Update app.py

app.py

@@ -224,8 +224,8 @@ def entity_extractor_by_llm(query, llm, show_process = False, max_length = 512):
         delta = chunk['choices'][0]['delta']
         if "content" in delta:
             out_text += delta['content']
-            from IPython.display import clear_output
-            clear_output(wait=True)
+            #from IPython.display import clear_output
+            #clear_output(wait=True)
             if show_process:
                 print(out_text)
             if len(out_text) >= max_length:
@@ -284,8 +284,8 @@ def query_content_ask_func(question, content_list,
             delta = chunk['choices'][0]['delta']
             if "content" in delta:
                 out_text += delta['content']
-                from IPython.display import clear_output
-                clear_output(wait=True)
+                #from IPython.display import clear_output
+                #clear_output(wait=True)
                 if show_process:
                     print(out_text)
                 if len(out_text) >= max_length:
@@ -388,7 +388,7 @@ def mistral_predict(prompt, llm, show_process = True, max_length = 512):
                 ],
                 stream=True
                 )
-    from IPython.display import clear_output
+    #from IPython.display import clear_output
     out_text = ""
     for chunk in out:
         delta = chunk['choices'][0]['delta']
@@ -398,8 +398,8 @@ def mistral_predict(prompt, llm, show_process = True, max_length = 512):
                 print(out_text)
             if len(out_text) >= max_length:
                 break
-            clear_output(wait=True)
-    clear_output(wait=True)
+            #clear_output(wait=True)
+    #clear_output(wait=True)
     return out_text
 
 def run_all(query, docsearch_bge_loaded, bge_book_embeddings, book_df,