Version 3.74: Merge latest updates on dev branch (frontier) (#1621)

* Update version to 3.74

* Add support for Yi Model API (#1635)

* 更新以支持零一万物模型

* 删除newbing

* 修改config

---------

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

* Refactor function signatures in bridge files

* fix qwen api change

* rename and ref functions

* rename and move some cookie functions

* 增加haiku模型，新增endpoint配置说明 (#1626)

* haiku added

* 新增haiku，新增endpoint配置说明

* Haiku added

* 将说明同步至最新Endpoint

---------

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

* private_upload目录下进行文件鉴权 (#1596)

* private_upload目录下进行文件鉴权

* minor fastapi adjustment

* Add logging functionality to enable saving
conversation records

* waiting to fix username retrieve

* support 2rd web path

* allow accessing default user dir

---------

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

* remove yaml deps

* fix favicon

* fix abs path auth problem

* forget to write a return

* add `dashscope` to deps

* fix GHSA-v9q9-xj86-953p

* 用户名重叠越权访问patch (#1681)

* add cohere model api access

* cohere + can_multi_thread

* fix block user access(fail)

* fix fastapi bug

* change cohere api endpoint

* explain version

---------

Co-authored-by: Menghuan1918 <menghuan2003@outlook.com>
Co-authored-by: Skyzayre <120616113+Skyzayre@users.noreply.github.com>
Co-authored-by: XIao <46100050+Kilig947@users.noreply.github.com>

request_llms/bridge_claude.py

@@ -13,11 +13,11 @@ import logging
 import os
 import time
 import traceback
-from toolbox import get_conf, update_ui, trimmed_format_exc, encode_image, every_image_file_in_path
 import json
 import requests
+from toolbox import get_conf, update_ui, trimmed_format_exc, encode_image, every_image_file_in_path, log_chat
 picture_system_prompt = "\n当回复图像时,必须说明正在回复哪张图像。所有图像仅在最后一个问题中提供,即使它们在历史记录中被提及。请使用'这是第X张图像:'的格式来指明您正在描述的是哪张图像。"
-Claude_3_Models = ["claude-3-sonnet-20240229", "claude-3-opus-20240229"]
+Claude_3_Models = ["claude-3-haiku-20240307", "claude-3-sonnet-20240229", "claude-3-opus-20240229"]
 
 # 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
@@ -95,7 +95,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
             # make a POST request to the API endpoint, stream=False
             from .bridge_all import model_info
             endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
-            response = requests.post(endpoint, headers=headers, json=message, 
+            response = requests.post(endpoint, headers=headers, json=message,
                                      proxies=proxies, stream=True, timeout=TIMEOUT_SECONDS);break
         except requests.exceptions.ReadTimeout as e:
             retry += 1
@@ -116,7 +116,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
                 if need_to_pass:
                     pass
                 elif is_last_chunk:
-                    logging.info(f'[response] {result}')
+                    # logging.info(f'[response] {result}')
                     break
                 else:
                     if chunkjson and chunkjson['type'] == 'content_block_delta':
@@ -194,7 +194,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
             # make a POST request to the API endpoint, stream=True
             from .bridge_all import model_info
             endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
-            response = requests.post(endpoint, headers=headers, json=message, 
+            response = requests.post(endpoint, headers=headers, json=message,
                                      proxies=proxies, stream=True, timeout=TIMEOUT_SECONDS);break
         except requests.exceptions.ReadTimeout as e:
             retry += 1
@@ -216,7 +216,8 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
                 if need_to_pass:
                     pass
                 elif is_last_chunk:
-                    logging.info(f'[response] {gpt_replying_buffer}')
+                    log_chat(llm_model=llm_kwargs["llm_model"], input_str=inputs, output_str=gpt_replying_buffer)
+                    # logging.info(f'[response] {gpt_replying_buffer}')
                     break
                 else:
                     if chunkjson and chunkjson['type'] == 'content_block_delta':
@@ -305,4 +306,4 @@ def generate_payload(inputs, llm_kwargs, history, system_prompt, image_paths):
         'stream': True,
         'system': system_prompt
     }
-    return headers, payload
+    return headers, payload