chunzhi/chatgpt_academic
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

merge frontier branch (#1620)

Browse Source 
* 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

* tailing space removal

* Fix missing MATHPIX_APPID and MATHPIX_APPKEY
configuration

* Prompt fix、脑图提示词优化 (#1537)

* 适配 google gemini 优化为从用户input中提取文件

* 脑图提示词优化

* Fix missing MATHPIX_APPID and MATHPIX_APPKEY
configuration

---------

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

* 优化“PDF翻译中文并重新编译PDF”插件 (#1602)

* Add gemini_endpoint to API_URL_REDIRECT (#1560)

* Add gemini_endpoint to API_URL_REDIRECT

* Update gemini-pro and gemini-pro-vision model_info
endpoints

* Update to support new claude models (#1606)

* Add anthropic library and update claude models

* 更新bridge_claude.py文件，添加了对图片输入的支持。修复了一些bug。

* 添加Claude_3_Models变量以限制图片数量

* Refactor code to improve readability and
maintainability

* minor claude bug fix

* more flexible one-api support

* reformat config

* fix one-api new access bug

* dummy

* compat non-standard api

* version 3.73

---------

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 2024-03-11 17:26:09 +08:00 committed by GitHub
parent cd18663800
commit c3140ce344
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
85 changed files with 866 additions and 642 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
check_proxy.py
View File

@ -47,7 +47,7 @@ def backup_and_download(current_version, remote_version):
shutil.copytree('./', backup_dir, ignore=lambda x, y: ['history'])
proxies = get_conf('proxies')
try: r = requests.get('https://github.com/binary-husky/chatgpt_academic/archive/refs/heads/master.zip', proxies=proxies, stream=True)
except: r = requests.get('https://public.gpt-academic.top/publish/master.zip', proxies=proxies, stream=True)
except: r = requests.get('https://public.agent-matrix.com/publish/master.zip', proxies=proxies, stream=True)
zip_file_path = backup_dir+'/master.zip'
with open(zip_file_path, 'wb+') as f:
f.write(r.content)
@ -81,7 +81,7 @@ def patch_and_restart(path):
dir_util.copy_tree(path_new_version, './')
print亮绿('代码已经更新，即将更新pip包依赖……')
for i in reversed(range(5)): time.sleep(1); print(i)
try:
try:
import subprocess
subprocess.check_call([sys.executable, '-m', 'pip', 'install', '-r', 'requirements.txt'])
except:
@ -113,7 +113,7 @@ def auto_update(raise_error=False):
import json
proxies = get_conf('proxies')
try: response = requests.get("https://raw.githubusercontent.com/binary-husky/chatgpt_academic/master/version", proxies=proxies, timeout=5)
except: response = requests.get("https://public.gpt-academic.top/publish/version", proxies=proxies, timeout=5)
except: response = requests.get("https://public.agent-matrix.com/publish/version", proxies=proxies, timeout=5)
remote_json_data = json.loads(response.text)
remote_version = remote_json_data['version']
if remote_json_data["show_feature"]:
@ -159,7 +159,7 @@ def warm_up_modules():
enc.encode("模块预热", disallowed_special=())
enc = model_info["gpt-4"]['tokenizer']
enc.encode("模块预热", disallowed_special=())
def warm_up_vectordb():
print('正在执行一些模块的预热 ...')
from toolbox import ProxyNetworkActivate
@ -167,7 +167,7 @@ def warm_up_vectordb():
import nltk
with ProxyNetworkActivate("Warmup_Modules"): nltk.download("punkt")
if __name__ == '__main__':
import os
os.environ['no_proxy'] = '*' # 避免代理网络产生意外污染

2
colorful.py
View File

@ -3,7 +3,7 @@ from sys import stdout
if platform.system()=="Linux":
pass
else:
else:
from colorama import init
init()

77
config.py
View File

@ -30,7 +30,32 @@ if USE_PROXY:
else:
proxies = None
# ------------------------------------ 以下配置可以优化体验, 但大部分场合下并不需要修改 ------------------------------------
# [step 3]>> 模型选择是 (注意: LLM_MODEL是默认选中的模型, 它*必须*被包含在AVAIL_LLM_MODELS列表中 )
LLM_MODEL = "gpt-3.5-turbo-16k" # 可选 ↓↓↓
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-4", "gpt-4-32k", "azure-gpt-4", "glm-4", "glm-3-turbo",
"gemini-pro", "chatglm3"
]
# --- --- --- ---
# P.S. 其他可用的模型还包括
# AVAIL_LLM_MODELS = [
# "qianfan", "deepseekcoder",
# "spark", "sparkv2", "sparkv3", "sparkv3.5",
# "qwen-turbo", "qwen-plus", "qwen-max", "qwen-local",
# "moonshot-v1-128k", "moonshot-v1-32k", "moonshot-v1-8k",
# "gpt-3.5-turbo-0613", "gpt-3.5-turbo-16k-0613", "gpt-3.5-turbo-0125"
# "claude-3-sonnet-20240229","claude-3-opus-20240229", "claude-2.1", "claude-instant-1.2",
# "moss", "llama2", "chatglm_onnx", "internlm", "jittorllms_pangualpha", "jittorllms_llama",
# ]
# --- --- --- ---
# 此外，为了更灵活地接入one-api多模型管理界面，您还可以在接入one-api时，
# 使用"one-api-*"前缀直接使用非标准方式接入的模型，例如
# AVAIL_LLM_MODELS = ["one-api-claude-3-sonnet-20240229(max_token=100000)"]
# --- --- --- ---
# --------------- 以下配置可以优化体验 ---------------
# 重新URL重新定向，实现更换API_URL的作用（高危设置! 常规情况下不要修改! 通过修改此设置，您将把您的API-KEY和对话隐私完全暴露给您设定的中间人！）
# 格式: API_URL_REDIRECT = {"https://api.openai.com/v1/chat/completions": "在这里填写重定向的api.openai.com的URL"}
@ -85,22 +110,6 @@ MAX_RETRY = 2
DEFAULT_FN_GROUPS = ['对话', '编程', '学术', '智能体']
# 模型选择是 (注意: LLM_MODEL是默认选中的模型, 它*必须*被包含在AVAIL_LLM_MODELS列表中 )
LLM_MODEL = "gpt-3.5-turbo-16k" # 可选 ↓↓↓
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-4", "gpt-4-32k", "azure-gpt-4", "glm-4", "glm-3-turbo",
"gemini-pro", "chatglm3", "claude-2"]
# P.S. 其他可用的模型还包括 [
# "moonshot-v1-128k", "moonshot-v1-32k", "moonshot-v1-8k",
# "qwen-turbo", "qwen-plus", "qwen-max",
# "zhipuai", "qianfan", "deepseekcoder", "llama2", "qwen-local", "gpt-3.5-turbo-0613", "moss",
# "gpt-3.5-turbo-16k-0613", "gpt-3.5-random", "api2d-gpt-3.5-turbo", 'api2d-gpt-3.5-turbo-16k',
# "spark", "sparkv2", "sparkv3", "sparkv3.5",
# "chatglm_onnx", "claude-1-100k", "claude-2", "internlm", "jittorllms_pangualpha", "jittorllms_llama"
# ]
# 定义界面上“询问多个GPT模型”插件应该使用哪些模型，请从AVAIL_LLM_MODELS中选择，并在不同模型之间用`&`间隔，例如"gpt-3.5-turbo&chatglm3&azure-gpt-4"
MULTI_QUERY_LLM_MODELS = "gpt-3.5-turbo&chatglm3"
@ -129,6 +138,7 @@ CHATGLM_PTUNING_CHECKPOINT = "" # 例如"/home/hmp/ChatGLM2-6B/ptuning/output/6b
LOCAL_MODEL_DEVICE = "cpu" # 可选 "cuda"
LOCAL_MODEL_QUANT = "FP16" # 默认 "FP16" "INT4" 启用量化INT4版本 "INT8" 启用量化INT8版本
# 设置gradio的并行线程数（不需要修改）
CONCURRENT_COUNT = 100
@ -174,14 +184,8 @@ AZURE_ENGINE = "填入你亲手写的部署名" # 读 docs\use_azure.
AZURE_CFG_ARRAY = {}
# 使用Newbing (不推荐使用，未来将删除)
NEWBING_STYLE = "creative" # ["creative", "balanced", "precise"]
NEWBING_COOKIES = """
put your new bing cookies here
"""
# 阿里云实时语音识别 配置难度较高 仅建议高手用户使用 参考 https://github.com/binary-husky/gpt_academic/blob/master/docs/use_audio.md
# 阿里云实时语音识别 配置难度较高
# 参考 https://github.com/binary-husky/gpt_academic/blob/master/docs/use_audio.md
ENABLE_AUDIO = False
ALIYUN_TOKEN="" # 例如 f37f30e0f9934c34a992f6f64f7eba4f
ALIYUN_APPKEY="" # 例如 RoPlZrM88DnAFkZK
@ -200,18 +204,14 @@ ZHIPUAI_API_KEY = ""
ZHIPUAI_MODEL = "" # 此选项已废弃，不再需要填写
# # 火山引擎YUNQUE大模型
# YUNQUE_SECRET_KEY = ""
# YUNQUE_ACCESS_KEY = ""
# YUNQUE_MODEL = ""
# Claude API KEY
ANTHROPIC_API_KEY = ""
# 月之暗面 API KEY
MOONSHOT_API_KEY = ""
# Mathpix 拥有执行PDF的OCR功能，但是需要注册账号
MATHPIX_APPID = ""
MATHPIX_APPKEY = ""
@ -270,7 +270,11 @@ PLUGIN_HOT_RELOAD = False
# 自定义按钮的最大数量限制
NUM_CUSTOM_BASIC_BTN = 4
"""
--------------- 配置关联关系说明 ---------------
在线大模型配置关联关系示意图
│
├── "gpt-3.5-turbo" 等openai模型
@ -294,7 +298,7 @@ NUM_CUSTOM_BASIC_BTN = 4
│ ├── XFYUN_API_SECRET
│ └── XFYUN_API_KEY
│
├── "claude-1-100k" 等claude模型
├── "claude-3-opus-20240229" 等claude模型
│ └── ANTHROPIC_API_KEY
│
├── "stack-claude"
@ -315,9 +319,10 @@ NUM_CUSTOM_BASIC_BTN = 4
├── "Gemini"
│ └── GEMINI_API_KEY
│
└── "newbing" Newbing接口不再稳定，不推荐使用
├── NEWBING_STYLE
└── NEWBING_COOKIES
└── "one-api-...(max_token=...)" 用一种更方便的方式接入one-api多模型管理界面
├── AVAIL_LLM_MODELS
├── API_KEY
└── API_URL_REDIRECT
本地大模型示意图
@ -364,4 +369,4 @@ NUM_CUSTOM_BASIC_BTN = 4
└── MATHPIX_APPKEY
"""
"""

40
core_functional.py
View File

@ -34,16 +34,16 @@ def get_core_functions():
# [6] 文本预处理 （可选参数，默认 None，举例：写个函数移除所有的换行符）
"PreProcess": None,
},
"总结绘制脑图": {
# 前缀，会被加在你的输入之前。例如，用来描述你的要求，例如翻译、解释代码、润色等等
"Prefix": r"",
"Prefix": '''"""\n\n''',
# 后缀，会被加在你的输入之后。例如，配合前缀可以把你的输入内容用引号圈起来
"Suffix":
# dedent() 函数用于去除多行字符串的缩进
dedent("\n"+r'''
==============================
dedent("\n\n"+r'''
"""
使用mermaid flowchart对以上文本进行总结，概括上述段落的内容以及内在逻辑关系，例如：
@ -57,15 +57,15 @@ def get_core_functions():
C --> |"箭头名2"| F["节点名6"]
```
警告：
注意：
（1）使用中文
（2）节点名字使用引号包裹，如["Laptop"]
（3）`|` 和 `"`之间不要存在空格
（4）根据情况选择flowchart LR（从左到右）或者flowchart TD（从上到下）
'''),
},
"查找语法错误": {
"Prefix": r"Help me ensure that the grammar and the spelling is correct. "
r"Do not try to polish the text, if no mistake is found, tell me that this paragraph is good. "
@ -85,14 +85,14 @@ def get_core_functions():
"Suffix": r"",
"PreProcess": clear_line_break, # 预处理：清除换行符
},
"中译英": {
"Prefix": r"Please translate following sentence to English:" + "\n\n",
"Suffix": r"",
},
"学术英中互译": {
"Prefix": build_gpt_academic_masked_string_langbased(
text_show_chinese=
@ -112,29 +112,29 @@ def get_core_functions():
) + "\n\n",
"Suffix": r"",
},
"英译中": {
"Prefix": r"翻译成地道的中文：" + "\n\n",
"Suffix": r"",
"Visible": False,
},
"找图片": {
"Prefix": r"我需要你找一张网络图片。使用Unsplash API(https://source.unsplash.com/960x640/?<英语关键词>)获取图片URL，"
r"然后请使用Markdown格式封装，并且不要有反斜线，不要用代码块。现在，请按以下描述给我发送图片：" + "\n\n",
"Suffix": r"",
"Visible": False,
},
"解释代码": {
"Prefix": r"请解释以下代码：" + "\n```\n",
"Suffix": "\n```\n",
},
"参考文献转Bib": {
"Prefix": r"Here are some bibliography items, please transform them into bibtex style."
r"Note that, reference styles maybe more than one kind, you should transform each item correctly."

28
crazy_functions/Latex全文润色.py
View File

@ -46,7 +46,7 @@ class PaperFileGroup():
manifest.append(path + '.polish.tex')
f.write(res)
return manifest
def zip_result(self):
import os, time
folder = os.path.dirname(self.file_paths[0])
@ -59,7 +59,7 @@ def 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
# <-------- 读取Latex文件，删除其中的所有注释 ---------->
# <-------- 读取Latex文件，删除其中的所有注释 ---------->
pfg = PaperFileGroup()
for index, fp in enumerate(file_manifest):
@ -73,31 +73,31 @@ def 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
pfg.file_paths.append(fp)
pfg.file_contents.append(clean_tex_content)
# <-------- 拆分过长的latex文件 ---------->
# <-------- 拆分过长的latex文件 ---------->
pfg.run_file_split(max_token_limit=1024)
n_split = len(pfg.sp_file_contents)
# <-------- 多线程润色开始 ---------->
# <-------- 多线程润色开始 ---------->
if language == 'en':
if mode == 'polish':
inputs_array = ["Below is a section from an academic paper, polish this section to meet the academic standard, " +
"improve the grammar, clarity and overall readability, do not modify any latex command such as \section, \cite and equations:" +
inputs_array = ["Below is a section from an academic paper, polish this section to meet the academic standard, " +
"improve the grammar, clarity and overall readability, do not modify any latex command such as \section, \cite and equations:" +
f"\n\n{frag}" for frag in pfg.sp_file_contents]
else:
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. " +
r"Answer me only with the revised text:" +
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. " +
r"Answer me only with the revised text:" +
f"\n\n{frag}" for frag in pfg.sp_file_contents]
inputs_show_user_array = [f"Polish {f}" for f in pfg.sp_file_tag]
sys_prompt_array = ["You are a professional academic paper writer." for _ in range(n_split)]
elif language == 'zh':
if mode == 'polish':
inputs_array = [f"以下是一篇学术论文中的一段内容，请将此部分润色以满足学术标准，提高语法、清晰度和整体可读性，不要修改任何LaTeX命令，例如\section，\cite和方程式：" +
inputs_array = [f"以下是一篇学术论文中的一段内容，请将此部分润色以满足学术标准，提高语法、清晰度和整体可读性，不要修改任何LaTeX命令，例如\section，\cite和方程式：" +
f"\n\n{frag}" for frag in pfg.sp_file_contents]
else:
inputs_array = [f"以下是一篇学术论文中的一段内容，请对这部分内容进行语法矫正。不要修改任何LaTeX命令，例如\section，\cite和方程式：" +
f"\n\n{frag}" for frag in pfg.sp_file_contents]
inputs_array = [f"以下是一篇学术论文中的一段内容，请对这部分内容进行语法矫正。不要修改任何LaTeX命令，例如\section，\cite和方程式：" +
f"\n\n{frag}" for frag in pfg.sp_file_contents]
inputs_show_user_array = [f"润色 {f}" for f in pfg.sp_file_tag]
sys_prompt_array=["你是一位专业的中文学术论文作家。" for _ in range(n_split)]
@ -113,7 +113,7 @@ def 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
scroller_max_len = 80
)
# <-------- 文本碎片重组为完整的tex文件，整理结果为压缩包 ---------->
# <-------- 文本碎片重组为完整的tex文件，整理结果为压缩包 ---------->
try:
pfg.sp_file_result = []
for i_say, gpt_say in zip(gpt_response_collection[0::2], gpt_response_collection[1::2]):
@ -124,7 +124,7 @@ def 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
except:
print(trimmed_format_exc())
# <-------- 整理结果，退出 ---------->
# <-------- 整理结果，退出 ---------->
create_report_file_name = time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime()) + f"-chatgpt.polish.md"
res = write_history_to_file(gpt_response_collection, file_basename=create_report_file_name)
promote_file_to_downloadzone(res, chatbot=chatbot)

14
crazy_functions/Latex全文翻译.py
View File

@ -39,7 +39,7 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
import time, os, re
from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
# <-------- 读取Latex文件，删除其中的所有注释 ---------->
# <-------- 读取Latex文件，删除其中的所有注释 ---------->
pfg = PaperFileGroup()
for index, fp in enumerate(file_manifest):
@ -53,11 +53,11 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
pfg.file_paths.append(fp)
pfg.file_contents.append(clean_tex_content)
# <-------- 拆分过长的latex文件 ---------->
# <-------- 拆分过长的latex文件 ---------->
pfg.run_file_split(max_token_limit=1024)
n_split = len(pfg.sp_file_contents)
# <-------- 抽取摘要 ---------->
# <-------- 抽取摘要 ---------->
# if language == 'en':
# abs_extract_inputs = f"Please write an abstract for this paper"
@ -70,14 +70,14 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
# sys_prompt="Your job is to collect information from materials。",
# )
# <-------- 多线程润色开始 ---------->
# <-------- 多线程润色开始 ---------->
if language == 'en->zh':
inputs_array = ["Below is a section from an English academic paper, translate it into Chinese, do not modify any latex command such as \section, \cite and equations:" +
inputs_array = ["Below is a section from an English academic paper, translate it into Chinese, do not modify any latex command such as \section, \cite and equations:" +
f"\n\n{frag}" for frag in pfg.sp_file_contents]
inputs_show_user_array = [f"翻译 {f}" for f in pfg.sp_file_tag]
sys_prompt_array = ["You are a professional academic paper translator." for _ in range(n_split)]
elif language == 'zh->en':
inputs_array = [f"Below is a section from a Chinese academic paper, translate it into English, do not modify any latex command such as \section, \cite and equations:" +
inputs_array = [f"Below is a section from a Chinese academic paper, translate it into English, do not modify any latex command such as \section, \cite and equations:" +
f"\n\n{frag}" for frag in pfg.sp_file_contents]
inputs_show_user_array = [f"翻译 {f}" for f in pfg.sp_file_tag]
sys_prompt_array = ["You are a professional academic paper translator." for _ in range(n_split)]
@ -93,7 +93,7 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
scroller_max_len = 80
)
# <-------- 整理结果，退出 ---------->
# <-------- 整理结果，退出 ---------->
create_report_file_name = time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime()) + f"-chatgpt.polish.md"
res = write_history_to_file(gpt_response_collection, create_report_file_name)
promote_file_to_downloadzone(res, chatbot=chatbot)

146
crazy_functions/Latex输出PDF.py
View File

@ -1,4 +1,4 @@
from toolbox import update_ui, trimmed_format_exc, get_conf, get_log_folder, promote_file_to_downloadzone
from toolbox import update_ui, trimmed_format_exc, get_conf, get_log_folder, promote_file_to_downloadzone, check_repeat_upload, map_file_to_sha256
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
@ -40,7 +40,7 @@ def switch_prompt(pfg, mode, more_requirement):
def desend_to_extracted_folder_if_exist(project_folder):
"""
"""
Descend into the extracted folder if it exists, otherwise return the original folder.
Args:
@ -56,7 +56,7 @@ def desend_to_extracted_folder_if_exist(project_folder):
def move_project(project_folder, arxiv_id=None):
"""
"""
Create a new work folder and copy the project folder to it.
Args:
@ -112,9 +112,9 @@ def arxiv_download(chatbot, history, txt, allow_cache=True):
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'):
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)
@ -214,7 +214,7 @@ def pdf2tex_project(pdf_file_path):
return None
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序1 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序1 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
@CatchException
@ -291,7 +291,7 @@ def Latex英文纠错加PDF对比(txt, llm_kwargs, plugin_kwargs, chatbot, histo
return success
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序2 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 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):
@ -326,7 +326,7 @@ def Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot,
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。",
"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
@ -385,7 +385,7 @@ def Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot,
return success
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=- 插件主程序3 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=- 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):
@ -438,47 +438,101 @@ def PDF翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, h
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
# <-------------- convert pdf into tex ------------->
project_folder = pdf2tex_project(file_manifest[0])
hash_tag = map_file_to_sha256(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
# <-------------- check repeated pdf ------------->
chatbot.append([f"检查PDF是否被重复上传", "正在检查..."])
yield from update_ui(chatbot=chatbot, history=history)
repeat, project_folder = check_repeat_upload(file_manifest[0], hash_tag)
# <-------------- if is a zip/tar file ------------->
project_folder = desend_to_extracted_folder_if_exist(project_folder)
except_flag = False
# <-------------- move latex project away from temp folder ------------->
project_folder = move_project(project_folder)
if repeat:
yield from update_ui_lastest_msg(f"发现重复上传，请查收结果（压缩包）...", chatbot=chatbot, history=history)
# <-------------- 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_)
try:
trans_html_file = [f for f in glob.glob(f'{project_folder}/**/*.trans.html', recursive=True)][0]
promote_file_to_downloadzone(trans_html_file, rename_file=None, chatbot=chatbot)
# <-------------- 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)
translate_pdf = [f for f in glob.glob(f'{project_folder}/**/merge_translate_zh.pdf', recursive=True)][0]
promote_file_to_downloadzone(translate_pdf, rename_file=None, chatbot=chatbot)
# <-------------- 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)
comparison_pdf = [f for f in glob.glob(f'{project_folder}/**/comparison.pdf', recursive=True)][0]
promote_file_to_downloadzone(comparison_pdf, rename_file=None, chatbot=chatbot)
# <-------------- we are done ------------->
return success
zip_res = zip_result(project_folder)
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
return True
except:
report_exception(chatbot, history, b=f"发现重复上传，但是无法找到相关文件")
yield from update_ui(chatbot=chatbot, history=history)
chatbot.append([f"没有相关文件", '尝试重新翻译PDF...'])
yield from update_ui(chatbot=chatbot, history=history)
except_flag = True
elif not repeat or except_flag:
yield from update_ui_lastest_msg(f"未发现重复上传", chatbot=chatbot, history=history)
# <-------------- convert pdf into tex ------------->
chatbot.append([f"解析项目: {txt}", "正在将PDF转换为tex项目，请耐心等待..."])
yield from update_ui(chatbot=chatbot, history=history)
project_folder = pdf2tex_project(file_manifest[0])
if project_folder is None:
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"PDF转换为tex项目失败")
yield from update_ui(chatbot=chatbot, history=history)
return False
# <-------------- translate latex file into Chinese ------------->
yield from update_ui_lastest_msg("正在tex项目将翻译为中文...", chatbot=chatbot, history=history)
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)
# <-------------- set a hash tag for repeat-checking ------------->
with open(pj(project_folder, hash_tag + '.tag'), 'w') as f:
f.write(hash_tag)
f.close()
# <-------------- 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 ------------->
yield from update_ui_lastest_msg("正在将翻译好的项目tex项目编译为PDF...", chatbot=chatbot, history=history)
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

14
crazy_functions/agent_fns/pipe.py
View File

@ -72,7 +72,7 @@ class PluginMultiprocessManager:
if file_type.lower() in ['png', 'jpg']:
image_path = os.path.abspath(fp)
self.chatbot.append([
'检测到新生图像:',
'检测到新生图像:',
f'本地文件预览: <br/><div align="center"><img src="file={image_path}"></div>'
])
yield from update_ui(chatbot=self.chatbot, history=self.history)
@ -114,21 +114,21 @@ class PluginMultiprocessManager:
self.cnt = 1
self.parent_conn = self.launch_subprocess_with_pipe() # ⭐⭐⭐
repeated, cmd_to_autogen = self.send_command(txt)
if txt == 'exit':
if txt == 'exit':
self.chatbot.append([f"结束", "结束信号已明确，终止AutoGen程序。"])
yield from update_ui(chatbot=self.chatbot, history=self.history)
self.terminate()
return "terminate"
# patience = 10
while True:
time.sleep(0.5)
if not self.alive:
# the heartbeat watchdog might have it killed
self.terminate()
return "terminate"
if self.parent_conn.poll():
if self.parent_conn.poll():
self.feed_heartbeat_watchdog()
if "[GPT-Academic] 等待中" in self.chatbot[-1][-1]:
self.chatbot.pop(-1) # remove the last line
@ -152,8 +152,8 @@ class PluginMultiprocessManager:
yield from update_ui(chatbot=self.chatbot, history=self.history)
if msg.cmd == "interact":
yield from self.overwatch_workdir_file_change()
self.chatbot.append([f"程序抵达用户反馈节点.", msg.content +
"\n\n等待您的进一步指令." +
self.chatbot.append([f"程序抵达用户反馈节点.", msg.content +
"\n\n等待您的进一步指令." +
"\n\n(1) 一般情况下您不需要说什么, 清空输入区, 然后直接点击“提交”以继续. " +
"\n\n(2) 如果您需要补充些什么, 输入要反馈的内容, 直接点击“提交”以继续. " +
"\n\n(3) 如果您想终止程序, 输入exit, 直接点击“提交”以终止AutoGen并解锁. "

2
crazy_functions/agent_fns/watchdog.py
View File

@ -8,7 +8,7 @@ class WatchDog():
self.interval = interval
self.msg = msg
self.kill_dog = False
def watch(self):
while True:
if self.kill_dog: break

8
crazy_functions/chatglm微调工具.py
View File

@ -46,7 +46,7 @@ def 微调数据集生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
chatbot.append(("这是什么功能？", "[Local Message] 微调数据集生成"))
if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
args = plugin_kwargs.get("advanced_arg", None)
if args is None:
if args is None:
chatbot.append(("没给定指令", "退出"))
yield from update_ui(chatbot=chatbot, history=history); return
else:
@ -69,7 +69,7 @@ def 微调数据集生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
sys_prompt_array=[arguments.system_prompt for _ in (batch)],
max_workers=10 # OpenAI所允许的最大并行过载
)
with open(txt+'.generated.json', 'a+', encoding='utf8') as f:
for b, r in zip(batch, res[1::2]):
f.write(json.dumps({"content":b, "summary":r}, ensure_ascii=False)+'\n')
@ -95,12 +95,12 @@ def 启动微调(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
chatbot.append(("这是什么功能？", "[Local Message] 微调数据集生成"))
if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
args = plugin_kwargs.get("advanced_arg", None)
if args is None:
if args is None:
chatbot.append(("没给定指令", "退出"))
yield from update_ui(chatbot=chatbot, history=history); return
else:
arguments = string_to_options(arguments=args)
pre_seq_len = arguments.pre_seq_len # 128

2
crazy_functions/diagram_fns/file_tree.py
View File

@ -10,7 +10,7 @@ class FileNode:
self.parenting_ship = []
self.comment = ""
self.comment_maxlen_show = 50
@staticmethod
def add_linebreaks_at_spaces(string, interval=10):
return '\n'.join(string[i:i+interval] for i in range(0, len(string), interval))

2
crazy_functions/game_fns/game_ascii_art.py
View File

@ -8,7 +8,7 @@ import random
class MiniGame_ASCII_Art(GptAcademicGameBaseState):
def step(self, prompt, chatbot, history):
if self.step_cnt == 0:
if self.step_cnt == 0:
chatbot.append(["我画你猜（动物）", "请稍等..."])
else:
if prompt.strip() == 'exit':

26
crazy_functions/game_fns/game_interactive_story.py
View File

@ -88,8 +88,8 @@ class MiniGame_ResumeStory(GptAcademicGameBaseState):
self.story = []
chatbot.append(["互动写故事", f"这次的故事开头是：{self.headstart}"])
self.sys_prompt_ = '你是一个想象力丰富的杰出作家。正在与你的朋友互动，一起写故事，因此你每次写的故事段落应少于300字（结局除外）。'
def generate_story_image(self, story_paragraph):
try:
from crazy_functions.图片生成 import gen_image
@ -98,13 +98,13 @@ class MiniGame_ResumeStory(GptAcademicGameBaseState):
return f'<br/><div align="center"><img src="file={image_path}"></div>'
except:
return ''
def step(self, prompt, chatbot, history):
"""
首先，处理游戏初始化等特殊情况
"""
if self.step_cnt == 0:
if self.step_cnt == 0:
self.begin_game_step_0(prompt, chatbot, history)
self.lock_plugin(chatbot)
self.cur_task = 'head_start'
@ -132,7 +132,7 @@ class MiniGame_ResumeStory(GptAcademicGameBaseState):
inputs_ = prompts_hs.format(headstart=self.headstart)
history_ = []
story_paragraph = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs_, '故事开头', self.llm_kwargs,
inputs_, '故事开头', self.llm_kwargs,
chatbot, history_, self.sys_prompt_
)
self.story.append(story_paragraph)
@ -147,7 +147,7 @@ class MiniGame_ResumeStory(GptAcademicGameBaseState):
inputs_ = prompts_interact.format(previously_on_story=previously_on_story)
history_ = []
self.next_choices = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs_, '请在以下几种故事走向中，选择一种（当然，您也可以选择给出其他故事走向）：', self.llm_kwargs,
inputs_, '请在以下几种故事走向中，选择一种（当然，您也可以选择给出其他故事走向）：', self.llm_kwargs,
chatbot,
history_,
self.sys_prompt_
@ -166,7 +166,7 @@ class MiniGame_ResumeStory(GptAcademicGameBaseState):
inputs_ = prompts_resume.format(previously_on_story=previously_on_story, choice=self.next_choices, user_choice=prompt)
history_ = []
story_paragraph = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs_, f'下一段故事（您的选择是：{prompt}）。', self.llm_kwargs,
inputs_, f'下一段故事（您的选择是：{prompt}）。', self.llm_kwargs,
chatbot, history_, self.sys_prompt_
)
self.story.append(story_paragraph)
@ -181,10 +181,10 @@ class MiniGame_ResumeStory(GptAcademicGameBaseState):
inputs_ = prompts_interact.format(previously_on_story=previously_on_story)
history_ = []
self.next_choices = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs_,
'请在以下几种故事走向中，选择一种。当然，您也可以给出您心中的其他故事走向。另外，如果您希望剧情立即收尾，请输入剧情走向，并以“剧情收尾”四个字提示程序。', self.llm_kwargs,
chatbot,
history_,
inputs_,
'请在以下几种故事走向中，选择一种。当然，您也可以给出您心中的其他故事走向。另外，如果您希望剧情立即收尾，请输入剧情走向，并以“剧情收尾”四个字提示程序。', self.llm_kwargs,
chatbot,
history_,
self.sys_prompt_
)
self.cur_task = 'user_choice'
@ -200,7 +200,7 @@ class MiniGame_ResumeStory(GptAcademicGameBaseState):
inputs_ = prompts_terminate.format(previously_on_story=previously_on_story, user_choice=prompt)
history_ = []
story_paragraph = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs_, f'故事收尾（您的选择是：{prompt}）。', self.llm_kwargs,
inputs_, f'故事收尾（您的选择是：{prompt}）。', self.llm_kwargs,
chatbot, history_, self.sys_prompt_
)
# # 配图

10
crazy_functions/game_fns/game_utils.py
View File

@ -5,7 +5,7 @@ def get_code_block(reply):
import re
pattern = r"```([\s\S]*?)```" # regex pattern to match code blocks
matches = re.findall(pattern, reply) # find all code blocks in text
if len(matches) == 1:
if len(matches) == 1:
return "```" + matches[0] + "```" # code block
raise RuntimeError("GPT is not generating proper code.")
@ -13,10 +13,10 @@ def is_same_thing(a, b, llm_kwargs):
from pydantic import BaseModel, Field
class IsSameThing(BaseModel):
is_same_thing: bool = Field(description="determine whether two objects are same thing.", default=False)
def run_gpt_fn(inputs, sys_prompt, history=[]):
def run_gpt_fn(inputs, sys_prompt, history=[]):
return predict_no_ui_long_connection(
inputs=inputs, llm_kwargs=llm_kwargs,
inputs=inputs, llm_kwargs=llm_kwargs,
history=history, sys_prompt=sys_prompt, observe_window=[]
)
@ -24,7 +24,7 @@ def is_same_thing(a, b, llm_kwargs):
inputs_01 = "Identity whether the user input and the target is the same thing: \n target object: {a} \n user input object: {b} \n\n\n".format(a=a, b=b)
inputs_01 += "\n\n\n Note that the user may describe the target object with a different language, e.g. cat and 猫 are the same thing."
analyze_res_cot_01 = run_gpt_fn(inputs_01, "", [])
inputs_02 = inputs_01 + gpt_json_io.format_instructions
analyze_res = run_gpt_fn(inputs_02, "", [inputs_01, analyze_res_cot_01])

4
crazy_functions/gen_fns/gen_fns_shared.py
View File

@ -41,11 +41,11 @@ def is_function_successfully_generated(fn_path, class_name, return_dict):
# Now you can create an instance of the class
instance = some_class()
return_dict['success'] = True
return
return
except:
return_dict['traceback'] = trimmed_format_exc()
return
def subprocess_worker(code, file_path, return_dict):
return_dict['result'] = None
return_dict['success'] = False

2
crazy_functions/ipc_fns/mp.py
View File

@ -1,4 +1,4 @@
import platform
import platform
import pickle
import multiprocessing

2
crazy_functions/json_fns/pydantic_io.py
View File

@ -89,7 +89,7 @@ class GptJsonIO():
error + "\n\n" + \
"Now, fix this json string. \n\n"
return prompt
def generate_output_auto_repair(self, response, gpt_gen_fn):
"""
response: string containing canidate json

56
crazy_functions/latex_fns/latex_actions.py
View File

@ -90,16 +90,16 @@ class LatexPaperSplit():
"版权归原文作者所有。翻译内容可靠性无保障，请仔细鉴别并以原文为准。" + \
"项目Github地址 \\url{https://github.com/binary-husky/gpt_academic/}。"
# 请您不要删除或修改这行警告，除非您是论文的原作者（如果您是论文原作者，欢迎加REAME中的QQ联系开发者）
self.msg_declare = "为了防止大语言模型的意外谬误产生扩散影响，禁止移除或修改此警告。}}\\\\"
self.msg_declare = "为了防止大语言模型的意外谬误产生扩散影响，禁止移除或修改此警告。}}\\\\"
self.title = "unknown"
self.abstract = "unknown"
def read_title_and_abstract(self, txt):
try:
title, abstract = find_title_and_abs(txt)
if title is not None:
if title is not None:
self.title = title.replace('\n', ' ').replace('\\\\', ' ').replace(' ', '').replace(' ', '')
if abstract is not None:
if abstract is not None:
self.abstract = abstract.replace('\n', ' ').replace('\\\\', ' ').replace(' ', '').replace(' ', '')
except:
pass
@ -111,7 +111,7 @@ class LatexPaperSplit():
result_string = ""
node_cnt = 0
line_cnt = 0
for node in self.nodes:
if node.preserve:
line_cnt += node.string.count('\n')
@ -144,7 +144,7 @@ class LatexPaperSplit():
return result_string
def split(self, txt, project_folder, opts):
def split(self, txt, project_folder, opts):
"""
break down latex file to a linked list,
each node use a preserve flag to indicate whether it should
@ -155,7 +155,7 @@ class LatexPaperSplit():
manager = multiprocessing.Manager()
return_dict = manager.dict()
p = multiprocessing.Process(
target=split_subprocess,
target=split_subprocess,
args=(txt, project_folder, return_dict, opts))
p.start()
p.join()
@ -217,13 +217,13 @@ def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin
from ..crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
from .latex_actions import LatexPaperFileGroup, LatexPaperSplit
# <-------- 寻找主tex文件 ---------->
# <-------- 寻找主tex文件 ---------->
maintex = find_main_tex_file(file_manifest, mode)
chatbot.append((f"定位主Latex文件", f'[Local Message] 分析结果：该项目的Latex主文件是{maintex}, 如果分析错误, 请立即终止程序, 删除或修改歧义文件, 然后重试。主程序即将开始, 请稍候。'))
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
time.sleep(3)
# <-------- 读取Latex文件, 将多文件tex工程融合为一个巨型tex ---------->
# <-------- 读取Latex文件, 将多文件tex工程融合为一个巨型tex ---------->
main_tex_basename = os.path.basename(maintex)
assert main_tex_basename.endswith('.tex')
main_tex_basename_bare = main_tex_basename[:-4]
@ -240,13 +240,13 @@ def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin
with open(project_folder + '/merge.tex', 'w', encoding='utf-8', errors='replace') as f:
f.write(merged_content)
# <-------- 精细切分latex文件 ---------->
# <-------- 精细切分latex文件 ---------->
chatbot.append((f"Latex文件融合完成", f'[Local Message] 正在精细切分latex文件，这需要一段时间计算，文档越长耗时越长，请耐心等待。'))
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
lps = LatexPaperSplit()
lps.read_title_and_abstract(merged_content)
res = lps.split(merged_content, project_folder, opts) # 消耗时间的函数
# <-------- 拆分过长的latex片段 ---------->
# <-------- 拆分过长的latex片段 ---------->
pfg = LatexPaperFileGroup()
for index, r in enumerate(res):
pfg.file_paths.append('segment-' + str(index))
@ -255,17 +255,17 @@ def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin
pfg.run_file_split(max_token_limit=1024)
n_split = len(pfg.sp_file_contents)
# <-------- 根据需要切换prompt ---------->
# <-------- 根据需要切换prompt ---------->
inputs_array, sys_prompt_array = switch_prompt(pfg, mode)
inputs_show_user_array = [f"{mode} {f}" for f in pfg.sp_file_tag]
if os.path.exists(pj(project_folder,'temp.pkl')):
# <-------- 【仅调试】如果存在调试缓存文件，则跳过GPT请求环节 ---------->
# <-------- 【仅调试】如果存在调试缓存文件，则跳过GPT请求环节 ---------->
pfg = objload(file=pj(project_folder,'temp.pkl'))
else:
# <-------- gpt 多线程请求 ---------->
# <-------- gpt 多线程请求 ---------->
history_array = [[""] for _ in range(n_split)]
# LATEX_EXPERIMENTAL, = get_conf('LATEX_EXPERIMENTAL')
# if LATEX_EXPERIMENTAL:
@ -284,32 +284,32 @@ def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin
scroller_max_len = 40
)
# <-------- 文本碎片重组为完整的tex片段 ---------->
# <-------- 文本碎片重组为完整的tex片段 ---------->
pfg.sp_file_result = []
for i_say, gpt_say, orig_content in zip(gpt_response_collection[0::2], gpt_response_collection[1::2], pfg.sp_file_contents):
pfg.sp_file_result.append(gpt_say)
pfg.merge_result()
# <-------- 临时存储用于调试 ---------->
# <-------- 临时存储用于调试 ---------->
pfg.get_token_num = None
objdump(pfg, file=pj(project_folder,'temp.pkl'))
write_html(pfg.sp_file_contents, pfg.sp_file_result, chatbot=chatbot, project_folder=project_folder)
# <-------- 写出文件 ---------->
# <-------- 写出文件 ---------->
msg = f"当前大语言模型: {llm_kwargs['llm_model']}，当前语言模型温度设定: {llm_kwargs['temperature']}。"
final_tex = lps.merge_result(pfg.file_result, mode, msg)
objdump((lps, pfg.file_result, mode, msg), file=pj(project_folder,'merge_result.pkl'))
with open(project_folder + f'/merge_{mode}.tex', 'w', encoding='utf-8', errors='replace') as f:
if mode != 'translate_zh' or "binary" in final_tex: f.write(final_tex)
# <-------- 整理结果, 退出 ---------->
# <-------- 整理结果, 退出 ---------->
chatbot.append((f"完成了吗？", 'GPT结果已输出, 即将编译PDF'))
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
# <-------- 返回 ---------->
# <-------- 返回 ---------->
return project_folder + f'/merge_{mode}.tex'
@ -362,7 +362,7 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译转化后的PDF ...', chatbot, history) # 刷新Gradio前端界面
ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex', work_folder_modified)
if ok and os.path.exists(pj(work_folder_modified, f'{main_file_modified}.pdf')):
# 只有第二步成功，才能继续下面的步骤
yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译BibTex ...', chatbot, history) # 刷新Gradio前端界面
@ -393,9 +393,9 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
original_pdf_success = os.path.exists(pj(work_folder_original, f'{main_file_original}.pdf'))
modified_pdf_success = os.path.exists(pj(work_folder_modified, f'{main_file_modified}.pdf'))
diff_pdf_success = os.path.exists(pj(work_folder, f'merge_diff.pdf'))
results_ += f"原始PDF编译是否成功: {original_pdf_success};"
results_ += f"转化PDF编译是否成功: {modified_pdf_success};"
results_ += f"对比PDF编译是否成功: {diff_pdf_success};"
results_ += f"原始PDF编译是否成功: {original_pdf_success};"
results_ += f"转化PDF编译是否成功: {modified_pdf_success};"
results_ += f"对比PDF编译是否成功: {diff_pdf_success};"
yield from update_ui_lastest_msg(f'第{n_fix}编译结束:<br/>{results_}...', chatbot, history) # 刷新Gradio前端界面
if diff_pdf_success:
@ -409,7 +409,7 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
shutil.copyfile(result_pdf, pj(work_folder, '..', 'translation', 'translate_zh.pdf'))
promote_file_to_downloadzone(result_pdf, rename_file=None, chatbot=chatbot) # promote file to web UI
# 将两个PDF拼接
if original_pdf_success:
if original_pdf_success:
try:
from .latex_toolbox import merge_pdfs
concat_pdf = pj(work_folder_modified, f'comparison.pdf')
@ -425,7 +425,7 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
if n_fix>=max_try: break
n_fix += 1
can_retry, main_file_modified, buggy_lines = remove_buggy_lines(
file_path=pj(work_folder_modified, f'{main_file_modified}.tex'),
file_path=pj(work_folder_modified, f'{main_file_modified}.tex'),
log_path=pj(work_folder_modified, f'{main_file_modified}.log'),
tex_name=f'{main_file_modified}.tex',
tex_name_pure=f'{main_file_modified}',
@ -445,14 +445,14 @@ def write_html(sp_file_contents, sp_file_result, chatbot, project_folder):
import shutil
from crazy_functions.pdf_fns.report_gen_html import construct_html
from toolbox import gen_time_str
ch = construct_html()
ch = construct_html()
orig = ""
trans = ""
final = []
for c,r in zip(sp_file_contents, sp_file_result):
for c,r in zip(sp_file_contents, sp_file_result):
final.append(c)
final.append(r)
for i, k in enumerate(final):
for i, k in enumerate(final):
if i%2==0:
orig = k
if i%2==1:

10
crazy_functions/live_audio/aliyunASR.py
View File

@ -85,8 +85,8 @@ def write_numpy_to_wave(filename, rate, data, add_header=False):
def is_speaker_speaking(vad, data, sample_rate):
# Function to detect if the speaker is speaking
# The WebRTC VAD only accepts 16-bit mono PCM audio,
# sampled at 8000, 16000, 32000 or 48000 Hz.
# The WebRTC VAD only accepts 16-bit mono PCM audio,
# sampled at 8000, 16000, 32000 or 48000 Hz.
# A frame must be either 10, 20, or 30 ms in duration:
frame_duration = 30
n_bit_each = int(sample_rate * frame_duration / 1000)*2 # x2 because audio is 16 bit (2 bytes)
@ -94,7 +94,7 @@ def is_speaker_speaking(vad, data, sample_rate):
for t in range(len(data)):
if t!=0 and t % n_bit_each == 0:
res_list.append(vad.is_speech(data[t-n_bit_each:t], sample_rate))
info = ''.join(['^' if r else '.' for r in res_list])
info = info[:10]
if any(res_list):
@ -186,10 +186,10 @@ class AliyunASR():
keep_alive_last_send_time = time.time()
while not self.stop:
# time.sleep(self.capture_interval)
audio = rad.read(uuid.hex)
audio = rad.read(uuid.hex)
if audio is not None:
# convert to pcm file
temp_file = f'{temp_folder}/{uuid.hex}.pcm' #
temp_file = f'{temp_folder}/{uuid.hex}.pcm' #
dsdata = change_sample_rate(audio, rad.rate, NEW_SAMPLERATE) # 48000 --> 16000
write_numpy_to_wave(temp_file, NEW_SAMPLERATE, dsdata)
# read pcm binary

6
crazy_functions/live_audio/audio_io.py
View File

@ -3,12 +3,12 @@ from scipy import interpolate
def Singleton(cls):
_instance = {}
def _singleton(*args, **kargs):
if cls not in _instance:
_instance[cls] = cls(*args, **kargs)
return _instance[cls]
return _singleton
@ -39,7 +39,7 @@ class RealtimeAudioDistribution():
else:
res = None
return res
def change_sample_rate(audio, old_sr, new_sr):
duration = audio.shape[0] / old_sr

8
crazy_functions/multi_stage/multi_stage_utils.py
View File

@ -40,7 +40,7 @@ class GptAcademicState():
class GptAcademicGameBaseState():
"""
1. first init: __init__ ->
1. first init: __init__ ->
"""
def init_game(self, chatbot, lock_plugin):
self.plugin_name = None
@ -53,7 +53,7 @@ class GptAcademicGameBaseState():
raise ValueError("callback_fn is None")
chatbot._cookies['lock_plugin'] = self.callback_fn
self.dump_state(chatbot)
def get_plugin_name(self):
if self.plugin_name is None:
raise ValueError("plugin_name is None")
@ -71,7 +71,7 @@ class GptAcademicGameBaseState():
state = chatbot._cookies.get(f'plugin_state/{plugin_name}', None)
if state is not None:
state = pickle.loads(state)
else:
else:
state = cls()
state.init_game(chatbot, lock_plugin)
state.plugin_name = plugin_name
@ -79,7 +79,7 @@ class GptAcademicGameBaseState():
state.chatbot = chatbot
state.callback_fn = callback_fn
return state
def continue_game(self, prompt, chatbot, history):
# 游戏主体
yield from self.step(prompt, chatbot, history)

2
crazy_functions/pdf_fns/breakdown_txt.py
View File

@ -35,7 +35,7 @@ def cut(limit, get_token_fn, txt_tocut, must_break_at_empty_line, break_anyway=F
remain_txt_to_cut_storage = ""
# 为了加速计算，我们采样一个特殊的手段。当 remain_txt_to_cut > `_max` 时， 我们把 _max 后的文字转存至 remain_txt_to_cut_storage
remain_txt_to_cut, remain_txt_to_cut_storage = maintain_storage(remain_txt_to_cut, remain_txt_to_cut_storage)
while True:
if get_token_fn(remain_txt_to_cut) <= limit:
# 如果剩余文本的token数小于限制，那么就不用切了

10
crazy_functions/pdf_fns/parse_pdf.py
View File

@ -64,8 +64,8 @@ def produce_report_markdown(gpt_response_collection, meta, paper_meta_info, chat
# 再做一个小修改：重新修改当前part的标题，默认用英文的
cur_value += value
translated_res_array.append(cur_value)
res_path = write_history_to_file(meta + ["# Meta Translation" , paper_meta_info] + translated_res_array,
file_basename = f"{gen_time_str()}-translated_only.md",
res_path = write_history_to_file(meta + ["# Meta Translation" , paper_meta_info] + translated_res_array,
file_basename = f"{gen_time_str()}-translated_only.md",
file_fullname = None,
auto_caption = False)
promote_file_to_downloadzone(res_path, rename_file=os.path.basename(res_path)+'.md', chatbot=chatbot)
@ -144,11 +144,11 @@ def translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_fi
produce_report_markdown(gpt_response_collection, meta, paper_meta_info, chatbot, fp, generated_conclusion_files)
# -=-=-=-=-=-=-=-= 写出HTML文件 -=-=-=-=-=-=-=-=
ch = construct_html()
ch = construct_html()
orig = ""
trans = ""
gpt_response_collection_html = copy.deepcopy(gpt_response_collection)
for i,k in enumerate(gpt_response_collection_html):
for i,k in enumerate(gpt_response_collection_html):
if i%2==0:
gpt_response_collection_html[i] = inputs_show_user_array[i//2]
else:
@ -159,7 +159,7 @@ def translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_fi
final = ["", "", "一、论文概况", "", "Abstract", paper_meta_info, "二、论文翻译", ""]
final.extend(gpt_response_collection_html)
for i, k in enumerate(final):
for i, k in enumerate(final):
if i%2==0:
orig = k
if i%2==1:

12
crazy_functions/pdf_fns/parse_word.py
View File

@ -22,10 +22,10 @@ def extract_text_from_files(txt, chatbot, history):
file_manifest = []
excption = ""
if txt == "":
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')
@ -35,12 +35,12 @@ def extract_text_from_files(txt, chatbot, history):
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
@ -61,7 +61,7 @@ def extract_text_from_files(txt, chatbot, history):
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:
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("")
@ -81,5 +81,5 @@ def extract_text_from_files(txt, chatbot, history):
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

22
crazy_functions/vector_fns/vector_database.py
View File

@ -28,7 +28,7 @@ EMBEDDING_DEVICE = "cpu"
# 基于上下文的prompt模版，请务必保留"{question}"和"{context}"
PROMPT_TEMPLATE = """已知信息：
{context}
{context}
根据上述已知信息，简洁和专业的来回答用户的问题。如果无法从中得到答案，请说 “根据已知信息无法回答该问题” 或 “没有提供足够的相关信息”，不允许在答案中添加编造成分，答案请使用中文。 问题是：{question}"""
@ -58,7 +58,7 @@ OPEN_CROSS_DOMAIN = False
def similarity_search_with_score_by_vector(
self, embedding: List[float], k: int = 4
) -> List[Tuple[Document, float]]:
def seperate_list(ls: List[int]) -> List[List[int]]:
lists = []
ls1 = [ls[0]]
@ -200,7 +200,7 @@ class LocalDocQA:
return vs_path, loaded_files
else:
raise RuntimeError("文件加载失败，请检查文件格式是否正确")
def get_loaded_file(self, vs_path):
ds = self.vector_store.docstore
return set([ds._dict[k].metadata['source'].split(vs_path)[-1] for k in ds._dict])
@ -290,10 +290,10 @@ class knowledge_archive_interface():
self.threadLock.acquire()
# import uuid
self.current_id = id
self.qa_handle, self.kai_path = construct_vector_store(
vs_id=self.current_id,
self.qa_handle, self.kai_path = construct_vector_store(
vs_id=self.current_id,
vs_path=vs_path,
files=file_manifest,
files=file_manifest,
sentence_size=100,
history=[],
one_conent="",
@ -304,7 +304,7 @@ class knowledge_archive_interface():
def get_current_archive_id(self):
return self.current_id
def get_loaded_file(self, vs_path):
return self.qa_handle.get_loaded_file(vs_path)
@ -312,10 +312,10 @@ class knowledge_archive_interface():
self.threadLock.acquire()
if not self.current_id == id:
self.current_id = id
self.qa_handle, self.kai_path = construct_vector_store(
vs_id=self.current_id,
self.qa_handle, self.kai_path = construct_vector_store(
vs_id=self.current_id,
vs_path=vs_path,
files=[],
files=[],
sentence_size=100,
history=[],
one_conent="",
@ -329,7 +329,7 @@ class knowledge_archive_interface():
query = txt,
vs_path = self.kai_path,
score_threshold=VECTOR_SEARCH_SCORE_THRESHOLD,
vector_search_top_k=VECTOR_SEARCH_TOP_K,
vector_search_top_k=VECTOR_SEARCH_TOP_K,
chunk_conent=True,
chunk_size=CHUNK_SIZE,
text2vec = self.get_chinese_text2vec(),

10
crazy_functions/vt_fns/vt_call_plugin.py
View File

@ -35,9 +35,9 @@ def get_recent_file_prompt_support(chatbot):
most_recent_uploaded = chatbot._cookies.get("most_recent_uploaded", None)
path = most_recent_uploaded['path']
prompt = "\nAdditional Information:\n"
prompt = "In case that this plugin requires a path or a file as argument,"
prompt += f"it is important for you to know that the user has recently uploaded a file, located at: `{path}`"
prompt += f"Only use it when necessary, otherwise, you can ignore this file."
prompt = "In case that this plugin requires a path or a file as argument,"
prompt += f"it is important for you to know that the user has recently uploaded a file, located at: `{path}`"
prompt += f"Only use it when necessary, otherwise, you can ignore this file."
return prompt
def get_inputs_show_user(inputs, plugin_arr_enum_prompt):
@ -82,7 +82,7 @@ def execute_plugin(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prom
msg += "\n但您可以尝试再试一次\n"
yield from update_ui_lastest_msg(lastmsg=msg, chatbot=chatbot, history=history, delay=2)
return
# ⭐ ⭐ ⭐ 确认插件参数
if not have_any_recent_upload_files(chatbot):
appendix_info = ""
@ -99,7 +99,7 @@ def execute_plugin(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prom
inputs = f"A plugin named {plugin_sel.plugin_selection} is selected, " + \
"you should extract plugin_arg from the user requirement, the user requirement is: \n\n" + \
">> " + (txt + appendix_info).rstrip('\n').replace('\n','\n>> ') + '\n\n' + \
gpt_json_io.format_instructions
gpt_json_io.format_instructions
run_gpt_fn = lambda inputs, sys_prompt: predict_no_ui_long_connection(
inputs=inputs, llm_kwargs=llm_kwargs, history=[], sys_prompt=sys_prompt, observe_window=[])
plugin_sel = gpt_json_io.generate_output_auto_repair(run_gpt_fn(inputs, ""), run_gpt_fn)

10
crazy_functions/vt_fns/vt_modify_config.py
View File

@ -10,7 +10,7 @@ def modify_configuration_hot(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
ALLOW_RESET_CONFIG = get_conf('ALLOW_RESET_CONFIG')
if not ALLOW_RESET_CONFIG:
yield from update_ui_lastest_msg(
lastmsg=f"当前配置不允许被修改！如需激活本功能，请在config.py中设置ALLOW_RESET_CONFIG=True后重启软件。",
lastmsg=f"当前配置不允许被修改！如需激活本功能，请在config.py中设置ALLOW_RESET_CONFIG=True后重启软件。",
chatbot=chatbot, history=history, delay=2
)
return
@ -35,7 +35,7 @@ def modify_configuration_hot(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
inputs = "Analyze how to change configuration according to following user input, answer me with json: \n\n" + \
">> " + txt.rstrip('\n').replace('\n','\n>> ') + '\n\n' + \
gpt_json_io.format_instructions
run_gpt_fn = lambda inputs, sys_prompt: predict_no_ui_long_connection(
inputs=inputs, llm_kwargs=llm_kwargs, history=[], sys_prompt=sys_prompt, observe_window=[])
user_intention = gpt_json_io.generate_output_auto_repair(run_gpt_fn(inputs, ""), run_gpt_fn)
@ -45,11 +45,11 @@ def modify_configuration_hot(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
ok = (explicit_conf in txt)
if ok:
yield from update_ui_lastest_msg(
lastmsg=f"正在执行任务: {txt}\n\n新配置{explicit_conf}={user_intention.new_option_value}",
lastmsg=f"正在执行任务: {txt}\n\n新配置{explicit_conf}={user_intention.new_option_value}",
chatbot=chatbot, history=history, delay=1
)
yield from update_ui_lastest_msg(
lastmsg=f"正在执行任务: {txt}\n\n新配置{explicit_conf}={user_intention.new_option_value}\n\n正在修改配置中",
lastmsg=f"正在执行任务: {txt}\n\n新配置{explicit_conf}={user_intention.new_option_value}\n\n正在修改配置中",
chatbot=chatbot, history=history, delay=2
)
@ -69,7 +69,7 @@ def modify_configuration_reboot(txt, llm_kwargs, plugin_kwargs, chatbot, history
ALLOW_RESET_CONFIG = get_conf('ALLOW_RESET_CONFIG')
if not ALLOW_RESET_CONFIG:
yield from update_ui_lastest_msg(
lastmsg=f"当前配置不允许被修改！如需激活本功能，请在config.py中设置ALLOW_RESET_CONFIG=True后重启软件。",
lastmsg=f"当前配置不允许被修改！如需激活本功能，请在config.py中设置ALLOW_RESET_CONFIG=True后重启软件。",
chatbot=chatbot, history=history, delay=2
)
return

2
crazy_functions/vt_fns/vt_state.py
View File

@ -6,7 +6,7 @@ class VoidTerminalState():
def reset_state(self):
self.has_provided_explaination = False
def lock_plugin(self, chatbot):
chatbot._cookies['lock_plugin'] = 'crazy_functions.虚空终端->虚空终端'
chatbot._cookies['plugin_state'] = pickle.dumps(self)

10
crazy_functions/下载arxiv论文翻译摘要.py
View File

@ -144,8 +144,8 @@ def 下载arxiv论文并翻译摘要(txt, llm_kwargs, plugin_kwargs, chatbot, hi
try:
import bs4
except:
report_exception(chatbot, history,
a = f"解析项目: {txt}",
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 beautifulsoup4```。")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
@ -157,12 +157,12 @@ def 下载arxiv论文并翻译摘要(txt, llm_kwargs, plugin_kwargs, chatbot, hi
try:
pdf_path, info = download_arxiv_(txt)
except:
report_exception(chatbot, history,
a = f"解析项目: {txt}",
report_exception(chatbot, history,
a = f"解析项目: {txt}",
b = f"下载pdf文件未成功")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
# 翻译摘要等
i_say = f"请你阅读以下学术论文相关的材料，提取摘要，翻译为中文。材料如下：{str(info)}"
i_say_show_user = f'请你阅读以下学术论文相关的材料，提取摘要，翻译为中文。论文：{pdf_path}'

12
crazy_functions/互动小游戏.py
View File

@ -12,9 +12,9 @@ def 随机小游戏(prompt, llm_kwargs, plugin_kwargs, chatbot, history, system_
# 选择游戏
cls = MiniGame_ResumeStory
# 如果之前已经初始化了游戏实例，则继续该实例；否则重新初始化
state = cls.sync_state(chatbot,
llm_kwargs,
cls,
state = cls.sync_state(chatbot,
llm_kwargs,
cls,
plugin_name='MiniGame_ResumeStory',
callback_fn='crazy_functions.互动小游戏->随机小游戏',
lock_plugin=True
@ -30,9 +30,9 @@ def 随机小游戏1(prompt, llm_kwargs, plugin_kwargs, chatbot, history, system
# 选择游戏
cls = MiniGame_ASCII_Art
# 如果之前已经初始化了游戏实例，则继续该实例；否则重新初始化
state = cls.sync_state(chatbot,
llm_kwargs,
cls,
state = cls.sync_state(chatbot,
llm_kwargs,
cls,
plugin_name='MiniGame_ASCII_Art',
callback_fn='crazy_functions.互动小游戏->随机小游戏1',
lock_plugin=True

2
crazy_functions/交互功能函数模板.py
View File

@ -38,7 +38,7 @@ def 交互功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
inputs=inputs_show_user=f"Extract all image urls in this html page, pick the first 5 images and show them with markdown format: \n\n {page_return}"
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=inputs, inputs_show_user=inputs_show_user,
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
sys_prompt="When you want to show an image, use markdown format. e.g. ![image_description](image_url). If there are no image url provided, answer 'no image url provided'"
)
chatbot[-1] = [chatbot[-1][0], gpt_say]

46
crazy_functions/函数动态生成.py
View File

@ -6,10 +6,10 @@
- 将图像转为灰度图像
- 将csv文件转excel表格
Testing:
- Crop the image, keeping the bottom half.
- Swap the blue channel and red channel of the image.
- Convert the image to grayscale.
Testing:
- Crop the image, keeping the bottom half.
- Swap the blue channel and red channel of the image.
- Convert the image to grayscale.
- Convert the CSV file to an Excel spreadsheet.
"""
@ -29,12 +29,12 @@ import multiprocessing
templete = """
```python
import ... # Put dependencies here, e.g. import numpy as np.
import ... # Put dependencies here, e.g. import numpy as np.
class TerminalFunction(object): # Do not change the name of the class, The name of the class must be `TerminalFunction`
def run(self, path): # The name of the function must be `run`, it takes only a positional argument.
# rewrite the function you have just written here
# rewrite the function you have just written here
...
return generated_file_path
```
@ -48,7 +48,7 @@ def get_code_block(reply):
import re
pattern = r"```([\s\S]*?)```" # regex pattern to match code blocks
matches = re.findall(pattern, reply) # find all code blocks in text
if len(matches) == 1:
if len(matches) == 1:
return matches[0].strip('python') # code block
for match in matches:
if 'class TerminalFunction' in match:
@ -68,8 +68,8 @@ def gpt_interact_multi_step(txt, file_type, llm_kwargs, chatbot, history):
# 第一步
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=i_say, inputs_show_user=i_say,
llm_kwargs=llm_kwargs, chatbot=chatbot, history=demo,
inputs=i_say, inputs_show_user=i_say,
llm_kwargs=llm_kwargs, chatbot=chatbot, history=demo,
sys_prompt= r"You are a world-class programmer."
)
history.extend([i_say, gpt_say])
@ -82,33 +82,33 @@ def gpt_interact_multi_step(txt, file_type, llm_kwargs, chatbot, history):
]
i_say = "".join(prompt_compose); inputs_show_user = "If previous stage is successful, rewrite the function you have just written to satisfy executable templete. "
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=i_say, inputs_show_user=inputs_show_user,
llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
inputs=i_say, inputs_show_user=inputs_show_user,
llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
sys_prompt= r"You are a programmer. You need to replace `...` with valid packages, do not give `...` in your answer!"
)
code_to_return = gpt_say
history.extend([i_say, gpt_say])
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
# # 第三步
# i_say = "Please list to packages to install to run the code above. Then show me how to use `try_install_deps` function to install them."
# i_say += 'For instance. `try_install_deps(["opencv-python", "scipy", "numpy"])`'
# installation_advance = yield from request_gpt_model_in_new_thread_with_ui_alive(
# inputs=i_say, inputs_show_user=inputs_show_user,
# llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
# inputs=i_say, inputs_show_user=inputs_show_user,
# llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
# sys_prompt= r"You are a programmer."
# )
# # # 第三步
# # # 第三步
# i_say = "Show me how to use `pip` to install packages to run the code above. "
# i_say += 'For instance. `pip install -r opencv-python scipy numpy`'
# installation_advance = yield from request_gpt_model_in_new_thread_with_ui_alive(
# inputs=i_say, inputs_show_user=i_say,
# llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
# inputs=i_say, inputs_show_user=i_say,
# llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
# sys_prompt= r"You are a programmer."
# )
installation_advance = ""
return code_to_return, installation_advance, txt, file_type, llm_kwargs, chatbot, history
@ -117,7 +117,7 @@ def gpt_interact_multi_step(txt, file_type, llm_kwargs, chatbot, history):
def for_immediate_show_off_when_possible(file_type, fp, chatbot):
if file_type in ['png', 'jpg']:
image_path = os.path.abspath(fp)
chatbot.append(['这是一张图片, 展示如下:',
chatbot.append(['这是一张图片, 展示如下:',
f'本地文件地址: <br/>`{image_path}`<br/>'+
f'本地文件预览: <br/><div align="center"><img src="file={image_path}"></div>'
])
@ -177,7 +177,7 @@ def 函数动态生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
chatbot.append(["文件检索", "没有发现任何近期上传的文件。"])
yield from update_ui_lastest_msg("没有发现任何近期上传的文件。", chatbot, history, 1)
return # 2. 如果没有文件
# 读取文件
file_type = file_list[0].split('.')[-1]
@ -185,7 +185,7 @@ def 函数动态生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
if is_the_upload_folder(txt):
yield from update_ui_lastest_msg(f"请在输入框内填写需求, 然后再次点击该插件! 至于您的文件，不用担心, 文件路径 {txt} 已经被记忆. ", chatbot, history, 1)
return
# 开始干正事
MAX_TRY = 3
for j in range(MAX_TRY): # 最多重试5次
@ -238,7 +238,7 @@ def 函数动态生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
# chatbot.append(["如果是缺乏依赖，请参考以下建议", installation_advance])
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
# 顺利完成，收尾
res = str(res)
if os.path.exists(res):
@ -248,5 +248,5 @@ def 函数动态生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
else:
chatbot.append(["执行成功了，结果是一个字符串", "结果：" + res])
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

4
crazy_functions/命令行助手.py
View File

@ -21,8 +21,8 @@ def 命令行助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
i_say = "请写bash命令实现以下功能：" + txt
# 开始
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=i_say, inputs_show_user=txt,
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
inputs=i_say, inputs_show_user=txt,
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
sys_prompt="你是一个Linux大师级用户。注意，当我要求你写bash命令时，尽可能地仅用一行命令解决我的要求。"
)
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新

8
crazy_functions/图片生成.py
View File

@ -7,7 +7,7 @@ def gen_image(llm_kwargs, prompt, resolution="1024x1024", model="dall-e-2", qual
from request_llms.bridge_all import model_info
proxies = get_conf('proxies')
# Set up OpenAI API key and model
# Set up OpenAI API key and model
api_key = select_api_key(llm_kwargs['api_key'], llm_kwargs['llm_model'])
chat_endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
# 'https://api.openai.com/v1/chat/completions'
@ -113,7 +113,7 @@ def 图片生成_DALLE2(prompt, llm_kwargs, plugin_kwargs, chatbot, history, sys
if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
resolution = plugin_kwargs.get("advanced_arg", '1024x1024')
image_url, image_path = gen_image(llm_kwargs, prompt, resolution)
chatbot.append([prompt,
chatbot.append([prompt,
f'图像中转网址: <br/>`{image_url}`<br/>'+
f'中转网址预览: <br/><div align="center"><img src="{image_url}"></div>'
f'本地文件地址: <br/>`{image_path}`<br/>'+
@ -144,7 +144,7 @@ def 图片生成_DALLE3(prompt, llm_kwargs, plugin_kwargs, chatbot, history, sys
elif part in ['vivid', 'natural']:
style = part
image_url, image_path = gen_image(llm_kwargs, prompt, resolution, model="dall-e-3", quality=quality, style=style)
chatbot.append([prompt,
chatbot.append([prompt,
f'图像中转网址: <br/>`{image_url}`<br/>'+
f'中转网址预览: <br/><div align="center"><img src="{image_url}"></div>'
f'本地文件地址: <br/>`{image_path}`<br/>'+
@ -164,7 +164,7 @@ class ImageEditState(GptAcademicState):
confirm = (len(file_manifest) >= 1 and file_manifest[0].endswith('.png') and os.path.exists(file_manifest[0]))
file = None if not confirm else file_manifest[0]
return confirm, file
def lock_plugin(self, chatbot):
chatbot._cookies['lock_plugin'] = 'crazy_functions.图片生成->图片修改_DALLE2'
self.dump_state(chatbot)

6
crazy_functions/多智能体.py
View File

@ -57,11 +57,11 @@ def 多智能体终端(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
if get_conf("AUTOGEN_USE_DOCKER"):
import docker
except:
chatbot.append([ f"处理任务: {txt}",
chatbot.append([ f"处理任务: {txt}",
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 pyautogen docker```。"])
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
# 尝试导入依赖，如果缺少依赖，则给出安装建议
try:
import autogen
@ -72,7 +72,7 @@ def 多智能体终端(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
chatbot.append([f"处理任务: {txt}", f"缺少docker运行环境！"])
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
# 解锁插件
chatbot.get_cookies()['lock_plugin'] = None
persistent_class_multi_user_manager = GradioMultiuserManagerForPersistentClasses()

10
crazy_functions/对话历史存档.py
View File

@ -66,7 +66,7 @@ def read_file_to_chat(chatbot, history, file_name):
i_say, gpt_say = h.split('<hr style="border-top: dotted 3px #ccc;">')
chatbot.append([i_say, gpt_say])
chatbot.append([f"存档文件详情？", f"[Local Message] 载入对话{len(html)}条，上下文{len(history)}条。"])
return chatbot, history
return chatbot, history
@CatchException
def 对话历史存档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
@ -80,7 +80,7 @@ def 对话历史存档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
user_request 当前用户的请求信息（IP地址等）
"""
chatbot.append(("保存当前对话",
chatbot.append(("保存当前对话",
f"[Local Message] {write_chat_to_file(chatbot, history)}，您可以调用下拉菜单中的“载入对话历史存档”还原当下的对话。"))
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间，我们先及时地做一次界面更新
@ -108,9 +108,9 @@ def 载入对话历史存档(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
if txt == "": txt = '空空如也的输入栏'
import glob
local_history = "<br/>".join([
"`"+hide_cwd(f)+f" ({gen_file_preview(f)})"+"`"
"`"+hide_cwd(f)+f" ({gen_file_preview(f)})"+"`"
for f in glob.glob(
f'{get_log_folder(get_user(chatbot), plugin_name="chat_history")}/**/{f_prefix}*.html',
f'{get_log_folder(get_user(chatbot), plugin_name="chat_history")}/**/{f_prefix}*.html',
recursive=True
)])
chatbot.append([f"正在查找对话历史文件（html格式）: {txt}", f"找不到任何html文件: {txt}。但本地存储了以下历史文件，您可以将任意一个文件路径粘贴到输入区，然后重试：<br/>{local_history}"])
@ -139,7 +139,7 @@ def 删除所有本地对话历史记录(txt, llm_kwargs, plugin_kwargs, chatbot
import glob, os
local_history = "<br/>".join([
"`"+hide_cwd(f)+"`"
"`"+hide_cwd(f)+"`"
for f in glob.glob(
f'{get_log_folder(get_user(chatbot), plugin_name="chat_history")}/**/{f_prefix}*.html', recursive=True
)])

12
crazy_functions/总结word文档.py
View File

@ -40,10 +40,10 @@ def 解析docx(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot
i_say = f'请对下面的文章片段用中文做概述，文件名是{os.path.relpath(fp, project_folder)}，文章内容是 ```{paper_frag}```'
i_say_show_user = f'请对下面的文章片段做概述: {os.path.abspath(fp)}的第{i+1}/{len(paper_fragments)}个片段。'
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=i_say,
inputs_show_user=i_say_show_user,
inputs=i_say,
inputs_show_user=i_say_show_user,
llm_kwargs=llm_kwargs,
chatbot=chatbot,
chatbot=chatbot,
history=[],
sys_prompt="总结文章。"
)
@ -56,10 +56,10 @@ def 解析docx(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot
if len(paper_fragments) > 1:
i_say = f"根据以上的对话，总结文章{os.path.abspath(fp)}的主要内容。"
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=i_say,
inputs_show_user=i_say,
inputs=i_say,
inputs_show_user=i_say,
llm_kwargs=llm_kwargs,
chatbot=chatbot,
chatbot=chatbot,
history=this_paper_history,
sys_prompt="总结文章。"
)

16
crazy_functions/批量Markdown翻译.py
View File

@ -53,7 +53,7 @@ class PaperFileGroup():
def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, language='en'):
from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
# <-------- 读取Markdown文件，删除其中的所有注释 ---------->
# <-------- 读取Markdown文件，删除其中的所有注释 ---------->
pfg = PaperFileGroup()
for index, fp in enumerate(file_manifest):
@ -63,23 +63,23 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
pfg.file_paths.append(fp)
pfg.file_contents.append(file_content)
# <-------- 拆分过长的Markdown文件 ---------->
# <-------- 拆分过长的Markdown文件 ---------->
pfg.run_file_split(max_token_limit=1500)
n_split = len(pfg.sp_file_contents)
# <-------- 多线程翻译开始 ---------->
# <-------- 多线程翻译开始 ---------->
if language == 'en->zh':
inputs_array = ["This is a Markdown file, translate it into Chinese, do not modify any existing Markdown commands:" +
inputs_array = ["This is a Markdown file, translate it into Chinese, do not modify any existing Markdown commands:" +
f"\n\n{frag}" for frag in pfg.sp_file_contents]
inputs_show_user_array = [f"翻译 {f}" for f in pfg.sp_file_tag]
sys_prompt_array = ["You are a professional academic paper translator." for _ in range(n_split)]
elif language == 'zh->en':
inputs_array = [f"This is a Markdown file, translate it into English, do not modify any existing Markdown commands:" +
inputs_array = [f"This is a Markdown file, translate it into English, do not modify any existing Markdown commands:" +
f"\n\n{frag}" for frag in pfg.sp_file_contents]
inputs_show_user_array = [f"翻译 {f}" for f in pfg.sp_file_tag]
sys_prompt_array = ["You are a professional academic paper translator." for _ in range(n_split)]
else:
inputs_array = [f"This is a Markdown file, translate it into {language}, do not modify any existing Markdown commands, only answer me with translated results:" +
inputs_array = [f"This is a Markdown file, translate it into {language}, do not modify any existing Markdown commands, only answer me with translated results:" +
f"\n\n{frag}" for frag in pfg.sp_file_contents]
inputs_show_user_array = [f"翻译 {f}" for f in pfg.sp_file_tag]
sys_prompt_array = ["You are a professional academic paper translator." for _ in range(n_split)]
@ -103,7 +103,7 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
except:
logging.error(trimmed_format_exc())
# <-------- 整理结果，退出 ---------->
# <-------- 整理结果，退出 ---------->
create_report_file_name = gen_time_str() + f"-chatgpt.md"
res = write_history_to_file(gpt_response_collection, file_basename=create_report_file_name)
promote_file_to_downloadzone(res, chatbot=chatbot)
@ -255,7 +255,7 @@ def Markdown翻译指定语言(txt, llm_kwargs, plugin_kwargs, chatbot, history,
report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.md文件: {txt}")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
language = plugin_kwargs.get("advanced_arg", 'Chinese')
yield from 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, language=language)

24
crazy_functions/批量总结PDF文档.py
View File

@ -17,7 +17,7 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
file_content, page_one = read_and_clean_pdf_text(file_name) # （尝试）按照章节切割PDF
file_content = file_content.encode('utf-8', 'ignore').decode() # avoid reading non-utf8 chars
page_one = str(page_one).encode('utf-8', 'ignore').decode() # avoid reading non-utf8 chars
TOKEN_LIMIT_PER_FRAGMENT = 2500
from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
@ -25,7 +25,7 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
page_one_fragments = breakdown_text_to_satisfy_token_limit(txt=str(page_one), limit=TOKEN_LIMIT_PER_FRAGMENT//4, llm_model=llm_kwargs['llm_model'])
# 为了更好的效果，我们剥离Introduction之后的部分（如果有）
paper_meta = page_one_fragments[0].split('introduction')[0].split('Introduction')[0].split('INTRODUCTION')[0]
############################## <第 1 步，从摘要中提取高价值信息，放到history中> ##################################
final_results = []
final_results.append(paper_meta)
@ -44,10 +44,10 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
i_say = f"Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} Chinese characters: {paper_fragments[i]}"
i_say_show_user = f"[{i+1}/{n_fragment}] Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} Chinese characters: {paper_fragments[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
llm_kwargs, chatbot,
llm_kwargs, chatbot,
history=["The main idea of the previous section is?", last_iteration_result], # 迭代上一次的结果
sys_prompt="Extract the main idea of this section with Chinese." # 提示
)
)
iteration_results.append(gpt_say)
last_iteration_result = gpt_say
@ -67,15 +67,15 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
- (2):What are the past methods? What are the problems with them? Is the approach well motivated?
- (3):What is the research methodology proposed in this paper?
- (4):On what task and what performance is achieved by the methods in this paper? Can the performance support their goals?
Follow the format of the output that follows:
Follow the format of the output that follows:
1. Title: xxx\n\n
2. Authors: xxx\n\n
3. Affiliation: xxx\n\n
4. Keywords: xxx\n\n
5. Urls: xxx or xxx , xxx \n\n
6. Summary: \n\n
- (1):xxx;\n
- (2):xxx;\n
- (1):xxx;\n
- (2):xxx;\n
- (3):xxx;\n
- (4):xxx.\n\n
Be sure to use Chinese answers (proper nouns need to be marked in English), statements as concise and academic as possible,
@ -85,8 +85,8 @@ do not have too much repetitive information, numerical values using the original
file_write_buffer.extend(final_results)
i_say, final_results = input_clipping(i_say, final_results, max_token_limit=2000)
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=i_say, inputs_show_user='开始最终总结',
llm_kwargs=llm_kwargs, chatbot=chatbot, history=final_results,
inputs=i_say, inputs_show_user='开始最终总结',
llm_kwargs=llm_kwargs, chatbot=chatbot, history=final_results,
sys_prompt= f"Extract the main idea of this paper with less than {NUM_OF_WORD} Chinese characters"
)
final_results.append(gpt_say)
@ -114,8 +114,8 @@ def 批量总结PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
try:
import fitz
except:
report_exception(chatbot, history,
a = f"解析项目: {txt}",
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
@ -134,7 +134,7 @@ def 批量总结PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
# 搜索需要处理的文件清单
file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.pdf', recursive=True)]
# 如果没找到任何文件
if len(file_manifest) == 0:
report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex或.pdf文件: {txt}")

16
crazy_functions/批量总结PDF文档pdfminer.py
View File

@ -85,10 +85,10 @@ def 解析Paper(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbo
msg = '正常'
# ** gpt request **
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=i_say,
inputs_show_user=i_say_show_user,
inputs=i_say,
inputs_show_user=i_say_show_user,
llm_kwargs=llm_kwargs,
chatbot=chatbot,
chatbot=chatbot,
history=[],
sys_prompt="总结文章。"
) # 带超时倒计时
@ -106,10 +106,10 @@ def 解析Paper(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbo
msg = '正常'
# ** gpt request **
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=i_say,
inputs_show_user=i_say,
inputs=i_say,
inputs_show_user=i_say,
llm_kwargs=llm_kwargs,
chatbot=chatbot,
chatbot=chatbot,
history=history,
sys_prompt="总结文章。"
) # 带超时倒计时
@ -138,8 +138,8 @@ def 批量总结PDF文档pdfminer(txt, llm_kwargs, plugin_kwargs, chatbot, histo
try:
import pdfminer, bs4
except:
report_exception(chatbot, history,
a = f"解析项目: {txt}",
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 pdfminer beautifulsoup4```。")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return

4
crazy_functions/批量翻译PDF文档_NOUGAT.py
View File

@ -76,8 +76,8 @@ def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
success_mmd, file_manifest_mmd, _ = get_files_from_everything(txt, type='.mmd')
success = success or success_mmd
file_manifest += file_manifest_mmd
chatbot.append(["文件列表：", ", ".join([e.split('/')[-1] for e in file_manifest])]);
yield from update_ui( chatbot=chatbot, history=history)
chatbot.append(["文件列表：", ", ".join([e.split('/')[-1] for e in file_manifest])]);
yield from update_ui( chatbot=chatbot, history=history)
# 检测输入参数，如没有给定输入参数，直接退出
if not success:
if txt == "": txt = '空空如也的输入栏'

12
crazy_functions/批量翻译PDF文档_多线程.py
View File

@ -68,7 +68,7 @@ def 解析PDF_基于GROBID(file_manifest, project_folder, llm_kwargs, plugin_kwa
with open(grobid_json_res, 'w+', encoding='utf8') as f:
f.write(json.dumps(article_dict, indent=4, ensure_ascii=False))
promote_file_to_downloadzone(grobid_json_res, chatbot=chatbot)
if article_dict is None: raise RuntimeError("解析PDF失败，请检查PDF是否损坏。")
yield from translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_files, TOKEN_LIMIT_PER_FRAGMENT, DST_LANG)
chatbot.append(("给出输出文件清单", str(generated_conclusion_files + generated_html_files)))
@ -97,7 +97,7 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
# 为了更好的效果，我们剥离Introduction之后的部分（如果有）
paper_meta = page_one_fragments[0].split('introduction')[0].split('Introduction')[0].split('INTRODUCTION')[0]
# 单线，获取文章meta信息
paper_meta_info = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=f"以下是一篇学术论文的基础信息，请从中提取出“标题”、“收录会议或期刊”、“作者”、“摘要”、“编号”、“作者邮箱”这六个部分。请用markdown格式输出，最后用中文翻译摘要部分。请提取：{paper_meta}",
@ -121,7 +121,7 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
)
gpt_response_collection_md = copy.deepcopy(gpt_response_collection)
# 整理报告的格式
for i,k in enumerate(gpt_response_collection_md):
for i,k in enumerate(gpt_response_collection_md):
if i%2==0:
gpt_response_collection_md[i] = f"\n\n---\n\n ## 原文[{i//2}/{len(gpt_response_collection_md)//2}]： \n\n {paper_fragments[i//2].replace('#', '')} \n\n---\n\n ## 翻译[{i//2}/{len(gpt_response_collection_md)//2}]：\n "
else:
@ -139,18 +139,18 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
# write html
try:
ch = construct_html()
ch = construct_html()
orig = ""
trans = ""
gpt_response_collection_html = copy.deepcopy(gpt_response_collection)
for i,k in enumerate(gpt_response_collection_html):
for i,k in enumerate(gpt_response_collection_html):
if i%2==0:
gpt_response_collection_html[i] = paper_fragments[i//2].replace('#', '')
else:
gpt_response_collection_html[i] = gpt_response_collection_html[i]
final = ["论文概况", paper_meta_info.replace('# ', '### '), "二、论文翻译", ""]
final.extend(gpt_response_collection_html)
for i, k in enumerate(final):
for i, k in enumerate(final):
if i%2==0:
orig = k
if i%2==1:

18
crazy_functions/数学动画生成manim.py
View File

@ -27,7 +27,7 @@ def eval_manim(code):
class_name = get_class_name(code)
try:
try:
time_str = gen_time_str()
subprocess.check_output([sys.executable, '-c', f"from gpt_log.MyAnimation import {class_name}; {class_name}().render()"])
shutil.move(f'media/videos/1080p60/{class_name}.mp4', f'gpt_log/{class_name}-{time_str}.mp4')
@ -36,7 +36,7 @@ def eval_manim(code):
output = e.output.decode()
print(f"Command returned non-zero exit status {e.returncode}: {output}.")
return f"Evaluating python script failed: {e.output}."
except:
except:
print('generating mp4 failed')
return "Generating mp4 failed."
@ -45,7 +45,7 @@ def get_code_block(reply):
import re
pattern = r"```([\s\S]*?)```" # regex pattern to match code blocks
matches = re.findall(pattern, reply) # find all code blocks in text
if len(matches) != 1:
if len(matches) != 1:
raise RuntimeError("GPT is not generating proper code.")
return matches[0].strip('python') # code block
@ -61,7 +61,7 @@ def 动画生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
user_request 当前用户的请求信息（IP地址等）
"""
# 清空历史，以免输入溢出
history = []
history = []
# 基本信息：功能、贡献者
chatbot.append([
@ -73,24 +73,24 @@ def 动画生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
# 尝试导入依赖, 如果缺少依赖, 则给出安装建议
dep_ok = yield from inspect_dependency(chatbot=chatbot, history=history) # 刷新界面
if not dep_ok: return
# 输入
i_say = f'Generate a animation to show: ' + txt
demo = ["Here is some examples of manim", examples_of_manim()]
_, demo = input_clipping(inputs="", history=demo, max_token_limit=2560)
# 开始
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=i_say, inputs_show_user=i_say,
llm_kwargs=llm_kwargs, chatbot=chatbot, history=demo,
inputs=i_say, inputs_show_user=i_say,
llm_kwargs=llm_kwargs, chatbot=chatbot, history=demo,
sys_prompt=
r"Write a animation script with 3blue1brown's manim. "+
r"Please begin with `from manim import *`. " +
r"Please begin with `from manim import *`. " +
r"Answer me with a code block wrapped by ```."
)
chatbot.append(["开始生成动画", "..."])
history.extend([i_say, gpt_say])
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
# 将代码转为动画
code = get_code_block(gpt_say)
res = eval_manim(code)

12
crazy_functions/理解PDF文档内容.py
View File

@ -15,7 +15,7 @@ def 解析PDF(file_name, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
file_content, page_one = read_and_clean_pdf_text(file_name) # （尝试）按照章节切割PDF
file_content = file_content.encode('utf-8', 'ignore').decode() # avoid reading non-utf8 chars
page_one = str(page_one).encode('utf-8', 'ignore').decode() # avoid reading non-utf8 chars
TOKEN_LIMIT_PER_FRAGMENT = 2500
from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
@ -23,7 +23,7 @@ def 解析PDF(file_name, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
page_one_fragments = breakdown_text_to_satisfy_token_limit(txt=str(page_one), limit=TOKEN_LIMIT_PER_FRAGMENT//4, llm_model=llm_kwargs['llm_model'])
# 为了更好的效果，我们剥离Introduction之后的部分（如果有）
paper_meta = page_one_fragments[0].split('introduction')[0].split('Introduction')[0].split('INTRODUCTION')[0]
############################## <第 1 步，从摘要中提取高价值信息，放到history中> ##################################
final_results = []
final_results.append(paper_meta)
@ -42,10 +42,10 @@ def 解析PDF(file_name, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
i_say = f"Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words: {paper_fragments[i]}"
i_say_show_user = f"[{i+1}/{n_fragment}] Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words: {paper_fragments[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
llm_kwargs, chatbot,
llm_kwargs, chatbot,
history=["The main idea of the previous section is?", last_iteration_result], # 迭代上一次的结果
sys_prompt="Extract the main idea of this section, answer me with Chinese." # 提示
)
)
iteration_results.append(gpt_say)
last_iteration_result = gpt_say
@ -76,8 +76,8 @@ def 理解PDF文档内容标准文件输入(txt, llm_kwargs, plugin_kwargs, chat
try:
import fitz
except:
report_exception(chatbot, history,
a = f"解析项目: {txt}",
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

4
crazy_functions/生成函数注释.py
View File

@ -16,7 +16,7 @@ def 生成函数注释(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
chatbot.append((i_say_show_user, "[Local Message] waiting gpt response."))
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
if not fast_debug:
if not fast_debug:
msg = '正常'
# ** gpt request **
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
@ -27,7 +27,7 @@ def 生成函数注释(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
if not fast_debug: time.sleep(2)
if not fast_debug:
if not fast_debug:
res = write_history_to_file(history)
promote_file_to_downloadzone(res, chatbot=chatbot)
chatbot.append(("完成了吗？", res))

28
crazy_functions/生成多种Mermaid图表.py
View File

@ -179,15 +179,15 @@ def 解析历史输入(history,llm_kwargs,file_manifest,chatbot,plugin_kwargs):
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]} ...."
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,
history=["The main content of the previous section is?", last_iteration_result], # 迭代上一次的结果
sys_prompt="Extracts the main content from the text section where it is located for graphing purposes, answer me with Chinese." # 提示
)
)
results.append(gpt_say)
last_iteration_result = gpt_say
############################## <第 2 步，根据整理的摘要选择图表类型> ##################################
if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
gpt_say = plugin_kwargs.get("advanced_arg", "") #将图表类型参数赋值为插件参数
gpt_say = plugin_kwargs.get("advanced_arg", "") #将图表类型参数赋值为插件参数
results_txt = '\n'.join(results) #合并摘要
if gpt_say not in ['1','2','3','4','5','6','7','8','9']: #如插件参数不正确则使用对话模型判断
i_say_show_user = f'接下来将判断适合的图表类型,如连续3次判断失败将会使用流程图进行绘制'; gpt_say = "[Local Message] 收到。" # 用户提示
@ -198,7 +198,7 @@ def 解析历史输入(history,llm_kwargs,file_manifest,chatbot,plugin_kwargs):
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=i_say,
inputs_show_user=i_say_show_user,
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
sys_prompt=""
)
if gpt_say in ['1','2','3','4','5','6','7','8','9']: #判断返回是否正确
@ -228,12 +228,12 @@ def 解析历史输入(history,llm_kwargs,file_manifest,chatbot,plugin_kwargs):
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=i_say,
inputs_show_user=i_say_show_user,
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
sys_prompt=""
)
history.append(gpt_say)
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
@CatchException
def 生成多种Mermaid图表(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
"""
@ -249,11 +249,11 @@ def 生成多种Mermaid图表(txt, llm_kwargs, plugin_kwargs, chatbot, history,
# 基本信息：功能、贡献者
chatbot.append([
"函数插件功能？",
"函数插件功能？",
"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"])
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
if os.path.exists(txt): #如输入区无内容则直接解析历史记录
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)
@ -264,15 +264,15 @@ def 生成多种Mermaid图表(txt, llm_kwargs, plugin_kwargs, chatbot, history,
if excption != "":
if excption == "word":
report_exception(chatbot, history,
a = f"解析项目: {txt}",
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。")
elif excption == "pdf":
report_exception(chatbot, history,
a = f"解析项目: {txt}",
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}",

8
crazy_functions/知识库问答.py
View File

@ -9,7 +9,7 @@ install_msg ="""
3. python -m pip install unstructured[all-docs] --upgrade
4. python -c 'import nltk; nltk.download("punkt")'
4. python -c 'import nltk; nltk.download("punkt")'
"""
@CatchException
@ -56,7 +56,7 @@ def 知识库文件注入(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
chatbot.append(["没有找到任何可读取文件", "当前支持的格式包括: txt, md, docx, pptx, pdf, json等"])
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
# < -------------------预热文本向量化模组--------------- >
chatbot.append(['<br/>'.join(file_manifest), "正在预热文本向量化模组, 如果是第一次运行, 将消耗较长时间下载中文向量化模型..."])
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
@ -109,8 +109,8 @@ def 读取知识库作答(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
chatbot.append((txt, f'[知识库 {kai_id}] ' + prompt))
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间，我们先及时地做一次界面更新
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=prompt, inputs_show_user=txt,
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
inputs=prompt, inputs_show_user=txt,
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
sys_prompt=system_prompt
)
history.extend((prompt, gpt_say))

14
crazy_functions/联网的ChatGPT.py
View File

@ -40,10 +40,10 @@ def scrape_text(url, proxies) -> str:
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.61 Safari/537.36',
'Content-Type': 'text/plain',
}
try:
try:
response = requests.get(url, headers=headers, proxies=proxies, timeout=8)
if response.encoding == "ISO-8859-1": response.encoding = response.apparent_encoding
except:
except:
return "无法连接到该网页"
soup = BeautifulSoup(response.text, "html.parser")
for script in soup(["script", "style"]):
@ -66,7 +66,7 @@ def 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
user_request 当前用户的请求信息（IP地址等）
"""
history = [] # 清空历史，以免输入溢出
chatbot.append((f"请结合互联网信息回答以下问题：{txt}",
chatbot.append((f"请结合互联网信息回答以下问题：{txt}",
"[Local Message] 请注意，您正在调用一个[函数插件]的模板，该模板可以实现ChatGPT联网信息综合。该函数面向希望实现更多有趣功能的开发者，它可以作为创建新功能函数的模板。您若希望分享新的功能模组，请不吝PR！"))
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间，我们先及时地做一次界面更新
@ -91,13 +91,13 @@ def 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
# ------------- < 第3步：ChatGPT综合 > -------------
i_say = f"从以上搜索结果中抽取信息，然后回答问题：{txt}"
i_say, history = input_clipping( # 裁剪输入，从最长的条目开始裁剪，防止爆token
inputs=i_say,
history=history,
inputs=i_say,
history=history,
max_token_limit=model_info[llm_kwargs['llm_model']]['max_token']*3//4
)
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=i_say, inputs_show_user=i_say,
llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
inputs=i_say, inputs_show_user=i_say,
llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
sys_prompt="请从给定的若干条搜索结果中抽取信息，对最相关的两个搜索结果进行总结，然后回答问题。"
)
chatbot[-1] = (i_say, gpt_say)

10
crazy_functions/虚空终端.py
View File

@ -33,7 +33,7 @@ explain_msg = """
- 「请调用插件，解析python源代码项目，代码我刚刚打包拖到上传区了」
- 「请问Transformer网络的结构是怎样的？」
2. 您可以打开插件下拉菜单以了解本项目的各种能力。
2. 您可以打开插件下拉菜单以了解本项目的各种能力。
3. 如果您使用「调用插件xxx」、「修改配置xxx」、「请问」等关键词，您的意图可以被识别的更准确。
@ -67,7 +67,7 @@ class UserIntention(BaseModel):
def chat(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_intention):
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=txt, inputs_show_user=txt,
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
sys_prompt=system_prompt
)
chatbot[-1] = [txt, gpt_say]
@ -115,7 +115,7 @@ def 虚空终端(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
if is_the_upload_folder(txt):
state.set_state(chatbot=chatbot, key='has_provided_explaination', value=False)
appendix_msg = "\n\n**很好，您已经上传了文件**，现在请您描述您的需求。"
if is_certain or (state.has_provided_explaination):
# 如果意图明确，跳过提示环节
state.set_state(chatbot=chatbot, key='has_provided_explaination', value=True)
@ -152,7 +152,7 @@ def 虚空终端主路由(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
analyze_res = run_gpt_fn(inputs, "")
try:
user_intention = gpt_json_io.generate_output_auto_repair(analyze_res, run_gpt_fn)
lastmsg=f"正在执行任务: {txt}\n\n用户意图理解: 意图={explain_intention_to_user[user_intention.intention_type]}",
lastmsg=f"正在执行任务: {txt}\n\n用户意图理解: 意图={explain_intention_to_user[user_intention.intention_type]}",
except JsonStringError as e:
yield from update_ui_lastest_msg(
lastmsg=f"正在执行任务: {txt}\n\n用户意图理解: 失败 当前语言模型（{llm_kwargs['llm_model']}）不能理解您的意图", chatbot=chatbot, history=history, delay=0)
@ -161,7 +161,7 @@ def 虚空终端主路由(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
pass
yield from update_ui_lastest_msg(
lastmsg=f"正在执行任务: {txt}\n\n用户意图理解: 意图={explain_intention_to_user[user_intention.intention_type]}",
lastmsg=f"正在执行任务: {txt}\n\n用户意图理解: 意图={explain_intention_to_user[user_intention.intention_type]}",
chatbot=chatbot, history=history, delay=0)
# 用户意图: 修改本项目的配置

8
crazy_functions/解析项目源代码.py
View File

@ -82,13 +82,13 @@ def 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
inputs=inputs, inputs_show_user=inputs_show_user, llm_kwargs=llm_kwargs, chatbot=chatbot,
history=this_iteration_history_feed, # 迭代之前的分析
sys_prompt="你是一个程序架构分析师，正在分析一个项目的源代码。" + sys_prompt_additional)
diagram_code = make_diagram(this_iteration_files, result, this_iteration_history_feed)
summary = "请用一句话概括这些文件的整体功能。\n\n" + diagram_code
summary_result = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=summary,
inputs_show_user=summary,
llm_kwargs=llm_kwargs,
inputs=summary,
inputs_show_user=summary,
llm_kwargs=llm_kwargs,
chatbot=chatbot,
history=[i_say, result], # 迭代之前的分析
sys_prompt="你是一个程序架构分析师，正在分析一个项目的源代码。" + sys_prompt_additional)

8
crazy_functions/询问多个大语言模型.py
View File

@ -20,8 +20,8 @@ def 同时问询(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
# llm_kwargs['llm_model'] = 'chatglm&gpt-3.5-turbo&api2d-gpt-3.5-turbo' # 支持任意数量的llm接口，用&符号分隔
llm_kwargs['llm_model'] = MULTI_QUERY_LLM_MODELS # 支持任意数量的llm接口，用&符号分隔
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=txt, inputs_show_user=txt,
llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
inputs=txt, inputs_show_user=txt,
llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
sys_prompt=system_prompt,
retry_times_at_unknown_error=0
)
@ -52,8 +52,8 @@ def 同时问询_指定模型(txt, llm_kwargs, plugin_kwargs, chatbot, history,
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间，我们先及时地做一次界面更新
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=txt, inputs_show_user=txt,
llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
inputs=txt, inputs_show_user=txt,
llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
sys_prompt=system_prompt,
retry_times_at_unknown_error=0
)

6
crazy_functions/语音助手.py
View File

@ -39,7 +39,7 @@ class AsyncGptTask():
try:
MAX_TOKEN_ALLO = 2560
i_say, history = input_clipping(i_say, history, max_token_limit=MAX_TOKEN_ALLO)
gpt_say_partial = predict_no_ui_long_connection(inputs=i_say, llm_kwargs=llm_kwargs, history=history, sys_prompt=sys_prompt,
gpt_say_partial = predict_no_ui_long_connection(inputs=i_say, llm_kwargs=llm_kwargs, history=history, sys_prompt=sys_prompt,
observe_window=observe_window[index], console_slience=True)
except ConnectionAbortedError as token_exceed_err:
print('至少一个线程任务Token溢出而失败', e)
@ -120,7 +120,7 @@ class InterviewAssistant(AliyunASR):
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
self.plugin_wd.feed()
if self.event_on_result_chg.is_set():
if self.event_on_result_chg.is_set():
# called when some words have finished
self.event_on_result_chg.clear()
chatbot[-1] = list(chatbot[-1])
@ -151,7 +151,7 @@ class InterviewAssistant(AliyunASR):
# add gpt task 创建子线程请求gpt，避免线程阻塞
history = chatbot2history(chatbot)
self.agt.add_async_gpt_task(self.buffered_sentence, len(chatbot)-1, llm_kwargs, history, system_prompt)
self.buffered_sentence = ""
chatbot.append(["[ 请讲话 ]", "[ 正在等您说完问题 ]"])
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面

16
crazy_functions/谷歌检索小助手.py
View File

@ -20,10 +20,10 @@ def get_meta_information(url, chatbot, history):
proxies = get_conf('proxies')
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36',
'Accept-Encoding': 'gzip, deflate, br',
'Accept-Encoding': 'gzip, deflate, br',
'Accept-Language': 'en-US,en;q=0.9,zh-CN;q=0.8,zh;q=0.7',
'Cache-Control':'max-age=0',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
'Connection': 'keep-alive'
}
try:
@ -95,7 +95,7 @@ def get_meta_information(url, chatbot, history):
)
try: paper = next(search.results())
except: paper = None
is_match = paper is not None and string_similar(title, paper.title) > 0.90
# 如果在Arxiv上匹配失败，检索文章的历史版本的题目
@ -146,8 +146,8 @@ def 谷歌检索小助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
import math
from bs4 import BeautifulSoup
except:
report_exception(chatbot, history,
a = f"解析项目: {txt}",
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 beautifulsoup4 arxiv```。")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
@ -163,7 +163,7 @@ def 谷歌检索小助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
if len(meta_paper_info_list[:batchsize]) > 0:
i_say = "下面是一些学术文献的数据，提取出以下内容：" + \
"1、英文题目；2、中文题目翻译；3、作者；4、arxiv公开（is_paper_in_arxiv）；4、引用数量（cite）；5、中文摘要翻译。" + \
f"以下是信息源：{str(meta_paper_info_list[:batchsize])}"
f"以下是信息源：{str(meta_paper_info_list[:batchsize])}"
inputs_show_user = f"请分析此页面中出现的所有文章：{txt}，这是第{batch+1}批"
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
@ -175,11 +175,11 @@ def 谷歌检索小助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
history.extend([ f"第{batch+1}批", gpt_say ])
meta_paper_info_list = meta_paper_info_list[batchsize:]
chatbot.append(["状态？",
chatbot.append(["状态？",
"已经全部完成，您可以试试让AI写一个Related Works，例如您可以继续输入Write a \"Related Works\" section about \"你搜索的研究领域\" for me."])
msg = '正常'
yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
path = write_history_to_file(history)
promote_file_to_downloadzone(path, chatbot=chatbot)
chatbot.append(("完成了吗？", path));
chatbot.append(("完成了吗？", path));
yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面

12
crazy_functions/高级功能函数模板.py
View File

@ -40,7 +40,7 @@ def 高阶功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
"""
history = [] # 清空历史，以免输入溢出
chatbot.append((
"您正在调用插件：历史上的今天",
"您正在调用插件：历史上的今天",
"[Local Message] 请注意，您正在调用一个[函数插件]的模板，该函数面向希望实现更多有趣功能的开发者，它可以作为创建新功能函数的模板（该函数只有20多行代码）。此外我们也提供可同步处理大量文件的多线程Demo供您参考。您若希望分享新的功能模组，请不吝PR！" + 高阶功能模板函数示意图))
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间，我们先及时地做一次界面更新
for i in range(5):
@ -48,8 +48,8 @@ def 高阶功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
currentDay = (datetime.date.today() + datetime.timedelta(days=i)).day
i_say = f'历史中哪些事件发生在{currentMonth}月{currentDay}日？列举两条并发送相关图片。发送图片时，请使用Markdown，将Unsplash API中的PUT_YOUR_QUERY_HERE替换成描述该事件的一个最重要的单词。'
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=i_say, inputs_show_user=i_say,
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
inputs=i_say, inputs_show_user=i_say,
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
sys_prompt="当你想发送一张照片时，请使用Markdown, 并且不要有反斜线, 不要用代码块。使用 Unsplash API (https://source.unsplash.com/1280x720/? < PUT_YOUR_QUERY_HERE >)。"
)
chatbot[-1] = (i_say, gpt_say)
@ -84,15 +84,15 @@ def 测试图表渲染(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
history = [] # 清空历史，以免输入溢出
chatbot.append(("这是什么功能？", "一个测试mermaid绘制图表的功能，您可以在输入框中输入一些关键词，然后使用mermaid+llm绘制图表。"))
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间，我们先及时地做一次界面更新
if txt == "": txt = "空白的输入栏" # 调皮一下
i_say_show_user = f'请绘制有关“{txt}”的逻辑关系图。'
i_say = PROMPT.format(subject=txt)
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=i_say,
inputs_show_user=i_say_show_user,
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
sys_prompt=""
)
history.append(i_say); history.append(gpt_say)

76
multi_language.py
View File

@ -1,7 +1,7 @@
"""
Translate this project to other languages (experimental, please open an issue if there is any bug)
Usage:
1. modify config.py, set your LLM_MODEL and API_KEY(s) to provide access to OPENAI (or any other LLM model provider)
@ -11,20 +11,20 @@
3. modify TransPrompt (below ↓)
TransPrompt = f"Replace each json value `#` with translated results in English, e.g., \"原始文本\":\"TranslatedText\". Keep Json format. Do not answer #."
4. Run `python multi_language.py`.
4. Run `python multi_language.py`.
Note: You need to run it multiple times to increase translation coverage because GPT makes mistakes sometimes.
(You can also run `CACHE_ONLY=True python multi_language.py` to use cached translation mapping)
5. Find the translated program in `multi-language\English\*`
P.S.
- The translation mapping will be stored in `docs/translation_xxxx.json`, you can revised mistaken translation there.
- If you would like to share your `docs/translation_xxxx.json`, (so that everyone can use the cached & revised translation mapping), please open a Pull Request
- If there is any translation error in `docs/translation_xxxx.json`, please open a Pull Request
- Welcome any Pull Request, regardless of language
"""
@ -58,7 +58,7 @@ if not os.path.exists(CACHE_FOLDER):
def lru_file_cache(maxsize=128, ttl=None, filename=None):
"""
Decorator that caches a function's return value after being called with given arguments.
Decorator that caches a function's return value after being called with given arguments.
It uses a Least Recently Used (LRU) cache strategy to limit the size of the cache.
maxsize: Maximum size of the cache. Defaults to 128.
ttl: Time-to-Live of the cache. If a value hasn't been accessed for `ttl` seconds, it will be evicted from the cache.
@ -151,7 +151,7 @@ def map_to_json(map, language):
def read_map_from_json(language):
if os.path.exists(f'docs/translate_{language.lower()}.json'):
with open(f'docs/translate_{language.lower()}.json', 'r', encoding='utf8') as f:
with open(f'docs/translate_{language.lower()}.json', 'r', encoding='utf8') as f:
res = json.load(f)
res = {k:v for k, v in res.items() if v is not None and contains_chinese(k)}
return res
@ -168,7 +168,7 @@ def advanced_split(splitted_string, spliter, include_spliter=False):
splitted[i] += spliter
splitted[i] = splitted[i].strip()
for i in reversed(range(len(splitted))):
if not contains_chinese(splitted[i]):
if not contains_chinese(splitted[i]):
splitted.pop(i)
splitted_string_tmp.extend(splitted)
else:
@ -183,12 +183,12 @@ def trans(word_to_translate, language, special=False):
if len(word_to_translate) == 0: return {}
from crazy_functions.crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
from toolbox import get_conf, ChatBotWithCookies, load_chat_cookies
cookies = load_chat_cookies()
llm_kwargs = {
'api_key': cookies['api_key'],
'llm_model': cookies['llm_model'],
'top_p':1.0,
'top_p':1.0,
'max_length': None,
'temperature':0.4,
}
@ -204,12 +204,12 @@ def trans(word_to_translate, language, special=False):
sys_prompt_array = [f"Translate following sentences to {LANG}. E.g., You should translate sentences to the following format ['translation of sentence 1', 'translation of sentence 2']. Do NOT answer with Chinese!" for _ in inputs_array]
chatbot = ChatBotWithCookies(llm_kwargs)
gpt_say_generator = request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
inputs_array,
inputs_show_user_array,
llm_kwargs,
chatbot,
history_array,
sys_prompt_array,
inputs_array,
inputs_show_user_array,
llm_kwargs,
chatbot,
history_array,
sys_prompt_array,
)
while True:
try:
@ -224,7 +224,7 @@ def trans(word_to_translate, language, special=False):
try:
res_before_trans = eval(result[i-1])
res_after_trans = eval(result[i])
if len(res_before_trans) != len(res_after_trans):
if len(res_before_trans) != len(res_after_trans):
raise RuntimeError
for a,b in zip(res_before_trans, res_after_trans):
translated_result[a] = b
@ -246,12 +246,12 @@ def trans_json(word_to_translate, language, special=False):
if len(word_to_translate) == 0: return {}
from crazy_functions.crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
from toolbox import get_conf, ChatBotWithCookies, load_chat_cookies
cookies = load_chat_cookies()
llm_kwargs = {
'api_key': cookies['api_key'],
'llm_model': cookies['llm_model'],
'top_p':1.0,
'top_p':1.0,
'max_length': None,
'temperature':0.4,
}
@ -261,18 +261,18 @@ def trans_json(word_to_translate, language, special=False):
word_to_translate_split = split_list(word_to_translate, N_EACH_REQ)
inputs_array = [{k:"#" for k in s} for s in word_to_translate_split]
inputs_array = [ json.dumps(i, ensure_ascii=False) for i in inputs_array]
inputs_show_user_array = inputs_array
history_array = [[] for _ in inputs_array]
sys_prompt_array = [TransPrompt for _ in inputs_array]
chatbot = ChatBotWithCookies(llm_kwargs)
gpt_say_generator = request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
inputs_array,
inputs_show_user_array,
llm_kwargs,
chatbot,
history_array,
sys_prompt_array,
inputs_array,
inputs_show_user_array,
llm_kwargs,
chatbot,
history_array,
sys_prompt_array,
)
while True:
try:
@ -336,7 +336,7 @@ def step_1_core_key_translate():
cached_translation = read_map_from_json(language=LANG_STD)
cached_translation_keys = list(cached_translation.keys())
for d in chinese_core_keys_norepeat:
if d not in cached_translation_keys:
if d not in cached_translation_keys:
need_translate.append(d)
if CACHE_ONLY:
@ -379,7 +379,7 @@ def step_1_core_key_translate():
# read again
with open(file_path, 'r', encoding='utf-8') as f:
content = f.read()
for k, v in chinese_core_keys_norepeat_mapping.items():
content = content.replace(k, v)
@ -390,7 +390,7 @@ def step_1_core_key_translate():
def step_2_core_key_translate():
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
# step2
# step2
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
def load_string(strings, string_input):
@ -423,7 +423,7 @@ def step_2_core_key_translate():
splitted_string = advanced_split(splitted_string, spliter=" ", include_spliter=False)
splitted_string = advanced_split(splitted_string, spliter="- ", include_spliter=False)
splitted_string = advanced_split(splitted_string, spliter="---", include_spliter=False)
# --------------------------------------
for j, s in enumerate(splitted_string): # .com
if '.com' in s: continue
@ -457,7 +457,7 @@ def step_2_core_key_translate():
comments_arr = []
for code_sp in content.splitlines():
comments = re.findall(r'#.*$', code_sp)
for comment in comments:
for comment in comments:
load_string(strings=comments_arr, string_input=comment)
string_literals.extend(comments_arr)
@ -479,7 +479,7 @@ def step_2_core_key_translate():
cached_translation = read_map_from_json(language=LANG)
cached_translation_keys = list(cached_translation.keys())
for d in chinese_literal_names_norepeat:
if d not in cached_translation_keys:
if d not in cached_translation_keys:
need_translate.append(d)
if CACHE_ONLY:
@ -504,18 +504,18 @@ def step_2_core_key_translate():
# read again
with open(file_path, 'r', encoding='utf-8') as f:
content = f.read()
for k, v in cached_translation.items():
if v is None: continue
if '"' in v:
if '"' in v:
v = v.replace('"', "`")
if '\'' in v:
if '\'' in v:
v = v.replace('\'', "`")
content = content.replace(k, v)
with open(file_path, 'w', encoding='utf-8') as f:
f.write(content)
if file.strip('.py') in cached_translation:
file_new = cached_translation[file.strip('.py')] + '.py'
file_path_new = os.path.join(root, file_new)

98
request_llms/bridge_all.py
View File

@ -8,10 +8,10 @@
具备多线程调用能力的函数：在函数插件中被调用，灵活而简洁
2. predict_no_ui_long_connection(...)
"""
import tiktoken, copy
import tiktoken, copy, re
from functools import lru_cache
from concurrent.futures import ThreadPoolExecutor
from toolbox import get_conf, trimmed_format_exc, apply_gpt_academic_string_mask
from toolbox import get_conf, trimmed_format_exc, apply_gpt_academic_string_mask, read_one_api_model_name
from .bridge_chatgpt import predict_no_ui_long_connection as chatgpt_noui
from .bridge_chatgpt import predict as chatgpt_ui
@ -61,6 +61,9 @@ API_URL_REDIRECT, AZURE_ENDPOINT, AZURE_ENGINE = get_conf("API_URL_REDIRECT", "A
openai_endpoint = "https://api.openai.com/v1/chat/completions"
api2d_endpoint = "https://openai.api2d.net/v1/chat/completions"
newbing_endpoint = "wss://sydney.bing.com/sydney/ChatHub"
gemini_endpoint = "https://generativelanguage.googleapis.com/v1beta/models"
claude_endpoint = "https://api.anthropic.com"
if not AZURE_ENDPOINT.endswith('/'): AZURE_ENDPOINT += '/'
azure_endpoint = AZURE_ENDPOINT + f'openai/deployments/{AZURE_ENGINE}/chat/completions?api-version=2023-05-15'
# 兼容旧版的配置
@ -75,7 +78,8 @@ except:
if openai_endpoint in API_URL_REDIRECT: openai_endpoint = API_URL_REDIRECT[openai_endpoint]
if api2d_endpoint in API_URL_REDIRECT: api2d_endpoint = API_URL_REDIRECT[api2d_endpoint]
if newbing_endpoint in API_URL_REDIRECT: newbing_endpoint = API_URL_REDIRECT[newbing_endpoint]
if gemini_endpoint in API_URL_REDIRECT: gemini_endpoint = API_URL_REDIRECT[gemini_endpoint]
if claude_endpoint in API_URL_REDIRECT: claude_endpoint = API_URL_REDIRECT[claude_endpoint]
# 获取tokenizer
tokenizer_gpt35 = LazyloadTiktoken("gpt-3.5-turbo")
@ -291,7 +295,7 @@ model_info = {
"gemini-pro": {
"fn_with_ui": genai_ui,
"fn_without_ui": genai_noui,
"endpoint": None,
"endpoint": gemini_endpoint,
"max_token": 1024 * 32,
"tokenizer": tokenizer_gpt35,
"token_cnt": get_token_num_gpt35,
@ -299,7 +303,7 @@ model_info = {
"gemini-pro-vision": {
"fn_with_ui": genai_ui,
"fn_without_ui": genai_noui,
"endpoint": None,
"endpoint": gemini_endpoint,
"max_token": 1024 * 32,
"tokenizer": tokenizer_gpt35,
"token_cnt": get_token_num_gpt35,
@ -349,25 +353,57 @@ for model in AVAIL_LLM_MODELS:
model_info.update({model: mi})
# -=-=-=-=-=-=- 以下部分是新加入的模型，可能附带额外依赖 -=-=-=-=-=-=-
if "claude-1-100k" in AVAIL_LLM_MODELS or "claude-2" in AVAIL_LLM_MODELS:
# claude家族
claude_models = ["claude-instant-1.2","claude-2.0","claude-2.1","claude-3-sonnet-20240229","claude-3-opus-20240229"]
if any(item in claude_models for item in AVAIL_LLM_MODELS):
from .bridge_claude import predict_no_ui_long_connection as claude_noui
from .bridge_claude import predict as claude_ui
model_info.update({
"claude-1-100k": {
"claude-instant-1.2": {
"fn_with_ui": claude_ui,
"fn_without_ui": claude_noui,
"endpoint": None,
"max_token": 8196,
"endpoint": claude_endpoint,
"max_token": 100000,
"tokenizer": tokenizer_gpt35,
"token_cnt": get_token_num_gpt35,
},
})
model_info.update({
"claude-2": {
"claude-2.0": {
"fn_with_ui": claude_ui,
"fn_without_ui": claude_noui,
"endpoint": None,
"max_token": 8196,
"endpoint": claude_endpoint,
"max_token": 100000,
"tokenizer": tokenizer_gpt35,
"token_cnt": get_token_num_gpt35,
},
})
model_info.update({
"claude-2.1": {
"fn_with_ui": claude_ui,
"fn_without_ui": claude_noui,
"endpoint": claude_endpoint,
"max_token": 200000,
"tokenizer": tokenizer_gpt35,
"token_cnt": get_token_num_gpt35,
},
})
model_info.update({
"claude-3-sonnet-20240229": {
"fn_with_ui": claude_ui,
"fn_without_ui": claude_noui,
"endpoint": claude_endpoint,
"max_token": 200000,
"tokenizer": tokenizer_gpt35,
"token_cnt": get_token_num_gpt35,
},
})
model_info.update({
"claude-3-opus-20240229": {
"fn_with_ui": claude_ui,
"fn_without_ui": claude_noui,
"endpoint": claude_endpoint,
"max_token": 200000,
"tokenizer": tokenizer_gpt35,
"token_cnt": get_token_num_gpt35,
},
@ -675,22 +711,28 @@ if "deepseekcoder" in AVAIL_LLM_MODELS: # deepseekcoder
})
except:
print(trimmed_format_exc())
# if "skylark" in AVAIL_LLM_MODELS:
# try:
# from .bridge_skylark2 import predict_no_ui_long_connection as skylark_noui
# from .bridge_skylark2 import predict as skylark_ui
# model_info.update({
# "skylark": {
# "fn_with_ui": skylark_ui,
# "fn_without_ui": skylark_noui,
# "endpoint": None,
# "max_token": 4096,
# "tokenizer": tokenizer_gpt35,
# "token_cnt": get_token_num_gpt35,
# }
# })
# except:
# print(trimmed_format_exc())
# -=-=-=-=-=-=- one-api 对齐支持 -=-=-=-=-=-=-
for model in [m for m in AVAIL_LLM_MODELS if m.startswith("one-api-")]:
# 为了更灵活地接入one-api多模型管理界面，设计了此接口，例子：AVAIL_LLM_MODELS = ["one-api-mixtral-8x7b(max_token=6666)"]
# 其中
# "one-api-" 是前缀（必要）
# "mixtral-8x7b" 是模型名（必要）
# "(max_token=6666)" 是配置（非必要）
try:
_, max_token_tmp = read_one_api_model_name(model)
except:
print(f"one-api模型 {model} 的 max_token 配置不是整数，请检查配置文件。")
continue
model_info.update({
model: {
"fn_with_ui": chatgpt_ui,
"fn_without_ui": chatgpt_noui,
"endpoint": openai_endpoint,
"max_token": max_token_tmp,
"tokenizer": tokenizer_gpt35,
"token_cnt": get_token_num_gpt35,
},
})
# <-- 用于定义和切换多个azure模型 -->

8
request_llms/bridge_chatglm.py
View File

@ -56,15 +56,15 @@ class GetGLM2Handle(LocalLLMHandle):
query, max_length, top_p, temperature, history = adaptor(kwargs)
for response, history in self._model.stream_chat(self._tokenizer,
query,
history,
for response, history in self._model.stream_chat(self._tokenizer,
query,
history,
max_length=max_length,
top_p=top_p,
temperature=temperature,
):
yield response
def try_to_import_special_deps(self, **kwargs):
# import something that will raise error if the user does not install requirement_*.txt
# 🏃‍♂️🏃‍♂️🏃‍♂️ 主进程执行

8
request_llms/bridge_chatglm3.py
View File

@ -55,15 +55,15 @@ class GetGLM3Handle(LocalLLMHandle):
query, max_length, top_p, temperature, history = adaptor(kwargs)
for response, history in self._model.stream_chat(self._tokenizer,
query,
history,
for response, history in self._model.stream_chat(self._tokenizer,
query,
history,
max_length=max_length,
top_p=top_p,
temperature=temperature,
):
yield response
def try_to_import_special_deps(self, **kwargs):
# import something that will raise error if the user does not install requirement_*.txt
# 🏃‍♂️🏃‍♂️🏃‍♂️ 主进程执行

14
request_llms/bridge_chatglmft.py
View File

@ -37,7 +37,7 @@ class GetGLMFTHandle(Process):
self.check_dependency()
self.start()
self.threadLock = threading.Lock()
def check_dependency(self):
try:
import sentencepiece
@ -101,7 +101,7 @@ class GetGLMFTHandle(Process):
break
except Exception as e:
retry += 1
if retry > 3:
if retry > 3:
self.child.send('[Local Message] Call ChatGLMFT fail 不能正常加载ChatGLMFT的参数。')
raise RuntimeError("不能正常加载ChatGLMFT的参数！")
@ -113,7 +113,7 @@ class GetGLMFTHandle(Process):
for response, history in self.chatglmft_model.stream_chat(self.chatglmft_tokenizer, **kwargs):
self.child.send(response)
# # 中途接收可能的终止指令（如果有的话）
# if self.child.poll():
# if self.child.poll():
# command = self.child.recv()
# if command == '[Terminate]': break
except:
@ -133,7 +133,7 @@ class GetGLMFTHandle(Process):
else:
break
self.threadLock.release()
global glmft_handle
glmft_handle = None
#################################################################################
@ -146,7 +146,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
if glmft_handle is None:
glmft_handle = GetGLMFTHandle()
if len(observe_window) >= 1: observe_window[0] = load_message + "\n\n" + glmft_handle.info
if not glmft_handle.success:
if not glmft_handle.success:
error = glmft_handle.info
glmft_handle = None
raise RuntimeError(error)
@ -161,7 +161,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
response = ""
for response in glmft_handle.stream_chat(query=inputs, history=history_feedin, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']):
if len(observe_window) >= 1: 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。")
return response
@ -180,7 +180,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
glmft_handle = GetGLMFTHandle()
chatbot[-1] = (inputs, load_message + "\n\n" + glmft_handle.info)
yield from update_ui(chatbot=chatbot, history=[])
if not glmft_handle.success:
if not glmft_handle.success:
glmft_handle = None
return

2
request_llms/bridge_chatglmonnx.py
View File

@ -59,7 +59,7 @@ class GetONNXGLMHandle(LocalLLMHandle):
temperature=temperature,
):
yield answer
def try_to_import_special_deps(self, **kwargs):
# import something that will raise error if the user does not install requirement_*.txt
# 🏃‍♂️🏃‍♂️🏃‍♂️ 子进程执行

5
request_llms/bridge_chatgpt.py
View File

@ -21,7 +21,7 @@ import random
# config_private.py放自己的秘密如API和代理网址
# 读取时首先看是否存在私密的config_private配置文件（不受git管控），如果有，则覆盖原config文件
from toolbox import get_conf, update_ui, is_any_api_key, select_api_key, what_keys, clip_history, trimmed_format_exc, is_the_upload_folder
from toolbox import get_conf, update_ui, is_any_api_key, select_api_key, what_keys, clip_history, trimmed_format_exc, is_the_upload_folder, read_one_api_model_name
proxies, TIMEOUT_SECONDS, MAX_RETRY, API_ORG, AZURE_CFG_ARRAY = \
get_conf('proxies', 'TIMEOUT_SECONDS', 'MAX_RETRY', 'API_ORG', 'AZURE_CFG_ARRAY')
@ -358,6 +358,9 @@ def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
model = llm_kwargs['llm_model']
if llm_kwargs['llm_model'].startswith('api2d-'):
model = llm_kwargs['llm_model'][len('api2d-'):]
if llm_kwargs['llm_model'].startswith('one-api-'):
model = llm_kwargs['llm_model'][len('one-api-'):]
model, _ = read_one_api_model_name(model)
if model == "gpt-3.5-random": # 随机选择, 绕过openai访问频率限制
model = random.choice([

24
request_llms/bridge_chatgpt_vision.py
View File

@ -27,7 +27,7 @@ timeout_bot_msg = '[Local Message] Request timeout. Network error. Please check
def report_invalid_key(key):
if get_conf("BLOCK_INVALID_APIKEY"):
if get_conf("BLOCK_INVALID_APIKEY"):
# 实验性功能，自动检测并屏蔽失效的KEY，请勿使用
from request_llms.key_manager import ApiKeyManager
api_key = ApiKeyManager().add_key_to_blacklist(key)
@ -51,13 +51,13 @@ def decode_chunk(chunk):
choice_valid = False
has_content = False
has_role = False
try:
try:
chunkjson = json.loads(chunk_decoded[6:])
has_choices = 'choices' in chunkjson
if has_choices: choice_valid = (len(chunkjson['choices']) > 0)
if has_choices and choice_valid: has_content = "content" in chunkjson['choices'][0]["delta"]
if has_choices and choice_valid: has_role = "role" in chunkjson['choices'][0]["delta"]
except:
except:
pass
return chunk_decoded, chunkjson, has_choices, choice_valid, has_content, has_role
@ -103,7 +103,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
raw_input = inputs
logging.info(f'[raw_input] {raw_input}')
def make_media_input(inputs, image_paths):
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
@ -122,7 +122,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
chatbot[-1] = (inputs, f"您提供的api-key不满足要求，不包含任何可用于{llm_kwargs['llm_model']}的api-key。您可能选择了错误的模型或请求源。")
yield from update_ui(chatbot=chatbot, history=history, msg="api-key不满足要求") # 刷新界面
return
# 检查endpoint是否合法
try:
from .bridge_all import model_info
@ -150,7 +150,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
if retry > MAX_RETRY: raise TimeoutError
gpt_replying_buffer = ""
is_head_of_the_stream = True
if stream:
stream_response = response.iter_lines()
@ -162,21 +162,21 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
chunk_decoded = chunk.decode()
error_msg = chunk_decoded
# 首先排除一个one-api没有done数据包的第三方Bug情形
if len(gpt_replying_buffer.strip()) > 0 and len(error_msg) == 0:
if len(gpt_replying_buffer.strip()) > 0 and len(error_msg) == 0:
yield from update_ui(chatbot=chatbot, history=history, msg="检测到有缺陷的非OpenAI官方接口，建议选择更稳定的接口。")
break
# 其他情况，直接返回报错
chatbot, history = handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg, api_key)
yield from update_ui(chatbot=chatbot, history=history, msg="非OpenAI官方接口返回了错误:" + chunk.decode()) # 刷新界面
return
# 提前读取一些信息 （用于判断异常）
chunk_decoded, chunkjson, has_choices, choice_valid, has_content, has_role = decode_chunk(chunk)
if is_head_of_the_stream and (r'"object":"error"' not in chunk_decoded) and (r"content" not in chunk_decoded):
# 数据流的第一帧不携带content
is_head_of_the_stream = False; continue
if chunk:
try:
if has_choices and not choice_valid:
@ -220,7 +220,7 @@ def handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg,
openai_website = ' 请登录OpenAI查看详情 https://platform.openai.com/signup'
if "reduce the length" in error_msg:
if len(history) >= 2: history[-1] = ""; history[-2] = "" # 清除当前溢出的输入：history[-2] 是本次输入, history[-1] 是本次输出
history = clip_history(inputs=inputs, history=history, tokenizer=model_info[llm_kwargs['llm_model']]['tokenizer'],
history = clip_history(inputs=inputs, history=history, tokenizer=model_info[llm_kwargs['llm_model']]['tokenizer'],
max_token_limit=(model_info[llm_kwargs['llm_model']]['max_token'])) # history至少释放二分之一
chatbot[-1] = (chatbot[-1][0], "[Local Message] Reduce the length. 本次输入过长, 或历史数据过长. 历史缓存数据已部分释放, 您可以请再次尝试. (若再次失败则更可能是因为输入过长.)")
elif "does not exist" in error_msg:
@ -260,7 +260,7 @@ def generate_payload(inputs, llm_kwargs, history, system_prompt, image_paths):
"Authorization": f"Bearer {api_key}"
}
if API_ORG.startswith('org-'): headers.update({"OpenAI-Organization": API_ORG})
if llm_kwargs['llm_model'].startswith('azure-'):
if llm_kwargs['llm_model'].startswith('azure-'):
headers.update({"api-key": api_key})
if llm_kwargs['llm_model'] in AZURE_CFG_ARRAY.keys():
azure_api_key_unshared = AZURE_CFG_ARRAY[llm_kwargs['llm_model']]["AZURE_API_KEY"]
@ -294,7 +294,7 @@ def generate_payload(inputs, llm_kwargs, history, system_prompt, image_paths):
payload = {
"model": model,
"messages": messages,
"messages": messages,
"temperature": llm_kwargs['temperature'], # 1.0,
"top_p": llm_kwargs['top_p'], # 1.0,
"n": 1,

22
request_llms/bridge_chatgpt_website.py
View File

@ -73,12 +73,12 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
result = ''
while True:
try: chunk = next(stream_response).decode()
except StopIteration:
except StopIteration:
break
except requests.exceptions.ConnectionError:
chunk = next(stream_response).decode() # 失败了，重试一次？再失败就没办法了。
if len(chunk)==0: continue
if not chunk.startswith('data:'):
if not chunk.startswith('data:'):
error_msg = get_full_error(chunk.encode('utf8'), stream_response).decode()
if "reduce the length" in error_msg:
raise ConnectionAbortedError("OpenAI拒绝了请求:" + error_msg)
@ -89,14 +89,14 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
delta = json_data["delta"]
if len(delta) == 0: break
if "role" in delta: continue
if "content" in delta:
if "content" in delta:
result += delta["content"]
if not console_slience: print(delta["content"], end='')
if observe_window is not None:
if observe_window is not None:
# 观测窗，把已经获取的数据显示出去
if len(observe_window) >= 1: observe_window[0] += delta["content"]
# 看门狗，如果超过期限没有喂狗，则终止
if len(observe_window) >= 2:
if len(observe_window) >= 2:
if (time.time()-observe_window[1]) > watch_dog_patience:
raise RuntimeError("用户取消了程序。")
else: raise RuntimeError("意外Json结构："+delta)
@ -132,7 +132,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
chatbot[-1] = (inputs, f"您提供的api-key不满足要求，不包含任何可用于{llm_kwargs['llm_model']}的api-key。您可能选择了错误的模型或请求源。")
yield from update_ui(chatbot=chatbot, history=history, msg="api-key不满足要求") # 刷新界面
return
history.append(inputs); history.append("")
retry = 0
@ -151,7 +151,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
if retry > MAX_RETRY: raise TimeoutError
gpt_replying_buffer = ""
is_head_of_the_stream = True
if stream:
stream_response = response.iter_lines()
@ -165,12 +165,12 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
chatbot, history = handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg)
yield from update_ui(chatbot=chatbot, history=history, msg="非Openai官方接口返回了错误:" + chunk.decode()) # 刷新界面
return
# print(chunk.decode()[6:])
if is_head_of_the_stream and (r'"object":"error"' not in chunk.decode()):
# 数据流的第一帧不携带content
is_head_of_the_stream = False; continue
if chunk:
try:
chunk_decoded = chunk.decode()
@ -203,7 +203,7 @@ def handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg)
openai_website = ' 请登录OpenAI查看详情 https://platform.openai.com/signup'
if "reduce the length" in error_msg:
if len(history) >= 2: history[-1] = ""; history[-2] = "" # 清除当前溢出的输入：history[-2] 是本次输入, history[-1] 是本次输出
history = clip_history(inputs=inputs, history=history, tokenizer=model_info[llm_kwargs['llm_model']]['tokenizer'],
history = clip_history(inputs=inputs, history=history, tokenizer=model_info[llm_kwargs['llm_model']]['tokenizer'],
max_token_limit=(model_info[llm_kwargs['llm_model']]['max_token'])) # history至少释放二分之一
chatbot[-1] = (chatbot[-1][0], "[Local Message] Reduce the length. 本次输入过长, 或历史数据过长. 历史缓存数据已部分释放, 您可以请再次尝试. (若再次失败则更可能是因为输入过长.)")
# history = [] # 清除历史
@ -264,7 +264,7 @@ def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
payload = {
"model": llm_kwargs['llm_model'].strip('api2d-'),
"messages": messages,
"messages": messages,
"temperature": llm_kwargs['temperature'], # 1.0,
"top_p": llm_kwargs['top_p'], # 1.0,
"n": 1,

153
request_llms/bridge_claude.py
View File

@ -11,13 +11,12 @@
"""
import os
import json
import time
import gradio as gr
import logging
import traceback
import requests
import importlib
from toolbox import get_conf, update_ui, trimmed_format_exc, encode_image, every_image_file_in_path
picture_system_prompt = "\n当回复图像时,必须说明正在回复哪张图像。所有图像仅在最后一个问题中提供,即使它们在历史记录中被提及。请使用'这是第X张图像:'的格式来指明您正在描述的是哪张图像。"
Claude_3_Models = ["claude-3-sonnet-20240229", "claude-3-opus-20240229"]
# config_private.py放自己的秘密如API和代理网址
# 读取时首先看是否存在私密的config_private配置文件（不受git管控），如果有，则覆盖原config文件
@ -56,7 +55,8 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
"""
from anthropic import Anthropic
watch_dog_patience = 5 # 看门狗的耐心, 设置5秒即可
prompt = generate_payload(inputs, llm_kwargs, history, system_prompt=sys_prompt, stream=True)
if inputs == "": inputs = "空空如也的输入栏"
message = generate_payload(inputs, llm_kwargs, history, stream=True, image_paths=None)
retry = 0
if len(ANTHROPIC_API_KEY) == 0:
raise RuntimeError("没有设置ANTHROPIC_API_KEY选项")
@ -65,15 +65,16 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
try:
# make a POST request to the API endpoint, stream=False
from .bridge_all import model_info
anthropic = Anthropic(api_key=ANTHROPIC_API_KEY)
anthropic = Anthropic(api_key=ANTHROPIC_API_KEY, base_url=model_info[llm_kwargs['llm_model']]['endpoint'])
# endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
# with ProxyNetworkActivate()
stream = anthropic.completions.create(
prompt=prompt,
max_tokens_to_sample=4096, # The maximum number of tokens to generate before stopping.
stream = anthropic.messages.create(
messages=message,
max_tokens=4096, # The maximum number of tokens to generate before stopping.
model=llm_kwargs['llm_model'],
stream=True,
temperature = llm_kwargs['temperature']
temperature = llm_kwargs['temperature'],
system=sys_prompt
)
break
except Exception as e:
@ -82,15 +83,19 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
if retry > MAX_RETRY: raise TimeoutError
if MAX_RETRY!=0: print(f'请求超时，正在重试 ({retry}/{MAX_RETRY}) ……')
result = ''
try:
try:
for completion in stream:
result += completion.completion
if not console_slience: print(completion.completion, end='')
if observe_window is not None:
if completion.type == "message_start" or completion.type == "content_block_start":
continue
elif completion.type == "message_stop" or completion.type == "content_block_stop" or completion.type == "message_delta":
break
result += completion.delta.text
if not console_slience: print(completion.delta.text, end='')
if observe_window is not None:
# 观测窗，把已经获取的数据显示出去
if len(observe_window) >= 1: observe_window[0] += completion.completion
if len(observe_window) >= 1: observe_window[0] += completion.delta.text
# 看门狗，如果超过期限没有喂狗，则终止
if len(observe_window) >= 2:
if len(observe_window) >= 2:
if (time.time()-observe_window[1]) > watch_dog_patience:
raise RuntimeError("用户取消了程序。")
except Exception as e:
@ -98,6 +103,10 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
return result
def make_media_input(history,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(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream = True, additional_fn=None):
"""
@ -109,23 +118,34 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
chatbot 为WebUI中显示的对话列表，修改它，然后yeild出去，可以直接修改对话界面内容
additional_fn代表点击的哪个按钮，按钮见functional.py
"""
if inputs == "": inputs = "空空如也的输入栏"
from anthropic import Anthropic
if len(ANTHROPIC_API_KEY) == 0:
chatbot.append((inputs, "没有设置ANTHROPIC_API_KEY"))
yield from update_ui(chatbot=chatbot, history=history, msg="等待响应") # 刷新界面
return
if additional_fn is not None:
from core_functional import handle_core_functionality
inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
raw_input = inputs
logging.info(f'[raw_input] {raw_input}')
chatbot.append((inputs, ""))
yield from update_ui(chatbot=chatbot, history=history, msg="等待响应") # 刷新界面
have_recent_file, image_paths = every_image_file_in_path(chatbot)
if len(image_paths) > 20:
chatbot.append((inputs, "图片数量超过api上限(20张)"))
yield from update_ui(chatbot=chatbot, history=history, msg="等待响应")
return
if any([llm_kwargs['llm_model'] == model for model in Claude_3_Models]) and have_recent_file:
if inputs == "" or inputs == "空空如也的输入栏": inputs = "请描述给出的图片"
system_prompt += picture_system_prompt # 由于没有单独的参数保存包含图片的历史，所以只能通过提示词对第几张图片进行定位
chatbot.append((make_media_input(history,inputs, image_paths), ""))
yield from update_ui(chatbot=chatbot, history=history, msg="等待响应") # 刷新界面
else:
chatbot.append((inputs, ""))
yield from update_ui(chatbot=chatbot, history=history, msg="等待响应") # 刷新界面
try:
prompt = generate_payload(inputs, llm_kwargs, history, system_prompt, stream)
message = generate_payload(inputs, llm_kwargs, history, stream, image_paths)
except RuntimeError as e:
chatbot[-1] = (inputs, f"您提供的api-key不满足要求，不包含任何可用于{llm_kwargs['llm_model']}的api-key。您可能选择了错误的模型或请求源。")
yield from update_ui(chatbot=chatbot, history=history, msg="api-key不满足要求") # 刷新界面
@ -138,17 +158,17 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
try:
# make a POST request to the API endpoint, stream=True
from .bridge_all import model_info
anthropic = Anthropic(api_key=ANTHROPIC_API_KEY)
anthropic = Anthropic(api_key=ANTHROPIC_API_KEY, base_url=model_info[llm_kwargs['llm_model']]['endpoint'])
# endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
# with ProxyNetworkActivate()
stream = anthropic.completions.create(
prompt=prompt,
max_tokens_to_sample=4096, # The maximum number of tokens to generate before stopping.
stream = anthropic.messages.create(
messages=message,
max_tokens=4096, # The maximum number of tokens to generate before stopping.
model=llm_kwargs['llm_model'],
stream=True,
temperature = llm_kwargs['temperature']
temperature = llm_kwargs['temperature'],
system=system_prompt
)
break
except:
retry += 1
@ -158,10 +178,14 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
if retry > MAX_RETRY: raise TimeoutError
gpt_replying_buffer = ""
for completion in stream:
if completion.type == "message_start" or completion.type == "content_block_start":
continue
elif completion.type == "message_stop" or completion.type == "content_block_stop" or completion.type == "message_delta":
break
try:
gpt_replying_buffer = gpt_replying_buffer + completion.completion
gpt_replying_buffer = gpt_replying_buffer + completion.delta.text
history[-1] = gpt_replying_buffer
chatbot[-1] = (history[-2], history[-1])
yield from update_ui(chatbot=chatbot, history=history, msg='正常') # 刷新界面
@ -172,57 +196,52 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
chatbot[-1] = (chatbot[-1][0], f"[Local Message] 异常 \n\n{tb_str}")
yield from update_ui(chatbot=chatbot, history=history, msg="Json异常" + tb_str) # 刷新界面
return
# https://github.com/jtsang4/claude-to-chatgpt/blob/main/claude_to_chatgpt/adapter.py
def convert_messages_to_prompt(messages):
prompt = ""
role_map = {
"system": "Human",
"user": "Human",
"assistant": "Assistant",
}
for message in messages:
role = message["role"]
content = message["content"]
transformed_role = role_map[role]
prompt += f"\n\n{transformed_role.capitalize()}: {content}"
prompt += "\n\nAssistant: "
return prompt
def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
def generate_payload(inputs, llm_kwargs, history, stream, image_paths):
"""
整合所有信息，选择LLM模型，生成http请求，为发送请求做准备
"""
from anthropic import Anthropic, HUMAN_PROMPT, AI_PROMPT
conversation_cnt = len(history) // 2
messages = [{"role": "system", "content": system_prompt}]
messages = []
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_i_have_asked["content"] = [{"type": "text", "text": 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
what_gpt_answer["content"] = [{"type": "text", "text": history[index+1]}]
if what_i_have_asked["content"][0]["text"] != "":
if what_i_have_asked["content"][0]["text"] == "": continue
if what_i_have_asked["content"][0]["text"] == timeout_bot_msg: continue
messages.append(what_i_have_asked)
messages.append(what_gpt_answer)
else:
messages[-1]['content'] = what_gpt_answer['content']
messages[-1]['content'][0]['text'] = what_gpt_answer['content'][0]['text']
what_i_ask_now = {}
what_i_ask_now["role"] = "user"
what_i_ask_now["content"] = inputs
if any([llm_kwargs['llm_model'] == model for model in Claude_3_Models]) and image_paths:
base64_images = []
for image_path in image_paths:
base64_images.append(encode_image(image_path))
what_i_ask_now = {}
what_i_ask_now["role"] = "user"
what_i_ask_now["content"] = []
for base64_image in base64_images:
what_i_ask_now["content"].append({
"type": "image",
"source": {
"type": "base64",
"media_type": "image/jpeg",
"data": base64_image,
}
})
what_i_ask_now["content"].append({"type": "text", "text": inputs})
else:
what_i_ask_now = {}
what_i_ask_now["role"] = "user"
what_i_ask_now["content"] = [{"type": "text", "text": inputs}]
messages.append(what_i_ask_now)
prompt = convert_messages_to_prompt(messages)
return prompt
return messages

6
request_llms/bridge_deepseekcoder.py
View File

@ -88,7 +88,7 @@ class GetCoderLMHandle(LocalLLMHandle):
temperature = kwargs['temperature']
history = kwargs['history']
return query, max_length, top_p, temperature, history
query, max_length, top_p, temperature, history = adaptor(kwargs)
history.append({ 'role': 'user', 'content': query})
messages = history
@ -97,14 +97,14 @@ class GetCoderLMHandle(LocalLLMHandle):
inputs = inputs[:, -max_length:]
inputs = inputs.to(self._model.device)
generation_kwargs = dict(
inputs=inputs,
inputs=inputs,
max_new_tokens=max_length,
do_sample=False,
top_p=top_p,
streamer = self._streamer,
top_k=50,
temperature=temperature,
num_return_sequences=1,
num_return_sequences=1,
eos_token_id=32021,
)
thread = Thread(target=self._model.generate, kwargs=generation_kwargs, daemon=True)

6
request_llms/bridge_google_gemini.py
View File

@ -20,7 +20,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
if get_conf("GEMINI_API_KEY") == "":
raise ValueError(f"请配置 GEMINI_API_KEY。")
genai = GoogleChatInit()
genai = GoogleChatInit(llm_kwargs)
watch_dog_patience = 5 # 看门狗的耐心, 设置5秒即可
gpt_replying_buffer = ''
stream_response = genai.generate_chat(inputs, llm_kwargs, history, sys_prompt)
@ -61,7 +61,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
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:
inputs = inputs + f'<br/><br/><div align="center"><img src="file={os.path.abspath(image_path)}"></div>'
return inputs
@ -70,7 +70,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
chatbot.append((inputs, ""))
yield from update_ui(chatbot=chatbot, history=history)
genai = GoogleChatInit()
genai = GoogleChatInit(llm_kwargs)
retry = 0
while True:
try:

6
request_llms/bridge_internlm.py
View File

@ -82,7 +82,7 @@ class GetInternlmHandle(LocalLLMHandle):
history = kwargs['history']
real_prompt = combine_history(prompt, history)
return model, tokenizer, real_prompt, max_length, top_p, temperature
model, tokenizer, prompt, max_length, top_p, temperature = adaptor()
prefix_allowed_tokens_fn = None
logits_processor = None
@ -183,7 +183,7 @@ class GetInternlmHandle(LocalLLMHandle):
outputs, model_kwargs, is_encoder_decoder=False
)
unfinished_sequences = unfinished_sequences.mul((min(next_tokens != i for i in eos_token_id)).long())
output_token_ids = input_ids[0].cpu().tolist()
output_token_ids = output_token_ids[input_length:]
for each_eos_token_id in eos_token_id:
@ -196,7 +196,7 @@ class GetInternlmHandle(LocalLLMHandle):
if unfinished_sequences.max() == 0 or stopping_criteria(input_ids, scores):
return
# ------------------------------------------------------------------------------------------------------------------------
# 🔌💻 GPT-Academic Interface
# ------------------------------------------------------------------------------------------------------------------------

10
request_llms/bridge_jittorllms_llama.py
View File

@ -20,7 +20,7 @@ class GetGLMHandle(Process):
self.check_dependency()
self.start()
self.threadLock = threading.Lock()
def check_dependency(self):
try:
import pandas
@ -102,7 +102,7 @@ class GetGLMHandle(Process):
else:
break
self.threadLock.release()
global llama_glm_handle
llama_glm_handle = None
#################################################################################
@ -115,7 +115,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
if llama_glm_handle is None:
llama_glm_handle = GetGLMHandle()
if len(observe_window) >= 1: observe_window[0] = load_message + "\n\n" + llama_glm_handle.info
if not llama_glm_handle.success:
if not llama_glm_handle.success:
error = llama_glm_handle.info
llama_glm_handle = None
raise RuntimeError(error)
@ -130,7 +130,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
for response in llama_glm_handle.stream_chat(query=inputs, history=history_feedin, system_prompt=sys_prompt, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']):
print(response)
if len(observe_window) >= 1: 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。")
return response
@ -149,7 +149,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
llama_glm_handle = GetGLMHandle()
chatbot[-1] = (inputs, load_message + "\n\n" + llama_glm_handle.info)
yield from update_ui(chatbot=chatbot, history=[])
if not llama_glm_handle.success:
if not llama_glm_handle.success:
llama_glm_handle = None
return

10
request_llms/bridge_jittorllms_pangualpha.py
View File

@ -20,7 +20,7 @@ class GetGLMHandle(Process):
self.check_dependency()
self.start()
self.threadLock = threading.Lock()
def check_dependency(self):
try:
import pandas
@ -102,7 +102,7 @@ class GetGLMHandle(Process):
else:
break
self.threadLock.release()
global pangu_glm_handle
pangu_glm_handle = None
#################################################################################
@ -115,7 +115,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
if pangu_glm_handle is None:
pangu_glm_handle = GetGLMHandle()
if len(observe_window) >= 1: observe_window[0] = load_message + "\n\n" + pangu_glm_handle.info
if not pangu_glm_handle.success:
if not pangu_glm_handle.success:
error = pangu_glm_handle.info
pangu_glm_handle = None
raise RuntimeError(error)
@ -130,7 +130,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
for response in pangu_glm_handle.stream_chat(query=inputs, history=history_feedin, system_prompt=sys_prompt, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']):
print(response)
if len(observe_window) >= 1: 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。")
return response
@ -149,7 +149,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
pangu_glm_handle = GetGLMHandle()
chatbot[-1] = (inputs, load_message + "\n\n" + pangu_glm_handle.info)
yield from update_ui(chatbot=chatbot, history=[])
if not pangu_glm_handle.success:
if not pangu_glm_handle.success:
pangu_glm_handle = None
return

10
request_llms/bridge_jittorllms_rwkv.py
View File

@ -20,7 +20,7 @@ class GetGLMHandle(Process):
self.check_dependency()
self.start()
self.threadLock = threading.Lock()
def check_dependency(self):
try:
import pandas
@ -102,7 +102,7 @@ class GetGLMHandle(Process):
else:
break
self.threadLock.release()
global rwkv_glm_handle
rwkv_glm_handle = None
#################################################################################
@ -115,7 +115,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
if rwkv_glm_handle is None:
rwkv_glm_handle = GetGLMHandle()
if len(observe_window) >= 1: observe_window[0] = load_message + "\n\n" + rwkv_glm_handle.info
if not rwkv_glm_handle.success:
if not rwkv_glm_handle.success:
error = rwkv_glm_handle.info
rwkv_glm_handle = None
raise RuntimeError(error)
@ -130,7 +130,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
for response in rwkv_glm_handle.stream_chat(query=inputs, history=history_feedin, system_prompt=sys_prompt, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']):
print(response)
if len(observe_window) >= 1: 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。")
return response
@ -149,7 +149,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
rwkv_glm_handle = GetGLMHandle()
chatbot[-1] = (inputs, load_message + "\n\n" + rwkv_glm_handle.info)
yield from update_ui(chatbot=chatbot, history=[])
if not rwkv_glm_handle.success:
if not rwkv_glm_handle.success:
rwkv_glm_handle = None
return

8
request_llms/bridge_llama2.py
View File

@ -48,7 +48,7 @@ class GetLlamaHandle(LocalLLMHandle):
history = kwargs['history']
console_slience = kwargs.get('console_slience', True)
return query, max_length, top_p, temperature, history, console_slience
def convert_messages_to_prompt(query, history):
prompt = ""
for a, b in history:
@ -56,7 +56,7 @@ class GetLlamaHandle(LocalLLMHandle):
prompt += "\n{b}" + b
prompt += f"\n[INST]{query}[/INST]"
return prompt
query, max_length, top_p, temperature, history, console_slience = adaptor(kwargs)
prompt = convert_messages_to_prompt(query, history)
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=--=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=--=-=-
@ -70,13 +70,13 @@ class GetLlamaHandle(LocalLLMHandle):
thread = Thread(target=self._model.generate, kwargs=generation_kwargs)
thread.start()
generated_text = ""
for new_text in streamer:
for new_text in streamer:
generated_text += new_text
if not console_slience: print(new_text, end='')
yield generated_text.lstrip(prompt_tk_back).rstrip("</s>")
if not console_slience: print()
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=--=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=--=-=-
def try_to_import_special_deps(self, **kwargs):
# import something that will raise error if the user does not install requirement_*.txt
# 🏃‍♂️🏃‍♂️🏃‍♂️ 主进程执行

32
request_llms/bridge_moss.py
View File

@ -18,7 +18,7 @@ class GetGLMHandle(Process):
if self.check_dependency():
self.start()
self.threadLock = threading.Lock()
def check_dependency(self): # 主进程执行
try:
import datasets, os
@ -54,9 +54,9 @@ class GetGLMHandle(Process):
from models.tokenization_moss import MossTokenizer
parser = argparse.ArgumentParser()
parser.add_argument("--model_name", default="fnlp/moss-moon-003-sft-int4",
choices=["fnlp/moss-moon-003-sft",
"fnlp/moss-moon-003-sft-int8",
parser.add_argument("--model_name", default="fnlp/moss-moon-003-sft-int4",
choices=["fnlp/moss-moon-003-sft",
"fnlp/moss-moon-003-sft-int8",
"fnlp/moss-moon-003-sft-int4"], type=str)
parser.add_argument("--gpu", default="0", type=str)
args = parser.parse_args()
@ -76,7 +76,7 @@ class GetGLMHandle(Process):
config = MossConfig.from_pretrained(model_path)
self.tokenizer = MossTokenizer.from_pretrained(model_path)
if num_gpus > 1:
if num_gpus > 1:
print("Waiting for all devices to be ready, it may take a few minutes...")
with init_empty_weights():
raw_model = MossForCausalLM._from_config(config, torch_dtype=torch.float16)
@ -135,15 +135,15 @@ class GetGLMHandle(Process):
inputs = self.tokenizer(self.prompt, return_tensors="pt")
with torch.no_grad():
outputs = self.model.generate(
inputs.input_ids.cuda(),
attention_mask=inputs.attention_mask.cuda(),
max_length=2048,
do_sample=True,
top_k=40,
top_p=0.8,
inputs.input_ids.cuda(),
attention_mask=inputs.attention_mask.cuda(),
max_length=2048,
do_sample=True,
top_k=40,
top_p=0.8,
temperature=0.7,
repetition_penalty=1.02,
num_return_sequences=1,
num_return_sequences=1,
eos_token_id=106068,
pad_token_id=self.tokenizer.pad_token_id)
response = self.tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
@ -167,7 +167,7 @@ class GetGLMHandle(Process):
else:
break
self.threadLock.release()
global moss_handle
moss_handle = None
#################################################################################
@ -180,7 +180,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
if moss_handle is None:
moss_handle = GetGLMHandle()
if len(observe_window) >= 1: observe_window[0] = load_message + "\n\n" + moss_handle.info
if not moss_handle.success:
if not moss_handle.success:
error = moss_handle.info
moss_handle = None
raise RuntimeError(error)
@ -194,7 +194,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
response = ""
for response in moss_handle.stream_chat(query=inputs, history=history_feedin, sys_prompt=sys_prompt, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']):
if len(observe_window) >= 1: 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。")
return response
@ -213,7 +213,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
moss_handle = GetGLMHandle()
chatbot[-1] = (inputs, load_message + "\n\n" + moss_handle.info)
yield from update_ui(chatbot=chatbot, history=[])
if not moss_handle.success:
if not moss_handle.success:
moss_handle = None
return
else:

2
request_llms/bridge_qwen_local.py
View File

@ -45,7 +45,7 @@ class GetQwenLMHandle(LocalLLMHandle):
for response in self._model.chat_stream(self._tokenizer, query, history=history):
yield response
def try_to_import_special_deps(self, **kwargs):
# import something that will raise error if the user does not install requirement_*.txt
# 🏃‍♂️🏃‍♂️🏃‍♂️ 主进程执行

14
request_llms/bridge_tgui.py
View File

@ -76,7 +76,7 @@ async def run(context, max_token, temperature, top_p, addr, port):
pass
elif content["msg"] in ["process_generating", "process_completed"]:
yield content["output"]["data"][0]
# You can search for your desired end indicator and
# You can search for your desired end indicator and
# stop generation by closing the websocket here
if (content["msg"] == "process_completed"):
break
@ -117,12 +117,12 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
async def get_result(mutable):
# "tgui:galactica-1.3b@localhost:7860"
async for response in run(context=prompt, max_token=llm_kwargs['max_length'],
temperature=llm_kwargs['temperature'],
async for response in run(context=prompt, max_token=llm_kwargs['max_length'],
temperature=llm_kwargs['temperature'],
top_p=llm_kwargs['top_p'], addr=addr, port=port):
print(response[len(mutable[0]):])
mutable[0] = response
if (time.time() - mutable[1]) > 3:
if (time.time() - mutable[1]) > 3:
print('exit when no listener')
break
asyncio.run(get_result(mutable))
@ -154,12 +154,12 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history, sys_prompt, obser
def run_coorotine(observe_window):
async def get_result(observe_window):
async for response in run(context=prompt, max_token=llm_kwargs['max_length'],
temperature=llm_kwargs['temperature'],
async for response in run(context=prompt, max_token=llm_kwargs['max_length'],
temperature=llm_kwargs['temperature'],
top_p=llm_kwargs['top_p'], addr=addr, port=port):
print(response[len(observe_window[0]):])
observe_window[0] = response
if (time.time() - observe_window[1]) > 5:
if (time.time() - observe_window[1]) > 5:
print('exit when no listener')
break
asyncio.run(get_result(observe_window))

2
request_llms/chatglmoonx.py
View File

@ -119,7 +119,7 @@ class ChatGLMModel():
past_key_values = { k: v for k, v in zip(past_names, past_key_values) }
next_token = self.sample_next_token(logits[0, -1], top_k=top_k, top_p=top_p, temperature=temperature)
output_tokens += [next_token]
if next_token == self.eop_token_id or len(output_tokens) > max_generated_tokens:

6
request_llms/com_google.py
View File

@ -114,8 +114,10 @@ def html_local_img(__file, layout="left", max_width=None, max_height=None, md=Tr
class GoogleChatInit:
def __init__(self):
self.url_gemini = "https://generativelanguage.googleapis.com/v1beta/models/%m:streamGenerateContent?key=%k"
def __init__(self, llm_kwargs):
from .bridge_all import model_info
endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
self.url_gemini = endpoint + "/%m:streamGenerateContent?key=%k"
def generate_chat(self, inputs, llm_kwargs, history, system_prompt):
headers, payload = self.generate_message_payload(

2
request_llms/com_zhipuglm.py
View File

@ -8,7 +8,7 @@ from toolbox import get_conf, encode_image, get_pictures_list
import logging, os
def input_encode_handler(inputs, llm_kwargs):
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 = []

6
request_llms/key_manager.py
View File

@ -2,12 +2,12 @@ import random
def Singleton(cls):
_instance = {}
def _singleton(*args, **kargs):
if cls not in _instance:
_instance[cls] = cls(*args, **kargs)
return _instance[cls]
return _singleton
@ -16,7 +16,7 @@ class OpenAI_ApiKeyManager():
def __init__(self, mode='blacklist') -> None:
# self.key_avail_list = []
self.key_black_list = []
def add_key_to_blacklist(self, key):
self.key_black_list.append(key)

6
request_llms/local_llm_class.py
View File

@ -90,7 +90,7 @@ class LocalLLMHandle(Process):
return self.state
def set_state(self, new_state):
# ⭐run in main process or 🏃‍♂️🏃‍♂️🏃‍♂️ run in child process
# ⭐run in main process or 🏃‍♂️🏃‍♂️🏃‍♂️ run in child process
if self.is_main_process:
self.state = new_state
else:
@ -178,8 +178,8 @@ class LocalLLMHandle(Process):
r = self.parent.recv()
continue
break
return
return
def stream_chat(self, **kwargs):
# ⭐run in main process
if self.get_state() == "`准备就绪`":

2
requirements.txt
View File

@ -8,6 +8,7 @@ pydantic==2.5.2
protobuf==3.18
transformers>=4.27.1
scipdf_parser>=0.52
anthropic>=0.18.1
python-markdown-math
pymdown-extensions
websocket-client
@ -16,7 +17,6 @@ prompt_toolkit
latex2mathml
python-docx
mdtex2html
anthropic
pyautogen
colorama
Markdown

2
shared_utils/key_pattern_manager.py
View File

@ -62,7 +62,7 @@ def select_api_key(keys, llm_model):
avail_key_list = []
key_list = keys.split(',')
if llm_model.startswith('gpt-'):
if llm_model.startswith('gpt-') or llm_model.startswith('one-api-'):
for k in key_list:
if is_openai_api_key(k): avail_key_list.append(k)

34
shared_utils/map_names.py Normal file
View File

@ -0,0 +1,34 @@
import re
mapping_dic = {
# "qianfan": "qianfan（文心一言大模型）",
# "zhipuai": "zhipuai（智谱GLM4超级模型🔥）",
# "gpt-4-1106-preview": "gpt-4-1106-preview（新调优版本GPT-4🔥）",
# "gpt-4-vision-preview": "gpt-4-vision-preview（识图模型GPT-4V）",
}
rev_mapping_dic = {}
for k, v in mapping_dic.items():
rev_mapping_dic[v] = k
def map_model_to_friendly_names(m):
if m in mapping_dic:
return mapping_dic[m]
return m
def map_friendly_names_to_model(m):
if m in rev_mapping_dic:
return rev_mapping_dic[m]
return m
def read_one_api_model_name(model: str):
"""return real model name and max_token.
"""
max_token_pattern = r"\(max_token=(\d+)\)"
match = re.search(max_token_pattern, model)
if match:
max_token_tmp = match.group(1) # 获取 max_token 的值
max_token_tmp = int(max_token_tmp)
model = re.sub(max_token_pattern, "", model) # 从原字符串中删除 "(max_token=...)"
else:
max_token_tmp = 4096
return model, max_token_tmp

2
shared_utils/text_mask.py
View File

@ -59,7 +59,7 @@ def apply_gpt_academic_string_mask_langbased(string, lang_reference):
lang_reference = "hello world"
输出1
"注意，lang_reference这段文字是：英语"
输入2
string = "注意，lang_reference这段文字是中文" # 注意这里没有掩码tag，所以不会被处理
lang_reference = "hello world"

65
toolbox.py
View File

@ -25,6 +25,9 @@ from shared_utils.text_mask import apply_gpt_academic_string_mask
from shared_utils.text_mask import build_gpt_academic_masked_string
from shared_utils.text_mask import apply_gpt_academic_string_mask_langbased
from shared_utils.text_mask import build_gpt_academic_masked_string_langbased
from shared_utils.map_names import map_friendly_names_to_model
from shared_utils.map_names import map_model_to_friendly_names
from shared_utils.map_names import read_one_api_model_name
from shared_utils.handle_upload import html_local_file
from shared_utils.handle_upload import html_local_img
from shared_utils.handle_upload import file_manifest_filter_type
@ -919,6 +922,18 @@ def have_any_recent_upload_image_files(chatbot):
else:
return False, None # most_recent_uploaded is too old
# Claude3 model supports graphic context dialogue, reads all images
def every_image_file_in_path(chatbot):
if chatbot is None:
return False, [] # chatbot is None
most_recent_uploaded = chatbot._cookies.get("most_recent_uploaded", None)
if not most_recent_uploaded:
return False, [] # most_recent_uploaded is None
path = most_recent_uploaded["path"]
file_manifest = get_pictures_list(path)
if len(file_manifest) == 0:
return False, []
return True, file_manifest
# Function to encode the image
def encode_image(image_path):
@ -939,3 +954,53 @@ def check_packages(packages=[]):
spam_spec = importlib.util.find_spec(p)
if spam_spec is None:
raise ModuleNotFoundError
def map_file_to_sha256(file_path):
import hashlib
with open(file_path, 'rb') as file:
content = file.read()
# Calculate the SHA-256 hash of the file contents
sha_hash = hashlib.sha256(content).hexdigest()
return sha_hash
def check_repeat_upload(new_pdf_path, pdf_hash):
'''
检查历史上传的文件是否与新上传的文件相同，如果相同则返回(True, 重复文件路径)，否则返回(False，None)
'''
from toolbox import get_conf
import PyPDF2
user_upload_dir = os.path.dirname(os.path.dirname(new_pdf_path))
file_name = os.path.basename(new_pdf_path)
file_manifest = [f for f in glob.glob(f'{user_upload_dir}/**/{file_name}', recursive=True)]
for saved_file in file_manifest:
with open(new_pdf_path, 'rb') as file1, open(saved_file, 'rb') as file2:
reader1 = PyPDF2.PdfFileReader(file1)
reader2 = PyPDF2.PdfFileReader(file2)
# 比较页数是否相同
if reader1.getNumPages() != reader2.getNumPages():
continue
# 比较每一页的内容是否相同
for page_num in range(reader1.getNumPages()):
page1 = reader1.getPage(page_num).extractText()
page2 = reader2.getPage(page_num).extractText()
if page1 != page2:
continue
maybe_project_dir = glob.glob('{}/**/{}'.format(get_log_folder(), pdf_hash + ".tag"), recursive=True)
if len(maybe_project_dir) > 0:
return True, os.path.dirname(maybe_project_dir[0])
# 如果所有页的内容都相同，返回 True
return False, None

4
version
View File

@ -1,5 +1,5 @@
{
"version": 3.72,
"version": 3.73,
"show_feature": true,
"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"
"new_feature": "优化oneapi接入方法 <-> 接入月之暗面模型 <-> 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）"
}