Update app.py

app.py

@@ -25,6 +25,7 @@ def findpdftype(file):
         ocr_df[float_cols] = ocr_df[float_cols].round(0).astype(int)
         ocr_df = ocr_df.replace(r'^\s*$', np.nan, regex=True)
         words = ' '.join([word for word in ocr_df.text if str(word) != 'nan'])
+        words = words[:1000]
         results.append(words)
     results=pipe(results)
     return pd.DataFrame(results).label.value_counts().sort_values(ascending=False).index[0]