Docstrings for cleaner code

app.py

@@ -7,7 +7,7 @@ import io
 
 st.set_page_config(page_title="Docurizzer", layout="centered")
 st.title("📄 Docurizzer")
-st.write("Summarize text, images, or PDFs with AI")
+st.write("Intelligent document summarization tool")
 
 st.sidebar.header("Summarization Settings")
 min_len = st.sidebar.slider("Min Length", min_value=10, max_value=100, value=40, step=10)
@@ -22,47 +22,48 @@ def load_model():
 tokenizer, model = load_model()
 
 def extract_text_from_image(image):
-    """Extract text from image using OCR"""
-    return pytesseract.image_to_string(image)
+    try:
+        return pytesseract.image_to_string(image)
+    except Exception as e:
+        st.error(f"Error extracting text from image: {str(e)}")
+        return ""
 
 def extract_text_from_pdf(pdf_file):
-    """Extract text from PDF file"""
     text = ""
-    with pdfplumber.open(pdf_file) as pdf:
-        for page in pdf.pages:
-            page_text = page.extract_text()
-            if page_text:
-                text += page_text + "\n"
-    return text
+    try:
+        with pdfplumber.open(pdf_file) as pdf:
+            for page in pdf.pages:
+                page_text = page.extract_text()
+                if page_text:
+                    text += page_text + "\n"
+        return text
+    except Exception as e:
+        st.error(f"Error extracting text from PDF: {str(e)}")
+        return ""
 
-def summarize_text(text, min_Len, max_Len):
-    """Summarize the given text"""
+def summarize_text(text, min_len, max_len):
     if not text.strip():
         return None
     input_text = "summarize: " + text[:4000]
     inputs = tokenizer(input_text, return_tensors="pt", max_length=512, truncation=True)
     input_token_count = inputs.input_ids.shape[1]
     
-    # For very short inputs, just return the original text
     if input_token_count < 15:
         return text.strip()
     
-    # Cap lengths to avoid repetition - max should not exceed input length
-    effective_max = min(max_Len, max(int(input_token_count * 0.6), 20))
-    effective_min = 5  # Minimum 5 tokens for a summary
+    effective_max = min(max_len, max(int(input_token_count * 0.6), 20))
+    effective_min = 5
     
-    # Ensure min < max
     if effective_min >= effective_max:
         effective_min = max(1, effective_max - 5)
     
-    # Use simpler generation for short inputs
     if input_token_count < 50:
         summary_ids = model.generate(
             inputs.input_ids, 
             max_length=effective_max, 
             min_length=effective_min,
-            do_sample=False,  # Deterministic
-            num_beams=1,  # No beam search for short inputs
+            do_sample=False,
+            num_beams=1,
             early_stopping=True
         )
     else:
@@ -152,4 +153,4 @@ with tab3:
                 st.warning("No text could be extracted from the PDF. The PDF might be image-based or empty.")
 
 st.divider()
-st.caption("Powered by T5 AI Model | Built with Streamlit | v1.1")
+st.caption("Built with Streamlit | v1.2")