Update app.py

app.py

@@ -103,108 +103,101 @@ async def get_docs(request: Request):
 from fastapi import FastAPI, Form, File, UploadFile
 from fastapi.responses import RedirectResponse
 from fastapi.staticfiles import StaticFiles
-from fastapi.middleware.cors import CORSMiddleware
-from fastapi.templating import Jinja2Templates
-from starlette.requests import Request
+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 FastAPI app
+# Initialize the app
 app = FastAPI()
 
-# Enable CORS for frontend communication
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=["*"],
-    allow_credentials=True,
-    allow_methods=["*"],
-    allow_headers=["*"],
-)
-
-# Mount static files (if you have HTML/CSS/JS)
+# Mount the static directory to serve HTML, CSS, JS files
 app.mount("/static", StaticFiles(directory="static"), name="static")
 
-# Initialize transformer models
+# 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 OCR
+# Initialize EasyOCR for image-based text extraction
 reader = easyocr.Reader(['en'])
 
-# Define templates for HTML pages
+# Define a template for rendering HTML
 templates = Jinja2Templates(directory="templates")
 
-# Ensure the temp directory exists
+# Ensure temp_files directory exists
 temp_dir = "temp_files"
 os.makedirs(temp_dir, exist_ok=True)
 
-# Function to extract text from PDF
+# Function to process PDFs
 def extract_pdf_text(file_path: str):
     with pdfplumber.open(file_path) as pdf:
-        return "\n".join([page.extract_text() or "" for page in pdf.pages])
+        text = ""
+        for page in pdf.pages:
+            text += page.extract_text()
+    return text
 
-# Function to extract text from DOCX
+# Function to process DOCX files
 def extract_docx_text(file_path: str):
     doc = docx.Document(file_path)
-    return "\n".join([para.text for para in doc.paragraphs])
+    text = "\n".join([para.text for para in doc.paragraphs])
+    return text
 
-# Function to extract text from PPTX
+# Function to process PPTX files
 def extract_pptx_text(file_path: str):
     from pptx import Presentation
     prs = Presentation(file_path)
-    return "\n".join([shape.text for slide in prs.slides for shape in slide.shapes if hasattr(shape, "text")])
+    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
+# Function to extract text from images using OCR
 def extract_text_from_image(image: Image):
     return pytesseract.image_to_string(image)
 
-# Redirect home to custom frontend page
+# Home route
 @app.get("/")
 def home():
-    return RedirectResponse(url="/app-ui")
-
-# Serve HTML interface (instead of showing FastAPI docs)
-@app.get("/app-ui")
-async def get_ui(request: Request):
-    return templates.TemplateResponse("index.html", {"request": request})
+    return RedirectResponse(url="/docs")
 
-# New endpoint for document-based question answering
-@app.post("/qa-docs")  # 🚨 Changed from `/docs` to `/qa-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_ext = file.filename.split(".")[-1].lower()
     file_path = os.path.join(temp_dir, file.filename)
-
     with open(file_path, "wb") as f:
         f.write(await file.read())
 
-    if file_ext == "pdf":
+    if file.filename.endswith(".pdf"):
         text = extract_pdf_text(file_path)
-    elif file_ext == "docx":
+    elif file.filename.endswith(".docx"):
         text = extract_docx_text(file_path)
-    elif file_ext == "pptx":
+    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']}
+    return templates.TemplateResponse("index.html", {"request": Request, "answer": qa_result['answer']})
 
-# New endpoint for image-based question answering
-@app.post("/qa-images")  # 🚨 Changed from `/images` to `/qa-images`
+# 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()))
-
-    # Extract text from image using OCR
     image_text = extract_text_from_image(image)
 
-    # Get answer from the VQA model
     image_qa_result = image_qa_pipeline({"image": image, "question": question})
     
-    return {"answer": image_qa_result[0]['answer'], "image_text": image_text}
+    return templates.TemplateResponse("index.html", {"request": Request, "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})