent
user_prompt = st.text_input("Enter your natural language prompt:")
if user_prompt:
    try:
        # Step 7: Retrieve context using RAG
        context = rag_chain.run(user_prompt)
        st.write(f"Retrieved Context: {context}")

        # Step 8: Generate SQL query using SQL agent
        generated_sql = sql_agent.run(f"{user_prompt} {context}")
        st.write(f"Generated SQL Query: {generated_sql}")

        # Step 9: Validate SQL query
        if not validate_sql_with_sqlparse(generated_sql):
            st.write("Generated SQL is not valid.")
        elif not validate_sql(generated_sql, valid_columns):
            st.write("Generated SQL references invalid columns.")
        else:
            # Step 10: Execute SQL query
            result = pd.read_sql(generated_sql, conn)
            st.write("Query Results:")
            st.dataframe(result)

    except Exception as e:
        logging.error(f"An error occurred: {e}")
        st.write(f"Error: {e}")