Merge Latest Frontier (#1991)

* logging sys to loguru: stage 1 complete

* import loguru: stage 2

* logging -> loguru: stage 3

* support o1-preview and o1-mini

* logging -> loguru stage 4

* update social helper

* logging -> loguru: final stage

* fix: console output

* update translation matrix

* fix: loguru argument error with proxy enabled (#1977)

* relax llama index version

* remove comment

* Added some modules to support openrouter (#1975)

* Added some modules for supporting openrouter model

Added some modules for supporting openrouter model

* Update config.py

* Update .gitignore

* Update bridge_openrouter.py

* Not changed actually

* Refactor logging in bridge_openrouter.py

---------

Co-authored-by: binary-husky <qingxu.fu@outlook.com>

* remove logging extra

---------

Co-authored-by: Steven Moder <java20131114@gmail.com>
Co-authored-by: Ren Lifei <2602264455@qq.com>

request_llms/oai_std_model_template.py

@@ -1,8 +1,8 @@
 import json
 import time
-import logging
 import traceback
 import requests
+from loguru import logger
 
 # config_private.py放自己的秘密如API和代理网址
 # 读取时首先看是否存在私密的config_private配置文件（不受git管控），如果有，则覆盖原config文件
@@ -106,10 +106,7 @@ def generate_message(input, model, key, history, max_output_token, system_prompt
         "stream": True,
         "max_tokens": max_output_token,
     }
-    try:
-        print(f" {model} : {conversation_cnt} : {input[:100]} ..........")
-    except:
-        print("输入中可能存在乱码。")
+
     return headers, playload
 
 
@@ -196,7 +193,7 @@ def get_predict_function(
                 if retry > MAX_RETRY:
                     raise TimeoutError
                 if MAX_RETRY != 0:
-                    print(f"请求超时，正在重试 ({retry}/{MAX_RETRY}) ……")
+                    logger.error(f"请求超时，正在重试 ({retry}/{MAX_RETRY}) ……")
 
         stream_response = response.iter_lines()
         result = ""
@@ -219,18 +216,17 @@ def get_predict_function(
             ):
                 chunk = get_full_error(chunk, stream_response)
                 chunk_decoded = chunk.decode()
-                print(chunk_decoded)
+                logger.error(chunk_decoded)
                 raise RuntimeError(
                     f"API异常,请检测终端输出。可能的原因是:{finish_reason}"
                 )
             if chunk:
                 try:
                     if finish_reason == "stop":
-                        logging.info(f"[response] {result}")
+                        if not console_slience:
+                            print(f"[response] {result}")
                         break
                     result += response_text
-                    if not console_slience:
-                        print(response_text, end="")
                     if observe_window is not None:
                         # 观测窗，把已经获取的数据显示出去
                         if len(observe_window) >= 1:
@@ -243,7 +239,7 @@ def get_predict_function(
                     chunk = get_full_error(chunk, stream_response)
                     chunk_decoded = chunk.decode()
                     error_msg = chunk_decoded
-                    print(error_msg)
+                    logger.error(error_msg)
                     raise RuntimeError("Json解析不合常规")
         return result
 
@@ -276,7 +272,7 @@ def get_predict_function(
             inputs, history = handle_core_functionality(
                 additional_fn, inputs, history, chatbot
             )
-        logging.info(f"[raw_input] {inputs}")
+        logger.info(f"[raw_input] {inputs}")
         chatbot.append((inputs, ""))
         yield from update_ui(
             chatbot=chatbot, history=history, msg="等待响应"
@@ -376,11 +372,11 @@ def get_predict_function(
                             history=history,
                             msg="API异常:" + chunk_decoded,
                         )  # 刷新界面
-                        print(chunk_decoded)
+                        logger.error(chunk_decoded)
                         return
 
                     if finish_reason == "stop":
-                        logging.info(f"[response] {gpt_replying_buffer}")
+                        logger.info(f"[response] {gpt_replying_buffer}")
                         break
                     status_text = f"finish_reason: {finish_reason}"
                     gpt_replying_buffer += response_text
@@ -403,7 +399,7 @@ def get_predict_function(
                     yield from update_ui(
                         chatbot=chatbot, history=history, msg="Json异常" + chunk_decoded
                     )  # 刷新界面
-                    print(chunk_decoded)
+                    logger.error(chunk_decoded)
                     return
 
     return predict_no_ui_long_connection, predict