support chatglm3

config.py

@@ -90,11 +90,15 @@
 AVAIL_LLM_MODELS = ["gpt-3.5-turbo-16k", "gpt-3.5-turbo", "azure-gpt-3.5",
                     "api2d-gpt-3.5-turbo", 'api2d-gpt-3.5-turbo-16k', 
                     "gpt-4", "gpt-4-32k", "azure-gpt-4", "api2d-gpt-4", 
-                    "chatglm", "moss", "newbing", "claude-2"]
+                    "chatglm3", "moss", "newbing", "claude-2"]
 # P.S. 其他可用的模型还包括 ["zhipuai", "qianfan", "llama2", "qwen", "gpt-3.5-turbo-0613", "gpt-3.5-turbo-16k-0613",  "gpt-3.5-random"
 # "spark", "sparkv2", "sparkv3", "chatglm_onnx", "claude-1-100k", "claude-2", "internlm", "jittorllms_pangualpha", "jittorllms_llama"]
 
 
+# 定义界面上“询问多个GPT模型”插件应该使用哪些模型，请从AVAIL_LLM_MODELS中选择，并在不同模型之间用`&`间隔，例如"gpt-3.5-turbo&chatglm3&azure-gpt-4"
+MULTI_QUERY_LLM_MODELS = "gpt-3.5-turbo&chatglm3"
+
+
 # 百度千帆（LLM_MODEL="qianfan"）
 BAIDU_CLOUD_API_KEY = ''
 BAIDU_CLOUD_SECRET_KEY = ''

crazy_functions/询问多个大语言模型.py

@@ -1,4 +1,4 @@
-from toolbox import CatchException, update_ui
+from toolbox import CatchException, update_ui, get_conf
 from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 import datetime
 @CatchException
@@ -13,11 +13,12 @@ def 同时问询(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
     web_port        当前软件运行的端口号
     """
     history = []    # 清空历史，以免输入溢出
-    chatbot.append((txt, "正在同时咨询ChatGPT和ChatGLM……"))
+    MULTI_QUERY_LLM_MODELS = get_conf('MULTI_QUERY_LLM_MODELS')
+    chatbot.append((txt, "正在同时咨询" + MULTI_QUERY_LLM_MODELS))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间，我们先及时地做一次界面更新
 
     # llm_kwargs['llm_model'] = 'chatglm&gpt-3.5-turbo&api2d-gpt-3.5-turbo' # 支持任意数量的llm接口，用&符号分隔
-    llm_kwargs['llm_model'] = 'chatglm&gpt-3.5-turbo' # 支持任意数量的llm接口，用&符号分隔
+    llm_kwargs['llm_model'] = MULTI_QUERY_LLM_MODELS # 支持任意数量的llm接口，用&符号分隔
     gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
         inputs=txt, inputs_show_user=txt, 
         llm_kwargs=llm_kwargs, chatbot=chatbot, history=history, 

main.py

@@ -433,7 +433,7 @@ def warm_up_mods(): time.sleep(4); warm_up_modules()
         server_port=PORT,
         favicon_path=os.path.join(os.path.dirname(__file__), "docs/logo.png"), 
         auth=AUTHENTICATION if len(AUTHENTICATION) != 0 else None,
-        blocked_paths=["config.py","config_private.py","docker-compose.yml","Dockerfile","gpt_log/admin"])
+        blocked_paths=["config.py","config_private.py","docker-compose.yml","Dockerfile",f"{PATH_LOGGING}/admin"])
 
     # 如果需要在二级路径下运行
     # CUSTOM_PATH = get_conf('CUSTOM_PATH')
@@ -442,7 +442,7 @@ def warm_up_mods(): time.sleep(4); warm_up_modules()
     #     run_gradio_in_subpath(demo, auth=AUTHENTICATION, port=PORT, custom_path=CUSTOM_PATH)
     # else: 
     #     demo.launch(server_name="0.0.0.0", server_port=PORT, auth=AUTHENTICATION, favicon_path="docs/logo.png",
-    #                 blocked_paths=["config.py","config_private.py","docker-compose.yml","Dockerfile"])
+    #                 blocked_paths=["config.py","config_private.py","docker-compose.yml","Dockerfile",f"{PATH_LOGGING}/admin"])
 
 if __name__ == "__main__":
     main()

request_llms/local_llm_class.py

@@ -5,18 +5,18 @@
 from contextlib import redirect_stdout
 from request_llms.queued_pipe import create_queue_pipe
 
-class DebugLock(object):
+class ThreadLock(object):
     def __init__(self):
         self._lock = threading.Lock()
 
     def acquire(self):
-        print("acquiring", self)
+        # print("acquiring", self)
         #traceback.print_tb
         self._lock.acquire()
-        print("acquired", self)
+        # print("acquired", self)
 
     def release(self):
-        print("released", self)
+        # print("released", self)
         #traceback.print_tb
         self._lock.release()
 
@@ -85,7 +85,7 @@ def __init__(self):
         self.is_main_process = False    # state wrap for child process
         self.start()
         self.is_main_process = True     # state wrap for child process
-        self.threadLock = DebugLock()
+        self.threadLock = ThreadLock()
 
     def get_state(self):
         # ⭐run in main process
@@ -159,7 +159,7 @@ def run(self):
             try:
                 for response_full in self.llm_stream_generator(**kwargs):
                     self.child.send(response_full)
-                    print('debug' + response_full)
+                    # print('debug' + response_full)
                 self.child.send('[Finish]')
                 # 请求处理结束，开始下一个循环
             except:
@@ -200,7 +200,7 @@ def stream_chat(self, **kwargs):
                 if res.startswith(self.std_tag):
                     new_output = res[len(self.std_tag):]
                     std_out = std_out[:std_out_clip_len]
-                    print(new_output, end='')
+                    # print(new_output, end='')
                     std_out = new_output + std_out
                     yield self.std_tag + '\n```\n' + std_out + '\n```\n'
                 elif res == '[Finish]':