Update app.py

app.py

@@ -1,104 +1,4 @@
-"""from fastapi import FastAPI, Form, File, UploadFile
-from fastapi.responses import RedirectResponse
-from fastapi.staticfiles import StaticFiles
-from pydantic import BaseModel
-from transformers import pipeline
-import os
-from PIL import Image
-import io
-import pdfplumber
-import docx
-import openpyxl
-import pytesseract
-from io import BytesIO
-import fitz  # PyMuPDF
-import easyocr
-from fastapi.templating import Jinja2Templates
-from starlette.requests import Request
-
-# Initialize the app
-app = FastAPI()
-
-# Mount the static directory to serve HTML, CSS, JS files
-app.mount("/static", StaticFiles(directory="static"), name="static")
-
-# Initialize transformers pipelines
-qa_pipeline = pipeline("question-answering", model="microsoft/phi-2", tokenizer="microsoft/phi-2")
-image_qa_pipeline = pipeline("vqa", model="Salesforce/blip-vqa-base")
-
-# Initialize EasyOCR for image-based text extraction
-reader = easyocr.Reader(['en'])
-
-# Define a template for rendering HTML
-templates = Jinja2Templates(directory="templates")
 
-# Ensure temp_files directory exists
-temp_dir = "temp_files"
-os.makedirs(temp_dir, exist_ok=True)
-
-# Function to process PDFs
-def extract_pdf_text(file_path: str):
-    with pdfplumber.open(file_path) as pdf:
-        text = ""
-        for page in pdf.pages:
-            text += page.extract_text()
-    return text
-
-# Function to process DOCX files
-def extract_docx_text(file_path: str):
-    doc = docx.Document(file_path)
-    text = "\n".join([para.text for para in doc.paragraphs])
-    return text
-
-# Function to process PPTX files
-def extract_pptx_text(file_path: str):
-    from pptx import Presentation
-    prs = Presentation(file_path)
-    text = "\n".join([shape.text for slide in prs.slides for shape in slide.shapes if hasattr(shape, "text")])
-    return text
-
-# Function to extract text from images using OCR
-def extract_text_from_image(image: Image):
-    return pytesseract.image_to_string(image)
-
-# Home route
-@app.get("/")
-def home():
-    return RedirectResponse(url="/docs")
-
-# Function to answer questions based on document content
-@app.post("/question-answering-doc")
-async def question_answering_doc(question: str = Form(...), file: UploadFile = File(...)):
-    file_path = os.path.join(temp_dir, file.filename)
-    with open(file_path, "wb") as f:
-        f.write(await file.read())
-
-    if file.filename.endswith(".pdf"):
-        text = extract_pdf_text(file_path)
-    elif file.filename.endswith(".docx"):
-        text = extract_docx_text(file_path)
-    elif file.filename.endswith(".pptx"):
-        text = extract_pptx_text(file_path)
-    else:
-        return {"error": "Unsupported file format"}
-
-    qa_result = qa_pipeline(question=question, context=text)
-    return {"answer": qa_result['answer']}
-
-# Function to answer questions based on images
-@app.post("/question-answering-image")
-async def question_answering_image(question: str = Form(...), image_file: UploadFile = File(...)):
-    image = Image.open(BytesIO(await image_file.read()))
-    image_text = extract_text_from_image(image)
-
-    image_qa_result = image_qa_pipeline({"image": image, "question": question})
-    
-    return {"answer": image_qa_result[0]['answer'], "image_text": image_text}
-
-# Serve the application in Hugging Face space
-@app.get("/docs")
-async def get_docs(request: Request):
-    return templates.TemplateResponse("index.html", {"request": request})
 """
 from fastapi import FastAPI
 from fastapi.responses import RedirectResponse
@@ -165,6 +65,129 @@ img_interface = gr.Interface(
 demo = gr.TabbedInterface([doc_interface, img_interface], ["Document QA", "Image QA"])
 app = gr.mount_gradio_app(app, demo, path="/")
 
+@app.get("/")
+def root():
+    return RedirectResponse(url="/")
+"""
+from fastapi import FastAPI
+from fastapi.responses import RedirectResponse
+import gradio as gr
+import pytesseract
+from PIL import Image
+import fitz  # PyMuPDF
+import pdfplumber
+import easyocr
+import docx
+import openpyxl
+from pptx import Presentation
+from transformers import pipeline
+from deep_translator import GoogleTranslator
+import json
+import os
+
+app = FastAPI()
+
+qa_pipeline = pipeline("question-answering", model="distilbert-base-uncased-distilled-squad")
+reader = easyocr.Reader(['en'])
+
+# Utility functions
+
+def extract_text_from_pdf(pdf_file):
+    with pdfplumber.open(pdf_file) as pdf:
+        return "\n".join([page.extract_text() for page in pdf.pages if page.extract_text()])
+
+def extract_text_from_docx(docx_file):
+    doc = docx.Document(docx_file)
+    return "\n".join([para.text for para in doc.paragraphs])
+
+def extract_text_from_pptx(pptx_file):
+    prs = Presentation(pptx_file)
+    text = []
+    for slide in prs.slides:
+        for shape in slide.shapes:
+            if hasattr(shape, "text"):
+                text.append(shape.text)
+    return "\n".join(text)
+
+def extract_text_from_xlsx(xlsx_file):
+    wb = openpyxl.load_workbook(xlsx_file)
+    text = []
+    for sheet in wb.worksheets:
+        for row in sheet.iter_rows():
+            text.extend([str(cell.value) for cell in row if cell.value is not None])
+    return "\n".join(text)
+
+def extract_text(file):
+    ext = os.path.splitext(file.name)[1].lower()
+    if ext == ".pdf":
+        return extract_text_from_pdf(file)
+    elif ext == ".docx":
+        return extract_text_from_docx(file)
+    elif ext == ".pptx":
+        return extract_text_from_pptx(file)
+    elif ext == ".xlsx":
+        return extract_text_from_xlsx(file)
+    else:
+        return "Unsupported file type"
+
+def answer_question_from_doc(file, question, translate_to="en"):
+    context = extract_text(file)
+    result = qa_pipeline(question=question, context=context)
+    translated = GoogleTranslator(source='auto', target=translate_to).translate(result["answer"])
+    return {
+        "answer": translated,
+        "score": result["score"],
+        "original": result["answer"]
+    }
+
+def answer_question_from_image(image, question, translate_to="en"):
+    img_text = pytesseract.image_to_string(image)
+    if not img_text.strip():
+        img_text = "\n".join([line[1] for line in reader.readtext(image)])
+    result = qa_pipeline(question=question, context=img_text)
+    translated = GoogleTranslator(source='auto', target=translate_to).translate(result["answer"])
+    return {
+        "answer": translated,
+        "score": result["score"],
+        "original": result["answer"]
+    }
+
+# Gradio Interfaces
+
+doc_interface = gr.Interface(
+    fn=answer_question_from_doc,
+    inputs=[
+        gr.File(label="Upload Document (PDF, DOCX, PPTX, XLSX)"),
+        gr.Textbox(label="Ask a Question"),
+        gr.Textbox(label="Translate Answer To (e.g., en, fr, ar)", value="en")
+    ],
+    outputs=[
+        gr.Textbox(label="Translated Answer"),
+        gr.Number(label="Confidence Score"),
+        gr.Textbox(label="Original Answer")
+    ],
+    title="📄 Document QA + Translation + Export"
+)
+
+img_interface = gr.Interface(
+    fn=answer_question_from_image,
+    inputs=[
+        gr.Image(label="Upload Image"),
+        gr.Textbox(label="Ask a Question"),
+        gr.Textbox(label="Translate Answer To (e.g., en, fr, ar)", value="en")
+    ],
+    outputs=[
+        gr.Textbox(label="Translated Answer"),
+        gr.Number(label="Confidence Score"),
+        gr.Textbox(label="Original Answer")
+    ],
+    title="🖼️ Image QA + OCR + Translation + Export"
+)
+
+# Combine interfaces
+demo = gr.TabbedInterface([doc_interface, img_interface], ["Document QA", "Image QA"])
+app = gr.mount_gradio_app(app, demo, path="/")
+
 @app.get("/")
 def root():
     return RedirectResponse(url="/")