Update app.py

app.py

@@ -2,7 +2,7 @@ import streamlit as st
 from transformers import pipeline
 import pdfplumber
 from PIL import Image
-import pytesseract
+import easyocr
 from langdetect import detect
 
 # Initialize Models
@@ -27,11 +27,12 @@ def extract_text_from_pdf(pdf_file):
             text += page.extract_text()
     return text.strip()
 
-# Extract text from Image
+# Extract text from Image using EasyOCR
 def extract_text_from_image(image_file):
+    reader = easyocr.Reader(['en'])  # Add more languages if needed
     image = Image.open(image_file)
-    text = pytesseract.image_to_string(image)
-    return text.strip()
+    result = reader.readtext(image, detail=0)  # `detail=0` returns only the text
+    return " ".join(result).strip()
 
 # Check if content is a lab report
 def is_lab_report(text, model):