Update app.py

app.py

@@ -1,80 +1,98 @@
-import logging
-from fastapi import FastAPI, File, UploadFile, HTTPException
-from fastapi.middleware.cors import CORSMiddleware
+import gradio as gr
+import tensorflow as tf
+import requests
+import os
+import numpy as np
+import pandas as pd
+import huggingface_hub
+from huggingface_hub import Repository
+from datetime import datetime
+import scipy.ndimage.interpolation as inter
+import datasets
+from datasets import load_dataset, Image
+from PIL import Image
 from paddleocr import PaddleOCR
 from doctr.io import DocumentFile
 from doctr.models import ocr_predictor
-import numpy as np
-from PIL import Image
-import io
-
-# Set up logging
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__name__)
 
-app = FastAPI()
 
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=["*"],
-    allow_credentials=True,
-    allow_methods=["*"],
-    allow_headers=["*"],
-)
 
-# Initialize models once at startup
 ocr_model = ocr_predictor(pretrained=True)
-paddle_ocr = PaddleOCR(lang='en', use_angle_cls=True)
 
+
+
+"""
+Perform OCR with doctr
+"""
 def ocr_with_doctr(file):
     text_output = ''
-    try:
-        logger.info("Processing PDF with Doctr...")
-        doc = DocumentFile.from_pdf(file)
-        result = ocr_model(doc)
-        for page in result.pages:
-            for block in page.blocks:
-                for line in block.lines:
-                    text_output += " ".join([word.value for word in line.words]) + "\n"
-    except Exception as e:
-        logger.error(f"Error processing PDF: {e}")
-        raise HTTPException(status_code=500, detail=f"Error processing PDF: {e}")
+    
+    # Load the document
+    doc = DocumentFile.from_pdf(file)
+    
+    # Perform OCR
+    result = ocr_model(doc)
+    
+    # Extract text from OCR result
+    for page in result.pages:
+        for block in page.blocks:
+            for line in block.lines:
+                text_output += " ".join([word.value for word in line.words]) + "\n"
+    
     return text_output
 
+"""
+Paddle OCR
+"""
 def ocr_with_paddle(img):
     finaltext = ''
-    try:
-        logger.info("Processing image with PaddleOCR...")
-        result = paddle_ocr.ocr(img)
-        for i in range(len(result[0])):
-            text = result[0][i][1][0]
-            finaltext += ' ' + text
-    except Exception as e:
-        logger.error(f"Error processing image: {e}")
-        raise HTTPException(status_code=500, detail=f"Error processing image: {e}")
+    ocr = PaddleOCR(lang='en', use_angle_cls=True)
+    # img_path = 'exp.jpeg'
+    result = ocr.ocr(img)
+    
+    for i in range(len(result[0])):
+        text = result[0][i][1][0]
+        finaltext += ' '+ text
     return finaltext
 
-@app.post("/ocr/")
-async def perform_ocr(file: UploadFile = File(...)):
-    try:
-        logger.info(f"Received file: {file.filename}")
-        file_bytes = await file.read()
-        
-        if file.filename.endswith('.pdf'):
-            logger.info("Detected PDF file")
-            text_output = ocr_with_doctr(io.BytesIO(file_bytes))
-        else:
-            logger.info("Detected image file")
-            img = np.array(Image.open(io.BytesIO(file_bytes)))
-            text_output = ocr_with_paddle(img)
-        
-        logger.info("OCR completed successfully")
-        return {"ocr_text": text_output}
-
-    except Exception as e:
-        logger.error(f"Internal server error: {e}")
-        raise HTTPException(status_code=500, detail=f"Internal server error: {e}")
-
-@app.get("/test/")
-async def test_call():
-    return {"message": "Hi. I'm running"}
+def generate_ocr(Method, file):
+    text_output = ''
+    if isinstance(file, bytes):  # Handle file uploaded as bytes
+        file = io.BytesIO(file)
+
+    if file.name.endswith('.pdf'):
+        # Perform OCR on the PDF using doctr
+        text_output = ocr_with_doctr(file)
+
+    else:
+        # Handle image file
+        img_np = np.array(Image.open(file))
+        text_output = generate_text_from_image(Method, img_np)
+    
+    return text_output
+
+def generate_text_from_image(Method, img):
+    text_output = ''
+    if Method == 'PaddleOCR':
+        text_output = ocr_with_paddle(img)
+    return text_output
+
+
+import gradio as gr
+
+image_or_pdf = gr.File(label="Upload an image or PDF")
+method = gr.Radio(["PaddleOCR"], value="PaddleOCR")
+output = gr.Textbox(label="Output")
+
+demo = gr.Interface(
+    generate_ocr,
+    [method, image_or_pdf],
+    output,
+    title="Optical Character Recognition",
+    css=".gradio-container {background-color: lightgray} #radio_div {background-color: #FFD8B4; font-size: 40px;}",
+    article="""<p style='text-align: center;'>Feel free to give us your thoughts on this demo and please contact us at 
+                <a href="mailto:[email protected]" target="_blank">[email protected]</a> 
+                <p style='text-align: center;'>Developed by: <a href="https://www.pragnakalp.com" target="_blank">Pragnakalp Techlabs</a></p>"""
+)
+
+demo.launch(show_error=True)