app.py

import gradio as gr
from transformers import pipeline
import fitz  # PyMuPDF
import docx
import pptx
import openpyxl
import os

from fastapi import FastAPI
from fastapi.responses import RedirectResponse

# Load your custom summarization model
pipe = pipeline("text2text-generation", model="FeruzaBoynazarovaas/my_awesome_billsum_model")

# Document text extraction function
def extract_text(file):
    ext = file.name.split(".")[-1].lower()
    path = file.name

    if ext == "pdf":
        try:
            with fitz.open(path) as doc:
                return "\n".join([page.get_text("text") for page in doc])
        except Exception as e:
            return f"Error reading PDF: {e}"

    elif ext == "docx":
        try:
            doc = docx.Document(path)
            return "\n".join([p.text for p in doc.paragraphs])
        except Exception as e:
            return f"Error reading DOCX: {e}"

    elif ext == "pptx":
        try:
            prs = pptx.Presentation(path)
            text = ""
            for slide in prs.slides:
                for shape in slide.shapes:
                    if hasattr(shape, "text"):
                        text += shape.text + "\n"
            return text
        except Exception as e:
            return f"Error reading PPTX: {e}"

    elif ext == "xlsx":
        try:
            wb = openpyxl.load_workbook(path)
            text = ""
            for sheet in wb.sheetnames:
                for row in wb[sheet].iter_rows(values_only=True):
                    text += " ".join([str(cell) for cell in row if cell]) + "\n"
            return text
        except Exception as e:
            return f"Error reading XLSX: {e}"
    else:
        return "Unsupported file format"

# Summarization logic
def summarize_document(file):
    text = extract_text(file)
    if "Error" in text or "Unsupported" in text:
        return text

    word_count = len(text.split())
    max_summary_len = max(20, int(word_count * 0.2))

    try:
        summary = pipe(text, max_length=max_summary_len, min_length=int(max_summary_len * 0.6), do_sample=False)
        return summary[0]['generated_text']
    except Exception as e:
        return f"Error during summarization: {e}"

# Gradio Interface
demo = gr.Interface(
    fn=summarize_document,
    inputs=gr.File(label="Upload a document (PDF, DOCX, PPTX, XLSX)", file_types=[".pdf", ".docx", ".pptx", ".xlsx"]),
    outputs=gr.Textbox(label="20% Summary"),
    title="📄 Document Summarizer (20% Length)",
    description="Upload a document and get a concise summary generated by your custom Hugging Face model."
)

# FastAPI setup
app = FastAPI()

# Mount Gradio at "/"
app = gr.mount_gradio_app(app, demo, path="/")

# Optional root redirect
@app.get("/")
def redirect_to_interface():
    return RedirectResponse(url="/")