Merge Frontier, Update to Version 3.72 (#1553)

* Zhipu sdk update 适配最新的智谱SDK,支持GLM4v (#1502)

* 适配 google gemini 优化为从用户input中提取文件

* 适配最新的智谱SDK、支持glm-4v

* requirements.txt fix

* pending history check

---------

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

* Update "生成多种Mermaid图表" plugin: Separate out the file reading function (#1520)

* Update crazy_functional.py with new functionality deal with PDF

* Update crazy_functional.py and Mermaid.py for plugin_kwargs

* Update crazy_functional.py with new chart type: mind map

* Update SELECT_PROMPT and i_say_show_user messages

* Update ArgsReminder message in get_crazy_functions() function

* Update with read md file and update PROMPTS

* Return the PROMPTS as the test found that the initial version worked best

* Update Mermaid chart generation function

* version 3.71

* 解决issues #1510

* Remove unnecessary text from sys_prompt in 解析历史输入 function

* Remove sys_prompt message in 解析历史输入 function

* Update bridge_all.py: supports gpt-4-turbo-preview (#1517)

* Update bridge_all.py: supports gpt-4-turbo-preview

supports gpt-4-turbo-preview

* Update bridge_all.py

---------

Co-authored-by: binary-husky <96192199+binary-husky@users.noreply.github.com>

* Update config.py: supports gpt-4-turbo-preview (#1516)

* Update config.py: supports gpt-4-turbo-preview

supports gpt-4-turbo-preview

* Update config.py

---------

Co-authored-by: binary-husky <96192199+binary-husky@users.noreply.github.com>

* Refactor 解析历史输入 function to handle file input

* Update Mermaid chart generation functionality

* rename files and functions

---------

Co-authored-by: binary-husky <qingxu.fu@outlook.com>
Co-authored-by: hongyi-zhao <hongyi.zhao@gmail.com>
Co-authored-by: binary-husky <96192199+binary-husky@users.noreply.github.com>

* 接入mathpix ocr功能 (#1468)

* Update Latex输出PDF结果.py

借助mathpix实现了PDF翻译中文并重新编译PDF

* Update config.py

add mathpix appid & appkey

* Add 'PDF翻译中文并重新编译PDF' feature to plugins.

---------

Co-authored-by: binary-husky <96192199+binary-husky@users.noreply.github.com>

* fix zhipuai

* check picture

* remove glm-4 due to bug

* 修改config

* 检查MATHPIX_APPID

* Remove unnecessary code and update
function_plugins dictionary

* capture non-standard token overflow

* bug fix #1524

* change mermaid style

* 支持mermaid 滚动放大缩小重置,鼠标滚动和拖拽 (#1530)

* 支持mermaid 滚动放大缩小重置,鼠标滚动和拖拽

* 微调未果 先stage一下

* update

---------

Co-authored-by: binary-husky <qingxu.fu@outlook.com>
Co-authored-by: binary-husky <96192199+binary-husky@users.noreply.github.com>

* ver 3.72

* change live2d

* save the status of ``clear btn` in cookie

* 前端选择保持

* js ui bug fix

* reset btn bug fix

* update live2d tips

* fix missing get_token_num method

* fix live2d toggle switch

* fix persistent custom btn with cookie

* fix zhipuai feedback with core functionality

* Refactor button update and clean up functions

---------

Co-authored-by: XIao <46100050+Kilig947@users.noreply.github.com>
Co-authored-by: Menghuan1918 <menghuan2003@outlook.com>
Co-authored-by: hongyi-zhao <hongyi.zhao@gmail.com>
Co-authored-by: Hao Ma <893017927@qq.com>
Co-authored-by: zeyuan huang <599012428@qq.com>
This commit is contained in:
binary-husky 2024-02-14 18:35:09 +08:00 committed by GitHub
parent e0c5859cf9
commit 2e9b4a5770
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
42 changed files with 1171 additions and 9635 deletions

View File

@ -89,8 +89,8 @@ DEFAULT_FN_GROUPS = ['对话', '编程', '学术', '智能体']
LLM_MODEL = "gpt-3.5-turbo-16k" # 可选 ↓↓↓ LLM_MODEL = "gpt-3.5-turbo-16k" # 可选 ↓↓↓
AVAIL_LLM_MODELS = ["gpt-4-1106-preview", "gpt-4-turbo-preview", "gpt-4-vision-preview", AVAIL_LLM_MODELS = ["gpt-4-1106-preview", "gpt-4-turbo-preview", "gpt-4-vision-preview",
"gpt-3.5-turbo-1106", "gpt-3.5-turbo-16k", "gpt-3.5-turbo", "azure-gpt-3.5", "gpt-3.5-turbo-1106", "gpt-3.5-turbo-16k", "gpt-3.5-turbo", "azure-gpt-3.5",
"gpt-4", "gpt-4-32k", "azure-gpt-4", "api2d-gpt-4", "gpt-4", "gpt-4-32k", "azure-gpt-4", "glm-4", "glm-3-turbo",
"gemini-pro", "chatglm3", "claude-2", "zhipuai"] "gemini-pro", "chatglm3", "claude-2"]
# P.S. 其他可用的模型还包括 [ # P.S. 其他可用的模型还包括 [
# "moss", "qwen-turbo", "qwen-plus", "qwen-max" # "moss", "qwen-turbo", "qwen-plus", "qwen-max"
# "zhipuai", "qianfan", "deepseekcoder", "llama2", "qwen-local", "gpt-3.5-turbo-0613", # "zhipuai", "qianfan", "deepseekcoder", "llama2", "qwen-local", "gpt-3.5-turbo-0613",
@ -195,7 +195,7 @@ XFYUN_API_KEY = "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"
# 接入智谱大模型 # 接入智谱大模型
ZHIPUAI_API_KEY = "" ZHIPUAI_API_KEY = ""
ZHIPUAI_MODEL = "glm-4" # 可选 "glm-3-turbo" "glm-4" ZHIPUAI_MODEL = "" # 此选项已废弃,不再需要填写
# # 火山引擎YUNQUE大模型 # # 火山引擎YUNQUE大模型
@ -208,6 +208,11 @@ ZHIPUAI_MODEL = "glm-4" # 可选 "glm-3-turbo" "glm-4"
ANTHROPIC_API_KEY = "" ANTHROPIC_API_KEY = ""
# Mathpix 拥有执行PDF的OCR功能但是需要注册账号
MATHPIX_APPID = ""
MATHPIX_APPKEY = ""
# 自定义API KEY格式 # 自定义API KEY格式
CUSTOM_API_KEY_PATTERN = "" CUSTOM_API_KEY_PATTERN = ""
@ -297,9 +302,8 @@ NUM_CUSTOM_BASIC_BTN = 4
BAIDU_CLOUD_API_KEY BAIDU_CLOUD_API_KEY
BAIDU_CLOUD_SECRET_KEY BAIDU_CLOUD_SECRET_KEY
"zhipuai" 智谱AI大模型chatglm_turbo "glm-4", "glm-3-turbo", "zhipuai" 智谱AI大模型
ZHIPUAI_API_KEY ZHIPUAI_API_KEY
ZHIPUAI_MODEL
"qwen-turbo" 等通义千问大模型 "qwen-turbo" 等通义千问大模型
DASHSCOPE_API_KEY DASHSCOPE_API_KEY
@ -351,6 +355,9 @@ NUM_CUSTOM_BASIC_BTN = 4
ALIYUN_SECRET ALIYUN_SECRET
PDF文档精准解析 PDF文档精准解析
GROBID_URLS GROBID_URLS
MATHPIX_APPID
MATHPIX_APPKEY
""" """

View File

@ -70,11 +70,11 @@ def get_crazy_functions():
"Info": "清除所有缓存文件,谨慎操作 | 不需要输入参数", "Info": "清除所有缓存文件,谨慎操作 | 不需要输入参数",
"Function": HotReload(清除缓存), "Function": HotReload(清除缓存),
}, },
"生成多种Mermaid图表(从当前对话或文件(.pdf/.md)中生产图表)": { "生成多种Mermaid图表(从当前对话或路径(.pdf/.md/.docx)中生产图表)": {
"Group": "对话", "Group": "对话",
"Color": "stop", "Color": "stop",
"AsButton": False, "AsButton": False,
"Info" : "基于当前对话或PDF生成多种Mermaid图表,图表类型由模型判断", "Info" : "基于当前对话或文件生成多种Mermaid图表,图表类型由模型判断",
"Function": HotReload(生成多种Mermaid图表), "Function": HotReload(生成多种Mermaid图表),
"AdvancedArgs": True, "AdvancedArgs": True,
"ArgsReminder": "请输入图类型对应的数字,不输入则为模型自行判断:1-流程图,2-序列图,3-类图,4-饼图,5-甘特图,6-状态图,7-实体关系图,8-象限提示图,9-思维导图", "ArgsReminder": "请输入图类型对应的数字,不输入则为模型自行判断:1-流程图,2-序列图,3-类图,4-饼图,5-甘特图,6-状态图,7-实体关系图,8-象限提示图,9-思维导图",
@ -532,8 +532,9 @@ def get_crazy_functions():
print("Load function plugin failed") print("Load function plugin failed")
try: try:
from crazy_functions.Latex输出PDF结果 import Latex英文纠错加PDF对比 from crazy_functions.Latex输出PDF import Latex英文纠错加PDF对比
from crazy_functions.Latex输出PDF结果 import Latex翻译中文并重新编译PDF from crazy_functions.Latex输出PDF import Latex翻译中文并重新编译PDF
from crazy_functions.Latex输出PDF import PDF翻译中文并重新编译PDF
function_plugins.update( function_plugins.update(
{ {
@ -550,9 +551,9 @@ def get_crazy_functions():
"Color": "stop", "Color": "stop",
"AsButton": False, "AsButton": False,
"AdvancedArgs": True, "AdvancedArgs": True,
"ArgsReminder": "如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 " "ArgsReminder": r"如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 "
+ "例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: " r"例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: "
+ 'If the term "agent" is used in this section, it should be translated to "智能体". ', r'If the term "agent" is used in this section, it should be translated to "智能体". ',
"Info": "Arixv论文精细翻译 | 输入参数arxiv论文的ID比如1812.10695", "Info": "Arixv论文精细翻译 | 输入参数arxiv论文的ID比如1812.10695",
"Function": HotReload(Latex翻译中文并重新编译PDF), "Function": HotReload(Latex翻译中文并重新编译PDF),
}, },
@ -561,11 +562,22 @@ def get_crazy_functions():
"Color": "stop", "Color": "stop",
"AsButton": False, "AsButton": False,
"AdvancedArgs": True, "AdvancedArgs": True,
"ArgsReminder": "如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 " "ArgsReminder": r"如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 "
+ "例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: " r"例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: "
+ 'If the term "agent" is used in this section, it should be translated to "智能体". ', r'If the term "agent" is used in this section, it should be translated to "智能体". ',
"Info": "本地Latex论文精细翻译 | 输入参数是路径", "Info": "本地Latex论文精细翻译 | 输入参数是路径",
"Function": HotReload(Latex翻译中文并重新编译PDF), "Function": HotReload(Latex翻译中文并重新编译PDF),
},
"PDF翻译中文并重新编译PDF上传PDF[需Latex]": {
"Group": "学术",
"Color": "stop",
"AsButton": False,
"AdvancedArgs": True,
"ArgsReminder": r"如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 "
r"例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: "
r'If the term "agent" is used in this section, it should be translated to "智能体". ',
"Info": "PDF翻译中文并重新编译PDF | 输入参数为路径",
"Function": HotReload(PDF翻译中文并重新编译PDF)
} }
} }
) )

View File

@ -0,0 +1,484 @@
from toolbox import update_ui, trimmed_format_exc, get_conf, get_log_folder, promote_file_to_downloadzone
from toolbox import CatchException, report_exception, update_ui_lastest_msg, zip_result, gen_time_str
from functools import partial
import glob, os, requests, time, json, tarfile
pj = os.path.join
ARXIV_CACHE_DIR = os.path.expanduser(f"~/arxiv_cache/")
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=- 工具函数 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
# 专业词汇声明 = 'If the term "agent" is used in this section, it should be translated to "智能体". '
def switch_prompt(pfg, mode, more_requirement):
"""
Generate prompts and system prompts based on the mode for proofreading or translating.
Args:
- pfg: Proofreader or Translator instance.
- mode: A string specifying the mode, either 'proofread' or 'translate_zh'.
Returns:
- inputs_array: A list of strings containing prompts for users to respond to.
- sys_prompt_array: A list of strings containing prompts for system prompts.
"""
n_split = len(pfg.sp_file_contents)
if mode == 'proofread_en':
inputs_array = [r"Below is a section from an academic paper, proofread this section." +
r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " + more_requirement +
r"Answer me only with the revised text:" +
f"\n\n{frag}" for frag in pfg.sp_file_contents]
sys_prompt_array = ["You are a professional academic paper writer." for _ in range(n_split)]
elif mode == 'translate_zh':
inputs_array = [
r"Below is a section from an English academic paper, translate it into Chinese. " + more_requirement +
r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " +
r"Answer me only with the translated text:" +
f"\n\n{frag}" for frag in pfg.sp_file_contents]
sys_prompt_array = ["You are a professional translator." for _ in range(n_split)]
else:
assert False, "未知指令"
return inputs_array, sys_prompt_array
def desend_to_extracted_folder_if_exist(project_folder):
"""
Descend into the extracted folder if it exists, otherwise return the original folder.
Args:
- project_folder: A string specifying the folder path.
Returns:
- A string specifying the path to the extracted folder, or the original folder if there is no extracted folder.
"""
maybe_dir = [f for f in glob.glob(f'{project_folder}/*') if os.path.isdir(f)]
if len(maybe_dir) == 0: return project_folder
if maybe_dir[0].endswith('.extract'): return maybe_dir[0]
return project_folder
def move_project(project_folder, arxiv_id=None):
"""
Create a new work folder and copy the project folder to it.
Args:
- project_folder: A string specifying the folder path of the project.
Returns:
- A string specifying the path to the new work folder.
"""
import shutil, time
time.sleep(2) # avoid time string conflict
if arxiv_id is not None:
new_workfolder = pj(ARXIV_CACHE_DIR, arxiv_id, 'workfolder')
else:
new_workfolder = f'{get_log_folder()}/{gen_time_str()}'
try:
shutil.rmtree(new_workfolder)
except:
pass
# align subfolder if there is a folder wrapper
items = glob.glob(pj(project_folder, '*'))
items = [item for item in items if os.path.basename(item) != '__MACOSX']
if len(glob.glob(pj(project_folder, '*.tex'))) == 0 and len(items) == 1:
if os.path.isdir(items[0]): project_folder = items[0]
shutil.copytree(src=project_folder, dst=new_workfolder)
return new_workfolder
def arxiv_download(chatbot, history, txt, allow_cache=True):
def check_cached_translation_pdf(arxiv_id):
translation_dir = pj(ARXIV_CACHE_DIR, arxiv_id, 'translation')
if not os.path.exists(translation_dir):
os.makedirs(translation_dir)
target_file = pj(translation_dir, 'translate_zh.pdf')
if os.path.exists(target_file):
promote_file_to_downloadzone(target_file, rename_file=None, chatbot=chatbot)
target_file_compare = pj(translation_dir, 'comparison.pdf')
if os.path.exists(target_file_compare):
promote_file_to_downloadzone(target_file_compare, rename_file=None, chatbot=chatbot)
return target_file
return False
def is_float(s):
try:
float(s)
return True
except ValueError:
return False
if ('.' in txt) and ('/' not in txt) and is_float(txt): # is arxiv ID
txt = 'https://arxiv.org/abs/' + txt.strip()
if ('.' in txt) and ('/' not in txt) and is_float(txt[:10]): # is arxiv ID
txt = 'https://arxiv.org/abs/' + txt[:10]
if not txt.startswith('https://arxiv.org'):
return txt, None # 是本地文件,跳过下载
# <-------------- inspect format ------------->
chatbot.append([f"检测到arxiv文档连接", '尝试下载 ...'])
yield from update_ui(chatbot=chatbot, history=history)
time.sleep(1) # 刷新界面
url_ = txt # https://arxiv.org/abs/1707.06690
if not txt.startswith('https://arxiv.org/abs/'):
msg = f"解析arxiv网址失败, 期望格式例如: https://arxiv.org/abs/1707.06690。实际得到格式: {url_}"
yield from update_ui_lastest_msg(msg, chatbot=chatbot, history=history) # 刷新界面
return msg, None
# <-------------- set format ------------->
arxiv_id = url_.split('/abs/')[-1]
if 'v' in arxiv_id: arxiv_id = arxiv_id[:10]
cached_translation_pdf = check_cached_translation_pdf(arxiv_id)
if cached_translation_pdf and allow_cache: return cached_translation_pdf, arxiv_id
url_tar = url_.replace('/abs/', '/e-print/')
translation_dir = pj(ARXIV_CACHE_DIR, arxiv_id, 'e-print')
extract_dst = pj(ARXIV_CACHE_DIR, arxiv_id, 'extract')
os.makedirs(translation_dir, exist_ok=True)
# <-------------- download arxiv source file ------------->
dst = pj(translation_dir, arxiv_id + '.tar')
if os.path.exists(dst):
yield from update_ui_lastest_msg("调用缓存", chatbot=chatbot, history=history) # 刷新界面
else:
yield from update_ui_lastest_msg("开始下载", chatbot=chatbot, history=history) # 刷新界面
proxies = get_conf('proxies')
r = requests.get(url_tar, proxies=proxies)
with open(dst, 'wb+') as f:
f.write(r.content)
# <-------------- extract file ------------->
yield from update_ui_lastest_msg("下载完成", chatbot=chatbot, history=history) # 刷新界面
from toolbox import extract_archive
extract_archive(file_path=dst, dest_dir=extract_dst)
return extract_dst, arxiv_id
def pdf2tex_project(pdf_file_path):
# Mathpix API credentials
app_id, app_key = get_conf('MATHPIX_APPID', 'MATHPIX_APPKEY')
headers = {"app_id": app_id, "app_key": app_key}
# Step 1: Send PDF file for processing
options = {
"conversion_formats": {"tex.zip": True},
"math_inline_delimiters": ["$", "$"],
"rm_spaces": True
}
response = requests.post(url="https://api.mathpix.com/v3/pdf",
headers=headers,
data={"options_json": json.dumps(options)},
files={"file": open(pdf_file_path, "rb")})
if response.ok:
pdf_id = response.json()["pdf_id"]
print(f"PDF processing initiated. PDF ID: {pdf_id}")
# Step 2: Check processing status
while True:
conversion_response = requests.get(f"https://api.mathpix.com/v3/pdf/{pdf_id}", headers=headers)
conversion_data = conversion_response.json()
if conversion_data["status"] == "completed":
print("PDF processing completed.")
break
elif conversion_data["status"] == "error":
print("Error occurred during processing.")
else:
print(f"Processing status: {conversion_data['status']}")
time.sleep(5) # wait for a few seconds before checking again
# Step 3: Save results to local files
output_dir = os.path.join(os.path.dirname(pdf_file_path), 'mathpix_output')
if not os.path.exists(output_dir):
os.makedirs(output_dir)
url = f"https://api.mathpix.com/v3/pdf/{pdf_id}.tex"
response = requests.get(url, headers=headers)
file_name_wo_dot = '_'.join(os.path.basename(pdf_file_path).split('.')[:-1])
output_name = f"{file_name_wo_dot}.tex.zip"
output_path = os.path.join(output_dir, output_name)
with open(output_path, "wb") as output_file:
output_file.write(response.content)
print(f"tex.zip file saved at: {output_path}")
import zipfile
unzip_dir = os.path.join(output_dir, file_name_wo_dot)
with zipfile.ZipFile(output_path, 'r') as zip_ref:
zip_ref.extractall(unzip_dir)
return unzip_dir
else:
print(f"Error sending PDF for processing. Status code: {response.status_code}")
return None
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序1 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
@CatchException
def Latex英文纠错加PDF对比(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
# <-------------- information about this plugin ------------->
chatbot.append(["函数插件功能?",
"对整个Latex项目进行纠错, 用latex编译为PDF对修正处做高亮。函数插件贡献者: Binary-Husky。注意事项: 目前仅支持GPT3.5/GPT4其他模型转化效果未知。目前对机器学习类文献转化效果最好其他类型文献转化效果未知。仅在Windows系统进行了测试其他操作系统表现未知。"])
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
# <-------------- more requirements ------------->
if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
more_req = plugin_kwargs.get("advanced_arg", "")
_switch_prompt_ = partial(switch_prompt, more_requirement=more_req)
# <-------------- check deps ------------->
try:
import glob, os, time, subprocess
subprocess.Popen(['pdflatex', '-version'])
from .latex_fns.latex_actions import Latex精细分解与转化, 编译Latex
except Exception as e:
chatbot.append([f"解析项目: {txt}",
f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
# <-------------- clear history and read input ------------->
history = []
if os.path.exists(txt):
project_folder = txt
else:
if txt == "": txt = '空空如也的输入栏'
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无权访问: {txt}")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
if len(file_manifest) == 0:
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何.tex文件: {txt}")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
# <-------------- if is a zip/tar file ------------->
project_folder = desend_to_extracted_folder_if_exist(project_folder)
# <-------------- move latex project away from temp folder ------------->
project_folder = move_project(project_folder, arxiv_id=None)
# <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
if not os.path.exists(project_folder + '/merge_proofread_en.tex'):
yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
chatbot, history, system_prompt, mode='proofread_en',
switch_prompt=_switch_prompt_)
# <-------------- compile PDF ------------->
success = yield from 编译Latex(chatbot, history, main_file_original='merge',
main_file_modified='merge_proofread_en',
work_folder_original=project_folder, work_folder_modified=project_folder,
work_folder=project_folder)
# <-------------- zip PDF ------------->
zip_res = zip_result(project_folder)
if success:
chatbot.append((f"成功啦", '请查收结果(压缩包)...'))
yield from update_ui(chatbot=chatbot, history=history);
time.sleep(1) # 刷新界面
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
else:
chatbot.append((f"失败了",
'虽然PDF生成失败了, 但请查收结果(压缩包), 内含已经翻译的Tex文档, 也是可读的, 您可以到Github Issue区, 用该压缩包+对话历史存档进行反馈 ...'))
yield from update_ui(chatbot=chatbot, history=history);
time.sleep(1) # 刷新界面
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
# <-------------- we are done ------------->
return success
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序2 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
@CatchException
def Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
# <-------------- information about this plugin ------------->
chatbot.append([
"函数插件功能?",
"对整个Latex项目进行翻译, 生成中文PDF。函数插件贡献者: Binary-Husky。注意事项: 此插件Windows支持最佳Linux下必须使用Docker安装详见项目主README.md。目前仅支持GPT3.5/GPT4其他模型转化效果未知。目前对机器学习类文献转化效果最好其他类型文献转化效果未知。"])
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
# <-------------- more requirements ------------->
if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
more_req = plugin_kwargs.get("advanced_arg", "")
no_cache = more_req.startswith("--no-cache")
if no_cache: more_req.lstrip("--no-cache")
allow_cache = not no_cache
_switch_prompt_ = partial(switch_prompt, more_requirement=more_req)
# <-------------- check deps ------------->
try:
import glob, os, time, subprocess
subprocess.Popen(['pdflatex', '-version'])
from .latex_fns.latex_actions import Latex精细分解与转化, 编译Latex
except Exception as e:
chatbot.append([f"解析项目: {txt}",
f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
# <-------------- clear history and read input ------------->
history = []
try:
txt, arxiv_id = yield from arxiv_download(chatbot, history, txt, allow_cache)
except tarfile.ReadError as e:
yield from update_ui_lastest_msg(
"无法自动下载该论文的Latex源码请前往arxiv打开此论文下载页面点other Formats然后download source手动下载latex源码包。接下来调用本地Latex翻译插件即可。",
chatbot=chatbot, history=history)
return
if txt.endswith('.pdf'):
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"发现已经存在翻译好的PDF文档")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
if os.path.exists(txt):
project_folder = txt
else:
if txt == "": txt = '空空如也的输入栏'
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无法处理: {txt}")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
if len(file_manifest) == 0:
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何.tex文件: {txt}")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
# <-------------- if is a zip/tar file ------------->
project_folder = desend_to_extracted_folder_if_exist(project_folder)
# <-------------- move latex project away from temp folder ------------->
project_folder = move_project(project_folder, arxiv_id)
# <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
if not os.path.exists(project_folder + '/merge_translate_zh.tex'):
yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
chatbot, history, system_prompt, mode='translate_zh',
switch_prompt=_switch_prompt_)
# <-------------- compile PDF ------------->
success = yield from 编译Latex(chatbot, history, main_file_original='merge',
main_file_modified='merge_translate_zh', mode='translate_zh',
work_folder_original=project_folder, work_folder_modified=project_folder,
work_folder=project_folder)
# <-------------- zip PDF ------------->
zip_res = zip_result(project_folder)
if success:
chatbot.append((f"成功啦", '请查收结果(压缩包)...'))
yield from update_ui(chatbot=chatbot, history=history);
time.sleep(1) # 刷新界面
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
else:
chatbot.append((f"失败了",
'虽然PDF生成失败了, 但请查收结果(压缩包), 内含已经翻译的Tex文档, 您可以到Github Issue区, 用该压缩包进行反馈。如系统是Linux请检查系统字体见Github wiki ...'))
yield from update_ui(chatbot=chatbot, history=history);
time.sleep(1) # 刷新界面
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
# <-------------- we are done ------------->
return success
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=- 插件主程序3 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
@CatchException
def PDF翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
# <-------------- information about this plugin ------------->
chatbot.append([
"函数插件功能?",
"将PDF转换为Latex项目翻译为中文后重新编译为PDF。函数插件贡献者: Marroh。注意事项: 此插件Windows支持最佳Linux下必须使用Docker安装详见项目主README.md。目前仅支持GPT3.5/GPT4其他模型转化效果未知。目前对机器学习类文献转化效果最好其他类型文献转化效果未知。"])
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
# <-------------- more requirements ------------->
if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
more_req = plugin_kwargs.get("advanced_arg", "")
no_cache = more_req.startswith("--no-cache")
if no_cache: more_req.lstrip("--no-cache")
allow_cache = not no_cache
_switch_prompt_ = partial(switch_prompt, more_requirement=more_req)
# <-------------- check deps ------------->
try:
import glob, os, time, subprocess
subprocess.Popen(['pdflatex', '-version'])
from .latex_fns.latex_actions import Latex精细分解与转化, 编译Latex
except Exception as e:
chatbot.append([f"解析项目: {txt}",
f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
# <-------------- clear history and read input ------------->
if os.path.exists(txt):
project_folder = txt
else:
if txt == "": txt = '空空如也的输入栏'
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无法处理: {txt}")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.pdf', recursive=True)]
if len(file_manifest) == 0:
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何.pdf文件: {txt}")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
if len(file_manifest) != 1:
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"不支持同时处理多个pdf文件: {txt}")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
app_id, app_key = get_conf('MATHPIX_APPID', 'MATHPIX_APPKEY')
if len(app_id) == 0 or len(app_key) == 0:
report_exception(chatbot, history, a=f"请配置 MATHPIX_APPID 和 MATHPIX_APPKEY")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
# <-------------- convert pdf into tex ------------->
project_folder = pdf2tex_project(file_manifest[0])
# Translate English Latex to Chinese Latex, and compile it
file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
if len(file_manifest) == 0:
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何.tex文件: {txt}")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
# <-------------- if is a zip/tar file ------------->
project_folder = desend_to_extracted_folder_if_exist(project_folder)
# <-------------- move latex project away from temp folder ------------->
project_folder = move_project(project_folder)
# <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
if not os.path.exists(project_folder + '/merge_translate_zh.tex'):
yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
chatbot, history, system_prompt, mode='translate_zh',
switch_prompt=_switch_prompt_)
# <-------------- compile PDF ------------->
success = yield from 编译Latex(chatbot, history, main_file_original='merge',
main_file_modified='merge_translate_zh', mode='translate_zh',
work_folder_original=project_folder, work_folder_modified=project_folder,
work_folder=project_folder)
# <-------------- zip PDF ------------->
zip_res = zip_result(project_folder)
if success:
chatbot.append((f"成功啦", '请查收结果(压缩包)...'))
yield from update_ui(chatbot=chatbot, history=history);
time.sleep(1) # 刷新界面
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
else:
chatbot.append((f"失败了",
'虽然PDF生成失败了, 但请查收结果(压缩包), 内含已经翻译的Tex文档, 您可以到Github Issue区, 用该压缩包进行反馈。如系统是Linux请检查系统字体见Github wiki ...'))
yield from update_ui(chatbot=chatbot, history=history);
time.sleep(1) # 刷新界面
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
# <-------------- we are done ------------->
return success

View File

@ -1,313 +0,0 @@
from toolbox import update_ui, trimmed_format_exc, get_conf, get_log_folder, promote_file_to_downloadzone
from toolbox import CatchException, report_exception, update_ui_lastest_msg, zip_result, gen_time_str
from functools import partial
import glob, os, requests, time, tarfile
pj = os.path.join
ARXIV_CACHE_DIR = os.path.expanduser(f"~/arxiv_cache/")
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=- 工具函数 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
# 专业词汇声明 = 'If the term "agent" is used in this section, it should be translated to "智能体". '
def switch_prompt(pfg, mode, more_requirement):
"""
Generate prompts and system prompts based on the mode for proofreading or translating.
Args:
- pfg: Proofreader or Translator instance.
- mode: A string specifying the mode, either 'proofread' or 'translate_zh'.
Returns:
- inputs_array: A list of strings containing prompts for users to respond to.
- sys_prompt_array: A list of strings containing prompts for system prompts.
"""
n_split = len(pfg.sp_file_contents)
if mode == 'proofread_en':
inputs_array = [r"Below is a section from an academic paper, proofread this section." +
r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " + more_requirement +
r"Answer me only with the revised text:" +
f"\n\n{frag}" for frag in pfg.sp_file_contents]
sys_prompt_array = ["You are a professional academic paper writer." for _ in range(n_split)]
elif mode == 'translate_zh':
inputs_array = [r"Below is a section from an English academic paper, translate it into Chinese. " + more_requirement +
r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " +
r"Answer me only with the translated text:" +
f"\n\n{frag}" for frag in pfg.sp_file_contents]
sys_prompt_array = ["You are a professional translator." for _ in range(n_split)]
else:
assert False, "未知指令"
return inputs_array, sys_prompt_array
def desend_to_extracted_folder_if_exist(project_folder):
"""
Descend into the extracted folder if it exists, otherwise return the original folder.
Args:
- project_folder: A string specifying the folder path.
Returns:
- A string specifying the path to the extracted folder, or the original folder if there is no extracted folder.
"""
maybe_dir = [f for f in glob.glob(f'{project_folder}/*') if os.path.isdir(f)]
if len(maybe_dir) == 0: return project_folder
if maybe_dir[0].endswith('.extract'): return maybe_dir[0]
return project_folder
def move_project(project_folder, arxiv_id=None):
"""
Create a new work folder and copy the project folder to it.
Args:
- project_folder: A string specifying the folder path of the project.
Returns:
- A string specifying the path to the new work folder.
"""
import shutil, time
time.sleep(2) # avoid time string conflict
if arxiv_id is not None:
new_workfolder = pj(ARXIV_CACHE_DIR, arxiv_id, 'workfolder')
else:
new_workfolder = f'{get_log_folder()}/{gen_time_str()}'
try:
shutil.rmtree(new_workfolder)
except:
pass
# align subfolder if there is a folder wrapper
items = glob.glob(pj(project_folder,'*'))
items = [item for item in items if os.path.basename(item)!='__MACOSX']
if len(glob.glob(pj(project_folder,'*.tex'))) == 0 and len(items) == 1:
if os.path.isdir(items[0]): project_folder = items[0]
shutil.copytree(src=project_folder, dst=new_workfolder)
return new_workfolder
def arxiv_download(chatbot, history, txt, allow_cache=True):
def check_cached_translation_pdf(arxiv_id):
translation_dir = pj(ARXIV_CACHE_DIR, arxiv_id, 'translation')
if not os.path.exists(translation_dir):
os.makedirs(translation_dir)
target_file = pj(translation_dir, 'translate_zh.pdf')
if os.path.exists(target_file):
promote_file_to_downloadzone(target_file, rename_file=None, chatbot=chatbot)
target_file_compare = pj(translation_dir, 'comparison.pdf')
if os.path.exists(target_file_compare):
promote_file_to_downloadzone(target_file_compare, rename_file=None, chatbot=chatbot)
return target_file
return False
def is_float(s):
try:
float(s)
return True
except ValueError:
return False
if ('.' in txt) and ('/' not in txt) and is_float(txt): # is arxiv ID
txt = 'https://arxiv.org/abs/' + txt.strip()
if ('.' in txt) and ('/' not in txt) and is_float(txt[:10]): # is arxiv ID
txt = 'https://arxiv.org/abs/' + txt[:10]
if not txt.startswith('https://arxiv.org'):
return txt, None # 是本地文件,跳过下载
# <-------------- inspect format ------------->
chatbot.append([f"检测到arxiv文档连接", '尝试下载 ...'])
yield from update_ui(chatbot=chatbot, history=history)
time.sleep(1) # 刷新界面
url_ = txt # https://arxiv.org/abs/1707.06690
if not txt.startswith('https://arxiv.org/abs/'):
msg = f"解析arxiv网址失败, 期望格式例如: https://arxiv.org/abs/1707.06690。实际得到格式: {url_}"
yield from update_ui_lastest_msg(msg, chatbot=chatbot, history=history) # 刷新界面
return msg, None
# <-------------- set format ------------->
arxiv_id = url_.split('/abs/')[-1]
if 'v' in arxiv_id: arxiv_id = arxiv_id[:10]
cached_translation_pdf = check_cached_translation_pdf(arxiv_id)
if cached_translation_pdf and allow_cache: return cached_translation_pdf, arxiv_id
url_tar = url_.replace('/abs/', '/e-print/')
translation_dir = pj(ARXIV_CACHE_DIR, arxiv_id, 'e-print')
extract_dst = pj(ARXIV_CACHE_DIR, arxiv_id, 'extract')
os.makedirs(translation_dir, exist_ok=True)
# <-------------- download arxiv source file ------------->
dst = pj(translation_dir, arxiv_id+'.tar')
if os.path.exists(dst):
yield from update_ui_lastest_msg("调用缓存", chatbot=chatbot, history=history) # 刷新界面
else:
yield from update_ui_lastest_msg("开始下载", chatbot=chatbot, history=history) # 刷新界面
proxies = get_conf('proxies')
r = requests.get(url_tar, proxies=proxies)
with open(dst, 'wb+') as f:
f.write(r.content)
# <-------------- extract file ------------->
yield from update_ui_lastest_msg("下载完成", chatbot=chatbot, history=history) # 刷新界面
from toolbox import extract_archive
extract_archive(file_path=dst, dest_dir=extract_dst)
return extract_dst, arxiv_id
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序1 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
@CatchException
def Latex英文纠错加PDF对比(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
# <-------------- information about this plugin ------------->
chatbot.append([ "函数插件功能?",
"对整个Latex项目进行纠错, 用latex编译为PDF对修正处做高亮。函数插件贡献者: Binary-Husky。注意事项: 目前仅支持GPT3.5/GPT4其他模型转化效果未知。目前对机器学习类文献转化效果最好其他类型文献转化效果未知。仅在Windows系统进行了测试其他操作系统表现未知。"])
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
# <-------------- more requirements ------------->
if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
more_req = plugin_kwargs.get("advanced_arg", "")
_switch_prompt_ = partial(switch_prompt, more_requirement=more_req)
# <-------------- check deps ------------->
try:
import glob, os, time, subprocess
subprocess.Popen(['pdflatex', '-version'])
from .latex_fns.latex_actions import Latex精细分解与转化, 编译Latex
except Exception as e:
chatbot.append([ f"解析项目: {txt}",
f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
# <-------------- clear history and read input ------------->
history = []
if os.path.exists(txt):
project_folder = txt
else:
if txt == "": txt = '空空如也的输入栏'
report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
if len(file_manifest) == 0:
report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex文件: {txt}")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
# <-------------- if is a zip/tar file ------------->
project_folder = desend_to_extracted_folder_if_exist(project_folder)
# <-------------- move latex project away from temp folder ------------->
project_folder = move_project(project_folder, arxiv_id=None)
# <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
if not os.path.exists(project_folder + '/merge_proofread_en.tex'):
yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
chatbot, history, system_prompt, mode='proofread_en', switch_prompt=_switch_prompt_)
# <-------------- compile PDF ------------->
success = yield from 编译Latex(chatbot, history, main_file_original='merge', main_file_modified='merge_proofread_en',
work_folder_original=project_folder, work_folder_modified=project_folder, work_folder=project_folder)
# <-------------- zip PDF ------------->
zip_res = zip_result(project_folder)
if success:
chatbot.append((f"成功啦", '请查收结果(压缩包)...'))
yield from update_ui(chatbot=chatbot, history=history); time.sleep(1) # 刷新界面
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
else:
chatbot.append((f"失败了", '虽然PDF生成失败了, 但请查收结果(压缩包), 内含已经翻译的Tex文档, 也是可读的, 您可以到Github Issue区, 用该压缩包+对话历史存档进行反馈 ...'))
yield from update_ui(chatbot=chatbot, history=history); time.sleep(1) # 刷新界面
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
# <-------------- we are done ------------->
return success
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序2 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
@CatchException
def Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
# <-------------- information about this plugin ------------->
chatbot.append([
"函数插件功能?",
"对整个Latex项目进行翻译, 生成中文PDF。函数插件贡献者: Binary-Husky。注意事项: 此插件Windows支持最佳Linux下必须使用Docker安装详见项目主README.md。目前仅支持GPT3.5/GPT4其他模型转化效果未知。目前对机器学习类文献转化效果最好其他类型文献转化效果未知。"])
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
# <-------------- more requirements ------------->
if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
more_req = plugin_kwargs.get("advanced_arg", "")
no_cache = more_req.startswith("--no-cache")
if no_cache: more_req.lstrip("--no-cache")
allow_cache = not no_cache
_switch_prompt_ = partial(switch_prompt, more_requirement=more_req)
# <-------------- check deps ------------->
try:
import glob, os, time, subprocess
subprocess.Popen(['pdflatex', '-version'])
from .latex_fns.latex_actions import Latex精细分解与转化, 编译Latex
except Exception as e:
chatbot.append([ f"解析项目: {txt}",
f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
# <-------------- clear history and read input ------------->
history = []
try:
txt, arxiv_id = yield from arxiv_download(chatbot, history, txt, allow_cache)
except tarfile.ReadError as e:
yield from update_ui_lastest_msg(
"无法自动下载该论文的Latex源码请前往arxiv打开此论文下载页面点other Formats然后download source手动下载latex源码包。接下来调用本地Latex翻译插件即可。",
chatbot=chatbot, history=history)
return
if txt.endswith('.pdf'):
report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"发现已经存在翻译好的PDF文档")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
if os.path.exists(txt):
project_folder = txt
else:
if txt == "": txt = '空空如也的输入栏'
report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无法处理: {txt}")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
if len(file_manifest) == 0:
report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex文件: {txt}")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
# <-------------- if is a zip/tar file ------------->
project_folder = desend_to_extracted_folder_if_exist(project_folder)
# <-------------- move latex project away from temp folder ------------->
project_folder = move_project(project_folder, arxiv_id)
# <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
if not os.path.exists(project_folder + '/merge_translate_zh.tex'):
yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
chatbot, history, system_prompt, mode='translate_zh', switch_prompt=_switch_prompt_)
# <-------------- compile PDF ------------->
success = yield from 编译Latex(chatbot, history, main_file_original='merge', main_file_modified='merge_translate_zh', mode='translate_zh',
work_folder_original=project_folder, work_folder_modified=project_folder, work_folder=project_folder)
# <-------------- zip PDF ------------->
zip_res = zip_result(project_folder)
if success:
chatbot.append((f"成功啦", '请查收结果(压缩包)...'))
yield from update_ui(chatbot=chatbot, history=history); time.sleep(1) # 刷新界面
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
else:
chatbot.append((f"失败了", '虽然PDF生成失败了, 但请查收结果(压缩包), 内含已经翻译的Tex文档, 您可以到Github Issue区, 用该压缩包进行反馈。如系统是Linux请检查系统字体见Github wiki ...'))
yield from update_ui(chatbot=chatbot, history=history); time.sleep(1) # 刷新界面
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
# <-------------- we are done ------------->
return success

View File

@ -0,0 +1,85 @@
from crazy_functions.crazy_utils import read_and_clean_pdf_text, get_files_from_everything
import os
import re
def extract_text_from_files(txt, chatbot, history):
"""
查找pdf/md/word并获取文本内容并返回状态以及文本
输入参数 Args:
chatbot: chatbot inputs and outputs 用户界面对话窗口句柄用于数据流可视化
history (list): List of chat history 历史对话历史列表
输出 Returns:
文件是否存在(bool)
final_result(list):文本内容
page_one(list):第一页内容/摘要
file_manifest(list):文件路径
excption(string):需要用户手动处理的信息,如没出错则保持为空
"""
final_result = []
page_one = []
file_manifest = []
excption = ""
if txt == "":
final_result.append(txt)
return False, final_result, page_one, file_manifest, excption #如输入区内容不是文件则直接返回输入区内容
#查找输入区内容中的文件
file_pdf,pdf_manifest,folder_pdf = get_files_from_everything(txt, '.pdf')
file_md,md_manifest,folder_md = get_files_from_everything(txt, '.md')
file_word,word_manifest,folder_word = get_files_from_everything(txt, '.docx')
file_doc,doc_manifest,folder_doc = get_files_from_everything(txt, '.doc')
if file_doc:
excption = "word"
return False, final_result, page_one, file_manifest, excption
file_num = len(pdf_manifest) + len(md_manifest) + len(word_manifest)
if file_num == 0:
final_result.append(txt)
return False, final_result, page_one, file_manifest, excption #如输入区内容不是文件则直接返回输入区内容
if file_pdf:
try: # 尝试导入依赖,如果缺少依赖,则给出安装建议
import fitz
except:
excption = "pdf"
return False, final_result, page_one, file_manifest, excption
for index, fp in enumerate(pdf_manifest):
file_content, pdf_one = read_and_clean_pdf_text(fp) # 尝试按照章节切割PDF
file_content = file_content.encode('utf-8', 'ignore').decode() # avoid reading non-utf8 chars
pdf_one = str(pdf_one).encode('utf-8', 'ignore').decode() # avoid reading non-utf8 chars
final_result.append(file_content)
page_one.append(pdf_one)
file_manifest.append(os.path.relpath(fp, folder_pdf))
if file_md:
for index, fp in enumerate(md_manifest):
with open(fp, 'r', encoding='utf-8', errors='replace') as f:
file_content = f.read()
file_content = file_content.encode('utf-8', 'ignore').decode()
headers = re.findall(r'^#\s(.*)$', file_content, re.MULTILINE) #接下来提取md中的一级/二级标题作为摘要
if len(headers) > 0:
page_one.append("\n".join(headers)) #合并所有的标题,以换行符分割
else:
page_one.append("")
final_result.append(file_content)
file_manifest.append(os.path.relpath(fp, folder_md))
if file_word:
try: # 尝试导入依赖,如果缺少依赖,则给出安装建议
from docx import Document
except:
excption = "word_pip"
return False, final_result, page_one, file_manifest, excption
for index, fp in enumerate(word_manifest):
doc = Document(fp)
file_content = '\n'.join([p.text for p in doc.paragraphs])
file_content = file_content.encode('utf-8', 'ignore').decode()
page_one.append(file_content[:200])
final_result.append(file_content)
file_manifest.append(os.path.relpath(fp, folder_word))
return True, final_result, page_one, file_manifest, excption

View File

@ -1,6 +1,5 @@
from toolbox import CatchException, update_ui, report_exception from toolbox import CatchException, update_ui, report_exception
from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
from .crazy_utils import read_and_clean_pdf_text
import datetime import datetime
#以下是每类图表的PROMPT #以下是每类图表的PROMPT
@ -162,7 +161,7 @@ mindmap
``` ```
""" """
def 解析历史输入(history,llm_kwargs,chatbot,plugin_kwargs): def 解析历史输入(history,llm_kwargs,file_manifest,chatbot,plugin_kwargs):
############################## <第 0 步,切割输入> ################################## ############################## <第 0 步,切割输入> ##################################
# 借用PDF切割中的函数对文本进行切割 # 借用PDF切割中的函数对文本进行切割
TOKEN_LIMIT_PER_FRAGMENT = 2500 TOKEN_LIMIT_PER_FRAGMENT = 2500
@ -170,8 +169,6 @@ def 解析历史输入(history,llm_kwargs,chatbot,plugin_kwargs):
from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
txt = breakdown_text_to_satisfy_token_limit(txt=txt, limit=TOKEN_LIMIT_PER_FRAGMENT, llm_model=llm_kwargs['llm_model']) txt = breakdown_text_to_satisfy_token_limit(txt=txt, limit=TOKEN_LIMIT_PER_FRAGMENT, llm_model=llm_kwargs['llm_model'])
############################## <第 1 步,迭代地历遍整个文章,提取精炼信息> ################################## ############################## <第 1 步,迭代地历遍整个文章,提取精炼信息> ##################################
i_say_show_user = f'首先你从历史记录或文件中提取摘要。'; gpt_say = "[Local Message] 收到。" # 用户提示
chatbot.append([i_say_show_user, gpt_say]); yield from update_ui(chatbot=chatbot, history=history) # 更新UI
results = [] results = []
MAX_WORD_TOTAL = 4096 MAX_WORD_TOTAL = 4096
n_txt = len(txt) n_txt = len(txt)
@ -179,7 +176,7 @@ def 解析历史输入(history,llm_kwargs,chatbot,plugin_kwargs):
if n_txt >= 20: print('文章极长,不能达到预期效果') if n_txt >= 20: print('文章极长,不能达到预期效果')
for i in range(n_txt): for i in range(n_txt):
NUM_OF_WORD = MAX_WORD_TOTAL // n_txt NUM_OF_WORD = MAX_WORD_TOTAL // n_txt
i_say = f"Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words: {txt[i]}" i_say = f"Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words in Chinese: {txt[i]}"
i_say_show_user = f"[{i+1}/{n_txt}] Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words: {txt[i][:200]} ...." i_say_show_user = f"[{i+1}/{n_txt}] Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words: {txt[i][:200]} ...."
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(i_say, i_say_show_user, # i_say=真正给chatgpt的提问 i_say_show_user=给用户看的提问 gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(i_say, i_say_show_user, # i_say=真正给chatgpt的提问 i_say_show_user=给用户看的提问
llm_kwargs, chatbot, llm_kwargs, chatbot,
@ -232,35 +229,11 @@ def 解析历史输入(history,llm_kwargs,chatbot,plugin_kwargs):
inputs=i_say, inputs=i_say,
inputs_show_user=i_say_show_user, inputs_show_user=i_say_show_user,
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[], llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
sys_prompt="你精通使用mermaid语法来绘制图表,首先确保语法正确,其次避免在mermaid语法中使用不允许的字符,此外也应当分考虑图表的可读性。" sys_prompt=""
) )
history.append(gpt_say) history.append(gpt_say)
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新 yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
def 输入区文件处理(txt):
if txt == "": return False, txt
success = True
import glob
from .crazy_utils import get_files_from_everything
file_pdf,pdf_manifest,folder_pdf = get_files_from_everything(txt, '.pdf')
file_md,md_manifest,folder_md = get_files_from_everything(txt, '.md')
if len(pdf_manifest) == 0 and len(md_manifest) == 0:
return False, txt #如输入区内容不是文件则直接返回输入区内容
final_result = ""
if file_pdf:
for index, fp in enumerate(pdf_manifest):
file_content, page_one = read_and_clean_pdf_text(fp) # 尝试按照章节切割PDF
file_content = file_content.encode('utf-8', 'ignore').decode() # avoid reading non-utf8 chars
final_result += "\n" + file_content
if file_md:
for index, fp in enumerate(md_manifest):
with open(fp, 'r', encoding='utf-8', errors='replace') as f:
file_content = f.read()
file_content = file_content.encode('utf-8', 'ignore').decode()
final_result += "\n" + file_content
return True, final_result
@CatchException @CatchException
def 生成多种Mermaid图表(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port): def 生成多种Mermaid图表(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
""" """
@ -277,26 +250,47 @@ def 生成多种Mermaid图表(txt, llm_kwargs, plugin_kwargs, chatbot, history,
# 基本信息:功能、贡献者 # 基本信息:功能、贡献者
chatbot.append([ chatbot.append([
"函数插件功能?", "函数插件功能?",
"根据当前聊天历史或文件(文件内容优先)绘制多种mermaid图表将会由对话模型首先判断适合的图表类型随后绘制图表。\ "根据当前聊天历史或指定的路径文件(文件内容优先)绘制多种mermaid图表将会由对话模型首先判断适合的图表类型随后绘制图表。\
\n您也可以使用插件参数指定绘制的图表类型,函数插件贡献者: Menghuan1918"]) \n您也可以使用插件参数指定绘制的图表类型,函数插件贡献者: Menghuan1918"])
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
# 尝试导入依赖,如果缺少依赖,则给出安装建议
try:
import fitz
except:
report_exception(chatbot, history,
a = f"解析项目: {txt}",
b = f"导入软件依赖失败。使用该模块需要额外依赖,安装方法```pip install --upgrade pymupdf```。")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
if os.path.exists(txt): #如输入区无内容则直接解析历史记录 if os.path.exists(txt): #如输入区无内容则直接解析历史记录
file_exist, txt = 输入区文件处理(txt) from crazy_functions.pdf_fns.parse_word import extract_text_from_files
file_exist, final_result, page_one, file_manifest, excption = extract_text_from_files(txt, chatbot, history)
else: else:
file_exist = False file_exist = False
excption = ""
file_manifest = []
if file_exist : history = [] #如输入区内容为文件则清空历史记录 if excption != "":
history.append(txt) #将解析后的txt传递加入到历史中 if excption == "word":
report_exception(chatbot, history,
a = f"解析项目: {txt}",
b = f"找到了.doc文件但是该文件格式不被支持请先转化为.docx格式。")
yield from 解析历史输入(history,llm_kwargs,chatbot,plugin_kwargs) elif excption == "pdf":
report_exception(chatbot, history,
a = f"解析项目: {txt}",
b = f"导入软件依赖失败。使用该模块需要额外依赖,安装方法```pip install --upgrade pymupdf```。")
elif excption == "word_pip":
report_exception(chatbot, history,
a=f"解析项目: {txt}",
b=f"导入软件依赖失败。使用该模块需要额外依赖,安装方法```pip install --upgrade python-docx pywin32```。")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
else:
if not file_exist:
history.append(txt) #如输入区不是文件则将输入区内容加入历史记录
i_say_show_user = f'首先你从历史记录中提取摘要。'; gpt_say = "[Local Message] 收到。" # 用户提示
chatbot.append([i_say_show_user, gpt_say]); yield from update_ui(chatbot=chatbot, history=history) # 更新UI
yield from 解析历史输入(history,llm_kwargs,file_manifest,chatbot,plugin_kwargs)
else:
file_num = len(file_manifest)
for i in range(file_num): #依次处理文件
i_say_show_user = f"[{i+1}/{file_num}]处理文件{file_manifest[i]}"; gpt_say = "[Local Message] 收到。" # 用户提示
chatbot.append([i_say_show_user, gpt_say]); yield from update_ui(chatbot=chatbot, history=history) # 更新UI
history = [] #如输入区内容为文件则清空历史记录
history.append(final_result[i])
yield from 解析历史输入(history,llm_kwargs,file_manifest,chatbot,plugin_kwargs)

View File

@ -1668,7 +1668,7 @@
"Markdown翻译指定语言": "TranslateMarkdownToSpecifiedLanguage", "Markdown翻译指定语言": "TranslateMarkdownToSpecifiedLanguage",
"Langchain知识库": "LangchainKnowledgeBase", "Langchain知识库": "LangchainKnowledgeBase",
"Latex英文纠错加PDF对比": "CorrectEnglishInLatexWithPDFComparison", "Latex英文纠错加PDF对比": "CorrectEnglishInLatexWithPDFComparison",
"Latex输出PDF结果": "OutputPDFFromLatex", "Latex输出PDF": "OutputPDFFromLatex",
"Latex翻译中文并重新编译PDF": "TranslateChineseToEnglishInLatexAndRecompilePDF", "Latex翻译中文并重新编译PDF": "TranslateChineseToEnglishInLatexAndRecompilePDF",
"sprint亮靛": "SprintIndigo", "sprint亮靛": "SprintIndigo",
"寻找Latex主文件": "FindLatexMainFile", "寻找Latex主文件": "FindLatexMainFile",

View File

@ -1492,7 +1492,7 @@
"交互功能模板函数": "InteractiveFunctionTemplateFunction", "交互功能模板函数": "InteractiveFunctionTemplateFunction",
"交互功能函数模板": "InteractiveFunctionFunctionTemplate", "交互功能函数模板": "InteractiveFunctionFunctionTemplate",
"Latex英文纠错加PDF对比": "LatexEnglishErrorCorrectionWithPDFComparison", "Latex英文纠错加PDF对比": "LatexEnglishErrorCorrectionWithPDFComparison",
"Latex输出PDF结果": "LatexOutputPDFResult", "Latex输出PDF": "LatexOutputPDFResult",
"Latex翻译中文并重新编译PDF": "TranslateChineseAndRecompilePDF", "Latex翻译中文并重新编译PDF": "TranslateChineseAndRecompilePDF",
"语音助手": "VoiceAssistant", "语音助手": "VoiceAssistant",
"微调数据集生成": "FineTuneDatasetGeneration", "微调数据集生成": "FineTuneDatasetGeneration",

View File

@ -16,7 +16,7 @@
"批量Markdown翻译": "BatchTranslateMarkdown", "批量Markdown翻译": "BatchTranslateMarkdown",
"连接bing搜索回答问题": "ConnectBingSearchAnswerQuestion", "连接bing搜索回答问题": "ConnectBingSearchAnswerQuestion",
"Langchain知识库": "LangchainKnowledgeBase", "Langchain知识库": "LangchainKnowledgeBase",
"Latex输出PDF结果": "OutputPDFFromLatex", "Latex输出PDF": "OutputPDFFromLatex",
"把字符太少的块清除为回车": "ClearBlocksWithTooFewCharactersToNewline", "把字符太少的块清除为回车": "ClearBlocksWithTooFewCharactersToNewline",
"Latex精细分解与转化": "DecomposeAndConvertLatex", "Latex精细分解与转化": "DecomposeAndConvertLatex",
"解析一个C项目的头文件": "ParseCProjectHeaderFiles", "解析一个C项目的头文件": "ParseCProjectHeaderFiles",

View File

@ -1468,7 +1468,7 @@
"交互功能模板函数": "InteractiveFunctionTemplateFunctions", "交互功能模板函数": "InteractiveFunctionTemplateFunctions",
"交互功能函数模板": "InteractiveFunctionFunctionTemplates", "交互功能函数模板": "InteractiveFunctionFunctionTemplates",
"Latex英文纠错加PDF对比": "LatexEnglishCorrectionWithPDFComparison", "Latex英文纠错加PDF对比": "LatexEnglishCorrectionWithPDFComparison",
"Latex输出PDF结果": "OutputPDFFromLatex", "Latex输出PDF": "OutputPDFFromLatex",
"Latex翻译中文并重新编译PDF": "TranslateLatexToChineseAndRecompilePDF", "Latex翻译中文并重新编译PDF": "TranslateLatexToChineseAndRecompilePDF",
"语音助手": "VoiceAssistant", "语音助手": "VoiceAssistant",
"微调数据集生成": "FineTuneDatasetGeneration", "微调数据集生成": "FineTuneDatasetGeneration",

View File

@ -1,30 +0,0 @@
try {
$("<link>").attr({href: "file=docs/waifu_plugin/waifu.css", rel: "stylesheet", type: "text/css"}).appendTo('head');
$('body').append('<div class="waifu"><div class="waifu-tips"></div><canvas id="live2d" class="live2d"></canvas><div class="waifu-tool"><span class="fui-home"></span> <span class="fui-chat"></span> <span class="fui-eye"></span> <span class="fui-user"></span> <span class="fui-photo"></span> <span class="fui-info-circle"></span> <span class="fui-cross"></span></div></div>');
$.ajax({url: "file=docs/waifu_plugin/waifu-tips.js", dataType:"script", cache: true, success: function() {
$.ajax({url: "file=docs/waifu_plugin/live2d.js", dataType:"script", cache: true, success: function() {
/* 可直接修改部分参数 */
live2d_settings['hitokotoAPI'] = "hitokoto.cn"; // 一言 API
live2d_settings['modelId'] = 5; // 默认模型 ID
live2d_settings['modelTexturesId'] = 1; // 默认材质 ID
live2d_settings['modelStorage'] = false; // 不储存模型 ID
live2d_settings['waifuSize'] = '210x187';
live2d_settings['waifuTipsSize'] = '187x52';
live2d_settings['canSwitchModel'] = true;
live2d_settings['canSwitchTextures'] = true;
live2d_settings['canSwitchHitokoto'] = false;
live2d_settings['canTakeScreenshot'] = false;
live2d_settings['canTurnToHomePage'] = false;
live2d_settings['canTurnToAboutPage'] = false;
live2d_settings['showHitokoto'] = false; // 显示一言
live2d_settings['showF12Status'] = false; // 显示加载状态
live2d_settings['showF12Message'] = false; // 显示看板娘消息
live2d_settings['showF12OpenMsg'] = false; // 显示控制台打开提示
live2d_settings['showCopyMessage'] = false; // 显示 复制内容 提示
live2d_settings['showWelcomeMessage'] = true; // 显示进入面页欢迎词
/* 在 initModel 前添加 */
initModel("file=docs/waifu_plugin/waifu-tips.json");
}});
}});
} catch(err) { console.log("[Error] JQuery is not defined.") }

93
main.py
View File

@ -15,22 +15,22 @@ help_menu_description = \
def main(): def main():
import gradio as gr import gradio as gr
if gr.__version__ not in ['3.32.6', '3.32.7', '3.32.8']: if gr.__version__ not in ['3.32.8']:
raise ModuleNotFoundError("使用项目内置Gradio获取最优体验! 请运行 `pip install -r requirements.txt` 指令安装内置Gradio及其他依赖, 详情信息见requirements.txt.") raise ModuleNotFoundError("使用项目内置Gradio获取最优体验! 请运行 `pip install -r requirements.txt` 指令安装内置Gradio及其他依赖, 详情信息见requirements.txt.")
from request_llms.bridge_all import predict from request_llms.bridge_all import predict
from toolbox import format_io, find_free_port, on_file_uploaded, on_report_generated, get_conf, ArgsGeneralWrapper, load_chat_cookies, DummyWith from toolbox import format_io, find_free_port, on_file_uploaded, on_report_generated, get_conf, ArgsGeneralWrapper, load_chat_cookies, DummyWith
# 建议您复制一个config_private.py放自己的秘密, 如API和代理网址 # 建议您复制一个config_private.py放自己的秘密, 如API和代理网址
proxies, WEB_PORT, LLM_MODEL, CONCURRENT_COUNT, AUTHENTICATION = get_conf('proxies', 'WEB_PORT', 'LLM_MODEL', 'CONCURRENT_COUNT', 'AUTHENTICATION') proxies, WEB_PORT, LLM_MODEL, CONCURRENT_COUNT, AUTHENTICATION = get_conf('proxies', 'WEB_PORT', 'LLM_MODEL', 'CONCURRENT_COUNT', 'AUTHENTICATION')
CHATBOT_HEIGHT, LAYOUT, AVAIL_LLM_MODELS, AUTO_CLEAR_TXT = get_conf('CHATBOT_HEIGHT', 'LAYOUT', 'AVAIL_LLM_MODELS', 'AUTO_CLEAR_TXT') CHATBOT_HEIGHT, LAYOUT, AVAIL_LLM_MODELS, AUTO_CLEAR_TXT = get_conf('CHATBOT_HEIGHT', 'LAYOUT', 'AVAIL_LLM_MODELS', 'AUTO_CLEAR_TXT')
ENABLE_AUDIO, AUTO_CLEAR_TXT, PATH_LOGGING, AVAIL_THEMES, THEME = get_conf('ENABLE_AUDIO', 'AUTO_CLEAR_TXT', 'PATH_LOGGING', 'AVAIL_THEMES', 'THEME') ENABLE_AUDIO, AUTO_CLEAR_TXT, PATH_LOGGING, AVAIL_THEMES, THEME, ADD_WAIFU = get_conf('ENABLE_AUDIO', 'AUTO_CLEAR_TXT', 'PATH_LOGGING', 'AVAIL_THEMES', 'THEME', 'ADD_WAIFU')
DARK_MODE, NUM_CUSTOM_BASIC_BTN, SSL_KEYFILE, SSL_CERTFILE = get_conf('DARK_MODE', 'NUM_CUSTOM_BASIC_BTN', 'SSL_KEYFILE', 'SSL_CERTFILE') DARK_MODE, NUM_CUSTOM_BASIC_BTN, SSL_KEYFILE, SSL_CERTFILE = get_conf('DARK_MODE', 'NUM_CUSTOM_BASIC_BTN', 'SSL_KEYFILE', 'SSL_CERTFILE')
INIT_SYS_PROMPT = get_conf('INIT_SYS_PROMPT') INIT_SYS_PROMPT = get_conf('INIT_SYS_PROMPT')
# 如果WEB_PORT是-1, 则随机选取WEB端口 # 如果WEB_PORT是-1, 则随机选取WEB端口
PORT = find_free_port() if WEB_PORT <= 0 else WEB_PORT PORT = find_free_port() if WEB_PORT <= 0 else WEB_PORT
from check_proxy import get_current_version from check_proxy import get_current_version
from themes.theme import adjust_theme, advanced_css, theme_declaration from themes.theme import adjust_theme, advanced_css, theme_declaration, js_code_clear, js_code_reset, js_code_show_or_hide, js_code_show_or_hide_group2
from themes.theme import js_code_for_css_changing, js_code_for_darkmode_init, js_code_for_toggle_darkmode, js_code_for_persistent_cookie_init from themes.theme import js_code_for_css_changing, js_code_for_toggle_darkmode, js_code_for_persistent_cookie_init
from themes.theme import load_dynamic_theme, to_cookie_str, from_cookie_str, init_cookie from themes.theme import load_dynamic_theme, to_cookie_str, from_cookie_str, init_cookie
title_html = f"<h1 align=\"center\">GPT 学术优化 {get_current_version()}</h1>{theme_declaration}" title_html = f"<h1 align=\"center\">GPT 学术优化 {get_current_version()}</h1>{theme_declaration}"
@ -76,7 +76,7 @@ def main():
predefined_btns = {} predefined_btns = {}
with gr.Blocks(title="GPT 学术优化", theme=set_theme, analytics_enabled=False, css=advanced_css) as demo: with gr.Blocks(title="GPT 学术优化", theme=set_theme, analytics_enabled=False, css=advanced_css) as demo:
gr.HTML(title_html) gr.HTML(title_html)
secret_css, dark_mode, persistent_cookie = gr.Textbox(visible=False), gr.Textbox(DARK_MODE, visible=False), gr.Textbox(visible=False) secret_css, dark_mode, py_pickle_cookie = gr.Textbox(visible=False), gr.Textbox(DARK_MODE, visible=False), gr.Textbox(visible=False)
cookies = gr.State(load_chat_cookies()) cookies = gr.State(load_chat_cookies())
with gr_L1(): with gr_L1():
with gr_L2(scale=2, elem_id="gpt-chat"): with gr_L2(scale=2, elem_id="gpt-chat"):
@ -98,6 +98,7 @@ def main():
audio_mic = gr.Audio(source="microphone", type="numpy", elem_id="elem_audio", streaming=True, show_label=False).style(container=False) audio_mic = gr.Audio(source="microphone", type="numpy", elem_id="elem_audio", streaming=True, show_label=False).style(container=False)
with gr.Row(): with gr.Row():
status = gr.Markdown(f"Tip: 按Enter提交, 按Shift+Enter换行。当前模型: {LLM_MODEL} \n {proxy_info}", elem_id="state-panel") status = gr.Markdown(f"Tip: 按Enter提交, 按Shift+Enter换行。当前模型: {LLM_MODEL} \n {proxy_info}", elem_id="state-panel")
with gr.Accordion("基础功能区", open=True, elem_id="basic-panel") as area_basic_fn: with gr.Accordion("基础功能区", open=True, elem_id="basic-panel") as area_basic_fn:
with gr.Row(): with gr.Row():
for k in range(NUM_CUSTOM_BASIC_BTN): for k in range(NUM_CUSTOM_BASIC_BTN):
@ -142,7 +143,6 @@ def main():
with gr.Accordion("点击展开“文件下载区”。", open=False) as area_file_up: with gr.Accordion("点击展开“文件下载区”。", open=False) as area_file_up:
file_upload = gr.Files(label="任何文件, 推荐上传压缩文件(zip, tar)", file_count="multiple", elem_id="elem_upload") file_upload = gr.Files(label="任何文件, 推荐上传压缩文件(zip, tar)", file_count="multiple", elem_id="elem_upload")
with gr.Floating(init_x="0%", init_y="0%", visible=True, width=None, drag="forbidden", elem_id="tooltip"): with gr.Floating(init_x="0%", init_y="0%", visible=True, width=None, drag="forbidden", elem_id="tooltip"):
with gr.Row(): with gr.Row():
with gr.Tab("上传文件", elem_id="interact-panel"): with gr.Tab("上传文件", elem_id="interact-panel"):
@ -158,10 +158,11 @@ def main():
with gr.Tab("界面外观", elem_id="interact-panel"): with gr.Tab("界面外观", elem_id="interact-panel"):
theme_dropdown = gr.Dropdown(AVAIL_THEMES, value=THEME, label="更换UI主题").style(container=False) theme_dropdown = gr.Dropdown(AVAIL_THEMES, value=THEME, label="更换UI主题").style(container=False)
checkboxes = gr.CheckboxGroup(["基础功能区", "函数插件区", "浮动输入区", "输入清除键", "插件参数区"], checkboxes = gr.CheckboxGroup(["基础功能区", "函数插件区", "浮动输入区", "输入清除键", "插件参数区"], value=["基础功能区", "函数插件区"], label="显示/隐藏功能区", elem_id='cbs').style(container=False)
value=["基础功能区", "函数插件区"], label="显示/隐藏功能区", elem_id='cbs').style(container=False) opt = ["自定义菜单"]
checkboxes_2 = gr.CheckboxGroup(["自定义菜单"], value=[]
value=[], label="显示/隐藏自定义菜单", elem_id='cbsc').style(container=False) if ADD_WAIFU: opt += ["添加Live2D形象"]; value += ["添加Live2D形象"]
checkboxes_2 = gr.CheckboxGroup(opt, value=value, label="显示/隐藏自定义菜单", elem_id='cbsc').style(container=False)
dark_mode_btn = gr.Button("切换界面明暗 ☀", variant="secondary").style(size="sm") dark_mode_btn = gr.Button("切换界面明暗 ☀", variant="secondary").style(size="sm")
dark_mode_btn.click(None, None, None, _js=js_code_for_toggle_darkmode) dark_mode_btn.click(None, None, None, _js=js_code_for_toggle_darkmode)
with gr.Tab("帮助", elem_id="interact-panel"): with gr.Tab("帮助", elem_id="interact-panel"):
@ -178,7 +179,7 @@ def main():
submitBtn2 = gr.Button("提交", variant="primary"); submitBtn2.style(size="sm") submitBtn2 = gr.Button("提交", variant="primary"); submitBtn2.style(size="sm")
resetBtn2 = gr.Button("重置", variant="secondary"); resetBtn2.style(size="sm") resetBtn2 = gr.Button("重置", variant="secondary"); resetBtn2.style(size="sm")
stopBtn2 = gr.Button("停止", variant="secondary"); stopBtn2.style(size="sm") stopBtn2 = gr.Button("停止", variant="secondary"); stopBtn2.style(size="sm")
clearBtn2 = gr.Button("清除", variant="secondary", visible=False); clearBtn2.style(size="sm") clearBtn2 = gr.Button("清除", elem_id="elem_clear2", variant="secondary", visible=False); clearBtn2.style(size="sm")
with gr.Floating(init_x="20%", init_y="50%", visible=False, width="40%", drag="top") as area_customize: with gr.Floating(init_x="20%", init_y="50%", visible=False, width="40%", drag="top") as area_customize:
@ -192,10 +193,12 @@ def main():
basic_fn_suffix = gr.Textbox(show_label=False, placeholder="输入新提示后缀", lines=4).style(container=False) basic_fn_suffix = gr.Textbox(show_label=False, placeholder="输入新提示后缀", lines=4).style(container=False)
with gr.Column(scale=1, min_width=70): with gr.Column(scale=1, min_width=70):
basic_fn_confirm = gr.Button("确认并保存", variant="primary"); basic_fn_confirm.style(size="sm") basic_fn_confirm = gr.Button("确认并保存", variant="primary"); basic_fn_confirm.style(size="sm")
basic_fn_load = gr.Button("加载已保存", variant="primary"); basic_fn_load.style(size="sm") basic_fn_clean = gr.Button("恢复默认", variant="primary"); basic_fn_clean.style(size="sm")
def assign_btn(persistent_cookie_, cookies_, basic_btn_dropdown_, basic_fn_title, basic_fn_prefix, basic_fn_suffix): def assign_btn(persistent_cookie_, cookies_, basic_btn_dropdown_, basic_fn_title, basic_fn_prefix, basic_fn_suffix, clean_up=False):
ret = {} ret = {}
# 读取之前的自定义按钮
customize_fn_overwrite_ = cookies_['customize_fn_overwrite'] customize_fn_overwrite_ = cookies_['customize_fn_overwrite']
# 更新新的自定义按钮
customize_fn_overwrite_.update({ customize_fn_overwrite_.update({
basic_btn_dropdown_: basic_btn_dropdown_:
{ {
@ -205,20 +208,34 @@ def main():
} }
} }
) )
cookies_.update(customize_fn_overwrite_) if clean_up:
customize_fn_overwrite_ = {}
cookies_.update(customize_fn_overwrite_) # 更新cookie
visible = (not clean_up) and (basic_fn_title != "")
if basic_btn_dropdown_ in customize_btns: if basic_btn_dropdown_ in customize_btns:
ret.update({customize_btns[basic_btn_dropdown_]: gr.update(visible=True, value=basic_fn_title)}) # 是自定义按钮,不是预定义按钮
ret.update({customize_btns[basic_btn_dropdown_]: gr.update(visible=visible, value=basic_fn_title)})
else: else:
ret.update({predefined_btns[basic_btn_dropdown_]: gr.update(visible=True, value=basic_fn_title)}) # 是预定义按钮
ret.update({predefined_btns[basic_btn_dropdown_]: gr.update(visible=visible, value=basic_fn_title)})
ret.update({cookies: cookies_}) ret.update({cookies: cookies_})
try: persistent_cookie_ = from_cookie_str(persistent_cookie_) # persistent cookie to dict try: persistent_cookie_ = from_cookie_str(persistent_cookie_) # persistent cookie to dict
except: persistent_cookie_ = {} except: persistent_cookie_ = {}
persistent_cookie_["custom_bnt"] = customize_fn_overwrite_ # dict update new value persistent_cookie_["custom_bnt"] = customize_fn_overwrite_ # dict update new value
persistent_cookie_ = to_cookie_str(persistent_cookie_) # persistent cookie to dict persistent_cookie_ = to_cookie_str(persistent_cookie_) # persistent cookie to dict
ret.update({persistent_cookie: persistent_cookie_}) # write persistent cookie ret.update({py_pickle_cookie: persistent_cookie_}) # write persistent cookie
return ret return ret
def reflesh_btn(persistent_cookie_, cookies_): # update btn
h = basic_fn_confirm.click(assign_btn, [py_pickle_cookie, cookies, basic_btn_dropdown, basic_fn_title, basic_fn_prefix, basic_fn_suffix],
[py_pickle_cookie, cookies, *customize_btns.values(), *predefined_btns.values()])
h.then(None, [py_pickle_cookie], None, _js="""(py_pickle_cookie)=>{setCookie("py_pickle_cookie", py_pickle_cookie, 365);}""")
# clean up btn
h2 = basic_fn_clean.click(assign_btn, [py_pickle_cookie, cookies, basic_btn_dropdown, basic_fn_title, basic_fn_prefix, basic_fn_suffix, gr.State(True)],
[py_pickle_cookie, cookies, *customize_btns.values(), *predefined_btns.values()])
h2.then(None, [py_pickle_cookie], None, _js="""(py_pickle_cookie)=>{setCookie("py_pickle_cookie", py_pickle_cookie, 365);}""")
def persistent_cookie_reload(persistent_cookie_, cookies_):
ret = {} ret = {}
for k in customize_btns: for k in customize_btns:
ret.update({customize_btns[k]: gr.update(visible=False, value="")}) ret.update({customize_btns[k]: gr.update(visible=False, value="")})
@ -236,25 +253,16 @@ def main():
else: ret.update({predefined_btns[k]: gr.update(visible=True, value=v['Title'])}) else: ret.update({predefined_btns[k]: gr.update(visible=True, value=v['Title'])})
return ret return ret
basic_fn_load.click(reflesh_btn, [persistent_cookie, cookies], [cookies, *customize_btns.values(), *predefined_btns.values()])
h = basic_fn_confirm.click(assign_btn, [persistent_cookie, cookies, basic_btn_dropdown, basic_fn_title, basic_fn_prefix, basic_fn_suffix],
[persistent_cookie, cookies, *customize_btns.values(), *predefined_btns.values()])
# save persistent cookie
h.then(None, [persistent_cookie], None, _js="""(persistent_cookie)=>{setCookie("persistent_cookie", persistent_cookie, 5);}""")
# 功能区显示开关与功能区的互动 # 功能区显示开关与功能区的互动
def fn_area_visibility(a): def fn_area_visibility(a):
ret = {} ret = {}
ret.update({area_basic_fn: gr.update(visible=("基础功能区" in a))})
ret.update({area_crazy_fn: gr.update(visible=("函数插件区" in a))})
ret.update({area_input_primary: gr.update(visible=("浮动输入区" not in a))}) ret.update({area_input_primary: gr.update(visible=("浮动输入区" not in a))})
ret.update({area_input_secondary: gr.update(visible=("浮动输入区" in a))}) ret.update({area_input_secondary: gr.update(visible=("浮动输入区" in a))})
ret.update({clearBtn: gr.update(visible=("输入清除键" in a))})
ret.update({clearBtn2: gr.update(visible=("输入清除键" in a))})
ret.update({plugin_advanced_arg: gr.update(visible=("插件参数区" in a))}) ret.update({plugin_advanced_arg: gr.update(visible=("插件参数区" in a))})
if "浮动输入区" in a: ret.update({txt: gr.update(value="")}) if "浮动输入区" in a: ret.update({txt: gr.update(value="")})
return ret return ret
checkboxes.select(fn_area_visibility, [checkboxes], [area_basic_fn, area_crazy_fn, area_input_primary, area_input_secondary, txt, txt2, clearBtn, clearBtn2, plugin_advanced_arg] ) checkboxes.select(fn_area_visibility, [checkboxes], [area_basic_fn, area_crazy_fn, area_input_primary, area_input_secondary, txt, txt2, plugin_advanced_arg] )
checkboxes.select(None, [checkboxes], None, _js=js_code_show_or_hide)
# 功能区显示开关与功能区的互动 # 功能区显示开关与功能区的互动
def fn_area_visibility_2(a): def fn_area_visibility_2(a):
@ -262,6 +270,7 @@ def main():
ret.update({area_customize: gr.update(visible=("自定义菜单" in a))}) ret.update({area_customize: gr.update(visible=("自定义菜单" in a))})
return ret return ret
checkboxes_2.select(fn_area_visibility_2, [checkboxes_2], [area_customize] ) checkboxes_2.select(fn_area_visibility_2, [checkboxes_2], [area_customize] )
checkboxes_2.select(None, [checkboxes_2], None, _js=js_code_show_or_hide_group2)
# 整理反复出现的控件句柄组合 # 整理反复出现的控件句柄组合
input_combo = [cookies, max_length_sl, md_dropdown, txt, txt2, top_p, temperature, chatbot, history, system_prompt, plugin_advanced_arg] input_combo = [cookies, max_length_sl, md_dropdown, txt, txt2, top_p, temperature, chatbot, history, system_prompt, plugin_advanced_arg]
@ -272,15 +281,17 @@ def main():
cancel_handles.append(txt2.submit(**predict_args)) cancel_handles.append(txt2.submit(**predict_args))
cancel_handles.append(submitBtn.click(**predict_args)) cancel_handles.append(submitBtn.click(**predict_args))
cancel_handles.append(submitBtn2.click(**predict_args)) cancel_handles.append(submitBtn2.click(**predict_args))
resetBtn.click(lambda: ([], [], "已重置"), None, [chatbot, history, status]) resetBtn.click(None, None, [chatbot, history, status], _js=js_code_reset) # 先在前端快速清除chatbot&status
resetBtn2.click(lambda: ([], [], "已重置"), None, [chatbot, history, status]) resetBtn2.click(None, None, [chatbot, history, status], _js=js_code_reset) # 先在前端快速清除chatbot&status
clearBtn.click(lambda: ("",""), None, [txt, txt2]) resetBtn.click(lambda: ([], [], "已重置"), None, [chatbot, history, status]) # 再在后端清除history
clearBtn2.click(lambda: ("",""), None, [txt, txt2]) resetBtn2.click(lambda: ([], [], "已重置"), None, [chatbot, history, status]) # 再在后端清除history
clearBtn.click(None, None, [txt, txt2], _js=js_code_clear)
clearBtn2.click(None, None, [txt, txt2], _js=js_code_clear)
if AUTO_CLEAR_TXT: if AUTO_CLEAR_TXT:
submitBtn.click(lambda: ("",""), None, [txt, txt2]) submitBtn.click(None, None, [txt, txt2], _js=js_code_clear)
submitBtn2.click(lambda: ("",""), None, [txt, txt2]) submitBtn2.click(None, None, [txt, txt2], _js=js_code_clear)
txt.submit(lambda: ("",""), None, [txt, txt2]) txt.submit(None, None, [txt, txt2], _js=js_code_clear)
txt2.submit(lambda: ("",""), None, [txt, txt2]) txt2.submit(None, None, [txt, txt2], _js=js_code_clear)
# 基础功能区的回调函数注册 # 基础功能区的回调函数注册
for k in functional: for k in functional:
if ("Visible" in functional[k]) and (not functional[k]["Visible"]): continue if ("Visible" in functional[k]) and (not functional[k]["Visible"]): continue
@ -360,10 +371,10 @@ def main():
audio_mic.stream(deal_audio, inputs=[audio_mic, cookies]) audio_mic.stream(deal_audio, inputs=[audio_mic, cookies])
demo.load(init_cookie, inputs=[cookies, chatbot], outputs=[cookies]) demo.load(init_cookie, inputs=[cookies], outputs=[cookies])
darkmode_js = js_code_for_darkmode_init demo.load(persistent_cookie_reload, inputs = [py_pickle_cookie, cookies],
demo.load(None, inputs=None, outputs=[persistent_cookie], _js=js_code_for_persistent_cookie_init) outputs = [py_pickle_cookie, cookies, *customize_btns.values(), *predefined_btns.values()], _js=js_code_for_persistent_cookie_init)
demo.load(None, inputs=[dark_mode], outputs=None, _js=darkmode_js) # 配置暗色主题或亮色主题 demo.load(None, inputs=[dark_mode], outputs=None, _js="""(dark_mode)=>{apply_cookie_for_checkbox(dark_mode);}""") # 配置暗色主题或亮色主题
demo.load(None, inputs=[gr.Textbox(LAYOUT, visible=False)], outputs=None, _js='(LAYOUT)=>{GptAcademicJavaScriptInit(LAYOUT);}') demo.load(None, inputs=[gr.Textbox(LAYOUT, visible=False)], outputs=None, _js='(LAYOUT)=>{GptAcademicJavaScriptInit(LAYOUT);}')
# gradio的inbrowser触发不太稳定回滚代码到原始的浏览器打开函数 # gradio的inbrowser触发不太稳定回滚代码到原始的浏览器打开函数

View File

@ -31,6 +31,9 @@ from .bridge_qianfan import predict as qianfan_ui
from .bridge_google_gemini import predict as genai_ui from .bridge_google_gemini import predict as genai_ui
from .bridge_google_gemini import predict_no_ui_long_connection as genai_noui from .bridge_google_gemini import predict_no_ui_long_connection as genai_noui
from .bridge_zhipu import predict_no_ui_long_connection as zhipu_noui
from .bridge_zhipu import predict as zhipu_ui
colors = ['#FF00FF', '#00FFFF', '#FF0000', '#990099', '#009999', '#990044'] colors = ['#FF00FF', '#00FFFF', '#FF0000', '#990099', '#009999', '#990044']
class LazyloadTiktoken(object): class LazyloadTiktoken(object):
@ -215,16 +218,25 @@ model_info = {
"token_cnt": get_token_num_gpt4, "token_cnt": get_token_num_gpt4,
}, },
# api_2d (此后不需要在此处添加api2d的接口了因为下面的代码会自动添加) # 智谱AI
"api2d-gpt-3.5-turbo": { "glm-4": {
"fn_with_ui": chatgpt_ui, "fn_with_ui": zhipu_ui,
"fn_without_ui": chatgpt_noui, "fn_without_ui": zhipu_noui,
"endpoint": api2d_endpoint, "endpoint": None,
"max_token": 4096, "max_token": 10124 * 8,
"tokenizer": tokenizer_gpt35,
"token_cnt": get_token_num_gpt35,
},
"glm-3-turbo": {
"fn_with_ui": zhipu_ui,
"fn_without_ui": zhipu_noui,
"endpoint": None,
"max_token": 10124 * 4,
"tokenizer": tokenizer_gpt35, "tokenizer": tokenizer_gpt35,
"token_cnt": get_token_num_gpt35, "token_cnt": get_token_num_gpt35,
}, },
# api_2d (此后不需要在此处添加api2d的接口了因为下面的代码会自动添加)
"api2d-gpt-4": { "api2d-gpt-4": {
"fn_with_ui": chatgpt_ui, "fn_with_ui": chatgpt_ui,
"fn_without_ui": chatgpt_noui, "fn_without_ui": chatgpt_noui,
@ -580,19 +592,17 @@ if "llama2" in AVAIL_LLM_MODELS: # llama2
}) })
except: except:
print(trimmed_format_exc()) print(trimmed_format_exc())
if "zhipuai" in AVAIL_LLM_MODELS: # zhipuai if "zhipuai" in AVAIL_LLM_MODELS: # zhipuai 是glm-4的别名向后兼容配置
try: try:
from .bridge_zhipu import predict_no_ui_long_connection as zhipu_noui
from .bridge_zhipu import predict as zhipu_ui
model_info.update({ model_info.update({
"zhipuai": { "zhipuai": {
"fn_with_ui": zhipu_ui, "fn_with_ui": zhipu_ui,
"fn_without_ui": zhipu_noui, "fn_without_ui": zhipu_noui,
"endpoint": None, "endpoint": None,
"max_token": 4096, "max_token": 10124 * 8,
"tokenizer": tokenizer_gpt35, "tokenizer": tokenizer_gpt35,
"token_cnt": get_token_num_gpt35, "token_cnt": get_token_num_gpt35,
} },
}) })
except: except:
print(trimmed_format_exc()) print(trimmed_format_exc())

View File

@ -113,6 +113,8 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
error_msg = get_full_error(chunk, stream_response).decode() error_msg = get_full_error(chunk, stream_response).decode()
if "reduce the length" in error_msg: if "reduce the length" in error_msg:
raise ConnectionAbortedError("OpenAI拒绝了请求:" + error_msg) raise ConnectionAbortedError("OpenAI拒绝了请求:" + error_msg)
elif """type":"upstream_error","param":"307""" in error_msg:
raise ConnectionAbortedError("正常结束但显示Token不足导致输出不完整请削减单次输入的文本量。")
else: else:
raise RuntimeError("OpenAI拒绝了请求" + error_msg) raise RuntimeError("OpenAI拒绝了请求" + error_msg)
if ('data: [DONE]' in chunk_decoded): break # api2d 正常完成 if ('data: [DONE]' in chunk_decoded): break # api2d 正常完成

View File

@ -57,6 +57,10 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
if "vision" in llm_kwargs["llm_model"]: if "vision" in llm_kwargs["llm_model"]:
have_recent_file, image_paths = have_any_recent_upload_image_files(chatbot) have_recent_file, image_paths = have_any_recent_upload_image_files(chatbot)
if not have_recent_file:
chatbot.append((inputs, "没有检测到任何近期上传的图像文件请上传jpg格式的图片此外请注意拓展名需要小写"))
yield from update_ui(chatbot=chatbot, history=history, msg="等待图片") # 刷新界面
return
def make_media_input(inputs, image_paths): def make_media_input(inputs, image_paths):
for image_path in image_paths: for image_path in image_paths:
inputs = inputs + f'<br/><br/><div align="center"><img src="file={os.path.abspath(image_path)}"></div>' inputs = inputs + f'<br/><br/><div align="center"><img src="file={os.path.abspath(image_path)}"></div>'

View File

@ -1,15 +1,21 @@
import time import time
import os
from toolbox import update_ui, get_conf, update_ui_lastest_msg from toolbox import update_ui, get_conf, update_ui_lastest_msg
from toolbox import check_packages, report_exception from toolbox import check_packages, report_exception, have_any_recent_upload_image_files
model_name = '智谱AI大模型' model_name = '智谱AI大模型'
zhipuai_default_model = 'glm-4'
def validate_key(): def validate_key():
ZHIPUAI_API_KEY = get_conf("ZHIPUAI_API_KEY") ZHIPUAI_API_KEY = get_conf("ZHIPUAI_API_KEY")
if ZHIPUAI_API_KEY == '': return False if ZHIPUAI_API_KEY == '': return False
return True return True
def make_media_input(inputs, image_paths):
for image_path in image_paths:
inputs = inputs + f'<br/><br/><div align="center"><img src="file={os.path.abspath(image_path)}"></div>'
return inputs
def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False): def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
""" """
多线程方法 多线程方法
@ -18,32 +24,38 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
watch_dog_patience = 5 watch_dog_patience = 5
response = "" response = ""
if llm_kwargs["llm_model"] == "zhipuai":
llm_kwargs["llm_model"] = zhipuai_default_model
if validate_key() is False: if validate_key() is False:
raise RuntimeError('请配置ZHIPUAI_API_KEY') raise RuntimeError('请配置ZHIPUAI_API_KEY')
from .com_zhipuapi import ZhipuRequestInstance # 开始接收回复
sri = ZhipuRequestInstance() from .com_zhipuglm import ZhipuChatInit
for response in sri.generate(inputs, llm_kwargs, history, sys_prompt): zhipu_bro_init = ZhipuChatInit()
for chunk, response in zhipu_bro_init.generate_chat(inputs, llm_kwargs, history, sys_prompt):
if len(observe_window) >= 1: if len(observe_window) >= 1:
observe_window[0] = response observe_window[0] = response
if len(observe_window) >= 2: if len(observe_window) >= 2:
if (time.time()-observe_window[1]) > watch_dog_patience: raise RuntimeError("程序终止。") if (time.time() - observe_window[1]) > watch_dog_patience:
raise RuntimeError("程序终止。")
return response return response
def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream = True, additional_fn=None):
def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream=True, additional_fn=None):
""" """
单线程方法 单线程方法
函数的说明请见 request_llms/bridge_all.py 函数的说明请见 request_llms/bridge_all.py
""" """
chatbot.append((inputs, "")) chatbot.append([inputs, ""])
yield from update_ui(chatbot=chatbot, history=history) yield from update_ui(chatbot=chatbot, history=history)
# 尝试导入依赖,如果缺少依赖,则给出安装建议 # 尝试导入依赖,如果缺少依赖,则给出安装建议
try: try:
check_packages(["zhipuai"]) check_packages(["zhipuai"])
except: except:
yield from update_ui_lastest_msg(f"导入软件依赖失败。使用该模型需要额外依赖,安装方法```pip install zhipuai==1.0.7```。", yield from update_ui_lastest_msg(f"导入软件依赖失败。使用该模型需要额外依赖,安装方法```pip install --upgrade zhipuai```。",
chatbot=chatbot, history=history, delay=0) chatbot=chatbot, history=history, delay=0)
return return
if validate_key() is False: if validate_key() is False:
@ -53,16 +65,29 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
if additional_fn is not None: if additional_fn is not None:
from core_functional import handle_core_functionality from core_functional import handle_core_functionality
inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot) inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
chatbot[-1] = [inputs, ""]
# 开始接收回复
from .com_zhipuapi import ZhipuRequestInstance
sri = ZhipuRequestInstance()
for response in sri.generate(inputs, llm_kwargs, history, system_prompt):
chatbot[-1] = (inputs, response)
yield from update_ui(chatbot=chatbot, history=history) yield from update_ui(chatbot=chatbot, history=history)
# 总结输出 if llm_kwargs["llm_model"] == "zhipuai":
if response == f"[Local Message] 等待{model_name}响应中 ...": llm_kwargs["llm_model"] = zhipuai_default_model
response = f"[Local Message] {model_name}响应异常 ..."
if llm_kwargs["llm_model"] in ["glm-4v"]:
have_recent_file, image_paths = have_any_recent_upload_image_files(chatbot)
if not have_recent_file:
chatbot.append((inputs, "没有检测到任何近期上传的图像文件请上传jpg格式的图片此外请注意拓展名需要小写"))
yield from update_ui(chatbot=chatbot, history=history, msg="等待图片") # 刷新界面
return
if have_recent_file:
inputs = make_media_input(inputs, image_paths)
chatbot[-1] = [inputs, ""]
yield from update_ui(chatbot=chatbot, history=history)
# 开始接收回复
from .com_zhipuglm import ZhipuChatInit
zhipu_bro_init = ZhipuChatInit()
for chunk, response in zhipu_bro_init.generate_chat(inputs, llm_kwargs, history, system_prompt):
chatbot[-1] = [inputs, response]
yield from update_ui(chatbot=chatbot, history=history)
history.extend([inputs, response]) history.extend([inputs, response])
yield from update_ui(chatbot=chatbot, history=history) yield from update_ui(chatbot=chatbot, history=history)

View File

@ -1,70 +0,0 @@
from toolbox import get_conf
import threading
import logging
timeout_bot_msg = '[Local Message] Request timeout. Network error.'
class ZhipuRequestInstance():
def __init__(self):
self.time_to_yield_event = threading.Event()
self.time_to_exit_event = threading.Event()
self.result_buf = ""
def generate(self, inputs, llm_kwargs, history, system_prompt):
# import _thread as thread
import zhipuai
ZHIPUAI_API_KEY, ZHIPUAI_MODEL = get_conf("ZHIPUAI_API_KEY", "ZHIPUAI_MODEL")
zhipuai.api_key = ZHIPUAI_API_KEY
self.result_buf = ""
response = zhipuai.model_api.sse_invoke(
model=ZHIPUAI_MODEL,
prompt=generate_message_payload(inputs, llm_kwargs, history, system_prompt),
top_p=llm_kwargs['top_p']*0.7, # 智谱的API抽风手动*0.7给做个线性变换
temperature=llm_kwargs['temperature']*0.95, # 智谱的API抽风手动*0.7给做个线性变换
)
for event in response.events():
if event.event == "add":
# if self.result_buf == "" and event.data.startswith(" "):
# event.data = event.data.lstrip(" ") # 每次智谱为啥都要带个空格开头呢?
self.result_buf += event.data
yield self.result_buf
elif event.event == "error" or event.event == "interrupted":
raise RuntimeError("Unknown error:" + event.data)
elif event.event == "finish":
yield self.result_buf
break
else:
raise RuntimeError("Unknown error:" + str(event))
if self.result_buf == "":
yield "智谱没有返回任何数据, 请检查ZHIPUAI_API_KEY和ZHIPUAI_MODEL是否填写正确."
logging.info(f'[raw_input] {inputs}')
logging.info(f'[response] {self.result_buf}')
return self.result_buf
def generate_message_payload(inputs, llm_kwargs, history, system_prompt):
conversation_cnt = len(history) // 2
messages = [{"role": "user", "content": system_prompt}, {"role": "assistant", "content": "Certainly!"}]
if conversation_cnt:
for index in range(0, 2*conversation_cnt, 2):
what_i_have_asked = {}
what_i_have_asked["role"] = "user"
what_i_have_asked["content"] = history[index]
what_gpt_answer = {}
what_gpt_answer["role"] = "assistant"
what_gpt_answer["content"] = history[index+1]
if what_i_have_asked["content"] != "":
if what_gpt_answer["content"] == "":
continue
if what_gpt_answer["content"] == timeout_bot_msg:
continue
messages.append(what_i_have_asked)
messages.append(what_gpt_answer)
else:
messages[-1]['content'] = what_gpt_answer['content']
what_i_ask_now = {}
what_i_ask_now["role"] = "user"
what_i_ask_now["content"] = inputs
messages.append(what_i_ask_now)
return messages

View File

@ -0,0 +1,84 @@
# encoding: utf-8
# @Time : 2024/1/22
# @Author : Kilig947 & binary husky
# @Descr : 兼容最新的智谱Ai
from toolbox import get_conf
from zhipuai import ZhipuAI
from toolbox import get_conf, encode_image, get_pictures_list
import logging, os
def input_encode_handler(inputs, llm_kwargs):
if llm_kwargs["most_recent_uploaded"].get("path"):
image_paths = get_pictures_list(llm_kwargs["most_recent_uploaded"]["path"])
md_encode = []
for md_path in image_paths:
type_ = os.path.splitext(md_path)[1].replace(".", "")
type_ = "jpeg" if type_ == "jpg" else type_
md_encode.append({"data": encode_image(md_path), "type": type_})
return inputs, md_encode
class ZhipuChatInit:
def __init__(self):
ZHIPUAI_API_KEY, ZHIPUAI_MODEL = get_conf("ZHIPUAI_API_KEY", "ZHIPUAI_MODEL")
if len(ZHIPUAI_MODEL) > 0:
logging.error('ZHIPUAI_MODEL 配置项选项已经弃用请在LLM_MODEL中配置')
self.zhipu_bro = ZhipuAI(api_key=ZHIPUAI_API_KEY)
self.model = ''
def __conversation_user(self, user_input: str, llm_kwargs):
if self.model not in ["glm-4v"]:
return {"role": "user", "content": user_input}
else:
input_, encode_img = input_encode_handler(user_input, llm_kwargs=llm_kwargs)
what_i_have_asked = {"role": "user", "content": []}
what_i_have_asked['content'].append({"type": 'text', "text": user_input})
if encode_img:
img_d = {"type": "image_url",
"image_url": {'url': encode_img}}
what_i_have_asked['content'].append(img_d)
return what_i_have_asked
def __conversation_history(self, history, llm_kwargs):
messages = []
conversation_cnt = len(history) // 2
if conversation_cnt:
for index in range(0, 2 * conversation_cnt, 2):
what_i_have_asked = self.__conversation_user(history[index], llm_kwargs)
what_gpt_answer = {
"role": "assistant",
"content": history[index + 1]
}
messages.append(what_i_have_asked)
messages.append(what_gpt_answer)
return messages
def __conversation_message_payload(self, inputs, llm_kwargs, history, system_prompt):
messages = []
if system_prompt:
messages.append({"role": "system", "content": system_prompt})
self.model = llm_kwargs['llm_model']
messages.extend(self.__conversation_history(history, llm_kwargs)) # 处理 history
messages.append(self.__conversation_user(inputs, llm_kwargs)) # 处理用户对话
response = self.zhipu_bro.chat.completions.create(
model=self.model, messages=messages, stream=True,
temperature=llm_kwargs.get('temperature', 0.95) * 0.95, # 只能传默认的 temperature 和 top_p
top_p=llm_kwargs.get('top_p', 0.7) * 0.7,
max_tokens=llm_kwargs.get('max_tokens', 1024 * 4), # 最大输出模型的一半
)
return response
def generate_chat(self, inputs, llm_kwargs, history, system_prompt):
self.model = llm_kwargs['llm_model']
response = self.__conversation_message_payload(inputs, llm_kwargs, history, system_prompt)
bro_results = ''
for chunk in response:
bro_results += chunk.choices[0].delta.content
yield chunk.choices[0].delta.content, bro_results
if __name__ == '__main__':
zhipu = ZhipuChatInit()
zhipu.generate_chat('你好', {'llm_model': 'glm-4'}, [], '你是WPSAi')

View File

@ -1,10 +1,10 @@
https://public.gpt-academic.top/publish/gradio-3.32.7-py3-none-any.whl https://public.gpt-academic.top/publish/gradio-3.32.8-py3-none-any.whl
gradio-client==0.8 gradio-client==0.8
pypdf2==2.12.1 pypdf2==2.12.1
zhipuai<2 zhipuai>=2
tiktoken>=0.3.3 tiktoken>=0.3.3
requests[socks] requests[socks]
pydantic==1.10.11 pydantic==2.5.2
protobuf==3.18 protobuf==3.18
transformers>=4.27.1 transformers>=4.27.1
scipdf_parser>=0.52 scipdf_parser>=0.52

View File

@ -20,10 +20,10 @@ if __name__ == "__main__":
# plugin_test(plugin='crazy_functions.函数动态生成->函数动态生成', main_input='交换图像的蓝色通道和红色通道', advanced_arg={"file_path_arg": "./build/ants.jpg"}) # plugin_test(plugin='crazy_functions.函数动态生成->函数动态生成', main_input='交换图像的蓝色通道和红色通道', advanced_arg={"file_path_arg": "./build/ants.jpg"})
# plugin_test(plugin='crazy_functions.Latex输出PDF结果->Latex翻译中文并重新编译PDF', main_input="2307.07522") # plugin_test(plugin='crazy_functions.Latex输出PDF->Latex翻译中文并重新编译PDF', main_input="2307.07522")
plugin_test( plugin_test(
plugin="crazy_functions.Latex输出PDF结果->Latex翻译中文并重新编译PDF", plugin="crazy_functions.Latex输出PDF->Latex翻译中文并重新编译PDF",
main_input="G:/SEAFILE_LOCAL/50503047/我的资料库/学位/paperlatex/aaai/Fu_8368_with_appendix", main_input="G:/SEAFILE_LOCAL/50503047/我的资料库/学位/paperlatex/aaai/Fu_8368_with_appendix",
) )
@ -66,7 +66,7 @@ if __name__ == "__main__":
# plugin_test(plugin='crazy_functions.知识库文件注入->读取知识库作答', main_input="远程云服务器部署?") # plugin_test(plugin='crazy_functions.知识库文件注入->读取知识库作答', main_input="远程云服务器部署?")
# plugin_test(plugin='crazy_functions.Latex输出PDF结果->Latex翻译中文并重新编译PDF', main_input="2210.03629") # plugin_test(plugin='crazy_functions.Latex输出PDF->Latex翻译中文并重新编译PDF', main_input="2210.03629")
# advanced_arg = {"advanced_arg":"--llm_to_learn=gpt-3.5-turbo --prompt_prefix='根据下面的服装类型提示想象一个穿着者对这个人外貌、身处的环境、内心世界、人设进行描写。要求100字以内用第二人称。' --system_prompt=''" } # advanced_arg = {"advanced_arg":"--llm_to_learn=gpt-3.5-turbo --prompt_prefix='根据下面的服装类型提示想象一个穿着者对这个人外貌、身处的环境、内心世界、人设进行描写。要求100字以内用第二人称。' --system_prompt=''" }
# plugin_test(plugin='crazy_functions.chatglm微调工具->微调数据集生成', main_input='build/dev.json', advanced_arg=advanced_arg) # plugin_test(plugin='crazy_functions.chatglm微调工具->微调数据集生成', main_input='build/dev.json', advanced_arg=advanced_arg)

View File

@ -1,296 +1 @@
/** // we have moved mermaid-related code to gradio-fix repository: binary-husky/gradio-fix@32150d0
* base64.ts
*
* Licensed under the BSD 3-Clause License.
* http://opensource.org/licenses/BSD-3-Clause
*
* References:
* http://en.wikipedia.org/wiki/Base64
*
* @author Dan Kogai (https://github.com/dankogai)
*/
const version = '3.7.2';
/**
* @deprecated use lowercase `version`.
*/
const VERSION = version;
const _hasatob = typeof atob === 'function';
const _hasbtoa = typeof btoa === 'function';
const _hasBuffer = typeof Buffer === 'function';
const _TD = typeof TextDecoder === 'function' ? new TextDecoder() : undefined;
const _TE = typeof TextEncoder === 'function' ? new TextEncoder() : undefined;
const b64ch = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/=';
const b64chs = Array.prototype.slice.call(b64ch);
const b64tab = ((a) => {
let tab = {};
a.forEach((c, i) => tab[c] = i);
return tab;
})(b64chs);
const b64re = /^(?:[A-Za-z\d+\/]{4})*?(?:[A-Za-z\d+\/]{2}(?:==)?|[A-Za-z\d+\/]{3}=?)?$/;
const _fromCC = String.fromCharCode.bind(String);
const _U8Afrom = typeof Uint8Array.from === 'function'
? Uint8Array.from.bind(Uint8Array)
: (it, fn = (x) => x) => new Uint8Array(Array.prototype.slice.call(it, 0).map(fn));
const _mkUriSafe = (src) => src
.replace(/=/g, '').replace(/[+\/]/g, (m0) => m0 == '+' ? '-' : '_');
const _tidyB64 = (s) => s.replace(/[^A-Za-z0-9\+\/]/g, '');
/**
* polyfill version of `btoa`
*/
const btoaPolyfill = (bin) => {
// console.log('polyfilled');
let u32, c0, c1, c2, asc = '';
const pad = bin.length % 3;
for (let i = 0; i < bin.length;) {
if ((c0 = bin.charCodeAt(i++)) > 255 ||
(c1 = bin.charCodeAt(i++)) > 255 ||
(c2 = bin.charCodeAt(i++)) > 255)
throw new TypeError('invalid character found');
u32 = (c0 << 16) | (c1 << 8) | c2;
asc += b64chs[u32 >> 18 & 63]
+ b64chs[u32 >> 12 & 63]
+ b64chs[u32 >> 6 & 63]
+ b64chs[u32 & 63];
}
return pad ? asc.slice(0, pad - 3) + "===".substring(pad) : asc;
};
/**
* does what `window.btoa` of web browsers do.
* @param {String} bin binary string
* @returns {string} Base64-encoded string
*/
const _btoa = _hasbtoa ? (bin) => btoa(bin)
: _hasBuffer ? (bin) => Buffer.from(bin, 'binary').toString('base64')
: btoaPolyfill;
const _fromUint8Array = _hasBuffer
? (u8a) => Buffer.from(u8a).toString('base64')
: (u8a) => {
// cf. https://stackoverflow.com/questions/12710001/how-to-convert-uint8-array-to-base64-encoded-string/12713326#12713326
const maxargs = 0x1000;
let strs = [];
for (let i = 0, l = u8a.length; i < l; i += maxargs) {
strs.push(_fromCC.apply(null, u8a.subarray(i, i + maxargs)));
}
return _btoa(strs.join(''));
};
/**
* converts a Uint8Array to a Base64 string.
* @param {boolean} [urlsafe] URL-and-filename-safe a la RFC4648 §5
* @returns {string} Base64 string
*/
const fromUint8Array = (u8a, urlsafe = false) => urlsafe ? _mkUriSafe(_fromUint8Array(u8a)) : _fromUint8Array(u8a);
// This trick is found broken https://github.com/dankogai/js-base64/issues/130
// const utob = (src: string) => unescape(encodeURIComponent(src));
// reverting good old fationed regexp
const cb_utob = (c) => {
if (c.length < 2) {
var cc = c.charCodeAt(0);
return cc < 0x80 ? c
: cc < 0x800 ? (_fromCC(0xc0 | (cc >>> 6))
+ _fromCC(0x80 | (cc & 0x3f)))
: (_fromCC(0xe0 | ((cc >>> 12) & 0x0f))
+ _fromCC(0x80 | ((cc >>> 6) & 0x3f))
+ _fromCC(0x80 | (cc & 0x3f)));
}
else {
var cc = 0x10000
+ (c.charCodeAt(0) - 0xD800) * 0x400
+ (c.charCodeAt(1) - 0xDC00);
return (_fromCC(0xf0 | ((cc >>> 18) & 0x07))
+ _fromCC(0x80 | ((cc >>> 12) & 0x3f))
+ _fromCC(0x80 | ((cc >>> 6) & 0x3f))
+ _fromCC(0x80 | (cc & 0x3f)));
}
};
const re_utob = /[\uD800-\uDBFF][\uDC00-\uDFFFF]|[^\x00-\x7F]/g;
/**
* @deprecated should have been internal use only.
* @param {string} src UTF-8 string
* @returns {string} UTF-16 string
*/
const utob = (u) => u.replace(re_utob, cb_utob);
//
const _encode = _hasBuffer
? (s) => Buffer.from(s, 'utf8').toString('base64')
: _TE
? (s) => _fromUint8Array(_TE.encode(s))
: (s) => _btoa(utob(s));
/**
* converts a UTF-8-encoded string to a Base64 string.
* @param {boolean} [urlsafe] if `true` make the result URL-safe
* @returns {string} Base64 string
*/
const encode = (src, urlsafe = false) => urlsafe
? _mkUriSafe(_encode(src))
: _encode(src);
/**
* converts a UTF-8-encoded string to URL-safe Base64 RFC4648 §5.
* @returns {string} Base64 string
*/
const encodeURI = (src) => encode(src, true);
// This trick is found broken https://github.com/dankogai/js-base64/issues/130
// const btou = (src: string) => decodeURIComponent(escape(src));
// reverting good old fationed regexp
const re_btou = /[\xC0-\xDF][\x80-\xBF]|[\xE0-\xEF][\x80-\xBF]{2}|[\xF0-\xF7][\x80-\xBF]{3}/g;
const cb_btou = (cccc) => {
switch (cccc.length) {
case 4:
var cp = ((0x07 & cccc.charCodeAt(0)) << 18)
| ((0x3f & cccc.charCodeAt(1)) << 12)
| ((0x3f & cccc.charCodeAt(2)) << 6)
| (0x3f & cccc.charCodeAt(3)), offset = cp - 0x10000;
return (_fromCC((offset >>> 10) + 0xD800)
+ _fromCC((offset & 0x3FF) + 0xDC00));
case 3:
return _fromCC(((0x0f & cccc.charCodeAt(0)) << 12)
| ((0x3f & cccc.charCodeAt(1)) << 6)
| (0x3f & cccc.charCodeAt(2)));
default:
return _fromCC(((0x1f & cccc.charCodeAt(0)) << 6)
| (0x3f & cccc.charCodeAt(1)));
}
};
/**
* @deprecated should have been internal use only.
* @param {string} src UTF-16 string
* @returns {string} UTF-8 string
*/
const btou = (b) => b.replace(re_btou, cb_btou);
/**
* polyfill version of `atob`
*/
const atobPolyfill = (asc) => {
// console.log('polyfilled');
asc = asc.replace(/\s+/g, '');
if (!b64re.test(asc))
throw new TypeError('malformed base64.');
asc += '=='.slice(2 - (asc.length & 3));
let u24, bin = '', r1, r2;
for (let i = 0; i < asc.length;) {
u24 = b64tab[asc.charAt(i++)] << 18
| b64tab[asc.charAt(i++)] << 12
| (r1 = b64tab[asc.charAt(i++)]) << 6
| (r2 = b64tab[asc.charAt(i++)]);
bin += r1 === 64 ? _fromCC(u24 >> 16 & 255)
: r2 === 64 ? _fromCC(u24 >> 16 & 255, u24 >> 8 & 255)
: _fromCC(u24 >> 16 & 255, u24 >> 8 & 255, u24 & 255);
}
return bin;
};
/**
* does what `window.atob` of web browsers do.
* @param {String} asc Base64-encoded string
* @returns {string} binary string
*/
const _atob = _hasatob ? (asc) => atob(_tidyB64(asc))
: _hasBuffer ? (asc) => Buffer.from(asc, 'base64').toString('binary')
: atobPolyfill;
//
const _toUint8Array = _hasBuffer
? (a) => _U8Afrom(Buffer.from(a, 'base64'))
: (a) => _U8Afrom(_atob(a), c => c.charCodeAt(0));
/**
* converts a Base64 string to a Uint8Array.
*/
const toUint8Array = (a) => _toUint8Array(_unURI(a));
//
const _decode = _hasBuffer
? (a) => Buffer.from(a, 'base64').toString('utf8')
: _TD
? (a) => _TD.decode(_toUint8Array(a))
: (a) => btou(_atob(a));
const _unURI = (a) => _tidyB64(a.replace(/[-_]/g, (m0) => m0 == '-' ? '+' : '/'));
/**
* converts a Base64 string to a UTF-8 string.
* @param {String} src Base64 string. Both normal and URL-safe are supported
* @returns {string} UTF-8 string
*/
const decode = (src) => _decode(_unURI(src));
/**
* check if a value is a valid Base64 string
* @param {String} src a value to check
*/
const isValid = (src) => {
if (typeof src !== 'string')
return false;
const s = src.replace(/\s+/g, '').replace(/={0,2}$/, '');
return !/[^\s0-9a-zA-Z\+/]/.test(s) || !/[^\s0-9a-zA-Z\-_]/.test(s);
};
//
const _noEnum = (v) => {
return {
value: v, enumerable: false, writable: true, configurable: true
};
};
/**
* extend String.prototype with relevant methods
*/
const extendString = function () {
const _add = (name, body) => Object.defineProperty(String.prototype, name, _noEnum(body));
_add('fromBase64', function () { return decode(this); });
_add('toBase64', function (urlsafe) { return encode(this, urlsafe); });
_add('toBase64URI', function () { return encode(this, true); });
_add('toBase64URL', function () { return encode(this, true); });
_add('toUint8Array', function () { return toUint8Array(this); });
};
/**
* extend Uint8Array.prototype with relevant methods
*/
const extendUint8Array = function () {
const _add = (name, body) => Object.defineProperty(Uint8Array.prototype, name, _noEnum(body));
_add('toBase64', function (urlsafe) { return fromUint8Array(this, urlsafe); });
_add('toBase64URI', function () { return fromUint8Array(this, true); });
_add('toBase64URL', function () { return fromUint8Array(this, true); });
};
/**
* extend Builtin prototypes with relevant methods
*/
const extendBuiltins = () => {
extendString();
extendUint8Array();
};
const gBase64 = {
version: version,
VERSION: VERSION,
atob: _atob,
atobPolyfill: atobPolyfill,
btoa: _btoa,
btoaPolyfill: btoaPolyfill,
fromBase64: decode,
toBase64: encode,
encode: encode,
encodeURI: encodeURI,
encodeURL: encodeURI,
utob: utob,
btou: btou,
decode: decode,
isValid: isValid,
fromUint8Array: fromUint8Array,
toUint8Array: toUint8Array,
extendString: extendString,
extendUint8Array: extendUint8Array,
extendBuiltins: extendBuiltins,
};
// makecjs:CUT //
export { version };
export { VERSION };
export { _atob as atob };
export { atobPolyfill };
export { _btoa as btoa };
export { btoaPolyfill };
export { decode as fromBase64 };
export { encode as toBase64 };
export { utob };
export { encode };
export { encodeURI };
export { encodeURI as encodeURL };
export { btou };
export { decode };
export { isValid };
export { fromUint8Array };
export { toUint8Array };
export { extendString };
export { extendUint8Array };
export { extendBuiltins };
// and finally,
export { gBase64 as Base64 };

View File

@ -59,6 +59,7 @@
/* Scrollbar Width */ /* Scrollbar Width */
::-webkit-scrollbar { ::-webkit-scrollbar {
height: 12px;
width: 12px; width: 12px;
} }

View File

@ -234,7 +234,7 @@ let timeoutID = null;
let lastInvocationTime = 0; let lastInvocationTime = 0;
let lastArgs = null; let lastArgs = null;
function do_something_but_not_too_frequently(min_interval, func) { function do_something_but_not_too_frequently(min_interval, func) {
return function(...args) { return function (...args) {
lastArgs = args; lastArgs = args;
const now = Date.now(); const now = Date.now();
if (!lastInvocationTime || (now - lastInvocationTime) >= min_interval) { if (!lastInvocationTime || (now - lastInvocationTime) >= min_interval) {
@ -263,13 +263,8 @@ function chatbotContentChanged(attempt = 1, force = false) {
gradioApp().querySelectorAll('#gpt-chatbot .message-wrap .message.bot').forEach(addCopyButton); gradioApp().querySelectorAll('#gpt-chatbot .message-wrap .message.bot').forEach(addCopyButton);
}, i === 0 ? 0 : 200); }, i === 0 ? 0 : 200);
} }
// we have moved mermaid-related code to gradio-fix repository: binary-husky/gradio-fix@32150d0
const run_mermaid_render = do_something_but_not_too_frequently(1000, function () {
const blocks = document.querySelectorAll(`pre.mermaid, diagram-div`);
if (blocks.length == 0) { return; }
uml("mermaid");
});
run_mermaid_render();
} }
@ -672,9 +667,9 @@ function limit_scroll_position() {
let scrollableDiv = document.querySelector('#gpt-chatbot > div.wrap'); let scrollableDiv = document.querySelector('#gpt-chatbot > div.wrap');
scrollableDiv.addEventListener('wheel', function (e) { scrollableDiv.addEventListener('wheel', function (e) {
let preventScroll = false; let preventScroll = false;
if (e.deltaX != 0) { prevented_offset = 0; return;} if (e.deltaX != 0) { prevented_offset = 0; return; }
if (this.scrollHeight == this.clientHeight) { prevented_offset = 0; return;} if (this.scrollHeight == this.clientHeight) { prevented_offset = 0; return; }
if (e.deltaY < 0) { prevented_offset = 0; return;} if (e.deltaY < 0) { prevented_offset = 0; return; }
if (e.deltaY > 0 && this.scrollHeight - this.clientHeight - this.scrollTop <= 1) { preventScroll = true; } if (e.deltaY > 0 && this.scrollHeight - this.clientHeight - this.scrollTop <= 1) { preventScroll = true; }
if (preventScroll) { if (preventScroll) {
@ -713,3 +708,161 @@ function GptAcademicJavaScriptInit(LAYOUT = "LEFT-RIGHT") {
// setInterval(function () { uml("mermaid") }, 5000); // 每50毫秒执行一次 // setInterval(function () { uml("mermaid") }, 5000); // 每50毫秒执行一次
} }
function loadLive2D() {
try {
$("<link>").attr({ href: "file=themes/waifu_plugin/waifu.css", rel: "stylesheet", type: "text/css" }).appendTo('head');
$('body').append('<div class="waifu"><div class="waifu-tips"></div><canvas id="live2d" class="live2d"></canvas><div class="waifu-tool"><span class="fui-home"></span> <span class="fui-chat"></span> <span class="fui-eye"></span> <span class="fui-user"></span> <span class="fui-photo"></span> <span class="fui-info-circle"></span> <span class="fui-cross"></span></div></div>');
$.ajax({
url: "file=themes/waifu_plugin/waifu-tips.js", dataType: "script", cache: true, success: function () {
$.ajax({
url: "file=themes/waifu_plugin/live2d.js", dataType: "script", cache: true, success: function () {
/* 可直接修改部分参数 */
live2d_settings['hitokotoAPI'] = "hitokoto.cn"; // 一言 API
live2d_settings['modelId'] = 3; // 默认模型 ID
live2d_settings['modelTexturesId'] = 44; // 默认材质 ID
live2d_settings['modelStorage'] = false; // 不储存模型 ID
live2d_settings['waifuSize'] = '210x187';
live2d_settings['waifuTipsSize'] = '187x52';
live2d_settings['canSwitchModel'] = true;
live2d_settings['canSwitchTextures'] = true;
live2d_settings['canSwitchHitokoto'] = false;
live2d_settings['canTakeScreenshot'] = false;
live2d_settings['canTurnToHomePage'] = false;
live2d_settings['canTurnToAboutPage'] = false;
live2d_settings['showHitokoto'] = false; // 显示一言
live2d_settings['showF12Status'] = false; // 显示加载状态
live2d_settings['showF12Message'] = false; // 显示看板娘消息
live2d_settings['showF12OpenMsg'] = false; // 显示控制台打开提示
live2d_settings['showCopyMessage'] = false; // 显示 复制内容 提示
live2d_settings['showWelcomeMessage'] = true; // 显示进入面页欢迎词
/* 在 initModel 前添加 */
initModel("file=themes/waifu_plugin/waifu-tips.json");
}
});
}
});
} catch (err) { console.log("[Error] JQuery is not defined.") }
}
function get_checkbox_selected_items(elem_id){
display_panel_arr = [];
document.getElementById(elem_id).querySelector('[data-testid="checkbox-group"]').querySelectorAll('label').forEach(label => {
// Get the span text
const spanText = label.querySelector('span').textContent;
// Get the input value
const checked = label.querySelector('input').checked;
if (checked) {
display_panel_arr.push(spanText)
}
});
return display_panel_arr;
}
function set_checkbox(key, bool, set_twice=false) {
set_success = false;
elem_ids = ["cbsc", "cbs"]
elem_ids.forEach(id => {
document.getElementById(id).querySelector('[data-testid="checkbox-group"]').querySelectorAll('label').forEach(label => {
// Get the span text
const spanText = label.querySelector('span').textContent;
if (spanText === key) {
if (bool){
label.classList.add('selected');
} else {
if (label.classList.contains('selected')) {
label.classList.remove('selected');
}
}
if (set_twice){
setTimeout(() => {
if (bool){
label.classList.add('selected');
} else {
if (label.classList.contains('selected')) {
label.classList.remove('selected');
}
}
}, 5000);
}
label.querySelector('input').checked = bool;
set_success = true;
return
}
});
});
if (!set_success){
console.log("设置checkbox失败没有找到对应的key")
}
}
function apply_cookie_for_checkbox(dark) {
// console.log("apply_cookie_for_checkboxes")
let searchString = "输入清除键";
let bool_value = "False";
////////////////// darkmode ///////////////////
if (getCookie("js_darkmode_cookie")) {
dark = getCookie("js_darkmode_cookie")
}
dark = dark == "True";
if (document.querySelectorAll('.dark').length) {
if (!dark) {
document.querySelectorAll('.dark').forEach(el => el.classList.remove('dark'));
}
} else {
if (dark) {
document.querySelector('body').classList.add('dark');
}
}
////////////////////// clearButton ///////////////////////////
if (getCookie("js_clearbtn_show_cookie")) {
// have cookie
bool_value = getCookie("js_clearbtn_show_cookie")
bool_value = bool_value == "True";
searchString = "输入清除键";
if (bool_value) {
let clearButton = document.getElementById("elem_clear");
let clearButton2 = document.getElementById("elem_clear2");
clearButton.style.display = "block";
clearButton2.style.display = "block";
set_checkbox(searchString, true);
} else {
let clearButton = document.getElementById("elem_clear");
let clearButton2 = document.getElementById("elem_clear2");
clearButton.style.display = "none";
clearButton2.style.display = "none";
set_checkbox(searchString, false);
}
}
////////////////////// live2d ///////////////////////////
if (getCookie("js_live2d_show_cookie")) {
// have cookie
searchString = "添加Live2D形象";
bool_value = getCookie("js_live2d_show_cookie");
bool_value = bool_value == "True";
if (bool_value) {
loadLive2D();
set_checkbox(searchString, true);
} else {
$('.waifu').hide();
set_checkbox(searchString, false);
}
} else {
// do not have cookie
// get conf
display_panel_arr = get_checkbox_selected_items("cbsc");
searchString = "添加Live2D形象";
if (display_panel_arr.includes(searchString)) {
loadLive2D();
} else {
}
}
}

View File

@ -5,17 +5,14 @@ def get_common_html_javascript_code():
js = "\n" js = "\n"
for jsf in [ for jsf in [
"file=themes/common.js", "file=themes/common.js",
"file=themes/mermaid.min.js",
"file=themes/mermaid_loader.js",
]: ]:
js += f"""<script src="{jsf}"></script>\n""" js += f"""<script src="{jsf}"></script>\n"""
# 添加Live2D # 添加Live2D
if ADD_WAIFU: if ADD_WAIFU:
for jsf in [ for jsf in [
"file=docs/waifu_plugin/jquery.min.js", "file=themes/waifu_plugin/jquery.min.js",
"file=docs/waifu_plugin/jquery-ui.min.js", "file=themes/waifu_plugin/jquery-ui.min.js",
"file=docs/waifu_plugin/autoload.js",
]: ]:
js += f"""<script src="{jsf}"></script>\n""" js += f"""<script src="{jsf}"></script>\n"""
return js return js

1590
themes/mermaid.min.js vendored

File diff suppressed because one or more lines are too long

View File

@ -1,55 +1 @@
import { deflate, inflate } from '/file=themes/pako.esm.mjs'; // we have moved mermaid-related code to gradio-fix repository: binary-husky/gradio-fix@32150d0
import { toUint8Array, fromUint8Array, toBase64, fromBase64 } from '/file=themes/base64.mjs';
const base64Serde = {
serialize: (state) => {
return toBase64(state, true);
},
deserialize: (state) => {
return fromBase64(state);
}
};
const pakoSerde = {
serialize: (state) => {
const data = new TextEncoder().encode(state);
const compressed = deflate(data, { level: 9 });
return fromUint8Array(compressed, true);
},
deserialize: (state) => {
const data = toUint8Array(state);
return inflate(data, { to: 'string' });
}
};
const serdes = {
base64: base64Serde,
pako: pakoSerde
};
export const serializeState = (state, serde = 'pako') => {
if (!(serde in serdes)) {
throw new Error(`Unknown serde type: ${serde}`);
}
const json = JSON.stringify(state);
const serialized = serdes[serde].serialize(json);
return `${serde}:${serialized}`;
};
const deserializeState = (state) => {
let type, serialized;
if (state.includes(':')) {
let tempType;
[tempType, serialized] = state.split(':');
if (tempType in serdes) {
type = tempType;
} else {
throw new Error(`Unknown serde type: ${tempType}`);
}
} else {
type = 'base64';
serialized = state;
}
const json = serdes[type].deserialize(serialized);
return JSON.parse(json);
};

View File

@ -1,197 +1 @@
const uml = async className => { // we have moved mermaid-related code to gradio-fix repository: binary-husky/gradio-fix@32150d0
// Custom element to encapsulate Mermaid content.
class MermaidDiv extends HTMLElement {
/**
* Creates a special Mermaid div shadow DOM.
* Works around issues of shared IDs.
* @return {void}
*/
constructor() {
super()
// Create the Shadow DOM and attach style
const shadow = this.attachShadow({ mode: "open" })
const style = document.createElement("style")
style.textContent = `
:host {
display: block;
line-height: initial;
font-size: 16px;
}
div.diagram {
margin: 0;
overflow: visible;
}`
shadow.appendChild(style)
}
}
if (typeof customElements.get("diagram-div") === "undefined") {
customElements.define("diagram-div", MermaidDiv)
}
const getFromCode = parent => {
// Handles <pre><code> text extraction.
let text = ""
for (let j = 0; j < parent.childNodes.length; j++) {
const subEl = parent.childNodes[j]
if (subEl.tagName.toLowerCase() === "code") {
for (let k = 0; k < subEl.childNodes.length; k++) {
const child = subEl.childNodes[k]
const whitespace = /^\s*$/
if (child.nodeName === "#text" && !(whitespace.test(child.nodeValue))) {
text = child.nodeValue
break
}
}
}
}
return text
}
function createOrUpdateHyperlink(parentElement, linkText, linkHref) {
// Search for an existing anchor element within the parentElement
let existingAnchor = parentElement.querySelector("a");
// Check if an anchor element already exists
if (existingAnchor) {
// Update the hyperlink reference if it's different from the current one
if (existingAnchor.href !== linkHref) {
existingAnchor.href = linkHref;
}
// Update the target attribute to ensure it opens in a new tab
existingAnchor.target = '_blank';
// If the text must be dynamic, uncomment and use the following line:
// existingAnchor.textContent = linkText;
} else {
// If no anchor exists, create one and append it to the parentElement
let anchorElement = document.createElement("a");
anchorElement.href = linkHref; // Set hyperlink reference
anchorElement.textContent = linkText; // Set text displayed
anchorElement.target = '_blank'; // Ensure it opens in a new tab
parentElement.appendChild(anchorElement); // Append the new anchor element to the parent
}
}
function removeLastLine(str) {
// 将字符串按换行符分割成数组
var lines = str.split('\n');
lines.pop();
// 将数组重新连接成字符串,并按换行符连接
var result = lines.join('\n');
return result;
}
// 给出配置 Provide a default config in case one is not specified
const defaultConfig = {
startOnLoad: false,
theme: "default",
flowchart: {
htmlLabels: false
},
er: {
useMaxWidth: false
},
sequence: {
useMaxWidth: false,
noteFontWeight: "14px",
actorFontSize: "14px",
messageFontSize: "16px"
}
}
if (document.body.classList.contains("dark")) {
defaultConfig.theme = "dark"
}
const Module = await import('/file=themes/mermaid_editor.js');
function do_render(block, code, codeContent, cnt) {
var rendered_content = mermaid.render(`_diagram_${cnt}`, code);
////////////////////////////// 记录有哪些代码已经被渲染了 ///////////////////////////////////
let codeFinishRenderElement = block.querySelector("code_finish_render"); // 如果block下已存在code_already_rendered元素则获取它
if (codeFinishRenderElement) { // 如果block下已存在code_already_rendered元素
codeFinishRenderElement.style.display = "none";
} else {
// 如果不存在code_finish_render元素则将code元素中的内容添加到新创建的code_finish_render元素中
let codeFinishRenderElementNew = document.createElement("code_finish_render"); // 创建一个新的code_already_rendered元素
codeFinishRenderElementNew.style.display = "none";
codeFinishRenderElementNew.textContent = "";
block.appendChild(codeFinishRenderElementNew); // 将新创建的code_already_rendered元素添加到block中
codeFinishRenderElement = codeFinishRenderElementNew;
}
////////////////////////////// 创建一个用于渲染的容器 ///////////////////////////////////
let mermaidRender = block.querySelector(".mermaid_render"); // 尝试获取已存在的<div class='mermaid_render'>
if (!mermaidRender) {
mermaidRender = document.createElement("div"); // 不存在,创建新的<div class='mermaid_render'>
mermaidRender.classList.add("mermaid_render");
block.appendChild(mermaidRender); // 将新创建的元素附加到block
}
mermaidRender.innerHTML = rendered_content
codeFinishRenderElement.textContent = code // 标记已经渲染的部分
////////////////////////////// 创建一个“点击这里编辑脑图” ///////////////////////////////
let pako_encode = Module.serializeState({
"code": codeContent,
"mermaid": "{\n \"theme\": \"default\"\n}",
"autoSync": true,
"updateDiagram": false
});
createOrUpdateHyperlink(block, "点击这里编辑脑图", "https://mermaid.live/edit#" + pako_encode)
}
// 加载配置 Load up the config
mermaid.mermaidAPI.globalReset() // 全局复位
const config = (typeof mermaidConfig === "undefined") ? defaultConfig : mermaidConfig
mermaid.initialize(config)
// 查找需要渲染的元素 Find all of our Mermaid sources and render them.
const blocks = document.querySelectorAll(`pre.mermaid`);
for (let i = 0; i < blocks.length; i++) {
var block = blocks[i]
////////////////////////////// 如果代码没有发生变化,就不渲染了 ///////////////////////////////////
var code = getFromCode(block);
let code_elem = block.querySelector("code");
let codeContent = code_elem.textContent; // 获取code元素中的文本内容
// 判断codeContent是否包含'<gpt_academic_hide_mermaid_code>'如果是则使code_elem隐藏
if (codeContent.indexOf('<gpt_academic_hide_mermaid_code>') !== -1) {
code_elem.style.display = "none";
}
// 如果block下已存在code_already_rendered元素则获取它
let codePendingRenderElement = block.querySelector("code_pending_render");
if (codePendingRenderElement) { // 如果block下已存在code_pending_render元素
codePendingRenderElement.style.display = "none";
if (codePendingRenderElement.textContent !== codeContent) {
codePendingRenderElement.textContent = codeContent; // 如果现有的code_pending_render元素中的内容与code元素中的内容不同更新code_pending_render元素中的内容
}
else {
continue; // 如果相同,就不处理了
}
} else { // 如果不存在code_pending_render元素则将code元素中的内容添加到新创建的code_pending_render元素中
let codePendingRenderElementNew = document.createElement("code_pending_render"); // 创建一个新的code_already_rendered元素
codePendingRenderElementNew.style.display = "none";
codePendingRenderElementNew.textContent = codeContent;
block.appendChild(codePendingRenderElementNew); // 将新创建的code_pending_render元素添加到block中
codePendingRenderElement = codePendingRenderElementNew;
}
////////////////////////////// 在这里才真正开始渲染 ///////////////////////////////////
try {
do_render(block, code, codeContent, i);
// console.log("渲染", codeContent);
} catch (err) {
try {
var lines = code.split('\n'); if (lines.length < 2) { continue; }
do_render(block, removeLastLine(code), codeContent, i);
// console.log("渲染", codeContent);
} catch (err) {
console.log("以下代码不能渲染", code, removeLastLine(code), err);
}
}
}
}

File diff suppressed because it is too large Load Diff

View File

@ -46,8 +46,7 @@ cookie相关工具函数
-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=- -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
""" """
def init_cookie(cookies):
def init_cookie(cookies, chatbot):
# 为每一位访问的用户赋予一个独一无二的uuid编码 # 为每一位访问的用户赋予一个独一无二的uuid编码
cookies.update({"uuid": uuid.uuid4()}) cookies.update({"uuid": uuid.uuid4()})
return cookies return cookies
@ -91,31 +90,107 @@ js_code_for_css_changing = """(css) => {
} }
""" """
js_code_for_darkmode_init = """(dark) => {
dark = dark == "True";
if (document.querySelectorAll('.dark').length) {
if (!dark){
document.querySelectorAll('.dark').forEach(el => el.classList.remove('dark'));
}
} else {
if (dark){
document.querySelector('body').classList.add('dark');
}
}
}
"""
js_code_for_toggle_darkmode = """() => { js_code_for_toggle_darkmode = """() => {
if (document.querySelectorAll('.dark').length) { if (document.querySelectorAll('.dark').length) {
setCookie("js_darkmode_cookie", "False", 365);
document.querySelectorAll('.dark').forEach(el => el.classList.remove('dark')); document.querySelectorAll('.dark').forEach(el => el.classList.remove('dark'));
} else { } else {
setCookie("js_darkmode_cookie", "True", 365);
document.querySelector('body').classList.add('dark'); document.querySelector('body').classList.add('dark');
} }
document.querySelectorAll('code_pending_render').forEach(code => {code.remove();}) document.querySelectorAll('code_pending_render').forEach(code => {code.remove();})
}""" }"""
js_code_for_persistent_cookie_init = """(persistent_cookie) => { js_code_for_persistent_cookie_init = """(py_pickle_cookie, cookie) => {
return getCookie("persistent_cookie"); return [getCookie("py_pickle_cookie"), cookie];
}
"""
js_code_reset = """
(a,b,c)=>{
return [[], [], "已重置"];
}
"""
js_code_clear = """
(a,b)=>{
return ["", ""];
}
"""
js_code_show_or_hide = """
(display_panel_arr)=>{
setTimeout(() => {
// get conf
display_panel_arr = get_checkbox_selected_items("cbs");
////////////////////// 输入清除键 ///////////////////////////
let searchString = "输入清除键";
let ele = "none";
if (display_panel_arr.includes(searchString)) {
let clearButton = document.getElementById("elem_clear");
let clearButton2 = document.getElementById("elem_clear2");
clearButton.style.display = "block";
clearButton2.style.display = "block";
setCookie("js_clearbtn_show_cookie", "True", 365);
} else {
let clearButton = document.getElementById("elem_clear");
let clearButton2 = document.getElementById("elem_clear2");
clearButton.style.display = "none";
clearButton2.style.display = "none";
setCookie("js_clearbtn_show_cookie", "False", 365);
}
////////////////////// 基础功能区 ///////////////////////////
searchString = "基础功能区";
if (display_panel_arr.includes(searchString)) {
ele = document.getElementById("basic-panel");
ele.style.display = "block";
} else {
ele = document.getElementById("basic-panel");
ele.style.display = "none";
}
////////////////////// 函数插件区 ///////////////////////////
searchString = "函数插件区";
if (display_panel_arr.includes(searchString)) {
ele = document.getElementById("plugin-panel");
ele.style.display = "block";
} else {
ele = document.getElementById("plugin-panel");
ele.style.display = "none";
}
}, 50);
}
"""
js_code_show_or_hide_group2 = """
(display_panel_arr)=>{
setTimeout(() => {
// console.log("display_panel_arr");
// get conf
display_panel_arr = get_checkbox_selected_items("cbsc");
////////////////////// 添加Live2D形象 ///////////////////////////
let searchString = "添加Live2D形象";
let ele = "none";
if (display_panel_arr.includes(searchString)) {
setCookie("js_live2d_show_cookie", "True", 365);
loadLive2D();
} else {
setCookie("js_live2d_show_cookie", "False", 365);
$('.waifu').hide();
}
}, 50);
} }
""" """

View File

View File

Before

Width:  |  Height:  |  Size: 56 KiB

After

Width:  |  Height:  |  Size: 56 KiB

View File

@ -92,7 +92,7 @@ String.prototype.render = function(context) {
}; };
var re = /x/; var re = /x/;
console.log(re); // console.log(re);
function empty(obj) {return typeof obj=="undefined"||obj==null||obj==""?true:false} function empty(obj) {return typeof obj=="undefined"||obj==null||obj==""?true:false}
function getRandText(text) {return Array.isArray(text) ? text[Math.floor(Math.random() * text.length + 1)-1] : text} function getRandText(text) {return Array.isArray(text) ? text[Math.floor(Math.random() * text.length + 1)-1] : text}
@ -120,7 +120,7 @@ function hideMessage(timeout) {
function initModel(waifuPath, type) { function initModel(waifuPath, type) {
/* console welcome message */ /* console welcome message */
eval(function(p,a,c,k,e,r){e=function(c){return(c<a?'':e(parseInt(c/a)))+((c=c%a)>35?String.fromCharCode(c+29):c.toString(36))};if(!''.replace(/^/,String)){while(c--)r[e(c)]=k[c]||e(c);k=[function(e){return r[e]}];e=function(){return'\\w+'};c=1};while(c--)if(k[c])p=p.replace(new RegExp('\\b'+e(c)+'\\b','g'),k[c]);return p}('8.d(" ");8.d("\\U,.\\y\\5.\\1\\1\\1\\1/\\1,\\u\\2 \\H\\n\\1\\1\\1\\1\\1\\b \', !-\\r\\j-i\\1/\\1/\\g\\n\\1\\1\\1 \\1 \\a\\4\\f\'\\1\\1\\1 L/\\a\\4\\5\\2\\n\\1\\1 \\1 /\\1 \\a,\\1 /|\\1 ,\\1 ,\\1\\1\\1 \',\\n\\1\\1\\1\\q \\1/ /-\\j/\\1\\h\\E \\9 \\5!\\1 i\\n\\1\\1\\1 \\3 \\6 7\\q\\4\\c\\1 \\3\'\\s-\\c\\2!\\t|\\1 |\\n\\1\\1\\1\\1 !,/7 \'0\'\\1\\1 \\X\\w| \\1 |\\1\\1\\1\\n\\1\\1\\1\\1 |.\\x\\"\\1\\l\\1\\1 ,,,, / |./ \\1 |\\n\\1\\1\\1\\1 \\3\'| i\\z.\\2,,A\\l,.\\B / \\1.i \\1|\\n\\1\\1\\1\\1\\1 \\3\'| | / C\\D/\\3\'\\5,\\1\\9.\\1|\\n\\1\\1\\1\\1\\1\\1 | |/i \\m|/\\1 i\\1,.\\6 |\\F\\1|\\n\\1\\1\\1\\1\\1\\1.|/ /\\1\\h\\G \\1 \\6!\\1\\1\\b\\1|\\n\\1\\1\\1 \\1 \\1 k\\5>\\2\\9 \\1 o,.\\6\\2 \\1 /\\2!\\n\\1\\1\\1\\1\\1\\1 !\'\\m//\\4\\I\\g\', \\b \\4\'7\'\\J\'\\n\\1\\1\\1\\1\\1\\1 \\3\'\\K|M,p,\\O\\3|\\P\\n\\1\\1\\1\\1\\1 \\1\\1\\1\\c-,/\\1|p./\\n\\1\\1\\1\\1\\1 \\1\\1\\1\'\\f\'\\1\\1!o,.:\\Q \\R\\S\\T v"+e.V+" / W "+e.N);8.d(" ");',60,60,'|u3000|uff64|uff9a|uff40|u30fd|uff8d||console|uff8a|uff0f|uff3c|uff84|log|live2d_settings|uff70|u00b4|uff49||u2010||u3000_|u3008||_|___|uff72|u2500|uff67|u30cf|u30fc||u30bd|u4ece|u30d8|uff1e|__|u30a4|k_|uff17_|u3000L_|u3000i|uff1a|u3009|uff34|uff70r|u30fdL__||___i|l2dVerDate|u30f3|u30ce|nLive2D|u770b|u677f|u5a18|u304f__|l2dVersion|FGHRSH|u00b40i'.split('|'),0,{})); // eval(function(p,a,c,k,e,r){e=function(c){return(c<a?'':e(parseInt(c/a)))+((c=c%a)>35?String.fromCharCode(c+29):c.toString(36))};if(!''.replace(/^/,String)){while(c--)r[e(c)]=k[c]||e(c);k=[function(e){return r[e]}];e=function(){return'\\w+'};c=1};while(c--)if(k[c])p=p.replace(new RegExp('\\b'+e(c)+'\\b','g'),k[c]);return p}('8.d(" ");8.d("\\U,.\\y\\5.\\1\\1\\1\\1/\\1,\\u\\2 \\H\\n\\1\\1\\1\\1\\1\\b \', !-\\r\\j-i\\1/\\1/\\g\\n\\1\\1\\1 \\1 \\a\\4\\f\'\\1\\1\\1 L/\\a\\4\\5\\2\\n\\1\\1 \\1 /\\1 \\a,\\1 /|\\1 ,\\1 ,\\1\\1\\1 \',\\n\\1\\1\\1\\q \\1/ /-\\j/\\1\\h\\E \\9 \\5!\\1 i\\n\\1\\1\\1 \\3 \\6 7\\q\\4\\c\\1 \\3\'\\s-\\c\\2!\\t|\\1 |\\n\\1\\1\\1\\1 !,/7 \'0\'\\1\\1 \\X\\w| \\1 |\\1\\1\\1\\n\\1\\1\\1\\1 |.\\x\\"\\1\\l\\1\\1 ,,,, / |./ \\1 |\\n\\1\\1\\1\\1 \\3\'| i\\z.\\2,,A\\l,.\\B / \\1.i \\1|\\n\\1\\1\\1\\1\\1 \\3\'| | / C\\D/\\3\'\\5,\\1\\9.\\1|\\n\\1\\1\\1\\1\\1\\1 | |/i \\m|/\\1 i\\1,.\\6 |\\F\\1|\\n\\1\\1\\1\\1\\1\\1.|/ /\\1\\h\\G \\1 \\6!\\1\\1\\b\\1|\\n\\1\\1\\1 \\1 \\1 k\\5>\\2\\9 \\1 o,.\\6\\2 \\1 /\\2!\\n\\1\\1\\1\\1\\1\\1 !\'\\m//\\4\\I\\g\', \\b \\4\'7\'\\J\'\\n\\1\\1\\1\\1\\1\\1 \\3\'\\K|M,p,\\O\\3|\\P\\n\\1\\1\\1\\1\\1 \\1\\1\\1\\c-,/\\1|p./\\n\\1\\1\\1\\1\\1 \\1\\1\\1\'\\f\'\\1\\1!o,.:\\Q \\R\\S\\T v"+e.V+" / W "+e.N);8.d(" ");',60,60,'|u3000|uff64|uff9a|uff40|u30fd|uff8d||console|uff8a|uff0f|uff3c|uff84|log|live2d_settings|uff70|u00b4|uff49||u2010||u3000_|u3008||_|___|uff72|u2500|uff67|u30cf|u30fc||u30bd|u4ece|u30d8|uff1e|__|u30a4|k_|uff17_|u3000L_|u3000i|uff1a|u3009|uff34|uff70r|u30fdL__||___i|l2dVerDate|u30f3|u30ce|nLive2D|u770b|u677f|u5a18|u304f__|l2dVersion|FGHRSH|u00b40i'.split('|'),0,{}));
/* 判断 JQuery */ /* 判断 JQuery */
if (typeof($.ajax) != 'function') typeof(jQuery.ajax) == 'function' ? window.$ = jQuery : console.log('[Error] JQuery is not defined.'); if (typeof($.ajax) != 'function') typeof(jQuery.ajax) == 'function' ? window.$ = jQuery : console.log('[Error] JQuery is not defined.');

View File

@ -44,8 +44,8 @@
{ "selector": ".container a[href^='http']", "text": ["要看看 <span style=\"color:#0099cc;\">{text}</span> 么?"] }, { "selector": ".container a[href^='http']", "text": ["要看看 <span style=\"color:#0099cc;\">{text}</span> 么?"] },
{ "selector": ".fui-home", "text": ["点击前往首页,想回到上一页可以使用浏览器的后退功能哦"] }, { "selector": ".fui-home", "text": ["点击前往首页,想回到上一页可以使用浏览器的后退功能哦"] },
{ "selector": ".fui-chat", "text": ["一言一语,一颦一笑。一字一句,一颗赛艇。"] }, { "selector": ".fui-chat", "text": ["一言一语,一颦一笑。一字一句,一颗赛艇。"] },
{ "selector": ".fui-eye", "text": ["嗯··· 要切换 看板娘 吗?"] }, { "selector": ".fui-eye", "text": ["嗯··· 要切换 Live2D形象 吗?"] },
{ "selector": ".fui-user", "text": ["喜欢换装 Play 吗?"] }, { "selector": ".fui-user", "text": ["喜欢换装吗?"] },
{ "selector": ".fui-photo", "text": ["要拍张纪念照片吗?"] }, { "selector": ".fui-photo", "text": ["要拍张纪念照片吗?"] },
{ "selector": ".fui-info-circle", "text": ["这里有关于我的信息呢"] }, { "selector": ".fui-info-circle", "text": ["这里有关于我的信息呢"] },
{ "selector": ".fui-cross", "text": ["你不喜欢我了吗..."] }, { "selector": ".fui-cross", "text": ["你不喜欢我了吗..."] },
@ -77,14 +77,28 @@
"看什么看(*^▽^*)", "看什么看(*^▽^*)",
"焦虑时,吃顿大餐心情就好啦^_^", "焦虑时,吃顿大餐心情就好啦^_^",
"你这个年纪,怎么睡得着觉的你^_^", "你这个年纪,怎么睡得着觉的你^_^",
"修改ADD_WAIFU=False我就不再打扰你了~", "打开“界面外观”菜单可选择关闭Live2D形象",
"经常去github看看我们的更新吧也许有好玩的新功能呢。", "经常去Github看看我们的更新吧也许有好玩的新功能呢。",
"试试本地大模型吧,有的也很强大的哦。", "试试本地大模型吧,有的也很强大的哦。",
"很多强大的函数插件隐藏在下拉菜单中呢。", "很多强大的函数插件隐藏在下拉菜单中呢。",
"红色的插件,使用之前需要把文件上传进去哦。", "插件使用之前,需要把文件上传进去哦。",
"想添加功能按钮吗读读readme很容易就学会啦。", "上传文件时,可以把文件直接拖进对话中的哦。",
"上传文件时,可以文件或图片粘贴到输入区哦。",
"想添加基础功能按钮吗?打开“界面外观”菜单进行自定义吧!",
"敏感或机密的信息不可以问AI的哦", "敏感或机密的信息不可以问AI的哦",
"LLM究竟是划时代的创新还是扼杀创造力的毒药呢" "LLM究竟是划时代的创新还是扼杀创造力的毒药呢",
"休息一下,起来走动走动吧!",
"今天的阳光也很不错哦,不妨外出晒晒。",
"笑一笑,生活更美好!",
"遇到难题,深呼吸就能解决一半。",
"偶尔换换环境,灵感也许就来了。",
"小憩片刻,醒来便是满血复活。",
"技术改变生活,让我们共同进步。",
"保持好奇心,探索未知的世界。",
"遇到困难记得还有朋友和AI陪在你身边。",
"劳逸结合,方能长久。",
"偶尔给自己放个假,放松心情。",
"不要害怕失败,勇敢尝试才能成功。"
] } ] }
], ],
"click": [ "click": [

View File

@ -1,5 +1,5 @@
{ {
"version": 3.71, "version": 3.72,
"show_feature": true, "show_feature": true,
"new_feature": "用绘图功能增强部分插件 <-> 基础功能区支持自动切换中英提示词 <-> 支持Mermaid绘图库让大模型绘制脑图 <-> 支持Gemini-pro <-> 支持直接拖拽文件到上传区 <-> 支持将图片粘贴到输入区" "new_feature": "支持切换多个智谱ai模型 <-> 用绘图功能增强部分插件 <-> 基础功能区支持自动切换中英提示词 <-> 支持Mermaid绘图库让大模型绘制脑图 <-> 支持Gemini-pro <-> 支持直接拖拽文件到上传区 <-> 支持将图片粘贴到输入区"
} }