working doc

app.py

@@ -72,7 +72,7 @@ app = gr.mount_gradio_app(app, demo, path="/")
 @app.get("/")
 def root():
     return RedirectResponse(url="/")
-
+"""
 import gradio as gr
 import fitz  # PyMuPDF for PDFs
 import easyocr  # OCR for images
@@ -95,7 +95,7 @@ reader = easyocr.Reader(['en', 'fr'])  # OCR for English & French
 
 # ---- TEXT EXTRACTION FUNCTIONS ----
 def extract_text_from_pdf(pdf_file):
-    "Extract text from a PDF file.""
+    """Extract text from a PDF file."""
     text = []
     try:
         with fitz.open(pdf_file) as doc:
@@ -106,12 +106,12 @@ def extract_text_from_pdf(pdf_file):
     return "\n".join(text)
 
 def extract_text_from_docx(docx_file):
-    "Extract text from a DOCX file."
+    """Extract text from a DOCX file."""
     doc = docx.Document(docx_file)
     return "\n".join([p.text for p in doc.paragraphs if p.text.strip()])
 
 def extract_text_from_pptx(pptx_file):
-    "Extract text from a PPTX file."
+    """Extract text from a PPTX file."""
     text = []
     try:
         presentation = pptx.Presentation(pptx_file)
@@ -124,7 +124,7 @@ def extract_text_from_pptx(pptx_file):
     return "\n".join(text)
 
 def extract_text_from_xlsx(xlsx_file):
-    "Extract text from an XLSX file."
+    """Extract text from an XLSX file."""
     text = []
     try:
         wb = openpyxl.load_workbook(xlsx_file)
@@ -137,13 +137,13 @@ def extract_text_from_xlsx(xlsx_file):
     return "\n".join(text)
 
 def extract_text_from_image(image_path):
-    "Extract text from an image using EasyOCR.""
+    """Extract text from an image using EasyOCR."""
     result = reader.readtext(image_path, detail=0)
     return " ".join(result)  # Return text as a single string
 
 # ---- MAIN PROCESSING FUNCTIONS ----
 def answer_question_from_doc(file, question):
-    "Process document and answer a question based on its content."
+    """Process document and answer a question based on its content."""
     ext = file.name.split(".")[-1].lower()
     
     if ext == "pdf":
@@ -155,10 +155,10 @@ def answer_question_from_doc(file, question):
     elif ext == "xlsx":
         context = extract_text_from_xlsx(file.name)
     else:
-        return "Unsupported file format."
+        return """Unsupported file format."""
 
     if not context.strip():
-        return "No text found in the document."
+        return """No text found in the document."""
 
     # Generate answer using QA pipeline correctly
     try:
@@ -168,10 +168,10 @@ def answer_question_from_doc(file, question):
         return f"Error generating answer: {e}"
 
 def answer_question_from_image(image, question):
-    "Process an image, extract text, and answer a question.""
+    """Process an image, extract text, and answer a question."""
     img_text = extract_text_from_image(image)
     if not img_text.strip():
-        return "No readable text found in the image."
+        return """No readable text found in the image."""
 
     try:
         result = qa_model({"question": question, "context": img_text})
@@ -203,146 +203,4 @@ app = gr.mount_gradio_app(app, demo, path="/")
 @app.get("/")
 def home():
     return RedirectResponse(url="/")
-"""
-from fastapi import FastAPI
-from fastapi.responses import RedirectResponse
-import gradio as gr
-
-import fitz  # PyMuPDF for PDFs
-import easyocr  # OCR for images
-import openpyxl  # XLSX processing
-import pptx  # PPTX processing
-import docx  # DOCX processing
-
-from transformers import pipeline, ViltProcessor, ViltForQuestionAnswering
-from PIL import Image
-import torch
-
-# === Initialize FastAPI App ===
-app = FastAPI()
-
-# === Initialize QA Model for Documents and OCR ===
-qa_model = pipeline("question-answering", model="deepset/roberta-base-squad2")
-
-# === Initialize Image QA Model (VQA) ===
-vqa_processor = ViltProcessor.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
-vqa_model = ViltForQuestionAnswering.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
-
-# === OCR Reader ===
-reader = easyocr.Reader(['en', 'fr'])
-
-# === Document Text Extraction Functions ===
-def extract_text_from_pdf(file_obj):
-    doc = fitz.open(stream=file_obj.read(), filetype="pdf")
-    return "\n".join([page.get_text() for page in doc])
-
-def extract_text_from_docx(docx_file):
-    doc = docx.Document(docx_file)
-    return "\n".join([p.text for p in doc.paragraphs if p.text.strip()])
-
-def extract_text_from_pptx(pptx_file):
-    text = []
-    try:
-        presentation = pptx.Presentation(pptx_file)
-        for slide in presentation.slides:
-            for shape in slide.shapes:
-                if hasattr(shape, "text"):
-                    text.append(shape.text)
-    except Exception as e:
-        return f"Error reading PPTX: {e}"
-    return "\n".join(text)
-
-def extract_text_from_xlsx(xlsx_file):
-    text = []
-    try:
-        wb = openpyxl.load_workbook(xlsx_file)
-        for sheet in wb.sheetnames:
-            ws = wb[sheet]
-            for row in ws.iter_rows(values_only=True):
-                text.append(" ".join(str(cell) for cell in row if cell))
-    except Exception as e:
-        return f"Error reading XLSX: {e}"
-    return "\n".join(text)
-
-# === Image OCR ===
-def extract_text_from_image(image_path):
-    result = reader.readtext(image_path, detail=0)
-    return " ".join(result)
-
-# === QA for Document Files ===
-def answer_question_from_doc(file, question):
-    if file is None or not question.strip():
-        return "Please upload a document and ask a question."
-    
-    ext = file.name.split(".")[-1].lower()
-    if ext == "pdf":
-        context = extract_text_from_pdf(file)
-    elif ext == "docx":
-        context = extract_text_from_docx(file)
-    elif ext == "pptx":
-        context = extract_text_from_pptx(file)
-    elif ext == "xlsx":
-        context = extract_text_from_xlsx(file)
-    else:
-        return "Unsupported file format."
-
-    if not context.strip():
-        return "No text found in the document."
-
-    try:
-        result = qa_model({"question": question, "context": context})
-        return result["answer"]
-    except Exception as e:
-        return f"Error generating answer: {e}"
-
-# === QA for Images using EasyOCR and QA model ===
-def answer_question_from_image_text(image, question):
-    img_text = extract_text_from_image(image)
-    if not img_text.strip():
-        return "No readable text found in the image."
-    try:
-        result = qa_model({"question": question, "context": img_text})
-        return result["answer"]
-    except Exception as e:
-        return f"Error generating answer: {e}"
 
-# === QA for Images using ViLT (Visual QA Model) ===
-def answer_question_from_image_visual(image, question):
-    if image is None or not question.strip():
-        return "Please upload an image and ask a question."
-    inputs = vqa_processor(image, question, return_tensors="pt")
-    with torch.no_grad():
-        outputs = vqa_model(**inputs)
-    predicted_id = outputs.logits.argmax(-1).item()
-    return vqa_model.config.id2label[predicted_id]
-
-# === Gradio Interfaces ===
-with gr.Blocks() as doc_interface:
-    gr.Markdown("## 📄 Document Question Answering")
-    file_input = gr.File(label="Upload DOCX, PPTX, XLSX, or PDF")
-    question_input = gr.Textbox(label="Ask a Question")
-    answer_output = gr.Textbox(label="Answer")
-    file_submit = gr.Button("Get Answer")
-    file_submit.click(fn=answer_question_from_doc, inputs=[file_input, question_input], outputs=answer_output)
-
-with gr.Blocks() as image_interface:
-    gr.Markdown("## 🖼️ Image Question Answering (OCR + VQA)")
-    with gr.Tabs():
-        with gr.TabItem("OCR-based Image QA"):
-            image_input = gr.Image(label="Upload Image")
-            img_question_input = gr.Textbox(label="Ask a Question")
-            img_answer_output = gr.Textbox(label="Answer")
-            gr.Button("Get Answer").click(fn=answer_question_from_image_text, inputs=[image_input, img_question_input], outputs=img_answer_output)
-        with gr.TabItem("Visual QA (ViLT)"):
-            image_input_vqa = gr.Image(label="Upload Image")
-            vqa_question_input = gr.Textbox(label="Ask a Question")
-            vqa_answer_output = gr.Textbox(label="Answer")
-            gr.Button("Get Answer").click(fn=answer_question_from_image_visual, inputs=[image_input_vqa, vqa_question_input], outputs=vqa_answer_output)
-
-# === Mount Gradio on FastAPI ===
-demo = gr.TabbedInterface([doc_interface, image_interface], ["Document QA", "Image QA"])
-app = gr.mount_gradio_app(app, demo, path="/")
-
-@app.get("/")
-def root():
-    return RedirectResponse(url="/")