Update app.py

app.py

@@ -103,83 +103,80 @@ async def get_docs(request: Request):
 from fastapi import FastAPI, Form, File, UploadFile
 from fastapi.responses import RedirectResponse
 from fastapi.staticfiles import StaticFiles
-from pydantic import BaseModel
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.templating import Jinja2Templates
+from starlette.requests import Request
 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
-from fastapi.middleware.cors import CORSMiddleware
 
-# Initialize the app
+# Initialize the FastAPI app
 app = FastAPI()
 
-# Enable CORS (for frontend interaction)
+# Enable CORS for frontend communication
 app.add_middleware(
     CORSMiddleware,
-    allow_origins=["*"],  # Adjust this for security
+    allow_origins=["*"],
     allow_credentials=True,
     allow_methods=["*"],
     allow_headers=["*"],
 )
 
-# Mount the static directory to serve HTML, CSS, JS files
+# Mount static files (if you have HTML/CSS/JS)
 app.mount("/static", StaticFiles(directory="static"), name="static")
 
-# Initialize transformers pipelines
+# Initialize transformer 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
+# Initialize OCR
 reader = easyocr.Reader(['en'])
 
-# Define a template for rendering HTML
+# Define templates for HTML pages
 templates = Jinja2Templates(directory="templates")
 
-# Ensure temp_files directory exists
+# Ensure the temp directory exists
 temp_dir = "temp_files"
 os.makedirs(temp_dir, exist_ok=True)
 
-# Function to process PDFs
+# Function to extract text from PDF
 def extract_pdf_text(file_path: str):
     with pdfplumber.open(file_path) as pdf:
-        text = ""
-        for page in pdf.pages:
-            extracted = page.extract_text()
-            if extracted:
-                text += extracted + "\n"
-    return text
+        return "\n".join([page.extract_text() or "" for page in pdf.pages])
 
-# Function to process DOCX files
+# Function to extract text from DOCX
 def extract_docx_text(file_path: str):
     doc = docx.Document(file_path)
     return "\n".join([para.text for para in doc.paragraphs])
 
-# Function to process PPTX files
+# Function to extract text from PPTX
 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")])
 
-# Function to extract text from images using OCR
+# Function to extract text from images
 def extract_text_from_image(image: Image):
     return pytesseract.image_to_string(image)
 
-# Home route
+# Redirect home to custom frontend page
 @app.get("/")
 def home():
-    return RedirectResponse(url="/docs")
+    return RedirectResponse(url="/app-ui")
 
-# Function to answer questions based on document content
-@app.post("/docs")
+# 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})
+
+# New endpoint for document-based question answering
+@app.post("/qa-docs")  # 🚨 Changed from `/docs` to `/qa-docs`
 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)
@@ -187,11 +184,11 @@ async def question_answering_doc(question: str = Form(...), file: UploadFile = F
     with open(file_path, "wb") as f:
         f.write(await file.read())
 
-    if file_ext in ["pdf"]:
+    if file_ext == "pdf":
         text = extract_pdf_text(file_path)
-    elif file_ext in ["docx"]:
+    elif file_ext == "docx":
         text = extract_docx_text(file_path)
-    elif file_ext in ["pptx"]:
+    elif file_ext == "pptx":
         text = extract_pptx_text(file_path)
     else:
         return {"error": "Unsupported file format"}
@@ -199,8 +196,8 @@ async def question_answering_doc(question: str = Form(...), file: UploadFile = F
     qa_result = qa_pipeline(question=question, context=text)
     return {"answer": qa_result['answer']}
 
-# Function to answer questions based on images
-@app.post("/images")
+# New endpoint for image-based question answering
+@app.post("/qa-images")  # 🚨 Changed from `/images` to `/qa-images`
 async def question_answering_image(question: str = Form(...), image_file: UploadFile = File(...)):
     image = Image.open(BytesIO(await image_file.read()))
 
@@ -211,8 +208,3 @@ async def question_answering_image(question: str = Form(...), image_file: Upload
     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})