app.py

import gradio as gr
import pdfplumber
import pytesseract
from PIL import Image
from transformers import pipeline
from sentence_transformers import SentenceTransformer, util

# Load Hugging Face models
qa_pipeline = pipeline("question-answering", model="deepset/roberta-base-squad2")
summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
embedder = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")

# Function to extract text from PDF
def extract_text_from_pdf(pdf_file):
    text = ""
    with pdfplumber.open(pdf_file) as pdf:
        for page in pdf.pages:
            text += page.extract_text() + "\n"
    return text

# Function to extract text from image using OCR
def extract_text_from_image(image_file):
    image = Image.open(image_file)
    return pytesseract.image_to_string(image)

# Function to process document and answer questions
def document_processor(uploaded_file, query):
    text = ""
    if uploaded_file.name.endswith(".pdf"):
        text = extract_text_from_pdf(uploaded_file.name)
    elif uploaded_file.name.endswith((".png", ".jpg", ".jpeg")):
        text = extract_text_from_image(uploaded_file.name)
    else:
        text = uploaded_file.read().decode("utf-8")

    if query.lower() == "summarize":
        summary = summarizer(text, max_length=150, min_length=30, do_sample=False)
        return summary[0]["summary_text"]

    # Find the best-matching answer
    answer = qa_pipeline(question=query, context=text)
    return answer["answer"]

# Gradio UI
with gr.Blocks() as app:
    gr.Markdown("# 📄 Smart Document Explorer")
    
    with gr.Row():
        uploaded_file = gr.File(label="Upload Document (PDF, Image, or Text)")
        query = gr.Textbox(label="Ask a question (or type 'summarize')", placeholder="What is this document about?")
    
    output_text = gr.Textbox(label="AI Response")

    submit_btn = gr.Button("Process Document")
    submit_btn.click(document_processor, inputs=[uploaded_file, query], outputs=output_text)

app.launch()