app.py

# ==========================================================
# SAFE-MODE PRELAUNCH CLEANUP (runs before any heavy imports)
# ==========================================================
import os, shutil, time, glob

def _prelaunch_cleanup(threshold_gb=45.0):
    """Early cleanup to prevent Hugging Face Space eviction (50 GB limit)."""
    def _used_gb(path="/home/user/app"):
        try:
            total, used, free = shutil.disk_usage(path)
            used_gb = max(0.0, min(used / (1024**3), 49.9))
            return used_gb
        except Exception:
            return 0.0

    used = _used_gb()
    print(f"\n💾 Startup disk usage: {used:.2f} GB")

    cache_paths = [
        os.path.expanduser("~/.cache/huggingface"),
        os.path.expanduser("~/.cache/hfhub"),
        "/home/user/.cache/huggingface",
        "/home/user/.cache",
        "/home/user/app/__pycache__",
        "/home/user/app/data/__pycache__",
    ]
    for p in cache_paths:
        if os.path.exists(p):
            shutil.rmtree(p, ignore_errors=True)

    if used > threshold_gb:
        print(f"⚠️ Usage {used:.2f} GB > {threshold_gb} GB — performing aggressive cleanup.")
        preserve = {"faiss.index", "faiss.index.meta.json", "glossary.json"}
        folders = ["/home/user/app/data/docs_cache", "/home/user/app/tmp_docs", "/home/user/app/persistent"]
        for folder in folders:
            if os.path.exists(folder):
                for f in glob.glob(os.path.join(folder, "*")):
                    if os.path.basename(f) in preserve:
                        continue
                    try:
                        if os.path.isfile(f):
                            os.remove(f)
                        else:
                            shutil.rmtree(f, ignore_errors=True)
                    except Exception:
                        pass
        print("🧹 Aggressive cleanup complete.")

    print(f"✨ Disk after cleanup: {_used_gb():.2f} GB\n")
    shutil.rmtree("/home/user/app/runtime_faiss", ignore_errors=True)

_prelaunch_cleanup()

# ==========================================================
# MAIN APP — Clinical Trial Chatbot
# ==========================================================
import gradio as gr
from sentence_transformers import SentenceTransformer
from core.hybrid_retriever import summarize_combined

APP_TITLE = "🧠 Clinical Trial Basics"
APP_DESC = (
    "Ask any clinical trial or GCP-related question. "
    "Retrieves and summarizes from ICH, GCDMP, EMA, FDA, Excel, and Web datasets."
)

# Detect deployment mode
PUBLIC_MODE = os.environ.get("PUBLIC_MODE", "true").lower() == "true"
ADMIN_USER = os.environ.get("ADMIN_USER", "admin")
ADMIN_PASS = os.environ.get("ADMIN_PASS", "changeme")

print(f"🔐 Running in {'PUBLIC' if PUBLIC_MODE else 'ADMIN'} mode.")

# ----------------------------------------------------------
# ADMIN AUTHENTICATION HELPER
# ----------------------------------------------------------
def check_admin_login(username, password):
    """Authenticate admin before showing rebuild/clear tools."""
    return username == ADMIN_USER and password == ADMIN_PASS

# ----------------------------------------------------------
# MAINTENANCE FUNCTIONS
# ----------------------------------------------------------
import shutil, json, faiss, pandas as pd, numpy as np

DATA_PATHS = [
    "/home/user/app/persistent/faiss.index",
    "/home/user/app/persistent/faiss.index.meta.json",
    "/home/user/app/data/docs_cache",
]

def clear_index():
    removed = []
    for p in DATA_PATHS:
        if os.path.isdir(p):
            shutil.rmtree(p, ignore_errors=True)
            removed.append(f"🗑️ Deleted folder: {p}")
        elif os.path.exists(p):
            os.remove(p)
            removed.append(f"🗑️ Deleted file: {p}")
    msg = "\n".join(removed) if removed else "ℹ️ No cache files found."
    print(msg)
    return msg

def rebuild_index():
    try:
        from core.vector_sync import rebuild_faiss_from_glossary, _upload_to_dataset
        import pandas as pd, faiss, numpy as np
        from sentence_transformers import SentenceTransformer
        print("🧠 Rebuilding FAISS index (Glossary + Excel + Web)...")
        # ... (you can keep your current detailed rebuild logic here)
        return "✅ Rebuild complete (placeholder logic)."
    except Exception as e:
        return f"⚠️ Rebuild failed: {e}"

def rebuild_glossary():
    try:
        from core.glossary_builder import rebuild_and_upload
        rebuild_and_upload()
        return "✅ Glossary rebuilt and uploaded successfully."
    except Exception as e:
        return f"⚠️ Glossary rebuild failed: {e}"

# ----------------------------------------------------------
# CHATBOT CORE
# ----------------------------------------------------------
def chat_answer(query, mode="short"):
    try:
        query_clean = query.strip()
        if not query_clean:
            return "<i>⚠️ Please enter a valid query.</i>"
        return summarize_combined(query_clean, mode=mode)
    except Exception as e:
        print("❌ Chatbot error:", e)
        return f"<i>⚠️ Error: {e}</i>"

# ----------------------------------------------------------
# GRADIO UI
# ----------------------------------------------------------
with gr.Blocks(theme="gradio/soft") as demo:
    gr.Markdown(f"# {APP_TITLE}")
    gr.Markdown(APP_DESC)

    query_box = gr.Textbox(
        label="Ask your clinical trial question",
        placeholder="e.g. What is an eCRF?",
        lines=2,
        show_label=True
    )
    output_box = gr.HTML(label="Answer")

    with gr.Row():
        submit_btn = gr.Button("🚀 Submit", variant="primary")

        # Only show admin tools if not in PUBLIC mode
        if not PUBLIC_MODE:
            rebuild_btn = gr.Button("🔁 Rebuild Index")
            rebuild_glossary_btn = gr.Button("📘 Rebuild Glossary")
            clear_btn = gr.Button("🧹 Clear Cache / Index")

    submit_btn.click(fn=chat_answer, inputs=[query_box], outputs=output_box)
    query_box.submit(fn=chat_answer, inputs=[query_box], outputs=output_box)

    if not PUBLIC_MODE:
        rebuild_btn.click(fn=rebuild_index, outputs=output_box)
        rebuild_glossary_btn.click(fn=rebuild_glossary, outputs=output_box)
        clear_btn.click(fn=clear_index, outputs=output_box)

# ----------------------------------------------------------
# LAUNCH APP WITH AUTH
# ----------------------------------------------------------
if __name__ == "__main__":
    print("🚀 Starting Clinical Trial Chatbot...")
    print("🧠 Initializing retriever warm-up...")
    demo.launch(
        server_name="0.0.0.0",
        server_port=7860,
        share=False,
        auth=check_admin_login if not PUBLIC_MODE else None
    )