Update document_scrapped.py

document_scrapped.py

@@ -104,7 +104,7 @@ def excel(link : str) -> str:
                       sample_df = df
             json_data = sample_df.to_json(orient='records')
             js = json.loads(json_data)
-            rs = trim_input_words(f"{js}")
+            rs = select_words_until_char_limit(f"{js}", 32000)
             return rs
         else:
             print("Failed to download file")
@@ -134,7 +134,7 @@ def csv(link : str) -> str:
 
       json_data = sample_df.to_json(orient='records')
       js = json.loads(json_data)
-      rs = trim_input_words(f"{js}")
+      rs = select_words_until_char_limit(f"{js}", 32000)
       return rs
 
   except Exception as e:
@@ -156,7 +156,7 @@ def docx(url : str) -> str:
             full_text.append(para.text)
 
         f = "\n".join(full_text)
-        n = select_words_until_char_limit(f, 30000)
+        n = select_words_until_char_limit(f, 32000)
         return n
     except Exception as e:
         print(f"An error occurred: {e}")
@@ -182,7 +182,7 @@ def pptx(url : str) -> str:
                     full_text.append(shape.text)
 
         g = "\n".join(full_text)
-        c  = select_words_until_char_limit(g, 30000)
+        c  = select_words_until_char_limit(g, 32000)
         return c
     except Exception as e:
         print(f"An error occurred: {e}")