src/streamlit_app.py

# ======================================================
# 📊 Smart Data Analyst Pro (Chat Mode)
# Frontend & Orchestration — Uses utils.py for backend logic
# ======================================================

import os
import pandas as pd
import streamlit as st
from dotenv import load_dotenv
from huggingface_hub import InferenceClient, login
import google.generativeai as genai

# 🧠 Import backend logic
from utils import (
    ai_clean_dataset,
    query_analysis_model,
)

# ======================================================
# ⚙️ APP CONFIGURATION
# ======================================================
st.set_page_config(page_title="📊 Smart Data Analyst Pro", layout="wide")
st.title("📊 Smart Data Analyst Pro (Chat Mode)")
st.caption("Chat with your dataset — AI cleans, analyzes, and visualizes data. Hugging Face + Gemini compatible.")

# ======================================================
# 🔐 Load Environment Variables
# ======================================================
load_dotenv()
HF_TOKEN = os.getenv("HF_TOKEN") or os.getenv("HUGGINGFACE_API_KEY")
GEMINI_API_KEY = os.getenv("GEMINI_API_KEY")

if not HF_TOKEN:
    st.error("❌ Missing HF_TOKEN. Please set it in your .env file.")
else:
    login(token=HF_TOKEN)

if GEMINI_API_KEY:
    genai.configure(api_key=GEMINI_API_KEY)
else:
    st.warning("⚠️ Gemini API key missing. Gemini 2.5 Flash will not work.")

# ======================================================
# 🧠 MODEL SETTINGS (SIDEBAR)
# ======================================================
with st.sidebar:
    st.header("⚙️ Model Settings")

    CLEANER_MODEL = st.selectbox(
        "Select Cleaner Model:",
        [
            "Qwen/Qwen2.5-Coder-14B",
            "mistralai/Mistral-7B-Instruct-v0.3"
        ],
        index=0
    )

    ANALYST_MODEL = st.selectbox(
        "Select Analysis Model:",
        [
            "Gemini 2.5 Flash (Google)",
            "Qwen/Qwen2.5-14B-Instruct",
            "mistralai/Mistral-7B-Instruct-v0.3",
            "HuggingFaceH4/zephyr-7b-beta"
        ],
        index=0
    )

    temperature = st.slider("Temperature", 0.0, 1.0, 0.3)
    max_tokens = st.slider("Max Tokens", 128, 4096, 1024)

# ======================================================
# 🧩 MODEL CLIENTS
# ======================================================
hf_cleaner_client = InferenceClient(model=CLEANER_MODEL, token=HF_TOKEN)
hf_analyst_client = None
if ANALYST_MODEL != "Gemini 2.5 Flash (Google)":
    hf_analyst_client = InferenceClient(model=ANALYST_MODEL, token=HF_TOKEN)

# ======================================================
# 🚀 MAIN CHATBOT LOGIC
# ======================================================
uploaded = st.file_uploader("📎 Upload CSV or Excel file", type=["csv", "xlsx"])

if "messages" not in st.session_state:
    st.session_state.messages = []

if uploaded:
    # Load dataset
    df = pd.read_csv(uploaded) if uploaded.name.endswith(".csv") else pd.read_excel(uploaded)

    # 🧼 AI-BASED CLEANING
    with st.spinner("🧼 Cleaning your dataset..."):
        cleaned_df, cleaning_status = ai_clean_dataset(df, hf_cleaner_client)

    # Display cleaning info
    st.subheader("✅ Cleaning Status")
    st.info(cleaning_status)

    st.subheader("📊 Dataset Preview")
    st.dataframe(cleaned_df.head(), use_container_width=True)

    # 💬 Chat interface
    st.subheader("💬 Chat with Your Dataset")

    for msg in st.session_state.messages:
        with st.chat_message(msg["role"]):
            st.markdown(msg["content"])

    if user_query := st.chat_input("Ask something about your dataset..."):
        st.session_state.messages.append({"role": "user", "content": user_query})
        with st.chat_message("user"):
            st.markdown(user_query)

        with st.chat_message("assistant"):
            with st.spinner("🤖 Analyzing..."):
                result = query_analysis_model(
                    cleaned_df,
                    user_query,
                    uploaded.name,
                    ANALYST_MODEL,
                    hf_client=hf_analyst_client,
                    temperature=temperature,
                    max_tokens=max_tokens,
                    gemini_api_key=GEMINI_API_KEY
                )
                st.markdown(result)
                st.session_state.messages.append({"role": "assistant", "content": result})

else:
    st.info("📥 Upload a dataset to begin chatting with your AI analyst.")