the paid version of chatgbt of the app

app.py

@@ -100,129 +100,78 @@ async def question_answering_image(question: str = Form(...), image_file: Upload
 async def get_docs(request: Request):
     return templates.TemplateResponse("index.html", {"request": request})
 """
-from fastapi import FastAPI, Form, File, UploadFile, HTTPException
-from fastapi.responses import RedirectResponse
-from fastapi.staticfiles import StaticFiles
-from pydantic import BaseModel
+from fastapi import FastAPI
+import gradio as gr
 from transformers import pipeline
-import os
+import pdfplumber, docx
+from pptx import Presentation
 from PIL import Image
-import io
-import pdfplumber
-import docx
 import pytesseract
-from io import BytesIO
-import fitz  # PyMuPDF
+import fitz
 import easyocr
-from fastapi.templating import Jinja2Templates
-from starlette.requests import Request
+import os
 
-# Initialize the app
+# Initialize FastAPI app
 app = FastAPI()
 
-# Mount the static directory to serve HTML, CSS, JS files
-app.mount("/static", StaticFiles(directory="static"), name="static")
-
-# Define a template for rendering HTML
-templates = Jinja2Templates(directory="templates")
-
-# Initialize transformers pipelines
+# Load models
 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'])
 
-# Maximum allowed file size in bytes (e.g., 5 MB)
-MAX_FILE_SIZE = 5 * 1024 * 1024  # 5 MB
+# File parsing
+def extract_text_from_pdf(file):
+    with pdfplumber.open(file) as pdf:
+        return "\n".join(page.extract_text() for page in pdf.pages if page.extract_text())
 
-# 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
+def extract_text_from_docx(file):
+    doc = docx.Document(file)
+    return "\n".join(para.text for para in doc.paragraphs)
 
-# 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
+def extract_text_from_pptx(file):
+    prs = Presentation(file)
+    return "\n".join(shape.text for slide in prs.slides for shape in slide.shapes if hasattr(shape, "text"))
 
-# Function to extract text from images using OCR
-def extract_text_from_image(image: Image):
+def extract_text_from_image(file):
+    image = Image.open(file)
     return pytesseract.image_to_string(image)
 
-# Home route - Render the index page
-@app.get("/")
-async def home(request: Request):
-    return templates.TemplateResponse("index.html", {"request": request})
-
-# Function to answer questions based on document content
-@app.post("/question-answering-doc")
-async def question_answering_doc(request: Request, question: str = Form(...), file: UploadFile = File(...)):
-    # Validate file size
-    if file.spool_max_size > MAX_FILE_SIZE:
-        raise HTTPException(status_code=400, detail=f"File size exceeds the {MAX_FILE_SIZE / (1024 * 1024)} MB limit.")
-
-    try:
-        # Read the file content into memory
-        file_content = await file.read()
-
-        # Extract text based on the file type
-        if file.filename.endswith(".pdf"):
-            file_path = "/tmp/tempfile.pdf"
-            with open(file_path, "wb") as f:
-                f.write(file_content)
-            text = extract_pdf_text(file_path)
-            os.remove(file_path)
-        elif file.filename.endswith(".docx"):
-            file_path = "/tmp/tempfile.docx"
-            with open(file_path, "wb") as f:
-                f.write(file_content)
-            text = extract_docx_text(file_path)
-            os.remove(file_path)
-        elif file.filename.endswith(".pptx"):
-            file_path = "/tmp/tempfile.pptx"
-            with open(file_path, "wb") as f:
-                f.write(file_content)
-            text = extract_pptx_text(file_path)
-            os.remove(file_path)
-        else:
-            raise HTTPException(status_code=400, detail="Unsupported file format")
-    except Exception as e:
-        raise HTTPException(status_code=500, detail=f"An error occurred while processing the file: {str(e)}")
-
-    qa_result = qa_pipeline(question=question, context=text)
-    
-    return templates.TemplateResponse("index.html", {"request": request, "answer": qa_result['answer']})
-
-# Function to answer questions based on images
-@app.post("/question-answering-image")
-async def question_answering_image(request: Request, question: str = Form(...), image_file: UploadFile = File(...)):
-    # Validate file size
-    if image_file.spool_max_size > MAX_FILE_SIZE:
-        raise HTTPException(status_code=400, detail=f"File size exceeds the {MAX_FILE_SIZE / (1024 * 1024)} MB limit.")
-
-    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})
+# Main QA logic
+def answer_question(question, file):
+    file_ext = os.path.splitext(file.name)[-1].lower()
     
-    # Clean up the temporary image file
-    del image
-
-    return templates.TemplateResponse("index.html", {"request": request, "answer": image_qa_result[0]['answer'], "image_text": image_text})
+    if file_ext == ".pdf":
+        context = extract_text_from_pdf(file)
+    elif file_ext == ".docx":
+        context = extract_text_from_docx(file)
+    elif file_ext == ".pptx":
+        context = extract_text_from_pptx(file)
+    elif file_ext in [".png", ".jpg", ".jpeg", ".bmp"]:
+        context = extract_text_from_image(file)
+    else:
+        return "❌ Unsupported file format."
+
+    if not context.strip():
+        return "⚠️ No readable text found in the document."
+
+    result = qa_pipeline(question=question, context=context)
+    return result["answer"]
+
+# Gradio interface
+gr_interface = gr.Interface(
+    fn=answer_question,
+    inputs=[
+        gr.Textbox(label="Ask a question"),
+        gr.File(label="Upload a document or image")
+    ],
+    outputs=gr.Textbox(label="Answer"),
+    title="AI Question Answering (Text & Image)",
+    description="Upload a file (PDF, DOCX, PPTX, Image) and ask a question. Get instant answers from document content.",
+)
+
+# Mount Gradio app in FastAPI
+@app.get("/")
+def redirect_root():
+    return {"message": "Visit /gradio for the interface."}
 
-# Serve the application in Hugging Face space
-@app.get("/question-answering-doc")
-async def get_docs(request: Request):
-    return templates.TemplateResponse("index.html", {"request": request})
+app = gr.mount_gradio_app(app, gr_interface, path="/gradio")