Update app.py

app.py

@@ -1,9 +1,10 @@
-import gradio as gr
-from PIL import Image
-import pytesseract
-import re
 from typing import List
 
+import pytesseract
+from PIL import Image
+
+import gradio as gr
+
 def tesseract_ocr(filepath: str, languages: List[str]):
     image = Image.open(filepath)
     return pytesseract.image_to_string(image=image, lang=', '.join(languages))
@@ -19,31 +20,19 @@ examples = [
 
 language_choices = pytesseract.get_languages()
 
-def search_and_highlight(text, keyword):
-    highlighted_text = re.sub(f"({keyword})", r"<mark>\1</mark>", text, flags=re.IGNORECASE)
-    return highlighted_text
-
-def ocr_and_search(image, keyword):
-    if image is None:
-        return "Please upload an image."
-
-    extracted_text = perform_ocr(image)
-    
-    if keyword:
-        highlighted_text = search_and_highlight(extracted_text, keyword)
-        return highlighted_text
-    else:
-        return extracted_text
-
-iface = gr.Interface(
-    fn=ocr_and_search,  
+demo = gr.Interface(
+    fn=tesseract_ocr, 
     inputs=[
-        gr.Image(type="pil", label="Upload Image"),  
-        gr.Textbox(label="Enter keyword to search (optional)") 
-    ],
-    outputs=gr.HTML(label="Extracted and Highlighted Text"),
-    title="OCR and Keyword Search",
-    description="Upload an image for OCR processing and search for keywords in the extracted text."
+        gr.Image(type="filepath", label="Input"), 
+        gr.CheckboxGroup(language_choices, type="value", value=['eng'], label='language')
+        ],
+    outputs='text',
+    title=title,
+    description=description,
+    article=article,
+    examples=examples,
 )
 
-iface.launch()
+if __name__ == '__main__':
+    demo.launch()
+    print("Finished running")