Update app.py

app.py

@@ -1,4 +1,4 @@
-"""import gradio as gr
+import gradio as gr
 import uvicorn
 import numpy as np
 import fitz  # PyMuPDF
@@ -118,137 +118,3 @@ def home():
 # ✅ Run FastAPI + Gradio
 if __name__ == "__main__":
     uvicorn.run(app, host="0.0.0.0", port=7860)
-""" 
-import gradio as gr
-import uvicorn
-import numpy as np
-import pymupdf  # PyMuPDF
-import tika
-import torch
-from fastapi import FastAPI
-from transformers import pipeline
-from PIL import Image
-from io import BytesIO
-from starlette.responses import RedirectResponse
-from tika import parser
-from openpyxl import load_workbook
-from pptx import Presentation
-import os
-
-tika.initVM()
-app = FastAPI()
-
-device = "cuda" if torch.cuda.is_available() else "cpu"
-qa_pipeline = pipeline("text-generation", model="TinyLlama/TinyLlama-1.1B-Chat-v1.0", device=device)
-image_captioning_pipeline = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
-
-ALLOWED_EXTENSIONS = {"pdf", "docx", "pptx", "xlsx"}
-
-def validate_file_type(file):
-    if not file:
-        return "❌ No file uploaded!"
-    if isinstance(file, str) and os.path.exists(file):
-        return None
-    if hasattr(file, "name"):
-        ext = file.name.split(".")[-1].lower()
-        if ext not in ALLOWED_EXTENSIONS:
-            return f"❌ Unsupported file format: {ext}"
-        return None
-    return "❌ Invalid file format!"
-
-def extract_text_from_pdf(file_bytes):
-    try:
-        doc = pymupdf.open(stream=file_bytes, filetype="pdf")
-        return "\n".join([page.get_text("text") for page in doc])
-    except Exception as e:
-        return f"❌ PDF Error: {str(e)}"
-
-def extract_text_with_tika(file_bytes):
-    try:
-        parsed = parser.from_buffer(file_bytes)
-        return parsed.get("content", "⚠️ No text found.").strip()
-    except Exception as e:
-        return f"❌ Tika Error: {str(e)}"
-
-def extract_text_from_excel(file_bytes):
-    try:
-        wb = load_workbook(BytesIO(file_bytes), data_only=True)
-        text = []
-        for sheet in wb.worksheets:
-            for row in sheet.iter_rows(values_only=True):
-                text.append(" ".join(str(cell) for cell in row if cell))
-        return "\n".join(text) if text else "⚠️ No text found."
-    except Exception as e:
-        return f"❌ Excel Error: {str(e)}"
-
-def extract_text_from_pptx(file_bytes):
-    try:
-        ppt = Presentation(BytesIO(file_bytes))
-        text = []
-        for slide in ppt.slides:
-            for shape in slide.shapes:
-                if hasattr(shape, "text"):
-                    text.append(shape.text)
-        return "\n".join(text) if text else "⚠️ No text found."
-    except Exception as e:
-        return f"❌ PPTX Error: {str(e)}"
-
-def truncate_text(text, max_length=2048):
-    return text[:max_length] if len(text) > max_length else text
-
-def answer_question(file, question: str):
-    try:
-        validation_error = validate_file_type(file)
-        if validation_error:
-            return validation_error
-
-        file_bytes = None
-        file_ext = None
-
-        if isinstance(file, str) and os.path.exists(file):
-            file_ext = file.split(".")[-1].lower()
-            with open(file, "rb") as f:
-                file_bytes = f.read()
-        elif hasattr(file, "read"):
-            file_ext = file.name.split(".")[-1].lower()
-            file_bytes = file.read()
-        else:
-            return f"❌ Unexpected file type received! Type: {type(file)}"
-
-        if file_ext == "pdf":
-            text = extract_text_from_pdf(file_bytes)
-        elif file_ext in ["docx", "pptx"]:
-            text = extract_text_with_tika(file_bytes)
-        elif file_ext == "xlsx":
-            text = extract_text_from_excel(file_bytes)
-        else:
-            return f"❌ Unsupported file format: {file_ext}"
-
-        if not text or "❌" in text:
-            return f"⚠️ No text extracted. Error: {text}"
-
-        truncated_text = truncate_text(text)
-        response = qa_pipeline(f"Question: {question}\nContext: {truncated_text}")
-
-        return response[0]["generated_text"]
-
-    except Exception as e:
-        return f"❌ Processing Error: {str(e)}"
-
-with gr.Blocks() as demo:
-    gr.Markdown("## 📄 AI-Powered Document QA")
-    with gr.Row():
-        file_input = gr.File(label="Upload Document")
-        question_input = gr.Textbox(label="Ask a Question", placeholder="What is this document about?")
-    answer_output = gr.Textbox(label="Answer")
-    submit_btn = gr.Button("Get Answer")
-    submit_btn.click(answer_question, inputs=[file_input, question_input], outputs=answer_output)
-
-app = gr.mount_gradio_app(app, demo, path="/")
-
-@app.get("/")
-def home():
-    return RedirectResponse(url="/")
-
-if __name__ == "__main__":
-    uvicorn.run(app, host="0.0.0.0", port=7860)