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

77
config.py
View File

@ -30,7 +30,32 @@ if USE_PROXY:
else: else:
proxies = None 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！） # 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"} # 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'] 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" # 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" 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_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 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） # 设置gradio的并行线程数（不需要修改）
CONCURRENT_COUNT = 100 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 = {} AZURE_CFG_ARRAY = {}
# 使用Newbing (不推荐使用，未来将删除) # 阿里云实时语音识别 配置难度较高
NEWBING_STYLE = "creative" # ["creative", "balanced", "precise"] # 参考 https://github.com/binary-husky/gpt_academic/blob/master/docs/use_audio.md
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
ENABLE_AUDIO = False ENABLE_AUDIO = False
ALIYUN_TOKEN="" # 例如 f37f30e0f9934c34a992f6f64f7eba4f ALIYUN_TOKEN="" # 例如 f37f30e0f9934c34a992f6f64f7eba4f
ALIYUN_APPKEY="" # 例如 RoPlZrM88DnAFkZK 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 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 # Claude API KEY
ANTHROPIC_API_KEY = "" ANTHROPIC_API_KEY = ""
# 月之暗面 API KEY # 月之暗面 API KEY
MOONSHOT_API_KEY = "" MOONSHOT_API_KEY = ""
# Mathpix 拥有执行PDF的OCR功能，但是需要注册账号 # Mathpix 拥有执行PDF的OCR功能，但是需要注册账号
MATHPIX_APPID = "" MATHPIX_APPID = ""
MATHPIX_APPKEY = "" MATHPIX_APPKEY = ""
@ -270,7 +270,11 @@ PLUGIN_HOT_RELOAD = False
# 自定义按钮的最大数量限制 # 自定义按钮的最大数量限制
NUM_CUSTOM_BASIC_BTN = 4 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 在线大模型配置关联关系示意图
│ │
├── "gpt-3.5-turbo" 等openai模型 ├── "gpt-3.5-turbo" 等openai模型
@ -294,7 +298,7 @@ NUM_CUSTOM_BASIC_BTN = 4
│ ├── XFYUN_API_SECRET │ ├── XFYUN_API_SECRET
│ └── XFYUN_API_KEY │ └── XFYUN_API_KEY
│ │
├── "claude-1-100k" 等claude模型 ├── "claude-3-opus-20240229" 等claude模型
│ └── ANTHROPIC_API_KEY │ └── ANTHROPIC_API_KEY
│ │
├── "stack-claude" ├── "stack-claude"
@ -315,9 +319,10 @@ NUM_CUSTOM_BASIC_BTN = 4
├── "Gemini" ├── "Gemini"
│ └── GEMINI_API_KEY │ └── GEMINI_API_KEY
│ │
└── "newbing" Newbing接口不再稳定，不推荐使用 └── "one-api-...(max_token=...)" 用一种更方便的方式接入one-api多模型管理界面
├── NEWBING_STYLE ├── AVAIL_LLM_MODELS
└── NEWBING_COOKIES ├── API_KEY
└── API_URL_REDIRECT
本地大模型示意图 本地大模型示意图
@ -364,4 +369,4 @@ NUM_CUSTOM_BASIC_BTN = 4
└── MATHPIX_APPKEY └── 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） # [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, "PreProcess": None,
}, },
"总结绘制脑图": { "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 # 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 # 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": "Suffix":
# dedent() 函数用于去除多行字符串的缩进 # 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： 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"] C --> |"箭头名2"| F["节点名6"]
``` ```
警告： 注意：
（1）使用中文 （1）使用中文
（2）节点名字使用引号包裹，如["Laptop"] （2）节点名字使用引号包裹，如["Laptop"]
（3）`|` 和 `"`之间不要存在空格 （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） （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": { "查找语法错误": {
"Prefix": r"Help me ensure that the grammar and the spelling is correct. " "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. " 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"", "Suffix": r"",
"PreProcess": clear_line_break, # 预处理：清除换行符 "PreProcess": clear_line_break, # 预处理：清除换行符
}, },
"中译英": { "中译英": {
"Prefix": r"Please translate following sentence to English:" + "\n\n", "Prefix": r"Please translate following sentence to English:" + "\n\n",
"Suffix": r"", "Suffix": r"",
}, },
"学术英中互译": { "学术英中互译": {
"Prefix": build_gpt_academic_masked_string_langbased( "Prefix": build_gpt_academic_masked_string_langbased(
text_show_chinese= text_show_chinese=
@ -112,29 +112,29 @@ def get_core_functions():
) + "\n\n", ) + "\n\n",
"Suffix": r"", "Suffix": r"",
}, },
"英译中": { "英译中": {
"Prefix": r"翻译成地道的中文：" + "\n\n", "Prefix": r"翻译成地道的中文：" + "\n\n",
"Suffix": r"", "Suffix": r"",
"Visible": False, "Visible": False,
}, },
"找图片": { "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，" "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", 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"", "Suffix": r"",
"Visible": False, "Visible": False,
}, },
"解释代码": { "解释代码": {
"Prefix": r"请解释以下代码：" + "\n```\n", "Prefix": r"请解释以下代码：" + "\n```\n",
"Suffix": "\n```\n", "Suffix": "\n```\n",
}, },
"参考文献转Bib": { "参考文献转Bib": {
"Prefix": r"Here are some bibliography items, please transform them into bibtex style." "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." 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') manifest.append(path + '.polish.tex')
f.write(res) f.write(res)
return manifest return manifest
def zip_result(self): def zip_result(self):
import os, time import os, time
folder = os.path.dirname(self.file_paths[0]) 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 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() pfg = PaperFileGroup()
for index, fp in enumerate(file_manifest): 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_paths.append(fp)
pfg.file_contents.append(clean_tex_content) 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) pfg.run_file_split(max_token_limit=1024)
n_split = len(pfg.sp_file_contents) 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 language == 'en':
if mode == 'polish': if mode == 'polish':
inputs_array = ["Below is a section from an academic paper, polish this section to meet the academic standard, " + 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:" + "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] f"\n\n{frag}" for frag in pfg.sp_file_contents]
else: else:
inputs_array = [r"Below is a section from an academic paper, proofread this section." + 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"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " +
r"Answer me only with the revised text:" + r"Answer me only with the revised text:" +
f"\n\n{frag}" for frag in pfg.sp_file_contents] 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] 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)] sys_prompt_array = ["You are a professional academic paper writer." for _ in range(n_split)]
elif language == 'zh': elif language == 'zh':
if mode == 'polish': 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] f"\n\n{frag}" for frag in pfg.sp_file_contents]
else: 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：" + 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] 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] 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)] 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 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: try:
pfg.sp_file_result = [] pfg.sp_file_result = []
for i_say, gpt_say in zip(gpt_response_collection[0::2], gpt_response_collection[1::2]): 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: except:
print(trimmed_format_exc()) 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" 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) res = write_history_to_file(gpt_response_collection, file_basename=create_report_file_name)
promote_file_to_downloadzone(res, chatbot=chatbot) 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 import time, os, re
from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency 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() pfg = PaperFileGroup()
for index, fp in enumerate(file_manifest): 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_paths.append(fp)
pfg.file_contents.append(clean_tex_content) 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) pfg.run_file_split(max_token_limit=1024)
n_split = len(pfg.sp_file_contents) n_split = len(pfg.sp_file_contents)
# <-------- 抽取摘要 ----------> # <-------- 抽取摘要 ---------->
# if language == 'en': # if language == 'en':
# abs_extract_inputs = f"Please write an abstract for this paper" # 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。", # 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': 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] 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] 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)] sys_prompt_array = ["You are a professional academic paper translator." for _ in range(n_split)]
elif language == 'zh->en': 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] 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] 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)] 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 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" 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) res = write_history_to_file(gpt_response_collection, create_report_file_name)
promote_file_to_downloadzone(res, chatbot=chatbot) 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 toolbox import CatchException, report_exception, update_ui_lastest_msg, zip_result, gen_time_str
from functools import partial from functools import partial
import glob, os, requests, time, json, tarfile 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): def desend_to_extracted_folder_if_exist(project_folder):
""" """
Descend into the extracted folder if it exists, otherwise return the original folder. Descend into the extracted folder if it exists, otherwise return the original folder.
Args: Args:
@ -56,7 +56,7 @@ def desend_to_extracted_folder_if_exist(project_folder):
def move_project(project_folder, arxiv_id=None): def move_project(project_folder, arxiv_id=None):
""" """
Create a new work folder and copy the project folder to it. Create a new work folder and copy the project folder to it.
Args: 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 if ('.' in txt) and ('/' not in txt) and is_float(txt[:10]): # is arxiv ID
txt = 'https://arxiv.org/abs/' + txt[:10] 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 return txt, None # 是本地文件，跳过下载
# <-------------- inspect format -------------> # <-------------- inspect format ------------->
chatbot.append([f"检测到arxiv文档连接", '尝试下载 ...']) chatbot.append([f"检测到arxiv文档连接", '尝试下载 ...'])
yield from update_ui(chatbot=chatbot, history=history) yield from update_ui(chatbot=chatbot, history=history)
@ -214,7 +214,7 @@ def pdf2tex_project(pdf_file_path):
return None return None
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序1 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= # =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序1 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
@CatchException @CatchException
@ -291,7 +291,7 @@ def Latex英文纠错加PDF对比(txt, llm_kwargs, plugin_kwargs, chatbot, histo
return success return success
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序2 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= # =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序2 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
@CatchException @CatchException
def Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request): 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) txt, arxiv_id = yield from arxiv_download(chatbot, history, txt, allow_cache)
except tarfile.ReadError as e: except tarfile.ReadError as e:
yield from update_ui_lastest_msg( 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) chatbot=chatbot, history=history)
return 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 return success
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=- 插件主程序3 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= # =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=- 插件主程序3 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
@CatchException @CatchException
def PDF翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port): 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 yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return return
# <-------------- convert pdf into tex -------------> hash_tag = map_file_to_sha256(file_manifest[0])
project_folder = pdf2tex_project(file_manifest[0])
# Translate English Latex to Chinese Latex, and compile it # <-------------- check repeated pdf ------------->
file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)] chatbot.append([f"检查PDF是否被重复上传", "正在检查..."])
if len(file_manifest) == 0: yield from update_ui(chatbot=chatbot, history=history)
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何.tex文件: {txt}") repeat, project_folder = check_repeat_upload(file_manifest[0], hash_tag)
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
# <-------------- if is a zip/tar file -------------> except_flag = False
project_folder = desend_to_extracted_folder_if_exist(project_folder)
# <-------------- move latex project away from temp folder -------------> if repeat:
project_folder = move_project(project_folder) 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 -------------> try:
if not os.path.exists(project_folder + '/merge_translate_zh.tex'): trans_html_file = [f for f in glob.glob(f'{project_folder}/**/*.trans.html', recursive=True)][0]
yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs, promote_file_to_downloadzone(trans_html_file, rename_file=None, chatbot=chatbot)
chatbot, history, system_prompt, mode='translate_zh',
switch_prompt=_switch_prompt_)
# <-------------- compile PDF -------------> translate_pdf = [f for f in glob.glob(f'{project_folder}/**/merge_translate_zh.pdf', recursive=True)][0]
success = yield from 编译Latex(chatbot, history, main_file_original='merge', promote_file_to_downloadzone(translate_pdf, rename_file=None, chatbot=chatbot)
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 -------------> comparison_pdf = [f for f in glob.glob(f'{project_folder}/**/comparison.pdf', recursive=True)][0]
zip_res = zip_result(project_folder) promote_file_to_downloadzone(comparison_pdf, rename_file=None, chatbot=chatbot)
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 -------------> zip_res = zip_result(project_folder)
return success 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']: if file_type.lower() in ['png', 'jpg']:
image_path = os.path.abspath(fp) image_path = os.path.abspath(fp)
self.chatbot.append([ 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>' 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) yield from update_ui(chatbot=self.chatbot, history=self.history)
@ -114,21 +114,21 @@ class PluginMultiprocessManager:
self.cnt = 1 self.cnt = 1
self.parent_conn = self.launch_subprocess_with_pipe() # ⭐⭐⭐ self.parent_conn = self.launch_subprocess_with_pipe() # ⭐⭐⭐
repeated, cmd_to_autogen = self.send_command(txt) 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。"]) 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) yield from update_ui(chatbot=self.chatbot, history=self.history)
self.terminate() self.terminate()
return "terminate" return "terminate"
# patience = 10 # patience = 10
while True: while True:
time.sleep(0.5) time.sleep(0.5)
if not self.alive: if not self.alive:
# the heartbeat watchdog might have it killed # the heartbeat watchdog might have it killed
self.terminate() self.terminate()
return "terminate" return "terminate"
if self.parent_conn.poll(): if self.parent_conn.poll():
self.feed_heartbeat_watchdog() self.feed_heartbeat_watchdog()
if "[GPT-Academic] 等待中" in self.chatbot[-1][-1]: if "[GPT-Academic] 等待中" in self.chatbot[-1][-1]:
self.chatbot.pop(-1) # remove the last line self.chatbot.pop(-1) # remove the last line
@ -152,8 +152,8 @@ class PluginMultiprocessManager:
yield from update_ui(chatbot=self.chatbot, history=self.history) yield from update_ui(chatbot=self.chatbot, history=self.history)
if msg.cmd == "interact": if msg.cmd == "interact":
yield from self.overwatch_workdir_file_change() yield from self.overwatch_workdir_file_change()
self.chatbot.append([f"程序抵达用户反馈节点.", msg.content + 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(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(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. " "\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.interval = interval
self.msg = msg self.msg = msg
self.kill_dog = False self.kill_dog = False
def watch(self): def watch(self):
while True: while True:
if self.kill_dog: break 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")) 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") if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
args = plugin_kwargs.get("advanced_arg", None) args = plugin_kwargs.get("advanced_arg", None)
if args is None: if args is None:
chatbot.append(("没给定指令", "退出")) chatbot.append(("没给定指令", "退出"))
yield from update_ui(chatbot=chatbot, history=history); return yield from update_ui(chatbot=chatbot, history=history); return
else: 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)], sys_prompt_array=[arguments.system_prompt for _ in (batch)],
max_workers=10 # OpenAI所允许的最大并行过载 max_workers=10 # OpenAI所允许的最大并行过载
) )
with open(txt+'.generated.json', 'a+', encoding='utf8') as f: with open(txt+'.generated.json', 'a+', encoding='utf8') as f:
for b, r in zip(batch, res[1::2]): for b, r in zip(batch, res[1::2]):
f.write(json.dumps({"content":b, "summary":r}, ensure_ascii=False)+'\n') 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")) 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") if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
args = plugin_kwargs.get("advanced_arg", None) args = plugin_kwargs.get("advanced_arg", None)
if args is None: if args is None:
chatbot.append(("没给定指令", "退出")) chatbot.append(("没给定指令", "退出"))
yield from update_ui(chatbot=chatbot, history=history); return yield from update_ui(chatbot=chatbot, history=history); return
else: else:
arguments = string_to_options(arguments=args) arguments = string_to_options(arguments=args)
pre_seq_len = arguments.pre_seq_len # 128 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.parenting_ship = []
self.comment = "" self.comment = ""
self.comment_maxlen_show = 50 self.comment_maxlen_show = 50
@staticmethod @staticmethod
def add_linebreaks_at_spaces(string, interval=10): def add_linebreaks_at_spaces(string, interval=10):
return '\n'.join(string[i:i+interval] for i in range(0, len(string), interval)) 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): class MiniGame_ASCII_Art(GptAcademicGameBaseState):
def step(self, prompt, chatbot, history): 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..."]) chatbot.append(["我画你猜（动物）", "请稍等..."])
else: else:
if prompt.strip() == 'exit': 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 = [] self.story = []
chatbot.append(["互动写故事", f"这次的故事开头是：{self.headstart}"]) 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）。' 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): def generate_story_image(self, story_paragraph):
try: try:
from crazy_functions.图片生成 import gen_image 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>' return f'<br/><div align="center"><img src="file={image_path}"></div>'
except: except:
return '' return ''
def step(self, prompt, chatbot, history): def step(self, prompt, chatbot, history):
""" """
首先，处理游戏初始化等特殊情况 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.begin_game_step_0(prompt, chatbot, history)
self.lock_plugin(chatbot) self.lock_plugin(chatbot)
self.cur_task = 'head_start' self.cur_task = 'head_start'
@ -132,7 +132,7 @@ class MiniGame_ResumeStory(GptAcademicGameBaseState):
inputs_ = prompts_hs.format(headstart=self.headstart) inputs_ = prompts_hs.format(headstart=self.headstart)
history_ = [] history_ = []
story_paragraph = yield from request_gpt_model_in_new_thread_with_ui_alive( 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_ chatbot, history_, self.sys_prompt_
) )
self.story.append(story_paragraph) self.story.append(story_paragraph)
@ -147,7 +147,7 @@ class MiniGame_ResumeStory(GptAcademicGameBaseState):
inputs_ = prompts_interact.format(previously_on_story=previously_on_story) inputs_ = prompts_interact.format(previously_on_story=previously_on_story)
history_ = [] history_ = []
self.next_choices = yield from request_gpt_model_in_new_thread_with_ui_alive( 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, chatbot,
history_, history_,
self.sys_prompt_ 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) inputs_ = prompts_resume.format(previously_on_story=previously_on_story, choice=self.next_choices, user_choice=prompt)
history_ = [] history_ = []
story_paragraph = yield from request_gpt_model_in_new_thread_with_ui_alive( 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_ chatbot, history_, self.sys_prompt_
) )
self.story.append(story_paragraph) self.story.append(story_paragraph)
@ -181,10 +181,10 @@ class MiniGame_ResumeStory(GptAcademicGameBaseState):
inputs_ = prompts_interact.format(previously_on_story=previously_on_story) inputs_ = prompts_interact.format(previously_on_story=previously_on_story)
history_ = [] history_ = []
self.next_choices = yield from request_gpt_model_in_new_thread_with_ui_alive( self.next_choices = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs_, 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, '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, chatbot,
history_, history_,
self.sys_prompt_ self.sys_prompt_
) )
self.cur_task = 'user_choice' 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) inputs_ = prompts_terminate.format(previously_on_story=previously_on_story, user_choice=prompt)
history_ = [] history_ = []
story_paragraph = yield from request_gpt_model_in_new_thread_with_ui_alive( 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_ chatbot, history_, self.sys_prompt_
) )
# # 配图 # # 配图

10
crazy_functions/game_fns/game_utils.py
View File

@ -5,7 +5,7 @@ def get_code_block(reply):
import re import re
pattern = r"```([\s\S]*?)```" # regex pattern to match code blocks pattern = r"```([\s\S]*?)```" # regex pattern to match code blocks
matches = re.findall(pattern, reply) # find all code blocks in text matches = re.findall(pattern, reply) # find all code blocks in text
if len(matches) == 1: if len(matches) == 1:
return "```" + matches[0] + "```" # code block return "```" + matches[0] + "```" # code block
raise RuntimeError("GPT is not generating proper code.") 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 from pydantic import BaseModel, Field
class IsSameThing(BaseModel): class IsSameThing(BaseModel):
is_same_thing: bool = Field(description="determine whether two objects are same thing.", default=False) 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( 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=[] 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 = "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." 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, "", []) analyze_res_cot_01 = run_gpt_fn(inputs_01, "", [])
inputs_02 = inputs_01 + gpt_json_io.format_instructions inputs_02 = inputs_01 + gpt_json_io.format_instructions
analyze_res = run_gpt_fn(inputs_02, "", [inputs_01, analyze_res_cot_01]) 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 # Now you can create an instance of the class
instance = some_class() instance = some_class()
return_dict['success'] = True return_dict['success'] = True
return return
except: except:
return_dict['traceback'] = trimmed_format_exc() return_dict['traceback'] = trimmed_format_exc()
return return
def subprocess_worker(code, file_path, return_dict): def subprocess_worker(code, file_path, return_dict):
return_dict['result'] = None return_dict['result'] = None
return_dict['success'] = False return_dict['success'] = False

2
crazy_functions/ipc_fns/mp.py
View File

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

2
crazy_functions/json_fns/pydantic_io.py
View File

@ -89,7 +89,7 @@ class GptJsonIO():
error + "\n\n" + \ error + "\n\n" + \
"Now, fix this json string. \n\n" "Now, fix this json string. \n\n"
return prompt return prompt
def generate_output_auto_repair(self, response, gpt_gen_fn): def generate_output_auto_repair(self, response, gpt_gen_fn):
""" """
response: string containing canidate json 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。" + \ "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/}。" "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） # 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.title = "unknown"
self.abstract = "unknown" self.abstract = "unknown"
def read_title_and_abstract(self, txt): def read_title_and_abstract(self, txt):
try: try:
title, abstract = find_title_and_abs(txt) 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(' ', '') 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(' ', '') self.abstract = abstract.replace('\n', ' ').replace('\\\\', ' ').replace(' ', '').replace(' ', '')
except: except:
pass pass
@ -111,7 +111,7 @@ class LatexPaperSplit():
result_string = "" result_string = ""
node_cnt = 0 node_cnt = 0
line_cnt = 0 line_cnt = 0
for node in self.nodes: for node in self.nodes:
if node.preserve: if node.preserve:
line_cnt += node.string.count('\n') line_cnt += node.string.count('\n')
@ -144,7 +144,7 @@ class LatexPaperSplit():
return result_string 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, break down latex file to a linked list,
each node use a preserve flag to indicate whether it should each node use a preserve flag to indicate whether it should
@ -155,7 +155,7 @@ class LatexPaperSplit():
manager = multiprocessing.Manager() manager = multiprocessing.Manager()
return_dict = manager.dict() return_dict = manager.dict()
p = multiprocessing.Process( p = multiprocessing.Process(
target=split_subprocess, target=split_subprocess,
args=(txt, project_folder, return_dict, opts)) args=(txt, project_folder, return_dict, opts))
p.start() p.start()
p.join() 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 ..crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
from .latex_actions import LatexPaperFileGroup, LatexPaperSplit 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) 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。')) 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 yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
time.sleep(3) 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) main_tex_basename = os.path.basename(maintex)
assert main_tex_basename.endswith('.tex') assert main_tex_basename.endswith('.tex')
main_tex_basename_bare = main_tex_basename[:-4] 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: with open(project_folder + '/merge.tex', 'w', encoding='utf-8', errors='replace') as f:
f.write(merged_content) 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。')) 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 yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
lps = LatexPaperSplit() lps = LatexPaperSplit()
lps.read_title_and_abstract(merged_content) lps.read_title_and_abstract(merged_content)
res = lps.split(merged_content, project_folder, opts) # 消耗时间的函数 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() pfg = LatexPaperFileGroup()
for index, r in enumerate(res): for index, r in enumerate(res):
pfg.file_paths.append('segment-' + str(index)) 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) pfg.run_file_split(max_token_limit=1024)
n_split = len(pfg.sp_file_contents) 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_array, sys_prompt_array = switch_prompt(pfg, mode)
inputs_show_user_array = [f"{mode} {f}" for f in pfg.sp_file_tag] inputs_show_user_array = [f"{mode} {f}" for f in pfg.sp_file_tag]
if os.path.exists(pj(project_folder,'temp.pkl')): 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')) pfg = objload(file=pj(project_folder,'temp.pkl'))
else: else:
# <-------- gpt 多线程请求 ----------> # <-------- gpt 多线程请求 ---------->
history_array = [[""] for _ in range(n_split)] history_array = [[""] for _ in range(n_split)]
# LATEX_EXPERIMENTAL, = get_conf('LATEX_EXPERIMENTAL') # LATEX_EXPERIMENTAL, = get_conf('LATEX_EXPERIMENTAL')
# if 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 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 = [] 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): 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.sp_file_result.append(gpt_say)
pfg.merge_result() pfg.merge_result()
# <-------- 临时存储用于调试 ----------> # <-------- 临时存储用于调试 ---------->
pfg.get_token_num = None pfg.get_token_num = None
objdump(pfg, file=pj(project_folder,'temp.pkl')) objdump(pfg, file=pj(project_folder,'temp.pkl'))
write_html(pfg.sp_file_contents, pfg.sp_file_result, chatbot=chatbot, project_folder=project_folder) 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']}。" 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) final_tex = lps.merge_result(pfg.file_result, mode, msg)
objdump((lps, pfg.file_result, mode, msg), file=pj(project_folder,'merge_result.pkl')) 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: 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) 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')) 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 yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
# <-------- 返回 ----------> # <-------- 返回 ---------->
return project_folder + f'/merge_{mode}.tex' 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 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) 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')): 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 # 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 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')) 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')) 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')) 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"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"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"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 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: 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')) 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 promote_file_to_downloadzone(result_pdf, rename_file=None, chatbot=chatbot) # promote file to web UI
# 将两个PDF拼接 # 将两个PDF拼接
if original_pdf_success: if original_pdf_success:
try: try:
from .latex_toolbox import merge_pdfs from .latex_toolbox import merge_pdfs
concat_pdf = pj(work_folder_modified, f'comparison.pdf') 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 if n_fix>=max_try: break
n_fix += 1 n_fix += 1
can_retry, main_file_modified, buggy_lines = remove_buggy_lines( 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'), log_path=pj(work_folder_modified, f'{main_file_modified}.log'),
tex_name=f'{main_file_modified}.tex', tex_name=f'{main_file_modified}.tex',
tex_name_pure=f'{main_file_modified}', 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 import shutil
from crazy_functions.pdf_fns.report_gen_html import construct_html from crazy_functions.pdf_fns.report_gen_html import construct_html
from toolbox import gen_time_str from toolbox import gen_time_str
ch = construct_html() ch = construct_html()
orig = "" orig = ""
trans = "" trans = ""
final = [] 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(c)
final.append(r) final.append(r)
for i, k in enumerate(final): for i, k in enumerate(final):
if i%2==0: if i%2==0:
orig = k orig = k
if i%2==1: 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): def is_speaker_speaking(vad, data, sample_rate):
# Function to detect if the speaker is speaking # Function to detect if the speaker is speaking
# The WebRTC VAD only accepts 16-bit mono PCM audio, # The WebRTC VAD only accepts 16-bit mono PCM audio,
# sampled at 8000, 16000, 32000 or 48000 Hz. # sampled at 8000, 16000, 32000 or 48000 Hz.
# A frame must be either 10, 20, or 30 ms in duration: # A frame must be either 10, 20, or 30 ms in duration:
frame_duration = 30 frame_duration = 30
n_bit_each = int(sample_rate * frame_duration / 1000)*2 # x2 because audio is 16 bit (2 bytes) 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)): for t in range(len(data)):
if t!=0 and t % n_bit_each == 0: if t!=0 and t % n_bit_each == 0:
res_list.append(vad.is_speech(data[t-n_bit_each:t], sample_rate)) 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 = ''.join(['^' if r else '.' for r in res_list])
info = info[:10] info = info[:10]
if any(res_list): if any(res_list):
@ -186,10 +186,10 @@ class AliyunASR():
keep_alive_last_send_time = time.time() keep_alive_last_send_time = time.time()
while not self.stop: while not self.stop:
# time.sleep(self.capture_interval) # time.sleep(self.capture_interval)
audio = rad.read(uuid.hex) audio = rad.read(uuid.hex)
if audio is not None: if audio is not None:
# convert to pcm file # 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 dsdata = change_sample_rate(audio, rad.rate, NEW_SAMPLERATE) # 48000 --> 16000
write_numpy_to_wave(temp_file, NEW_SAMPLERATE, dsdata) write_numpy_to_wave(temp_file, NEW_SAMPLERATE, dsdata)
# read pcm binary # read pcm binary

6
crazy_functions/live_audio/audio_io.py
View File

@ -3,12 +3,12 @@ from scipy import interpolate
def Singleton(cls): def Singleton(cls):
_instance = {} _instance = {}
def _singleton(*args, **kargs): def _singleton(*args, **kargs):
if cls not in _instance: if cls not in _instance:
_instance[cls] = cls(*args, **kargs) _instance[cls] = cls(*args, **kargs)
return _instance[cls] return _instance[cls]
return _singleton return _singleton
@ -39,7 +39,7 @@ class RealtimeAudioDistribution():
else: else:
res = None res = None
return res return res
def change_sample_rate(audio, old_sr, new_sr): def change_sample_rate(audio, old_sr, new_sr):
duration = audio.shape[0] / old_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(): class GptAcademicGameBaseState():
""" """
1. first init: __init__ -> 1. first init: __init__ ->
""" """
def init_game(self, chatbot, lock_plugin): def init_game(self, chatbot, lock_plugin):
self.plugin_name = None self.plugin_name = None
@ -53,7 +53,7 @@ class GptAcademicGameBaseState():
raise ValueError("callback_fn is None") raise ValueError("callback_fn is None")
chatbot._cookies['lock_plugin'] = self.callback_fn chatbot._cookies['lock_plugin'] = self.callback_fn
self.dump_state(chatbot) self.dump_state(chatbot)
def get_plugin_name(self): def get_plugin_name(self):
if self.plugin_name is None: if self.plugin_name is None:
raise ValueError("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) state = chatbot._cookies.get(f'plugin_state/{plugin_name}', None)
if state is not None: if state is not None:
state = pickle.loads(state) state = pickle.loads(state)
else: else:
state = cls() state = cls()
state.init_game(chatbot, lock_plugin) state.init_game(chatbot, lock_plugin)
state.plugin_name = plugin_name state.plugin_name = plugin_name
@ -79,7 +79,7 @@ class GptAcademicGameBaseState():
state.chatbot = chatbot state.chatbot = chatbot
state.callback_fn = callback_fn state.callback_fn = callback_fn
return state return state
def continue_game(self, prompt, chatbot, history): def continue_game(self, prompt, chatbot, history):
# 游戏主体 # 游戏主体
yield from self.step(prompt, chatbot, history) 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 = "" 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 # 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) remain_txt_to_cut, remain_txt_to_cut_storage = maintain_storage(remain_txt_to_cut, remain_txt_to_cut_storage)
while True: while True:
if get_token_fn(remain_txt_to_cut) <= limit: 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 # 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 # 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 cur_value += value
translated_res_array.append(cur_value) translated_res_array.append(cur_value)
res_path = write_history_to_file(meta + ["# Meta Translation" , paper_meta_info] + translated_res_array, 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_basename = f"{gen_time_str()}-translated_only.md",
file_fullname = None, file_fullname = None,
auto_caption = False) auto_caption = False)
promote_file_to_downloadzone(res_path, rename_file=os.path.basename(res_path)+'.md', chatbot=chatbot) 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) produce_report_markdown(gpt_response_collection, meta, paper_meta_info, chatbot, fp, generated_conclusion_files)
# -=-=-=-=-=-=-=-= 写出HTML文件 -=-=-=-=-=-=-=-= # -=-=-=-=-=-=-=-= 写出HTML文件 -=-=-=-=-=-=-=-=
ch = construct_html() ch = construct_html()
orig = "" orig = ""
trans = "" trans = ""
gpt_response_collection_html = copy.deepcopy(gpt_response_collection) 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: if i%2==0:
gpt_response_collection_html[i] = inputs_show_user_array[i//2] gpt_response_collection_html[i] = inputs_show_user_array[i//2]
else: 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 = ["", "", "一、论文概况", "", "Abstract", paper_meta_info, "二、论文翻译", ""]
final.extend(gpt_response_collection_html) final.extend(gpt_response_collection_html)
for i, k in enumerate(final): for i, k in enumerate(final):
if i%2==0: if i%2==0:
orig = k orig = k
if i%2==1: 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 = [] file_manifest = []
excption = "" excption = ""
if txt == "": if txt == "":
final_result.append(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 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 #查找输入区内容中的文件
file_pdf,pdf_manifest,folder_pdf = get_files_from_everything(txt, '.pdf') file_pdf,pdf_manifest,folder_pdf = get_files_from_everything(txt, '.pdf')
file_md,md_manifest,folder_md = get_files_from_everything(txt, '.md') file_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: if file_doc:
excption = "word" excption = "word"
return False, final_result, page_one, file_manifest, excption return False, final_result, page_one, file_manifest, excption
file_num = len(pdf_manifest) + len(md_manifest) + len(word_manifest) file_num = len(pdf_manifest) + len(md_manifest) + len(word_manifest)
if file_num == 0: if file_num == 0:
final_result.append(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 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: if file_pdf:
try: # 尝试导入依赖，如果缺少依赖，则给出安装建议 try: # 尝试导入依赖，如果缺少依赖，则给出安装建议
import fitz import fitz
@ -61,7 +61,7 @@ def extract_text_from_files(txt, chatbot, history):
file_content = f.read() file_content = f.read()
file_content = file_content.encode('utf-8', 'ignore').decode() file_content = file_content.encode('utf-8', 'ignore').decode()
headers = re.findall(r'^#\s(.*)$', file_content, re.MULTILINE) #接下来提取md中的一级/二级标题作为摘要 headers = re.findall(r'^#\s(.*)$', 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 page_one.append("\n".join(headers)) #合并所有的标题,以换行符分割
else: else:
page_one.append("") page_one.append("")
@ -81,5 +81,5 @@ def extract_text_from_files(txt, chatbot, history):
page_one.append(file_content[:200]) page_one.append(file_content[:200])
final_result.append(file_content) final_result.append(file_content)
file_manifest.append(os.path.relpath(fp, folder_word)) file_manifest.append(os.path.relpath(fp, folder_word))
return True, final_result, page_one, file_manifest, excption 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}" # 基于上下文的prompt模版，请务必保留"{question}"和"{context}"
PROMPT_TEMPLATE = """已知信息： 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}""" 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( def similarity_search_with_score_by_vector(
self, embedding: List[float], k: int = 4 self, embedding: List[float], k: int = 4
) -> List[Tuple[Document, float]]: ) -> List[Tuple[Document, float]]:
def seperate_list(ls: List[int]) -> List[List[int]]: def seperate_list(ls: List[int]) -> List[List[int]]:
lists = [] lists = []
ls1 = [ls[0]] ls1 = [ls[0]]
@ -200,7 +200,7 @@ class LocalDocQA:
return vs_path, loaded_files return vs_path, loaded_files
else: else:
raise RuntimeError("文件加载失败，请检查文件格式是否正确") 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): def get_loaded_file(self, vs_path):
ds = self.vector_store.docstore ds = self.vector_store.docstore
return set([ds._dict[k].metadata['source'].split(vs_path)[-1] for k in ds._dict]) 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() self.threadLock.acquire()
# import uuid # import uuid
self.current_id = id self.current_id = id
self.qa_handle, self.kai_path = construct_vector_store( self.qa_handle, self.kai_path = construct_vector_store(
vs_id=self.current_id, vs_id=self.current_id,
vs_path=vs_path, vs_path=vs_path,
files=file_manifest, files=file_manifest,
sentence_size=100, sentence_size=100,
history=[], history=[],
one_conent="", one_conent="",
@ -304,7 +304,7 @@ class knowledge_archive_interface():
def get_current_archive_id(self): def get_current_archive_id(self):
return self.current_id return self.current_id
def get_loaded_file(self, vs_path): def get_loaded_file(self, vs_path):
return self.qa_handle.get_loaded_file(vs_path) return self.qa_handle.get_loaded_file(vs_path)
@ -312,10 +312,10 @@ class knowledge_archive_interface():
self.threadLock.acquire() self.threadLock.acquire()
if not self.current_id == id: if not self.current_id == id:
self.current_id = id self.current_id = id
self.qa_handle, self.kai_path = construct_vector_store( self.qa_handle, self.kai_path = construct_vector_store(
vs_id=self.current_id, vs_id=self.current_id,
vs_path=vs_path, vs_path=vs_path,
files=[], files=[],
sentence_size=100, sentence_size=100,
history=[], history=[],
one_conent="", one_conent="",
@ -329,7 +329,7 @@ class knowledge_archive_interface():
query = txt, query = txt,
vs_path = self.kai_path, vs_path = self.kai_path,
score_threshold=VECTOR_SEARCH_SCORE_THRESHOLD, 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_conent=True,
chunk_size=CHUNK_SIZE, chunk_size=CHUNK_SIZE,
text2vec = self.get_chinese_text2vec(), 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) most_recent_uploaded = chatbot._cookies.get("most_recent_uploaded", None)
path = most_recent_uploaded['path'] path = most_recent_uploaded['path']
prompt = "\nAdditional Information:\n" prompt = "\nAdditional Information:\n"
prompt = "In case that this plugin requires a path or a file as argument," 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"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 += f"Only use it when necessary, otherwise, you can ignore this file."
return prompt return prompt
def get_inputs_show_user(inputs, plugin_arr_enum_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" 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) yield from update_ui_lastest_msg(lastmsg=msg, chatbot=chatbot, history=history, delay=2)
return return
# ⭐ ⭐ ⭐ 确认插件参数 # ⭐ ⭐ ⭐ 确认插件参数
if not have_any_recent_upload_files(chatbot): if not have_any_recent_upload_files(chatbot):
appendix_info = "" 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, " + \ 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" + \ "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' + \ ">> " + (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( 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=[]) 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) 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') ALLOW_RESET_CONFIG = get_conf('ALLOW_RESET_CONFIG')
if not ALLOW_RESET_CONFIG: if not ALLOW_RESET_CONFIG:
yield from update_ui_lastest_msg( 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 chatbot=chatbot, history=history, delay=2
) )
return 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" + \ 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' + \ ">> " + txt.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( 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=[]) 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) 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) ok = (explicit_conf in txt)
if ok: if ok:
yield from update_ui_lastest_msg( 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 chatbot=chatbot, history=history, delay=1
) )
yield from update_ui_lastest_msg( 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 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') ALLOW_RESET_CONFIG = get_conf('ALLOW_RESET_CONFIG')
if not ALLOW_RESET_CONFIG: if not ALLOW_RESET_CONFIG:
yield from update_ui_lastest_msg( 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 chatbot=chatbot, history=history, delay=2
) )
return return

2
crazy_functions/vt_fns/vt_state.py
View File

@ -6,7 +6,7 @@ class VoidTerminalState():
def reset_state(self): def reset_state(self):
self.has_provided_explaination = False self.has_provided_explaination = False
def lock_plugin(self, chatbot): def lock_plugin(self, chatbot):
chatbot._cookies['lock_plugin'] = 'crazy_functions.虚空终端->虚空终端' chatbot._cookies['lock_plugin'] = 'crazy_functions.虚空终端->虚空终端'
chatbot._cookies['plugin_state'] = pickle.dumps(self) 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: try:
import bs4 import bs4
except: except:
report_exception(chatbot, history, report_exception(chatbot, history,
a = f"解析项目: {txt}", 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```。") 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 yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return return
@ -157,12 +157,12 @@ def 下载arxiv论文并翻译摘要(txt, llm_kwargs, plugin_kwargs, chatbot, hi
try: try:
pdf_path, info = download_arxiv_(txt) pdf_path, info = download_arxiv_(txt)
except: except:
report_exception(chatbot, history, report_exception(chatbot, history,
a = f"解析项目: {txt}", a = f"解析项目: {txt}",
b = f"下载pdf文件未成功") b = f"下载pdf文件未成功")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return return
# 翻译摘要等 # 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 = 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}' 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 # 选择游戏
cls = MiniGame_ResumeStory 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 # 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, state = cls.sync_state(chatbot,
llm_kwargs, llm_kwargs,
cls, cls,
plugin_name='MiniGame_ResumeStory', plugin_name='MiniGame_ResumeStory',
callback_fn='crazy_functions.互动小游戏->随机小游戏', callback_fn='crazy_functions.互动小游戏->随机小游戏',
lock_plugin=True 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 # 选择游戏
cls = MiniGame_ASCII_Art 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 # 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, state = cls.sync_state(chatbot,
llm_kwargs, llm_kwargs,
cls, cls,
plugin_name='MiniGame_ASCII_Art', plugin_name='MiniGame_ASCII_Art',
callback_fn='crazy_functions.互动小游戏->随机小游戏1', callback_fn='crazy_functions.互动小游戏->随机小游戏1',
lock_plugin=True 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}" 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( gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=inputs, inputs_show_user=inputs_show_user, 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'" 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] 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 - 将图像转为灰度图像
- 将csv文件转excel表格 - 将csv文件转excel表格
Testing: Testing:
- Crop the image, keeping the bottom half. - Crop the image, keeping the bottom half.
- Swap the blue channel and red channel of the image. - Swap the blue channel and red channel of the image.
- Convert the image to grayscale. - Convert the image to grayscale.
- Convert the CSV file to an Excel spreadsheet. - Convert the CSV file to an Excel spreadsheet.
""" """
@ -29,12 +29,12 @@ import multiprocessing
templete = """ templete = """
```python ```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` 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. 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 return generated_file_path
``` ```
@ -48,7 +48,7 @@ def get_code_block(reply):
import re import re
pattern = r"```([\s\S]*?)```" # regex pattern to match code blocks pattern = r"```([\s\S]*?)```" # regex pattern to match code blocks
matches = re.findall(pattern, reply) # find all code blocks in text 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 return matches[0].strip('python') # code block
for match in matches: for match in matches:
if 'class TerminalFunction' in match: if 'class TerminalFunction' in match:
@ -68,8 +68,8 @@ def gpt_interact_multi_step(txt, file_type, llm_kwargs, chatbot, history):
# 第一步 # 第一步
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive( 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, history=demo, llm_kwargs=llm_kwargs, chatbot=chatbot, history=demo,
sys_prompt= r"You are a world-class programmer." sys_prompt= r"You are a world-class programmer."
) )
history.extend([i_say, gpt_say]) 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. " 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( gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=i_say, inputs_show_user=inputs_show_user, inputs=i_say, inputs_show_user=inputs_show_user,
llm_kwargs=llm_kwargs, chatbot=chatbot, history=history, 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!" 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 code_to_return = gpt_say
history.extend([i_say, gpt_say]) history.extend([i_say, gpt_say])
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新 yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
# # 第三步 # # 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 = "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"])`' # i_say += 'For instance. `try_install_deps(["opencv-python", "scipy", "numpy"])`'
# installation_advance = yield from request_gpt_model_in_new_thread_with_ui_alive( # installation_advance = yield from request_gpt_model_in_new_thread_with_ui_alive(
# inputs=i_say, inputs_show_user=inputs_show_user, # inputs=i_say, inputs_show_user=inputs_show_user,
# llm_kwargs=llm_kwargs, chatbot=chatbot, history=history, # llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
# sys_prompt= r"You are a programmer." # 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 = "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`' # i_say += 'For instance. `pip install -r opencv-python scipy numpy`'
# installation_advance = yield from request_gpt_model_in_new_thread_with_ui_alive( # installation_advance = 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, history=history, # llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
# sys_prompt= r"You are a programmer." # sys_prompt= r"You are a programmer."
# ) # )
installation_advance = "" installation_advance = ""
return code_to_return, installation_advance, txt, file_type, llm_kwargs, chatbot, history 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): def for_immediate_show_off_when_possible(file_type, fp, chatbot):
if file_type in ['png', 'jpg']: if file_type in ['png', 'jpg']:
image_path = os.path.abspath(fp) 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'本地文件地址: <br/>`{image_path}`<br/>'+
f'本地文件预览: <br/><div align="center"><img src="file={image_path}"></div>' 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。"]) 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) 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 return # 2. 如果没有文件
# 读取文件 # 读取文件
file_type = file_list[0].split('.')[-1] 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): 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) 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 return
# 开始干正事 # 开始干正事
MAX_TRY = 3 MAX_TRY = 3
for j in range(MAX_TRY): # 最多重试5次 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]) # 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 yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return return
# 顺利完成，收尾 # 顺利完成，收尾
res = str(res) res = str(res)
if os.path.exists(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 yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
else: else:
chatbot.append(["执行成功了，结果是一个字符串", "结果：" + res]) 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 i_say = "请写bash命令实现以下功能：" + txt
# 开始 # 开始
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive( gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=i_say, inputs_show_user=txt, inputs=i_say, inputs_show_user=txt,
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[], 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。" 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 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 from request_llms.bridge_all import model_info
proxies = get_conf('proxies') 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']) api_key = select_api_key(llm_kwargs['api_key'], llm_kwargs['llm_model'])
chat_endpoint = model_info[llm_kwargs['llm_model']]['endpoint'] chat_endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
# 'https://api.openai.com/v1/chat/completions' # '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") if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
resolution = plugin_kwargs.get("advanced_arg", '1024x1024') resolution = plugin_kwargs.get("advanced_arg", '1024x1024')
image_url, image_path = gen_image(llm_kwargs, prompt, resolution) 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'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'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/>'+ 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']: elif part in ['vivid', 'natural']:
style = part style = part
image_url, image_path = gen_image(llm_kwargs, prompt, resolution, model="dall-e-3", quality=quality, style=style) 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'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'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/>'+ 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])) 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] file = None if not confirm else file_manifest[0]
return confirm, file return confirm, file
def lock_plugin(self, chatbot): def lock_plugin(self, chatbot):
chatbot._cookies['lock_plugin'] = 'crazy_functions.图片生成->图片修改_DALLE2' chatbot._cookies['lock_plugin'] = 'crazy_functions.图片生成->图片修改_DALLE2'
self.dump_state(chatbot) 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"): if get_conf("AUTOGEN_USE_DOCKER"):
import docker import docker
except: 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```。"]) 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 yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return return
# 尝试导入依赖，如果缺少依赖，则给出安装建议 # 尝试导入依赖，如果缺少依赖，则给出安装建议
try: try:
import autogen 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！"]) 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 yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return return
# 解锁插件 # 解锁插件
chatbot.get_cookies()['lock_plugin'] = None chatbot.get_cookies()['lock_plugin'] = None
persistent_class_multi_user_manager = GradioMultiuserManagerForPersistentClasses() 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;">') i_say, gpt_say = h.split('<hr style="border-top: dotted 3px #ccc;">')
chatbot.append([i_say, gpt_say]) 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。"]) 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 @CatchException
def 对话历史存档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request): 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） 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。")) 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 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' if txt == "": txt = '空空如也的输入栏'
import glob import glob
local_history = "<br/>".join([ 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( 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 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}"]) 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 import glob, os
local_history = "<br/>".join([ local_history = "<br/>".join([
"`"+hide_cwd(f)+"`" "`"+hide_cwd(f)+"`"
for f in glob.glob( for f in glob.glob(
f'{get_log_folder(get_user(chatbot), plugin_name="chat_history")}/**/{f_prefix}*.html', recursive=True 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 = 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。' 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( gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=i_say, inputs=i_say,
inputs_show_user=i_say_show_user, inputs_show_user=i_say_show_user,
llm_kwargs=llm_kwargs, llm_kwargs=llm_kwargs,
chatbot=chatbot, chatbot=chatbot,
history=[], history=[],
sys_prompt="总结文章。" 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: 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。" 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( gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=i_say, inputs=i_say,
inputs_show_user=i_say, inputs_show_user=i_say,
llm_kwargs=llm_kwargs, llm_kwargs=llm_kwargs,
chatbot=chatbot, chatbot=chatbot,
history=this_paper_history, history=this_paper_history,
sys_prompt="总结文章。" 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'): 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 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() pfg = PaperFileGroup()
for index, fp in enumerate(file_manifest): 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_paths.append(fp)
pfg.file_contents.append(file_content) 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) pfg.run_file_split(max_token_limit=1500)
n_split = len(pfg.sp_file_contents) 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': 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] 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] 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)] sys_prompt_array = ["You are a professional academic paper translator." for _ in range(n_split)]
elif language == 'zh->en': 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] 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] 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)] sys_prompt_array = ["You are a professional academic paper translator." for _ in range(n_split)]
else: 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] 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] 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)] 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: except:
logging.error(trimmed_format_exc()) 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" create_report_file_name = gen_time_str() + f"-chatgpt.md"
res = write_history_to_file(gpt_response_collection, file_basename=create_report_file_name) res = write_history_to_file(gpt_response_collection, file_basename=create_report_file_name)
promote_file_to_downloadzone(res, chatbot=chatbot) 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}") 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 yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return return
if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg") if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
language = plugin_kwargs.get("advanced_arg", 'Chinese') 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) 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, 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 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 page_one = str(page_one).encode('utf-8', 'ignore').decode() # avoid reading non-utf8 chars
TOKEN_LIMIT_PER_FRAGMENT = 2500 TOKEN_LIMIT_PER_FRAGMENT = 2500
from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
@ -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']) 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） # 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] 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> ################################## ############################## <第 1 步，从摘要中提取高价值信息，放到history中> ##################################
final_results = [] final_results = []
final_results.append(paper_meta) 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 = 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]}" 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 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 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 sys_prompt="Extract the main idea of this section with Chinese." # 提示
) )
iteration_results.append(gpt_say) iteration_results.append(gpt_say)
last_iteration_result = 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? - (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? - (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? - (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 1. Title: xxx\n\n
2. Authors: xxx\n\n 2. Authors: xxx\n\n
3. Affiliation: xxx\n\n 3. Affiliation: xxx\n\n
4. Keywords: xxx\n\n 4. Keywords: xxx\n\n
5. Urls: xxx or xxx , xxx \n\n 5. Urls: xxx or xxx , xxx \n\n
6. Summary: \n\n 6. Summary: \n\n
- (1):xxx;\n - (1):xxx;\n
- (2):xxx;\n - (2):xxx;\n
- (3):xxx;\n - (3):xxx;\n
- (4):xxx.\n\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, 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) file_write_buffer.extend(final_results)
i_say, final_results = input_clipping(i_say, final_results, max_token_limit=2000) 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( 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', inputs=i_say, inputs_show_user='开始最终总结',
llm_kwargs=llm_kwargs, chatbot=chatbot, history=final_results, 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" sys_prompt= f"Extract the main idea of this paper with less than {NUM_OF_WORD} Chinese characters"
) )
final_results.append(gpt_say) 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: try:
import fitz import fitz
except: except:
report_exception(chatbot, history, report_exception(chatbot, history,
a = f"解析项目: {txt}", 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```。") 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 yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return 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 # 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)] file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.pdf', recursive=True)]
# 如果没找到任何文件 # 如果没找到任何文件
if len(file_manifest) == 0: 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}") 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' msg = '正常'
# ** gpt request ** # ** gpt request **
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive( gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=i_say, inputs=i_say,
inputs_show_user=i_say_show_user, inputs_show_user=i_say_show_user,
llm_kwargs=llm_kwargs, llm_kwargs=llm_kwargs,
chatbot=chatbot, chatbot=chatbot,
history=[], history=[],
sys_prompt="总结文章。" sys_prompt="总结文章。"
) # 带超时倒计时 ) # 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' msg = '正常'
# ** gpt request ** # ** gpt request **
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive( gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=i_say, inputs=i_say,
inputs_show_user=i_say, inputs_show_user=i_say,
llm_kwargs=llm_kwargs, llm_kwargs=llm_kwargs,
chatbot=chatbot, chatbot=chatbot,
history=history, history=history,
sys_prompt="总结文章。" sys_prompt="总结文章。"
) # 带超时倒计时 ) # 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: try:
import pdfminer, bs4 import pdfminer, bs4
except: except:
report_exception(chatbot, history, report_exception(chatbot, history,
a = f"解析项目: {txt}", 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```。") 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 yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return 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_mmd, file_manifest_mmd, _ = get_files_from_everything(txt, type='.mmd')
success = success or success_mmd success = success or success_mmd
file_manifest += file_manifest_mmd file_manifest += file_manifest_mmd
chatbot.append(["文件列表：", ", ".join([e.split('/')[-1] for e in file_manifest])]); chatbot.append(["文件列表：", ", ".join([e.split('/')[-1] for e in file_manifest])]);
yield from update_ui( chatbot=chatbot, history=history) 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 # 检测输入参数，如没有给定输入参数，直接退出
if not success: if not success:
if txt == "": txt = '空空如也的输入栏' 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: with open(grobid_json_res, 'w+', encoding='utf8') as f:
f.write(json.dumps(article_dict, indent=4, ensure_ascii=False)) f.write(json.dumps(article_dict, indent=4, ensure_ascii=False))
promote_file_to_downloadzone(grobid_json_res, chatbot=chatbot) 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。") 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) 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))) 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） # 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] paper_meta = page_one_fragments[0].split('introduction')[0].split('Introduction')[0].split('INTRODUCTION')[0]
# 单线，获取文章meta信息 # 单线，获取文章meta信息
paper_meta_info = yield from request_gpt_model_in_new_thread_with_ui_alive( 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}", 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) gpt_response_collection_md = copy.deepcopy(gpt_response_collection)
# 整理报告的格式 # 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: 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 " 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: else:
@ -139,18 +139,18 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
# write html # write html
try: try:
ch = construct_html() ch = construct_html()
orig = "" orig = ""
trans = "" trans = ""
gpt_response_collection_html = copy.deepcopy(gpt_response_collection) 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: if i%2==0:
gpt_response_collection_html[i] = paper_fragments[i//2].replace('#', '') gpt_response_collection_html[i] = paper_fragments[i//2].replace('#', '')
else: else:
gpt_response_collection_html[i] = gpt_response_collection_html[i] 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 = ["论文概况", paper_meta_info.replace('# ', '### '), "二、论文翻译", ""]
final.extend(gpt_response_collection_html) final.extend(gpt_response_collection_html)
for i, k in enumerate(final): for i, k in enumerate(final):
if i%2==0: if i%2==0:
orig = k orig = k
if i%2==1: 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) class_name = get_class_name(code)
try: try:
time_str = gen_time_str() time_str = gen_time_str()
subprocess.check_output([sys.executable, '-c', f"from gpt_log.MyAnimation import {class_name}; {class_name}().render()"]) 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') 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() output = e.output.decode()
print(f"Command returned non-zero exit status {e.returncode}: {output}.") print(f"Command returned non-zero exit status {e.returncode}: {output}.")
return f"Evaluating python script failed: {e.output}." return f"Evaluating python script failed: {e.output}."
except: except:
print('generating mp4 failed') print('generating mp4 failed')
return "Generating mp4 failed." return "Generating mp4 failed."
@ -45,7 +45,7 @@ def get_code_block(reply):
import re import re
pattern = r"```([\s\S]*?)```" # regex pattern to match code blocks pattern = r"```([\s\S]*?)```" # regex pattern to match code blocks
matches = re.findall(pattern, reply) # find all code blocks in text 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.") raise RuntimeError("GPT is not generating proper code.")
return matches[0].strip('python') # code block 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） 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 # 清空历史，以免输入溢出
history = [] history = []
# 基本信息：功能、贡献者 # 基本信息：功能、贡献者
chatbot.append([ 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 # 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 dep_ok = yield from inspect_dependency(chatbot=chatbot, history=history) # 刷新界面
if not dep_ok: return if not dep_ok: return
# 输入 # 输入
i_say = f'Generate a animation to show: ' + txt i_say = f'Generate a animation to show: ' + txt
demo = ["Here is some examples of manim", examples_of_manim()] demo = ["Here is some examples of manim", examples_of_manim()]
_, demo = input_clipping(inputs="", history=demo, max_token_limit=2560) _, demo = input_clipping(inputs="", history=demo, max_token_limit=2560)
# 开始 # 开始
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive( 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, history=demo, llm_kwargs=llm_kwargs, chatbot=chatbot, history=demo,
sys_prompt= sys_prompt=
r"Write a animation script with 3blue1brown's manim. "+ 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 ```." r"Answer me with a code block wrapped by ```."
) )
chatbot.append(["开始生成动画", "..."]) chatbot.append(["开始生成动画", "..."])
history.extend([i_say, gpt_say]) history.extend([i_say, gpt_say])
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新 yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
# 将代码转为动画 # 将代码转为动画
code = get_code_block(gpt_say) code = get_code_block(gpt_say)
res = eval_manim(code) 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, 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 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 page_one = str(page_one).encode('utf-8', 'ignore').decode() # avoid reading non-utf8 chars
TOKEN_LIMIT_PER_FRAGMENT = 2500 TOKEN_LIMIT_PER_FRAGMENT = 2500
from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
@ -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']) 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） # 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] 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> ################################## ############################## <第 1 步，从摘要中提取高价值信息，放到history中> ##################################
final_results = [] final_results = []
final_results.append(paper_meta) 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 = 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]} ...." 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 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 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 sys_prompt="Extract the main idea of this section, answer me with Chinese." # 提示
) )
iteration_results.append(gpt_say) iteration_results.append(gpt_say)
last_iteration_result = 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: try:
import fitz import fitz
except: except:
report_exception(chatbot, history, report_exception(chatbot, history,
a = f"解析项目: {txt}", 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```。") 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 yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return 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.")) chatbot.append((i_say_show_user, "[Local Message] waiting gpt response."))
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
if not fast_debug: if not fast_debug:
msg = '正常' msg = '正常'
# ** gpt request ** # ** gpt request **
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive( 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 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: time.sleep(2)
if not fast_debug: if not fast_debug:
res = write_history_to_file(history) res = write_history_to_file(history)
promote_file_to_downloadzone(res, chatbot=chatbot) promote_file_to_downloadzone(res, chatbot=chatbot)
chatbot.append(("完成了吗？", res)) 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 = f"Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words in Chinese: {txt[i]}"
i_say_show_user = f"[{i+1}/{n_txt}] Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words: {txt[i][:200]} ...." i_say_show_user = f"[{i+1}/{n_txt}] Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words: {txt[i][:200]} ...."
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(i_say, i_say_show_user, # i_say=真正给chatgpt的提问， i_say_show_user=给用户看的提问 gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(i_say, i_say_show_user, # i_say=真正给chatgpt的提问， i_say_show_user=给用户看的提问
llm_kwargs, chatbot, llm_kwargs, chatbot,
history=["The main content of the previous section is?", last_iteration_result], # 迭代上一次的结果 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 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) results.append(gpt_say)
last_iteration_result = gpt_say last_iteration_result = gpt_say
############################## <第 2 步，根据整理的摘要选择图表类型> ################################## ############################## <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") 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 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 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 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( gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=i_say, inputs=i_say,
inputs_show_user=i_say_show_user, inputs_show_user=i_say_show_user,
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[], llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
sys_prompt="" sys_prompt=""
) )
if gpt_say in ['1','2','3','4','5','6','7','8','9']: #判断返回是否正确 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( gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=i_say, inputs=i_say,
inputs_show_user=i_say_show_user, inputs_show_user=i_say_show_user,
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[], llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
sys_prompt="" sys_prompt=""
) )
history.append(gpt_say) history.append(gpt_say)
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新 yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
@CatchException @CatchException
def 生成多种Mermaid图表(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port): def 生成多种Mermaid图表(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
""" """
@ -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 # 基本信息：功能、贡献者
chatbot.append([ chatbot.append([
"函数插件功能？", "函数插件功能？",
"根据当前聊天历史或指定的路径文件(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。\ "根据当前聊天历史或指定的路径文件(文件内容优先)绘制多种mermaid图表，将会由对话模型首先判断适合的图表类型，随后绘制图表。\
\n您也可以使用插件参数指定绘制的图表类型,函数插件贡献者: Menghuan1918"]) \n您也可以使用插件参数指定绘制的图表类型,函数插件贡献者: Menghuan1918"])
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
if os.path.exists(txt): #如输入区无内容则直接解析历史记录 if os.path.exists(txt): #如输入区无内容则直接解析历史记录
from crazy_functions.pdf_fns.parse_word import extract_text_from_files 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) 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 != "":
if excption == "word": if excption == "word":
report_exception(chatbot, history, report_exception(chatbot, history,
a = f"解析项目: {txt}", 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。") 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": elif excption == "pdf":
report_exception(chatbot, history, report_exception(chatbot, history,
a = f"解析项目: {txt}", 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```。") 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": elif excption == "word_pip":
report_exception(chatbot, history, report_exception(chatbot, history,
a=f"解析项目: {txt}", 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 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 @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"]) 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 yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return return
# < -------------------预热文本向量化模组--------------- > # < -------------------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..."]) 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 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)) 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 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( gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=prompt, inputs_show_user=txt, inputs=prompt, inputs_show_user=txt,
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[], llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
sys_prompt=system_prompt sys_prompt=system_prompt
) )
history.extend((prompt, gpt_say)) 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', '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', 'Content-Type': 'text/plain',
} }
try: try:
response = requests.get(url, headers=headers, proxies=proxies, timeout=8) response = requests.get(url, headers=headers, proxies=proxies, timeout=8)
if response.encoding == "ISO-8859-1": response.encoding = response.apparent_encoding if response.encoding == "ISO-8859-1": response.encoding = response.apparent_encoding
except: except:
return "无法连接到该网页" return "无法连接到该网页"
soup = BeautifulSoup(response.text, "html.parser") soup = BeautifulSoup(response.text, "html.parser")
for script in soup(["script", "style"]): 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） 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 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！")) "[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 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 > ------------- # ------------- < 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 = 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 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, inputs=i_say,
history=history, history=history,
max_token_limit=model_info[llm_kwargs['llm_model']]['max_token']*3//4 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( 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, history=history, 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。" 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) 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？」 - 「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。 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): 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( gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=txt, inputs_show_user=txt, inputs=txt, inputs_show_user=txt,
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[], llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
sys_prompt=system_prompt sys_prompt=system_prompt
) )
chatbot[-1] = [txt, gpt_say] 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): if is_the_upload_folder(txt):
state.set_state(chatbot=chatbot, key='has_provided_explaination', value=False) 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。" 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): if is_certain or (state.has_provided_explaination):
# 如果意图明确，跳过提示环节 # 如果意图明确，跳过提示环节
state.set_state(chatbot=chatbot, key='has_provided_explaination', value=True) 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, "") analyze_res = run_gpt_fn(inputs, "")
try: try:
user_intention = gpt_json_io.generate_output_auto_repair(analyze_res, run_gpt_fn) 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: except JsonStringError as e:
yield from update_ui_lastest_msg( 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) 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 pass
yield from update_ui_lastest_msg( 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) chatbot=chatbot, history=history, delay=0)
# 用户意图: 修改本项目的配置 # 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, 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 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) 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) 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 = "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( summary_result = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=summary, inputs=summary,
inputs_show_user=summary, inputs_show_user=summary,
llm_kwargs=llm_kwargs, llm_kwargs=llm_kwargs,
chatbot=chatbot, chatbot=chatbot,
history=[i_say, result], # 迭代之前的分析 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) 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'] = '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 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( gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=txt, inputs_show_user=txt, inputs=txt, inputs_show_user=txt,
llm_kwargs=llm_kwargs, chatbot=chatbot, history=history, llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
sys_prompt=system_prompt, sys_prompt=system_prompt,
retry_times_at_unknown_error=0 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 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( gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=txt, inputs_show_user=txt, inputs=txt, inputs_show_user=txt,
llm_kwargs=llm_kwargs, chatbot=chatbot, history=history, llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
sys_prompt=system_prompt, sys_prompt=system_prompt,
retry_times_at_unknown_error=0 retry_times_at_unknown_error=0
) )

6
crazy_functions/语音助手.py
View File

@ -39,7 +39,7 @@ class AsyncGptTask():
try: try:
MAX_TOKEN_ALLO = 2560 MAX_TOKEN_ALLO = 2560
i_say, history = input_clipping(i_say, history, max_token_limit=MAX_TOKEN_ALLO) 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) observe_window=observe_window[index], console_slience=True)
except ConnectionAbortedError as token_exceed_err: except ConnectionAbortedError as token_exceed_err:
print('至少一个线程任务Token溢出而失败', e) 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 yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
self.plugin_wd.feed() 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 # called when some words have finished
self.event_on_result_chg.clear() self.event_on_result_chg.clear()
chatbot[-1] = list(chatbot[-1]) 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 # add gpt task 创建子线程请求gpt，避免线程阻塞
history = chatbot2history(chatbot) history = chatbot2history(chatbot)
self.agt.add_async_gpt_task(self.buffered_sentence, len(chatbot)-1, llm_kwargs, history, system_prompt) self.agt.add_async_gpt_task(self.buffered_sentence, len(chatbot)-1, llm_kwargs, history, system_prompt)
self.buffered_sentence = "" self.buffered_sentence = ""
chatbot.append(["[ 请讲话 ]", "[ 正在等您说完问题 ]"]) 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 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') proxies = get_conf('proxies')
headers = { 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', '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', 'Accept-Language': 'en-US,en;q=0.9,zh-CN;q=0.8,zh;q=0.7',
'Cache-Control':'max-age=0', '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' 'Connection': 'keep-alive'
} }
try: try:
@ -95,7 +95,7 @@ def get_meta_information(url, chatbot, history):
) )
try: paper = next(search.results()) try: paper = next(search.results())
except: paper = None except: paper = None
is_match = paper is not None and string_similar(title, paper.title) > 0.90 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 # 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 import math
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
except: except:
report_exception(chatbot, history, report_exception(chatbot, history,
a = f"解析项目: {txt}", 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```。") 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 yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return 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: 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：" + \ 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。" + \ "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" 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( 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 ]) history.extend([ f"第{batch+1}批", gpt_say ])
meta_paper_info_list = meta_paper_info_list[batchsize:] 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."]) "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' msg = '正常'
yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面 yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
path = write_history_to_file(history) path = write_history_to_file(history)
promote_file_to_downloadzone(path, chatbot=chatbot) 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 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 history = [] # 清空历史，以免输入溢出
chatbot.append(( 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)) "[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 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): 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 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。' 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( 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, history=[], 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 >)。" 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) 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 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。")) 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 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 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_show_user = f'请绘制有关“{txt}”的逻辑关系图。'
i_say = PROMPT.format(subject=txt) i_say = PROMPT.format(subject=txt)
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive( gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=i_say, inputs=i_say,
inputs_show_user=i_say_show_user, inputs_show_user=i_say_show_user,
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[], llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
sys_prompt="" sys_prompt=""
) )
history.append(i_say); history.append(gpt_say) 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) Translate this project to other languages (experimental, please open an issue if there is any bug)
Usage: Usage:
1. modify config.py, set your LLM_MODEL and API_KEY(s) to provide access to OPENAI (or any other LLM model provider) 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 ↓) 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 #." 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. 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) (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\*` 5. Find the translated program in `multi-language\English\*`
P.S. P.S.
- The translation mapping will be stored in `docs/translation_xxxx.json`, you can revised mistaken translation there. - 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 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 - If there is any translation error in `docs/translation_xxxx.json`, please open a Pull Request
- Welcome any Pull Request, regardless of language - 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): 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. 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. 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. 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): def read_map_from_json(language):
if os.path.exists(f'docs/translate_{language.lower()}.json'): 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 = json.load(f)
res = {k:v for k, v in res.items() if v is not None and contains_chinese(k)} res = {k:v for k, v in res.items() if v is not None and contains_chinese(k)}
return res return res
@ -168,7 +168,7 @@ def advanced_split(splitted_string, spliter, include_spliter=False):
splitted[i] += spliter splitted[i] += spliter
splitted[i] = splitted[i].strip() splitted[i] = splitted[i].strip()
for i in reversed(range(len(splitted))): for i in reversed(range(len(splitted))):
if not contains_chinese(splitted[i]): if not contains_chinese(splitted[i]):
splitted.pop(i) splitted.pop(i)
splitted_string_tmp.extend(splitted) splitted_string_tmp.extend(splitted)
else: else:
@ -183,12 +183,12 @@ def trans(word_to_translate, language, special=False):
if len(word_to_translate) == 0: return {} 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 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 from toolbox import get_conf, ChatBotWithCookies, load_chat_cookies
cookies = load_chat_cookies() cookies = load_chat_cookies()
llm_kwargs = { llm_kwargs = {
'api_key': cookies['api_key'], 'api_key': cookies['api_key'],
'llm_model': cookies['llm_model'], 'llm_model': cookies['llm_model'],
'top_p':1.0, 'top_p':1.0,
'max_length': None, 'max_length': None,
'temperature':0.4, '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] 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) chatbot = ChatBotWithCookies(llm_kwargs)
gpt_say_generator = request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency( gpt_say_generator = request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
inputs_array, inputs_array,
inputs_show_user_array, inputs_show_user_array,
llm_kwargs, llm_kwargs,
chatbot, chatbot,
history_array, history_array,
sys_prompt_array, sys_prompt_array,
) )
while True: while True:
try: try:
@ -224,7 +224,7 @@ def trans(word_to_translate, language, special=False):
try: try:
res_before_trans = eval(result[i-1]) res_before_trans = eval(result[i-1])
res_after_trans = eval(result[i]) 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 raise RuntimeError
for a,b in zip(res_before_trans, res_after_trans): for a,b in zip(res_before_trans, res_after_trans):
translated_result[a] = b translated_result[a] = b
@ -246,12 +246,12 @@ def trans_json(word_to_translate, language, special=False):
if len(word_to_translate) == 0: return {} 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 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 from toolbox import get_conf, ChatBotWithCookies, load_chat_cookies
cookies = load_chat_cookies() cookies = load_chat_cookies()
llm_kwargs = { llm_kwargs = {
'api_key': cookies['api_key'], 'api_key': cookies['api_key'],
'llm_model': cookies['llm_model'], 'llm_model': cookies['llm_model'],
'top_p':1.0, 'top_p':1.0,
'max_length': None, 'max_length': None,
'temperature':0.4, '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) 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 = [{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_array = [ json.dumps(i, ensure_ascii=False) for i in inputs_array]
inputs_show_user_array = inputs_array inputs_show_user_array = inputs_array
history_array = [[] for _ in inputs_array] history_array = [[] for _ in inputs_array]
sys_prompt_array = [TransPrompt for _ in inputs_array] sys_prompt_array = [TransPrompt for _ in inputs_array]
chatbot = ChatBotWithCookies(llm_kwargs) chatbot = ChatBotWithCookies(llm_kwargs)
gpt_say_generator = request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency( gpt_say_generator = request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
inputs_array, inputs_array,
inputs_show_user_array, inputs_show_user_array,
llm_kwargs, llm_kwargs,
chatbot, chatbot,
history_array, history_array,
sys_prompt_array, sys_prompt_array,
) )
while True: while True:
try: try:
@ -336,7 +336,7 @@ def step_1_core_key_translate():
cached_translation = read_map_from_json(language=LANG_STD) cached_translation = read_map_from_json(language=LANG_STD)
cached_translation_keys = list(cached_translation.keys()) cached_translation_keys = list(cached_translation.keys())
for d in chinese_core_keys_norepeat: 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) need_translate.append(d)
if CACHE_ONLY: if CACHE_ONLY:
@ -379,7 +379,7 @@ def step_1_core_key_translate():
# read again # read again
with open(file_path, 'r', encoding='utf-8') as f: with open(file_path, 'r', encoding='utf-8') as f:
content = f.read() content = f.read()
for k, v in chinese_core_keys_norepeat_mapping.items(): for k, v in chinese_core_keys_norepeat_mapping.items():
content = content.replace(k, v) content = content.replace(k, v)
@ -390,7 +390,7 @@ def step_1_core_key_translate():
def step_2_core_key_translate(): def step_2_core_key_translate():
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= # =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
# step2 # step2
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= # =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
def load_string(strings, string_input): 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) 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 for j, s in enumerate(splitted_string): # .com
if '.com' in s: continue if '.com' in s: continue
@ -457,7 +457,7 @@ def step_2_core_key_translate():
comments_arr = [] comments_arr = []
for code_sp in content.splitlines(): for code_sp in content.splitlines():
comments = re.findall(r'#.*$', code_sp) comments = re.findall(r'#.*$', code_sp)
for comment in comments: for comment in comments:
load_string(strings=comments_arr, string_input=comment) load_string(strings=comments_arr, string_input=comment)
string_literals.extend(comments_arr) 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 = read_map_from_json(language=LANG)
cached_translation_keys = list(cached_translation.keys()) cached_translation_keys = list(cached_translation.keys())
for d in chinese_literal_names_norepeat: 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) need_translate.append(d)
if CACHE_ONLY: if CACHE_ONLY:
@ -504,18 +504,18 @@ def step_2_core_key_translate():
# read again # read again
with open(file_path, 'r', encoding='utf-8') as f: with open(file_path, 'r', encoding='utf-8') as f:
content = f.read() content = f.read()
for k, v in cached_translation.items(): for k, v in cached_translation.items():
if v is None: continue if v is None: continue
if '"' in v: if '"' in v:
v = v.replace('"', "`") v = v.replace('"', "`")
if '\'' in v: if '\'' in v:
v = v.replace('\'', "`") v = v.replace('\'', "`")
content = content.replace(k, v) content = content.replace(k, v)
with open(file_path, 'w', encoding='utf-8') as f: with open(file_path, 'w', encoding='utf-8') as f:
f.write(content) f.write(content)
if file.strip('.py') in cached_translation: if file.strip('.py') in cached_translation:
file_new = cached_translation[file.strip('.py')] + '.py' file_new = cached_translation[file.strip('.py')] + '.py'
file_path_new = os.path.join(root, file_new) 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 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(...) 2. predict_no_ui_long_connection(...)
""" """
import tiktoken, copy import tiktoken, copy, re
from functools import lru_cache from functools import lru_cache
from concurrent.futures import ThreadPoolExecutor 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_no_ui_long_connection as chatgpt_noui
from .bridge_chatgpt import predict as chatgpt_ui 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" openai_endpoint = "https://api.openai.com/v1/chat/completions"
api2d_endpoint = "https://openai.api2d.net/v1/chat/completions" api2d_endpoint = "https://openai.api2d.net/v1/chat/completions"
newbing_endpoint = "wss://sydney.bing.com/sydney/ChatHub" 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 += '/' if not AZURE_ENDPOINT.endswith('/'): AZURE_ENDPOINT += '/'
azure_endpoint = AZURE_ENDPOINT + f'openai/deployments/{AZURE_ENGINE}/chat/completions?api-version=2023-05-15' azure_endpoint = AZURE_ENDPOINT + f'openai/deployments/{AZURE_ENGINE}/chat/completions?api-version=2023-05-15'
# 兼容旧版的配置 # 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 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 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 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 # 获取tokenizer
tokenizer_gpt35 = LazyloadTiktoken("gpt-3.5-turbo") tokenizer_gpt35 = LazyloadTiktoken("gpt-3.5-turbo")
@ -291,7 +295,7 @@ model_info = {
"gemini-pro": { "gemini-pro": {
"fn_with_ui": genai_ui, "fn_with_ui": genai_ui,
"fn_without_ui": genai_noui, "fn_without_ui": genai_noui,
"endpoint": None, "endpoint": gemini_endpoint,
"max_token": 1024 * 32, "max_token": 1024 * 32,
"tokenizer": tokenizer_gpt35, "tokenizer": tokenizer_gpt35,
"token_cnt": get_token_num_gpt35, "token_cnt": get_token_num_gpt35,
@ -299,7 +303,7 @@ model_info = {
"gemini-pro-vision": { "gemini-pro-vision": {
"fn_with_ui": genai_ui, "fn_with_ui": genai_ui,
"fn_without_ui": genai_noui, "fn_without_ui": genai_noui,
"endpoint": None, "endpoint": gemini_endpoint,
"max_token": 1024 * 32, "max_token": 1024 * 32,
"tokenizer": tokenizer_gpt35, "tokenizer": tokenizer_gpt35,
"token_cnt": get_token_num_gpt35, "token_cnt": get_token_num_gpt35,
@ -349,25 +353,57 @@ for model in AVAIL_LLM_MODELS:
model_info.update({model: mi}) model_info.update({model: mi})
# -=-=-=-=-=-=- 以下部分是新加入的模型，可能附带额外依赖 -=-=-=-=-=-=- # -=-=-=-=-=-=- 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_no_ui_long_connection as claude_noui
from .bridge_claude import predict as claude_ui from .bridge_claude import predict as claude_ui
model_info.update({ model_info.update({
"claude-1-100k": { "claude-instant-1.2": {
"fn_with_ui": claude_ui, "fn_with_ui": claude_ui,
"fn_without_ui": claude_noui, "fn_without_ui": claude_noui,
"endpoint": None, "endpoint": claude_endpoint,
"max_token": 8196, "max_token": 100000,
"tokenizer": tokenizer_gpt35, "tokenizer": tokenizer_gpt35,
"token_cnt": get_token_num_gpt35, "token_cnt": get_token_num_gpt35,
}, },
}) })
model_info.update({ model_info.update({
"claude-2": { "claude-2.0": {
"fn_with_ui": claude_ui, "fn_with_ui": claude_ui,
"fn_without_ui": claude_noui, "fn_without_ui": claude_noui,
"endpoint": None, "endpoint": claude_endpoint,
"max_token": 8196, "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, "tokenizer": tokenizer_gpt35,
"token_cnt": get_token_num_gpt35, "token_cnt": get_token_num_gpt35,
}, },
@ -675,22 +711,28 @@ if "deepseekcoder" in AVAIL_LLM_MODELS: # deepseekcoder
}) })
except: except:
print(trimmed_format_exc()) print(trimmed_format_exc())
# if "skylark" in AVAIL_LLM_MODELS: # -=-=-=-=-=-=- one-api 对齐支持 -=-=-=-=-=-=-
# try: for model in [m for m in AVAIL_LLM_MODELS if m.startswith("one-api-")]:
# from .bridge_skylark2 import predict_no_ui_long_connection as skylark_noui # 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)"]
# from .bridge_skylark2 import predict as skylark_ui # 其中
# model_info.update({ # "one-api-" 是前缀（必要）
# "skylark": { # "mixtral-8x7b" 是模型名（必要）
# "fn_with_ui": skylark_ui, # "(max_token=6666)" 是配置（非必要）
# "fn_without_ui": skylark_noui, try:
# "endpoint": None, _, max_token_tmp = read_one_api_model_name(model)
# "max_token": 4096, except:
# "tokenizer": tokenizer_gpt35, print(f"one-api模型 {model} 的 max_token 配置不是整数，请检查配置文件。")
# "token_cnt": get_token_num_gpt35, continue
# } model_info.update({
# }) model: {
# except: "fn_with_ui": chatgpt_ui,
# print(trimmed_format_exc()) "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 --> # <-- 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) query, max_length, top_p, temperature, history = adaptor(kwargs)
for response, history in self._model.stream_chat(self._tokenizer, for response, history in self._model.stream_chat(self._tokenizer,
query, query,
history, history,
max_length=max_length, max_length=max_length,
top_p=top_p, top_p=top_p,
temperature=temperature, temperature=temperature,
): ):
yield response yield response
def try_to_import_special_deps(self, **kwargs): def try_to_import_special_deps(self, **kwargs):
# import something that will raise error if the user does not install requirement_*.txt # import something that will raise error if the user does not install requirement_*.txt
# 🏃‍♂️🏃‍♂️🏃‍♂️ 主进程执行 # 🏃‍♂️🏃‍♂️🏃‍♂️ 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) query, max_length, top_p, temperature, history = adaptor(kwargs)
for response, history in self._model.stream_chat(self._tokenizer, for response, history in self._model.stream_chat(self._tokenizer,
query, query,
history, history,
max_length=max_length, max_length=max_length,
top_p=top_p, top_p=top_p,
temperature=temperature, temperature=temperature,
): ):
yield response yield response
def try_to_import_special_deps(self, **kwargs): def try_to_import_special_deps(self, **kwargs):
# import something that will raise error if the user does not install requirement_*.txt # import something that will raise error if the user does not install requirement_*.txt
# 🏃‍♂️🏃‍♂️🏃‍♂️ 主进程执行 # 🏃‍♂️🏃‍♂️🏃‍♂️ 主进程执行

14
request_llms/bridge_chatglmft.py
View File

@ -37,7 +37,7 @@ class GetGLMFTHandle(Process):
self.check_dependency() self.check_dependency()
self.start() self.start()
self.threadLock = threading.Lock() self.threadLock = threading.Lock()
def check_dependency(self): def check_dependency(self):
try: try:
import sentencepiece import sentencepiece
@ -101,7 +101,7 @@ class GetGLMFTHandle(Process):
break break
except Exception as e: except Exception as e:
retry += 1 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。') 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！") 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): for response, history in self.chatglmft_model.stream_chat(self.chatglmft_tokenizer, **kwargs):
self.child.send(response) self.child.send(response)
# # 中途接收可能的终止指令（如果有的话） # # 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() # command = self.child.recv()
# if command == '[Terminate]': break # if command == '[Terminate]': break
except: except:
@ -133,7 +133,7 @@ class GetGLMFTHandle(Process):
else: else:
break break
self.threadLock.release() self.threadLock.release()
global glmft_handle global glmft_handle
glmft_handle = None glmft_handle = None
################################################################################# #################################################################################
@ -146,7 +146,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
if glmft_handle is None: if glmft_handle is None:
glmft_handle = GetGLMFTHandle() glmft_handle = GetGLMFTHandle()
if len(observe_window) >= 1: observe_window[0] = load_message + "\n\n" + glmft_handle.info 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 error = glmft_handle.info
glmft_handle = None glmft_handle = None
raise RuntimeError(error) raise RuntimeError(error)
@ -161,7 +161,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
response = "" 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']): 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) >= 1: observe_window[0] = response
if len(observe_window) >= 2: if len(observe_window) >= 2:
if (time.time()-observe_window[1]) > watch_dog_patience: if (time.time()-observe_window[1]) > watch_dog_patience:
raise RuntimeError("程序终止。") raise RuntimeError("程序终止。")
return response return response
@ -180,7 +180,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
glmft_handle = GetGLMFTHandle() glmft_handle = GetGLMFTHandle()
chatbot[-1] = (inputs, load_message + "\n\n" + glmft_handle.info) chatbot[-1] = (inputs, load_message + "\n\n" + glmft_handle.info)
yield from update_ui(chatbot=chatbot, history=[]) yield from update_ui(chatbot=chatbot, history=[])
if not glmft_handle.success: if not glmft_handle.success:
glmft_handle = None glmft_handle = None
return return

2
request_llms/bridge_chatglmonnx.py
View File

@ -59,7 +59,7 @@ class GetONNXGLMHandle(LocalLLMHandle):
temperature=temperature, temperature=temperature,
): ):
yield answer yield answer
def try_to_import_special_deps(self, **kwargs): def try_to_import_special_deps(self, **kwargs):
# import something that will raise error if the user does not install requirement_*.txt # import something that will raise error if the user does not install requirement_*.txt
# 🏃‍♂️🏃‍♂️🏃‍♂️ 子进程执行 # 🏃‍♂️🏃‍♂️🏃‍♂️ 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 # 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 # 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 = \ proxies, TIMEOUT_SECONDS, MAX_RETRY, API_ORG, AZURE_CFG_ARRAY = \
get_conf('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'] model = llm_kwargs['llm_model']
if llm_kwargs['llm_model'].startswith('api2d-'): if llm_kwargs['llm_model'].startswith('api2d-'):
model = llm_kwargs['llm_model'][len('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 if model == "gpt-3.5-random": # 随机选择, 绕过openai访问频率限制
model = random.choice([ 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): 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 # 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 from request_llms.key_manager import ApiKeyManager
api_key = ApiKeyManager().add_key_to_blacklist(key) api_key = ApiKeyManager().add_key_to_blacklist(key)
@ -51,13 +51,13 @@ def decode_chunk(chunk):
choice_valid = False choice_valid = False
has_content = False has_content = False
has_role = False has_role = False
try: try:
chunkjson = json.loads(chunk_decoded[6:]) chunkjson = json.loads(chunk_decoded[6:])
has_choices = 'choices' in chunkjson has_choices = 'choices' in chunkjson
if has_choices: choice_valid = (len(chunkjson['choices']) > 0) 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_content = "content" in chunkjson['choices'][0]["delta"]
if has_choices and choice_valid: has_role = "role" in chunkjson['choices'][0]["delta"] if has_choices and choice_valid: has_role = "role" in chunkjson['choices'][0]["delta"]
except: except:
pass pass
return chunk_decoded, chunkjson, has_choices, choice_valid, has_content, has_role 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 raw_input = inputs
logging.info(f'[raw_input] {raw_input}') 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: for image_path in image_paths:
inputs = inputs + f'<br/><br/><div align="center"><img src="file={os.path.abspath(image_path)}"></div>' inputs = inputs + f'<br/><br/><div align="center"><img src="file={os.path.abspath(image_path)}"></div>'
return inputs 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。") 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 yield from update_ui(chatbot=chatbot, history=history, msg="api-key不满足要求") # 刷新界面
return return
# 检查endpoint是否合法 # 检查endpoint是否合法
try: try:
from .bridge_all import model_info 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 if retry > MAX_RETRY: raise TimeoutError
gpt_replying_buffer = "" gpt_replying_buffer = ""
is_head_of_the_stream = True is_head_of_the_stream = True
if stream: if stream:
stream_response = response.iter_lines() stream_response = response.iter_lines()
@ -162,21 +162,21 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
chunk_decoded = chunk.decode() chunk_decoded = chunk.decode()
error_msg = chunk_decoded 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 # 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。") 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 break
# 其他情况，直接返回报错 # 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) 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 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 return
# 提前读取一些信息 （用于判断异常） # 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) 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): 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 # 数据流的第一帧不携带content
is_head_of_the_stream = False; continue is_head_of_the_stream = False; continue
if chunk: if chunk:
try: try:
if has_choices and not choice_valid: 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' openai_website = ' 请登录OpenAI查看详情 https://platform.openai.com/signup'
if "reduce the length" in error_msg: 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 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 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.)") 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: 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}" "Authorization": f"Bearer {api_key}"
} }
if API_ORG.startswith('org-'): headers.update({"OpenAI-Organization": API_ORG}) 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}) headers.update({"api-key": api_key})
if llm_kwargs['llm_model'] in AZURE_CFG_ARRAY.keys(): if llm_kwargs['llm_model'] in AZURE_CFG_ARRAY.keys():
azure_api_key_unshared = AZURE_CFG_ARRAY[llm_kwargs['llm_model']]["AZURE_API_KEY"] 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 = { payload = {
"model": model, "model": model,
"messages": messages, "messages": messages,
"temperature": llm_kwargs['temperature'], # 1.0, "temperature": llm_kwargs['temperature'], # 1.0,
"top_p": llm_kwargs['top_p'], # 1.0, "top_p": llm_kwargs['top_p'], # 1.0,
"n": 1, "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 = '' result = ''
while True: while True:
try: chunk = next(stream_response).decode() try: chunk = next(stream_response).decode()
except StopIteration: except StopIteration:
break break
except requests.exceptions.ConnectionError: except requests.exceptions.ConnectionError:
chunk = next(stream_response).decode() # 失败了，重试一次？再失败就没办法了。 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 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() error_msg = get_full_error(chunk.encode('utf8'), stream_response).decode()
if "reduce the length" in error_msg: if "reduce the length" in error_msg:
raise ConnectionAbortedError("OpenAI拒绝了请求:" + error_msg) raise ConnectionAbortedError("OpenAI拒绝了请求:" + error_msg)
@ -89,14 +89,14 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
delta = json_data["delta"] delta = json_data["delta"]
if len(delta) == 0: break if len(delta) == 0: break
if "role" in delta: continue if "role" in delta: continue
if "content" in delta: if "content" in delta:
result += delta["content"] result += delta["content"]
if not console_slience: print(delta["content"], end='') 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 # 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"] 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 # 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: if (time.time()-observe_window[1]) > watch_dog_patience:
raise RuntimeError("用户取消了程序。") raise RuntimeError("用户取消了程序。")
else: raise RuntimeError("意外Json结构："+delta) 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。") 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 yield from update_ui(chatbot=chatbot, history=history, msg="api-key不满足要求") # 刷新界面
return return
history.append(inputs); history.append("") history.append(inputs); history.append("")
retry = 0 retry = 0
@ -151,7 +151,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
if retry > MAX_RETRY: raise TimeoutError if retry > MAX_RETRY: raise TimeoutError
gpt_replying_buffer = "" gpt_replying_buffer = ""
is_head_of_the_stream = True is_head_of_the_stream = True
if stream: if stream:
stream_response = response.iter_lines() 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) 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 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 return
# print(chunk.decode()[6:]) # print(chunk.decode()[6:])
if is_head_of_the_stream and (r'"object":"error"' not in chunk.decode()): 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 # 数据流的第一帧不携带content
is_head_of_the_stream = False; continue is_head_of_the_stream = False; continue
if chunk: if chunk:
try: try:
chunk_decoded = chunk.decode() 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' openai_website = ' 请登录OpenAI查看详情 https://platform.openai.com/signup'
if "reduce the length" in error_msg: 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 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 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.)") 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 # history = [] # 清除历史
@ -264,7 +264,7 @@ def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
payload = { payload = {
"model": llm_kwargs['llm_model'].strip('api2d-'), "model": llm_kwargs['llm_model'].strip('api2d-'),
"messages": messages, "messages": messages,
"temperature": llm_kwargs['temperature'], # 1.0, "temperature": llm_kwargs['temperature'], # 1.0,
"top_p": llm_kwargs['top_p'], # 1.0, "top_p": llm_kwargs['top_p'], # 1.0,
"n": 1, "n": 1,

153
request_llms/bridge_claude.py
View File

@ -11,13 +11,12 @@
""" """
import os import os
import json
import time import time
import gradio as gr
import logging
import traceback import traceback
import requests from toolbox import get_conf, update_ui, trimmed_format_exc, encode_image, every_image_file_in_path
import importlib
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 # 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 # 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 from anthropic import Anthropic
watch_dog_patience = 5 # 看门狗的耐心, 设置5秒即可 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 retry = 0
if len(ANTHROPIC_API_KEY) == 0: if len(ANTHROPIC_API_KEY) == 0:
raise RuntimeError("没有设置ANTHROPIC_API_KEY选项") 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: try:
# make a POST request to the API endpoint, stream=False # make a POST request to the API endpoint, stream=False
from .bridge_all import model_info 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'] # endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
# with ProxyNetworkActivate() # with ProxyNetworkActivate()
stream = anthropic.completions.create( stream = anthropic.messages.create(
prompt=prompt, messages=message,
max_tokens_to_sample=4096, # The maximum number of tokens to generate before stopping. max_tokens=4096, # The maximum number of tokens to generate before stopping.
model=llm_kwargs['llm_model'], model=llm_kwargs['llm_model'],
stream=True, stream=True,
temperature = llm_kwargs['temperature'] temperature = llm_kwargs['temperature'],
system=sys_prompt
) )
break break
except Exception as e: 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 retry > MAX_RETRY: raise TimeoutError
if MAX_RETRY!=0: print(f'请求超时，正在重试 ({retry}/{MAX_RETRY}) ……') if MAX_RETRY!=0: print(f'请求超时，正在重试 ({retry}/{MAX_RETRY}) ……')
result = '' result = ''
try: try:
for completion in stream: for completion in stream:
result += completion.completion if completion.type == "message_start" or completion.type == "content_block_start":
if not console_slience: print(completion.completion, end='') continue
if observe_window is not None: 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 # 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 # 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: if (time.time()-observe_window[1]) > watch_dog_patience:
raise RuntimeError("用户取消了程序。") raise RuntimeError("用户取消了程序。")
except Exception as e: except Exception as e:
@ -98,6 +103,10 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
return result 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): 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 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 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 from anthropic import Anthropic
if len(ANTHROPIC_API_KEY) == 0: if len(ANTHROPIC_API_KEY) == 0:
chatbot.append((inputs, "没有设置ANTHROPIC_API_KEY")) 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 yield from update_ui(chatbot=chatbot, history=history, msg="等待响应") # 刷新界面
return return
if additional_fn is not None: if additional_fn is not None:
from core_functional import handle_core_functionality from core_functional import handle_core_functionality
inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot) inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
raw_input = inputs have_recent_file, image_paths = every_image_file_in_path(chatbot)
logging.info(f'[raw_input] {raw_input}') if len(image_paths) > 20:
chatbot.append((inputs, "")) 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") # 刷新界面 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: 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: 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。") 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 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: try:
# make a POST request to the API endpoint, stream=True # make a POST request to the API endpoint, stream=True
from .bridge_all import model_info 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'] # endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
# with ProxyNetworkActivate() # with ProxyNetworkActivate()
stream = anthropic.completions.create( stream = anthropic.messages.create(
prompt=prompt, messages=message,
max_tokens_to_sample=4096, # The maximum number of tokens to generate before stopping. max_tokens=4096, # The maximum number of tokens to generate before stopping.
model=llm_kwargs['llm_model'], model=llm_kwargs['llm_model'],
stream=True, stream=True,
temperature = llm_kwargs['temperature'] temperature = llm_kwargs['temperature'],
system=system_prompt
) )
break break
except: except:
retry += 1 retry += 1
@ -158,10 +178,14 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
if retry > MAX_RETRY: raise TimeoutError if retry > MAX_RETRY: raise TimeoutError
gpt_replying_buffer = "" gpt_replying_buffer = ""
for completion in stream: 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: try:
gpt_replying_buffer = gpt_replying_buffer + completion.completion gpt_replying_buffer = gpt_replying_buffer + completion.delta.text
history[-1] = gpt_replying_buffer history[-1] = gpt_replying_buffer
chatbot[-1] = (history[-2], history[-1]) chatbot[-1] = (history[-2], history[-1])
yield from update_ui(chatbot=chatbot, history=history, msg='正常') # 刷新界面 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}") 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 yield from update_ui(chatbot=chatbot, history=history, msg="Json异常" + tb_str) # 刷新界面
return return
def generate_payload(inputs, llm_kwargs, history, stream, image_paths):
# 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):
""" """
整合所有信息，选择LLM模型，生成http请求，为发送请求做准备 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 conversation_cnt = len(history) // 2
messages = [{"role": "system", "content": system_prompt}] messages = []
if conversation_cnt: if conversation_cnt:
for index in range(0, 2*conversation_cnt, 2): for index in range(0, 2*conversation_cnt, 2):
what_i_have_asked = {} what_i_have_asked = {}
what_i_have_asked["role"] = "user" 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 = {}
what_gpt_answer["role"] = "assistant" what_gpt_answer["role"] = "assistant"
what_gpt_answer["content"] = history[index+1] what_gpt_answer["content"] = [{"type": "text", "text": history[index+1]}]
if what_i_have_asked["content"] != "": if what_i_have_asked["content"][0]["text"] != "":
if what_gpt_answer["content"] == "": continue if what_i_have_asked["content"][0]["text"] == "": continue
if what_gpt_answer["content"] == timeout_bot_msg: continue if what_i_have_asked["content"][0]["text"] == timeout_bot_msg: continue
messages.append(what_i_have_asked) messages.append(what_i_have_asked)
messages.append(what_gpt_answer) messages.append(what_gpt_answer)
else: else:
messages[-1]['content'] = what_gpt_answer['content'] messages[-1]['content'][0]['text'] = what_gpt_answer['content'][0]['text']
what_i_ask_now = {} if any([llm_kwargs['llm_model'] == model for model in Claude_3_Models]) and image_paths:
what_i_ask_now["role"] = "user" base64_images = []
what_i_ask_now["content"] = inputs 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) messages.append(what_i_ask_now)
prompt = convert_messages_to_prompt(messages) return messages
return prompt

6
request_llms/bridge_deepseekcoder.py
View File

@ -88,7 +88,7 @@ class GetCoderLMHandle(LocalLLMHandle):
temperature = kwargs['temperature'] temperature = kwargs['temperature']
history = kwargs['history'] history = kwargs['history']
return query, max_length, top_p, temperature, history return query, max_length, top_p, temperature, history
query, max_length, top_p, temperature, history = adaptor(kwargs) query, max_length, top_p, temperature, history = adaptor(kwargs)
history.append({ 'role': 'user', 'content': query}) history.append({ 'role': 'user', 'content': query})
messages = history messages = history
@ -97,14 +97,14 @@ class GetCoderLMHandle(LocalLLMHandle):
inputs = inputs[:, -max_length:] inputs = inputs[:, -max_length:]
inputs = inputs.to(self._model.device) inputs = inputs.to(self._model.device)
generation_kwargs = dict( generation_kwargs = dict(
inputs=inputs, inputs=inputs,
max_new_tokens=max_length, max_new_tokens=max_length,
do_sample=False, do_sample=False,
top_p=top_p, top_p=top_p,
streamer = self._streamer, streamer = self._streamer,
top_k=50, top_k=50,
temperature=temperature, temperature=temperature,
num_return_sequences=1, num_return_sequences=1,
eos_token_id=32021, eos_token_id=32021,
) )
thread = Thread(target=self._model.generate, kwargs=generation_kwargs, daemon=True) 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") == "": if get_conf("GEMINI_API_KEY") == "":
raise ValueError(f"请配置 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 watch_dog_patience = 5 # 看门狗的耐心, 设置5秒即可
gpt_replying_buffer = '' gpt_replying_buffer = ''
stream_response = genai.generate_chat(inputs, llm_kwargs, history, sys_prompt) 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")) 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 yield from update_ui(chatbot=chatbot, history=history, msg="等待图片") # 刷新界面
return return
def make_media_input(inputs, image_paths): def make_media_input(inputs, image_paths):
for image_path in image_paths: for image_path in image_paths:
inputs = inputs + f'<br/><br/><div align="center"><img src="file={os.path.abspath(image_path)}"></div>' inputs = inputs + f'<br/><br/><div align="center"><img src="file={os.path.abspath(image_path)}"></div>'
return inputs return inputs
@ -70,7 +70,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
chatbot.append((inputs, "")) chatbot.append((inputs, ""))
yield from update_ui(chatbot=chatbot, history=history) yield from update_ui(chatbot=chatbot, history=history)
genai = GoogleChatInit() genai = GoogleChatInit(llm_kwargs)
retry = 0 retry = 0
while True: while True:
try: try:

6
request_llms/bridge_internlm.py
View File

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

10
request_llms/bridge_jittorllms_llama.py
View File

@ -20,7 +20,7 @@ class GetGLMHandle(Process):
self.check_dependency() self.check_dependency()
self.start() self.start()
self.threadLock = threading.Lock() self.threadLock = threading.Lock()
def check_dependency(self): def check_dependency(self):
try: try:
import pandas import pandas
@ -102,7 +102,7 @@ class GetGLMHandle(Process):
else: else:
break break
self.threadLock.release() self.threadLock.release()
global llama_glm_handle global llama_glm_handle
llama_glm_handle = None 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: if llama_glm_handle is None:
llama_glm_handle = GetGLMHandle() llama_glm_handle = GetGLMHandle()
if len(observe_window) >= 1: observe_window[0] = load_message + "\n\n" + llama_glm_handle.info 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 error = llama_glm_handle.info
llama_glm_handle = None llama_glm_handle = None
raise RuntimeError(error) 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']): 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) print(response)
if len(observe_window) >= 1: observe_window[0] = 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: if (time.time()-observe_window[1]) > watch_dog_patience:
raise RuntimeError("程序终止。") raise RuntimeError("程序终止。")
return response return response
@ -149,7 +149,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
llama_glm_handle = GetGLMHandle() llama_glm_handle = GetGLMHandle()
chatbot[-1] = (inputs, load_message + "\n\n" + llama_glm_handle.info) chatbot[-1] = (inputs, load_message + "\n\n" + llama_glm_handle.info)
yield from update_ui(chatbot=chatbot, history=[]) yield from update_ui(chatbot=chatbot, history=[])
if not llama_glm_handle.success: if not llama_glm_handle.success:
llama_glm_handle = None llama_glm_handle = None
return return

10
request_llms/bridge_jittorllms_pangualpha.py
View File

@ -20,7 +20,7 @@ class GetGLMHandle(Process):
self.check_dependency() self.check_dependency()
self.start() self.start()
self.threadLock = threading.Lock() self.threadLock = threading.Lock()
def check_dependency(self): def check_dependency(self):
try: try:
import pandas import pandas
@ -102,7 +102,7 @@ class GetGLMHandle(Process):
else: else:
break break
self.threadLock.release() self.threadLock.release()
global pangu_glm_handle global pangu_glm_handle
pangu_glm_handle = None 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: if pangu_glm_handle is None:
pangu_glm_handle = GetGLMHandle() pangu_glm_handle = GetGLMHandle()
if len(observe_window) >= 1: observe_window[0] = load_message + "\n\n" + pangu_glm_handle.info 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 error = pangu_glm_handle.info
pangu_glm_handle = None pangu_glm_handle = None
raise RuntimeError(error) 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']): 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) print(response)
if len(observe_window) >= 1: observe_window[0] = 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: if (time.time()-observe_window[1]) > watch_dog_patience:
raise RuntimeError("程序终止。") raise RuntimeError("程序终止。")
return response return response
@ -149,7 +149,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
pangu_glm_handle = GetGLMHandle() pangu_glm_handle = GetGLMHandle()
chatbot[-1] = (inputs, load_message + "\n\n" + pangu_glm_handle.info) chatbot[-1] = (inputs, load_message + "\n\n" + pangu_glm_handle.info)
yield from update_ui(chatbot=chatbot, history=[]) yield from update_ui(chatbot=chatbot, history=[])
if not pangu_glm_handle.success: if not pangu_glm_handle.success:
pangu_glm_handle = None pangu_glm_handle = None
return return

10
request_llms/bridge_jittorllms_rwkv.py
View File

@ -20,7 +20,7 @@ class GetGLMHandle(Process):
self.check_dependency() self.check_dependency()
self.start() self.start()
self.threadLock = threading.Lock() self.threadLock = threading.Lock()
def check_dependency(self): def check_dependency(self):
try: try:
import pandas import pandas
@ -102,7 +102,7 @@ class GetGLMHandle(Process):
else: else:
break break
self.threadLock.release() self.threadLock.release()
global rwkv_glm_handle global rwkv_glm_handle
rwkv_glm_handle = None 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: if rwkv_glm_handle is None:
rwkv_glm_handle = GetGLMHandle() rwkv_glm_handle = GetGLMHandle()
if len(observe_window) >= 1: observe_window[0] = load_message + "\n\n" + rwkv_glm_handle.info 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 error = rwkv_glm_handle.info
rwkv_glm_handle = None rwkv_glm_handle = None
raise RuntimeError(error) 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']): 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) print(response)
if len(observe_window) >= 1: observe_window[0] = 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: if (time.time()-observe_window[1]) > watch_dog_patience:
raise RuntimeError("程序终止。") raise RuntimeError("程序终止。")
return response return response
@ -149,7 +149,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
rwkv_glm_handle = GetGLMHandle() rwkv_glm_handle = GetGLMHandle()
chatbot[-1] = (inputs, load_message + "\n\n" + rwkv_glm_handle.info) chatbot[-1] = (inputs, load_message + "\n\n" + rwkv_glm_handle.info)
yield from update_ui(chatbot=chatbot, history=[]) yield from update_ui(chatbot=chatbot, history=[])
if not rwkv_glm_handle.success: if not rwkv_glm_handle.success:
rwkv_glm_handle = None rwkv_glm_handle = None
return return

8
request_llms/bridge_llama2.py
View File

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

32
request_llms/bridge_moss.py
View File

@ -18,7 +18,7 @@ class GetGLMHandle(Process):
if self.check_dependency(): if self.check_dependency():
self.start() self.start()
self.threadLock = threading.Lock() self.threadLock = threading.Lock()
def check_dependency(self): # 主进程执行 def check_dependency(self): # 主进程执行
try: try:
import datasets, os import datasets, os
@ -54,9 +54,9 @@ class GetGLMHandle(Process):
from models.tokenization_moss import MossTokenizer from models.tokenization_moss import MossTokenizer
parser = argparse.ArgumentParser() parser = argparse.ArgumentParser()
parser.add_argument("--model_name", default="fnlp/moss-moon-003-sft-int4", parser.add_argument("--model_name", default="fnlp/moss-moon-003-sft-int4",
choices=["fnlp/moss-moon-003-sft", choices=["fnlp/moss-moon-003-sft",
"fnlp/moss-moon-003-sft-int8", "fnlp/moss-moon-003-sft-int8",
"fnlp/moss-moon-003-sft-int4"], type=str) "fnlp/moss-moon-003-sft-int4"], type=str)
parser.add_argument("--gpu", default="0", type=str) parser.add_argument("--gpu", default="0", type=str)
args = parser.parse_args() args = parser.parse_args()
@ -76,7 +76,7 @@ class GetGLMHandle(Process):
config = MossConfig.from_pretrained(model_path) config = MossConfig.from_pretrained(model_path)
self.tokenizer = MossTokenizer.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...") print("Waiting for all devices to be ready, it may take a few minutes...")
with init_empty_weights(): with init_empty_weights():
raw_model = MossForCausalLM._from_config(config, torch_dtype=torch.float16) 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") inputs = self.tokenizer(self.prompt, return_tensors="pt")
with torch.no_grad(): with torch.no_grad():
outputs = self.model.generate( outputs = self.model.generate(
inputs.input_ids.cuda(), inputs.input_ids.cuda(),
attention_mask=inputs.attention_mask.cuda(), attention_mask=inputs.attention_mask.cuda(),
max_length=2048, max_length=2048,
do_sample=True, do_sample=True,
top_k=40, top_k=40,
top_p=0.8, top_p=0.8,
temperature=0.7, temperature=0.7,
repetition_penalty=1.02, repetition_penalty=1.02,
num_return_sequences=1, num_return_sequences=1,
eos_token_id=106068, eos_token_id=106068,
pad_token_id=self.tokenizer.pad_token_id) pad_token_id=self.tokenizer.pad_token_id)
response = self.tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True) response = self.tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
@ -167,7 +167,7 @@ class GetGLMHandle(Process):
else: else:
break break
self.threadLock.release() self.threadLock.release()
global moss_handle global moss_handle
moss_handle = None moss_handle = None
################################################################################# #################################################################################
@ -180,7 +180,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
if moss_handle is None: if moss_handle is None:
moss_handle = GetGLMHandle() moss_handle = GetGLMHandle()
if len(observe_window) >= 1: observe_window[0] = load_message + "\n\n" + moss_handle.info 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 error = moss_handle.info
moss_handle = None moss_handle = None
raise RuntimeError(error) raise RuntimeError(error)
@ -194,7 +194,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
response = "" 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']): 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) >= 1: observe_window[0] = response
if len(observe_window) >= 2: if len(observe_window) >= 2:
if (time.time()-observe_window[1]) > watch_dog_patience: if (time.time()-observe_window[1]) > watch_dog_patience:
raise RuntimeError("程序终止。") raise RuntimeError("程序终止。")
return response return response
@ -213,7 +213,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
moss_handle = GetGLMHandle() moss_handle = GetGLMHandle()
chatbot[-1] = (inputs, load_message + "\n\n" + moss_handle.info) chatbot[-1] = (inputs, load_message + "\n\n" + moss_handle.info)
yield from update_ui(chatbot=chatbot, history=[]) yield from update_ui(chatbot=chatbot, history=[])
if not moss_handle.success: if not moss_handle.success:
moss_handle = None moss_handle = None
return return
else: 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): for response in self._model.chat_stream(self._tokenizer, query, history=history):
yield response yield response
def try_to_import_special_deps(self, **kwargs): def try_to_import_special_deps(self, **kwargs):
# import something that will raise error if the user does not install requirement_*.txt # import something that will raise error if the user does not install requirement_*.txt
# 🏃‍♂️🏃‍♂️🏃‍♂️ 主进程执行 # 🏃‍♂️🏃‍♂️🏃‍♂️ 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 pass
elif content["msg"] in ["process_generating", "process_completed"]: elif content["msg"] in ["process_generating", "process_completed"]:
yield content["output"]["data"][0] 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 # stop generation by closing the websocket here
if (content["msg"] == "process_completed"): if (content["msg"] == "process_completed"):
break break
@ -117,12 +117,12 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
async def get_result(mutable): async def get_result(mutable):
# "tgui:galactica-1.3b@localhost:7860" # "tgui:galactica-1.3b@localhost:7860"
async for response in run(context=prompt, max_token=llm_kwargs['max_length'], async for response in run(context=prompt, max_token=llm_kwargs['max_length'],
temperature=llm_kwargs['temperature'], temperature=llm_kwargs['temperature'],
top_p=llm_kwargs['top_p'], addr=addr, port=port): top_p=llm_kwargs['top_p'], addr=addr, port=port):
print(response[len(mutable[0]):]) print(response[len(mutable[0]):])
mutable[0] = response mutable[0] = response
if (time.time() - mutable[1]) > 3: if (time.time() - mutable[1]) > 3:
print('exit when no listener') print('exit when no listener')
break break
asyncio.run(get_result(mutable)) 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): def run_coorotine(observe_window):
async def get_result(observe_window): async def get_result(observe_window):
async for response in run(context=prompt, max_token=llm_kwargs['max_length'], async for response in run(context=prompt, max_token=llm_kwargs['max_length'],
temperature=llm_kwargs['temperature'], temperature=llm_kwargs['temperature'],
top_p=llm_kwargs['top_p'], addr=addr, port=port): top_p=llm_kwargs['top_p'], addr=addr, port=port):
print(response[len(observe_window[0]):]) print(response[len(observe_window[0]):])
observe_window[0] = response observe_window[0] = response
if (time.time() - observe_window[1]) > 5: if (time.time() - observe_window[1]) > 5:
print('exit when no listener') print('exit when no listener')
break break
asyncio.run(get_result(observe_window)) 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) } 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) next_token = self.sample_next_token(logits[0, -1], top_k=top_k, top_p=top_p, temperature=temperature)
output_tokens += [next_token] output_tokens += [next_token]
if next_token == self.eop_token_id or len(output_tokens) > max_generated_tokens: 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: class GoogleChatInit:
def __init__(self): def __init__(self, llm_kwargs):
self.url_gemini = "https://generativelanguage.googleapis.com/v1beta/models/%m:streamGenerateContent?key=%k" 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): def generate_chat(self, inputs, llm_kwargs, history, system_prompt):
headers, payload = self.generate_message_payload( 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 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"): if llm_kwargs["most_recent_uploaded"].get("path"):
image_paths = get_pictures_list(llm_kwargs["most_recent_uploaded"]["path"]) image_paths = get_pictures_list(llm_kwargs["most_recent_uploaded"]["path"])
md_encode = [] md_encode = []

6
request_llms/key_manager.py
View File

@ -2,12 +2,12 @@ import random
def Singleton(cls): def Singleton(cls):
_instance = {} _instance = {}
def _singleton(*args, **kargs): def _singleton(*args, **kargs):
if cls not in _instance: if cls not in _instance:
_instance[cls] = cls(*args, **kargs) _instance[cls] = cls(*args, **kargs)
return _instance[cls] return _instance[cls]
return _singleton return _singleton
@ -16,7 +16,7 @@ class OpenAI_ApiKeyManager():
def __init__(self, mode='blacklist') -> None: def __init__(self, mode='blacklist') -> None:
# self.key_avail_list = [] # self.key_avail_list = []
self.key_black_list = [] self.key_black_list = []
def add_key_to_blacklist(self, key): def add_key_to_blacklist(self, key):
self.key_black_list.append(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 return self.state
def set_state(self, new_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: if self.is_main_process:
self.state = new_state self.state = new_state
else: else:
@ -178,8 +178,8 @@ class LocalLLMHandle(Process):
r = self.parent.recv() r = self.parent.recv()
continue continue
break break
return return
def stream_chat(self, **kwargs): def stream_chat(self, **kwargs):
# ⭐run in main process # ⭐run in main process
if self.get_state() == "`准备就绪`": if self.get_state() == "`准备就绪`":

2
requirements.txt
View File

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

2
shared_utils/key_pattern_manager.py
View File

@ -62,7 +62,7 @@ def select_api_key(keys, llm_model):
avail_key_list = [] avail_key_list = []
key_list = keys.split(',') 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: for k in key_list:
if is_openai_api_key(k): avail_key_list.append(k) 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" lang_reference = "hello world"
输出1 输出1
"注意，lang_reference这段文字是：英语" "注意，lang_reference这段文字是：英语"
输入2 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 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" 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 build_gpt_academic_masked_string
from shared_utils.text_mask import apply_gpt_academic_string_mask_langbased 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.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_file
from shared_utils.handle_upload import html_local_img from shared_utils.handle_upload import html_local_img
from shared_utils.handle_upload import file_manifest_filter_type from shared_utils.handle_upload import file_manifest_filter_type
@ -919,6 +922,18 @@ def have_any_recent_upload_image_files(chatbot):
else: else:
return False, None # most_recent_uploaded is too old 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 # Function to encode the image
def encode_image(image_path): def encode_image(image_path):
@ -939,3 +954,53 @@ def check_packages(packages=[]):
spam_spec = importlib.util.find_spec(p) spam_spec = importlib.util.find_spec(p)
if spam_spec is None: if spam_spec is None:
raise ModuleNotFoundError 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, "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）"
} }