Update app.py

app.py

@@ -51,7 +51,7 @@ def clean_extracted_text(text):
 
 # Polish the text using a model
 def polish_text_with_ai(cleaned_text):
-    prompt = f"Remove unwanted spaces between and inside words to join incomplete words, creating a meaningful sentence in either Hindi, English, or Hinglish without altering any words from the given extracted text. Then, return the corrected text with adjusted spaces, keeping it as close to the original as possible."
+    prompt = f"Remove unwanted spaces between and inside words to join incomplete words, creating a meaningful sentence in either Hindi, English, or Hinglish without altering any words from the given extracted text. Then, return the corrected text with adjusted spaces, keeping it as close to the original as possible. Extracted Text : {cleaned_text}"
     client = Groq(api_key="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")
     chat_completion = client.chat.completions.create(
         messages=[
@@ -172,18 +172,19 @@ if uploaded_file:
                     text_list = re.findall(r"text='(.*?)'", str(predictions[0]))
                     extracted_text = ' '.join(text_list)
 
-                # Clean and polish extracted text
-                cleaned_text = clean_extracted_text(extracted_text)
+        # Clean and polish extracted text
+        cleaned_text = clean_extracted_text(extracted_text)
                 polished_text = polish_text_with_ai(cleaned_text) if model_choice in ["GOT_CPU", "GOT_GPU"] else cleaned_text
 
-                # Save results to JSON file
-                result_data = {"polished_text": polished_text}
-                with open(result_path, 'w') as f:
-                    json.dump(result_data, f)
+        # Save results to JSON file
+        result_data = {"extracted_text":extracted_text,"cleaner_text":cleaned_text,"polished_text": polished_text}
+        with open(result_path, 'w') as f:
+            json.dump(result_data, f)
 
         # Display extracted text
         st.subheader("Extracted Text (Cleaned & Polished)")
-        st.markdown(extracted_text, unsafe_allow_html=True)
+        st.markdown(cleaned_text, unsafe_allow_html=True)
+        st.markdown(polished_text, unsafe_allow_html=True)
 
         # Search functionality
         def update_search():