gpt_academic text mask imp

core_functional.py

@@ -3,6 +3,7 @@
 # 'stop' 颜色对应 theme.py 中的 color_er
 import importlib
 from toolbox import clear_line_break
+from toolbox import build_gpt_academic_masked_string
 from textwrap import dedent
 
 def get_core_functions():
@@ -32,12 +33,12 @@ def get_core_functions():
             "Prefix":   r"",
             # 后缀，会被加在你的输入之后。例如，配合前缀可以把你的输入内容用引号圈起来
             "Suffix":
-                dedent("\n"+r'''
+                dedent("\n"+f'''
                     ==============================
                     使用mermaid flowchart对以上文本进行总结，概括上述段落的内容以及内在逻辑关系，例如：
 
                     以下是对以上文本的总结，以mermaid flowchart的形式展示：
-                    ```mermaid
+                    ```{build_gpt_academic_masked_string(text_show_llm="mermaid", text_show_render="")}
                     flowchart LR
                         A["节点名1"] --> B("节点名2")
                         B --> C{"节点名3"}

request_llms/bridge_all.py

@@ -11,7 +11,7 @@
 import tiktoken, copy
 from functools import lru_cache
 from concurrent.futures import ThreadPoolExecutor
-from toolbox import get_conf, trimmed_format_exc
+from toolbox import get_conf, trimmed_format_exc, apply_gpt_academic_string_mask
 
 from .bridge_chatgpt import predict_no_ui_long_connection as chatgpt_noui
 from .bridge_chatgpt import predict as chatgpt_ui
@@ -668,6 +668,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history, sys_prompt, obser
     """
     import threading, time, copy
 
+    inputs = apply_gpt_academic_string_mask(inputs, mode="show_llm")
     model = llm_kwargs['llm_model']
     n_model = 1
     if '&' not in model:
@@ -741,6 +742,7 @@ def predict(inputs, llm_kwargs, *args, **kwargs):
     additional_fn代表点击的哪个按钮，按钮见functional.py
     """
 
+    inputs = apply_gpt_academic_string_mask(inputs, mode="show_llm")
     method = model_info[llm_kwargs['llm_model']]["fn_with_ui"]  # 如果这里报错，检查config中的AVAIL_LLM_MODELS选项
     yield from method(inputs, llm_kwargs, *args, **kwargs)