app.py

import os
import random
import torch
import pandas as pd
from flask import Flask, render_template, request, jsonify
from sentence_transformers import SentenceTransformer, util
import gradio as gr
import uvicorn
import nest_asyncio
from fastapi import FastAPI
from fastapi.middleware.wsgi import WSGIMiddleware

# ==============================
# CONFIG
# ==============================
BASE_DIR = os.path.abspath(os.path.dirname(__file__))

CSV_DATA = "dataset_2026.csv"
EMB_FILE = "embeddings_questions.pt"
TOP_K_RECOMMANDATIONS = 5

# ==============================
# FLASK APP
# ==============================
app = Flask(
    __name__,
    template_folder=os.path.join(BASE_DIR, "templates"),
    static_folder=os.path.join(BASE_DIR, "static")
)

# ==============================
# MODEL
# ==============================
print("🔄 Chargement du modèle...")

try:
    model = SentenceTransformer(
        "OrdalieTech/Solon-embeddings-mini-beta-1.1",
        device="cpu",
        trust_remote_code=True
    )
    print("✓ Modèle principal chargé")
except Exception as e:
    print("⚠️ Modèle principal échoué:", e)
    model = SentenceTransformer(
        "paraphrase-multilingual-MiniLM-L12-v2",
        device="cpu"
    )
    print("✓ Modèle fallback chargé")

# ==============================
# GLOBAL CACHE (IMPORTANT FIX)
# ==============================
df = None
embeddings = None


# ==============================
# DATA LOADING (ROBUST FIX)
# ==============================
def load_data():
    global df

    try:
        try:
            df = pd.read_excel(CSV_DATA, engine="openpyxl")
        except Exception:
            # Fallback for csv
            df = pd.read_csv(CSV_DATA, sep=None, engine="python", encoding="utf-8", on_bad_lines="skip")

        # normalize column names (VERY IMPORTANT FIX)
        df.columns = df.columns.str.strip()

        print(f"✓ Données chargées: {len(df)} lignes")
        print("📌 Colonnes:", df.columns.tolist())

        return df

    except FileNotFoundError:
        print("❌ Dataset introuvable → création...")

        df = pd.DataFrame({
            "Question": ["Bonjour", "Comment ça va?", "Qu'est-ce que c'est?"],
            "Response": [
                "Bonjour! Comment puis-je vous aider?",
                "Je vais bien, merci!",
                "C'est une application Q/A"
            ],
            "Intent": ["salutation", "conversation", "information"]
        })

        df.to_csv(CSV_DATA, index=False)
        return df


# ==============================
# EMBEDDINGS (CACHE FIX)
# ==============================
def load_embeddings():
    global embeddings, df

    if embeddings is not None:
        return embeddings

    if os.path.exists(EMB_FILE):
        print("📂 Chargement embeddings...")
        loaded_embs = torch.load(EMB_FILE, map_location="cpu")
        
        expected_dim = model.get_sentence_embedding_dimension()
        if loaded_embs.shape[1] == expected_dim and loaded_embs.shape[0] == len(df):
            embeddings = loaded_embs
            return embeddings
        else:
            print(f"⚠️ Incohérence détectée (dim: {loaded_embs.shape[1]} vs {expected_dim}, taille: {loaded_embs.shape[0]} vs {len(df)}). Recréation des embeddings...")

    print("🔨 Création embeddings...")

    questions = df["Question"].astype(str).tolist()

    embeddings = model.encode(
        questions,
        convert_to_tensor=True,
        normalize_embeddings=True,
        show_progress_bar=True
    )

    torch.save(embeddings, EMB_FILE)
    print("✓ Embeddings sauvegardés")

    return embeddings


# ==============================
# UTILS
# ==============================
def enrich_message(text):
    prefixes = [
        "Bonne question 🙂",
        "Voici la réponse :",
        "Intéressant !",
        "D'après mes données :",
        "Réponse :",
        "🤖"
    ]
    return f"{random.choice(prefixes)} {text}"


def get_column(df, name):
    """
    SAFE column getter (fixes Intent/intent/spacing issues)
    """
    for col in df.columns:
        if col.lower() == name.lower():
            return col
    raise KeyError(f"Column '{name}' not found. Available: {df.columns.tolist()}")


# ==============================
# CORE LOGIC (FIXED)
# ==============================
def process_question(question):
    global df, embeddings

    if not question or not question.strip():
        return {
            "response": "Veuillez poser une question valide.",
            "confidence": 0,
            "matched": "—",
            "intent": "Invalid",
            "recs": []
        }

    try:
        df = load_data()
        embeddings = load_embeddings()

        q_col = get_column(df, "Question")
        r_col = get_column(df, "Response")
        i_col = get_column(df, "Intent")
        
        service_col = get_column(df, "Service")
        link_col = get_column(df, "ServiceLink")
        lat_col = get_column(df, "Latitude")
        lon_col = get_column(df, "Longitude")
        
        img_col = None
        for col in df.columns:
            if col.lower() in ["imageplan", "image", "plan"]:
                img_col = col
                break

        emb_q = model.encode(
            question,
            convert_to_tensor=True,
            normalize_embeddings=True
        )

        scores = util.pytorch_cos_sim(emb_q, embeddings)[0]

        best_idx = torch.argmax(scores).item()
        confidence = int(scores[best_idx].item() * 100)

        # LOW CONFIDENCE
        if confidence < 40:
            # Orientation : pick a few distinct topics to guide the user
            try:
                unique_intents = df[i_col].drop_duplicates()
                sampled_intents = unique_intents.sample(n=min(TOP_K_RECOMMANDATIONS, len(unique_intents)))
                
                orientation_recs = []
                for ui in sampled_intents:
                    # Take the first question from this intent
                    first_q = df[df[i_col] == ui][q_col].iloc[0]
                    orientation_recs.append(str(first_q))
            except Exception:
                # Fallback to random if something goes wrong
                orientation_recs = df[q_col].sample(min(TOP_K_RECOMMANDATIONS, len(df))).tolist()

            return {
                "response": "Je ne suis pas certain d'avoir la réponse exacte. Cependant, pour vous orienter, voici quelques exemples de sujets sur lesquels je peux vous accompagner :",
                "confidence": confidence,
                "matched": "—",
                "intent": "Besoin d'orientation",
                "recs": orientation_recs,
                "service": None,
                "link": None,
                "lat": None,
                "lon": None
            }

        # CONFIDENCE >= 40% (Final answer without recommendations)
        answer = df[r_col].iloc[best_idx]
        intent = df[i_col].iloc[best_idx]
        
        service = df[service_col].iloc[best_idx] if service_col else None
        link = df[link_col].iloc[best_idx] if link_col else None
        lat = df[lat_col].iloc[best_idx] if lat_col else None
        lon = df[lon_col].iloc[best_idx] if lon_col else None

        # Clean NaN/Null values
        service_val = str(service) if pd.notna(service) and str(service).lower() not in ['nan', 'none', 'null', ''] else None
        link_val = str(link) if pd.notna(link) and str(link).lower() not in ['nan', 'none', 'null', ''] else None
        
        image_val = None
        if img_col:
            raw_img = df[img_col].iloc[best_idx]
            image_val = str(raw_img) if pd.notna(raw_img) and str(raw_img).lower() not in ['nan', 'none', 'null', ''] else None
            
        try:
            lat_val = float(lat) if pd.notna(lat) and str(lat).lower() not in ['nan', 'none', 'null', ''] else None
            lon_val = float(lon) if pd.notna(lon) and str(lon).lower() not in ['nan', 'none', 'null', ''] else None
        except Exception:
            lat_val = None
            lon_val = None

        # No recommendations if similarity >= 40%
        recs = []

        return {
            "response": enrich_message(answer),
            "confidence": confidence,
            "matched": df[q_col].iloc[best_idx],
            "intent": intent,
            "recs": recs,
            "service": service_val,
            "link": link_val,
            "lat": lat_val,
            "lon": lon_val,
            "image": image_val
        }

    except Exception as e:
        print("❌ Erreur:", e)
        return {
            "response": "Erreur technique.",
            "confidence": 0,
            "matched": "—",
            "intent": "Error",
            "recs": [],
            "service": None,
            "link": None,
            "lat": None,
            "lon": None,
            "image": None
        }


# ==============================
# FLASK ROUTES
# ==============================
@app.route("/")
def index():
    return render_template("index.html")


@app.route("/ask", methods=["POST"])
def ask():
    try:
        data = request.get_json()
        question = data.get("question", "")
        return jsonify(process_question(question))
    except Exception as e:
        print(e)
        return jsonify({"response": "Erreur serveur"})

@app.route("/api/services", methods=["GET"])
def get_services():
    try:
        global df
        if df is None:
            df = load_data()
            
        service_col = get_column(df, "Service")
        lat_col = get_column(df, "Latitude")
        lon_col = get_column(df, "Longitude")
        
        # Filter rows having valid lat and lon and service
        valid_df = df.dropna(subset=[service_col, lat_col, lon_col])
        
        services_list = []
        seen = set()
        for _, row in valid_df.iterrows():
            srv = str(row[service_col]).strip()
            if srv and srv.lower() not in ['nan', 'none', 'null', ''] and srv not in seen:
                try:
                    lat_val = float(row[lat_col])
                    lon_val = float(row[lon_col])
                    if not pd.isna(lat_val) and not pd.isna(lon_val):
                        services_list.append({
                            "service": srv,
                            "lat": lat_val,
                            "lon": lon_val
                        })
                        seen.add(srv)
                except Exception:
                    pass
                    
        return jsonify({"status": "success", "services": services_list})
    except Exception as e:
        print("❌ Error API Services:", e)
        return jsonify({"status": "error", "services": []})


# ==============================
# GRADIO
# ==============================
def gradio_chat(message, history):
    return process_question(message)["response"]

iface = gr.ChatInterface(
    fn=gradio_chat,
    title="AskLaQ Assistant",
    description="Posez vos questions"
)


# ==============================
# FASTAPI WRAPPER
# ==============================
fastapi_app = FastAPI(title="AskLaQ API")

fastapi_app.mount("/", WSGIMiddleware(app))
fastapi_app = gr.mount_gradio_app(fastapi_app, iface, path="/chat")


# ==============================
# MAIN
# ==============================
if __name__ == "__main__":
    nest_asyncio.apply()

    print("=" * 60)
    print("🚀 ASKLAQ SYSTEM (ROBUST VERSION)")
    print("=" * 60)

    uvicorn.run(
        fastapi_app,
        host="0.0.0.0",
        port=7860,
        log_level="info"
    )