Update app.py

app.py

@@ -36,7 +36,7 @@ def preprocess_text(text):
     return ' '.join(tokens)
 
 # Initialize text processing components
-def extract_keywords(text, num_keywords=10, scores=True):
+def extract_keywords(text, num_keywords=10, scores=True, min_length=1):
     # Preprocess text
     processed_text = remove_stopwords(text.lower())
     tokens = simple_preprocess(processed_text, deacc=True)
@@ -52,17 +52,27 @@ def extract_keywords(text, num_keywords=10, scores=True):
     # Sort by scores
     sorted_keywords = sorted(tfidf_corpus, key=lambda x: x[1], reverse=True)
     
-    # Get top keywords
+    # Get top keywords and filter by length
     results = []
-    for word_id, score in sorted_keywords[:num_keywords]:
+    for word_id, score in sorted_keywords:
         word = dictionary[word_id]
-        if scores:
-            results.append(f"• {word:<30} (score: {score:.4f})")
-        else:
-            results.append(f"• {word}")
+        if len(word.split()) >= min_length:
+            if scores:
+                results.append(f"• {word:<30} (score: {score:.4f})")
+            else:
+                results.append(f"• {word}")
+        if len(results) >= num_keywords:
+            break
             
     return "\n".join(results) if results else "No keywords found."
 
+# Update the interface click handler to match the function parameters
+extract_btn.click(
+    extract_keywords,
+    inputs=[input_text, num_keywords, show_scores, min_length],
+    outputs=[output_text]
+)
+
 def load_example(example_name):
     return EXAMPLES.get(example_name, "")