比较提交

...

39 次代码提交

作者 SHA1 备注 提交日期
binary-husky
88ae16150b Update README.md 2024-01-16 02:13:27 +08:00
binary-husky
caa1ebc227 Update README.md 2024-01-16 02:06:47 +08:00
hongyi-zhao
2bc65a99ca Update bridge_all.py (#1472)
删除 "chatgpt_website" 函数,从而不再支持域基于逆向工程的方法的接口,该方法对应的实现项目为:https://github.com/acheong08/ChatGPT-to-API/。目前,该项目已被开发者 archived,且该方法由于其实现的原理,而不可能是稳健和完美的,因此不是可持续维护的。
2024-01-13 14:35:04 +08:00
binary-husky
0a2805513e better gui interaction (#1459) 2024-01-07 19:13:12 +08:00
binary-husky
c22867b74c Merge pull request #1458 from binary-husky/frontier
introduce Gemini & Format code
2024-01-07 16:24:33 +08:00
binary-husky
2abe665521 Merge branch 'master' into frontier 2024-01-05 16:12:41 +08:00
binary-husky
b0e6c4d365 change ui prompt 2024-01-05 16:11:30 +08:00
fzcqc
d883c7f34b fix: expected_words添加反斜杆 (#1442) 2024-01-03 19:57:10 +08:00
Menghuan1918
aba871342f 修复分割函数中使用的变量错误 (#1443)
* Fix force_breakdown function parameter name

* Add handling for PDFs with lowercase starting paragraphs

* Change first lowercase word in meta_txt to uppercase
2024-01-03 19:49:17 +08:00
qingxu fu
37744a9cb1 jpeg type align for gemini 2023-12-31 20:28:39 +08:00
qingxu fu
480516380d re-format code to with pre-commit 2023-12-31 19:30:32 +08:00
qingxu fu
60ba712131 use legacy image io for gemini 2023-12-31 19:02:40 +08:00
XIao
a7c960dcb0 适配 google gemini 优化为从用户input中提取文件 (#1419)
适配 google gemini 优化为从用户input中提取文件
2023-12-31 18:05:55 +08:00
binary-husky
a96f842b3a minor ui change 2023-12-30 02:57:42 +08:00
binary-husky
417ca91e23 minor css change 2023-12-30 00:55:52 +08:00
binary-husky
ef8fadfa18 fix ui element padding 2023-12-29 15:16:33 +08:00
binary-husky
865c4ca993 Update README.md 2023-12-26 22:51:56 +08:00
binary-husky
31304f481a remove console log 2023-12-25 22:57:09 +08:00
binary-husky
1bd3637d32 modify image gen plugin user interaction 2023-12-25 22:24:12 +08:00
binary-husky
160a683667 smart input panel swap 2023-12-25 22:05:14 +08:00
binary-husky
49ca03ca06 Merge branch 'master' into frontier 2023-12-25 21:43:33 +08:00
binary-husky
c625348ce1 smarter chatbot height adjustment 2023-12-25 21:26:24 +08:00
binary-husky
6d4a74893a Merge pull request #1415 from binary-husky/frontier
Merge Frontier Branch
2023-12-25 20:18:56 +08:00
qingxu fu
5c7499cada compat with some third party api 2023-12-25 17:21:35 +08:00
binary-husky
f522691529 Merge pull request #1398 from leike0813/frontier
添加通义千问在线模型系列支持&增加插件
2023-12-24 18:21:45 +08:00
binary-husky
ca85573ec1 Update README.md 2023-12-24 18:14:57 +08:00
binary-husky
2c7bba5c63 change dash scope api key check behavior 2023-12-23 21:35:42 +08:00
binary-husky
e22f0226d5 Merge branch 'master' into leike0813-frontier 2023-12-23 21:00:38 +08:00
binary-husky
0f250305b4 add urllib3 version limit 2023-12-23 20:59:32 +08:00
binary-husky
7606f5c130 name fix 2023-12-23 20:55:58 +08:00
binary-husky
4f0dcc431c Merge branch 'frontier' of https://github.com/leike0813/gpt_academic into leike0813-frontier 2023-12-23 20:42:43 +08:00
binary-husky
6ca0dd2f9e Merge pull request #1410 from binary-husky/frontier
fix spark image understanding api
2023-12-23 17:49:35 +08:00
binary-husky
e3e9921f6b correct the misuse of spark image understanding 2023-12-23 17:46:25 +08:00
binary-husky
867ddd355e adjust green theme layout 2023-12-22 21:59:18 +08:00
leike0813
c60a7452bf Improve NOUGAT pdf plugin
Add an API version of NOUGAT plugin
Add advanced argument support to NOUGAT plugin

Adapt new text breakdown function

bugfix
2023-12-20 08:57:27 +08:00
leike0813
68a49d3758 Add 2 plugins
相当于将“批量总结PDF文档”插件拆成了两部分,目的在于使用廉价的模型干粗活,再将关键的最终总结交给GPT-4,降低使用成本
批量总结PDF文档_初步:初步总结PDF,每个PDF输出一个md文档
批量总结Markdown文档_进阶:将所有md文档高度凝练并汇总至一个md文档,可直接使用“批量总结PDF文档_初步”的输出结果作为输入
2023-12-20 07:44:53 +08:00
leike0813
ac3d4cf073 Add support to aliyun qwen online models.
Rename model tag "qwen" to "qwen-local"
Add model tag "qwen-turbo", "qwen-plus", "qwen-max"
Add corresponding model interfaces in request_llms/bridge_all.py
Add configuration variable “DASHSCOPE_API_KEY"
Rename request_llms/bridge_qwen.py to bridge_qwen_local.py to distinguish it from the online model interface
2023-12-20 07:37:26 +08:00
binary-husky
9479dd984c avoid adding the same file multiple times
to the chatbot's files_to_promote list
2023-12-19 19:43:03 +08:00
binary-husky
3c271302cc improve long text breakdown perfomance 2023-12-19 19:30:44 +08:00
共有 71 个文件被更改,包括 1567 次插入643 次删除

查看文件

@@ -69,9 +69,3 @@ body:
attributes:
label: Terminal Traceback & Material to Help Reproduce Bugs | 终端traceback如有 + 帮助我们复现的测试材料样本(如有)
description: Terminal Traceback & Material to Help Reproduce Bugs | 终端traceback如有 + 帮助我们复现的测试材料样本(如有)

查看文件

@@ -21,8 +21,3 @@ body:
attributes:
label: Feature Request | 功能请求
description: Feature Request | 功能请求

1
.gitignore vendored
查看文件

@@ -152,3 +152,4 @@ request_llms/moss
media
flagged
request_llms/ChatGLM-6b-onnx-u8s8
.pre-commit-config.yaml

查看文件

@@ -2,7 +2,7 @@
>
> 2023.11.12: 某些依赖包尚不兼容python 3.12,推荐python 3.11。
>
> 2023.11.7: 安装依赖时,请选择`requirements.txt`中**指定的版本**。 安装命令:`pip install -r requirements.txt`。本项目开源免费,近期发现有人蔑视开源协议并利用本项目违规圈钱,请提高警惕,谨防上当受骗
> 2023.12.26: 安装依赖时,请选择`requirements.txt`中**指定的版本**。 安装命令:`pip install -r requirements.txt`。本项目完全开源免费,您可通过订阅[在线服务](https://github.com/binary-husky/gpt_academic/wiki/online)的方式鼓励本项目的发展
<br>
@@ -65,7 +65,7 @@ Read this in [English](docs/README.English.md) | [日本語](docs/README.Japanes
Latex全文[翻译](https://www.bilibili.com/video/BV1nk4y1Y7Js/)、[润色](https://www.bilibili.com/video/BV1FT411H7c5/) | [插件] 一键翻译或润色latex论文
批量注释生成 | [插件] 一键批量生成函数注释
Markdown[中英互译](https://www.bilibili.com/video/BV1yo4y157jV/) | [插件] 看到上面5种语言的[README](https://github.com/binary-husky/gpt_academic/blob/master/docs/README_EN.md)了吗?就是出自他的手笔
chat分析报告生成 | [插件] 运行后自动生成总结汇报
⭐支持mermaid图像渲染 | 支持让GPT生成[流程图](https://www.bilibili.com/video/BV18c41147H9/)、状态转移图、甘特图、饼状图、GitGraph等等3.7版本)
[PDF论文全文翻译功能](https://www.bilibili.com/video/BV1KT411x7Wn) | [插件] PDF论文提取题目&摘要+翻译全文(多线程)
[Arxiv小助手](https://www.bilibili.com/video/BV1LM4y1279X) | [插件] 输入arxiv文章url即可一键翻译摘要+下载PDF
Latex论文一键校对 | [插件] 仿Grammarly对Latex文章进行语法、拼写纠错+输出对照PDF
@@ -111,7 +111,7 @@ Latex论文一键校对 | [插件] 仿Grammarly对Latex文章进行语法、拼
<img src="https://user-images.githubusercontent.com/96192199/226935232-6b6a73ce-8900-4aee-93f9-733c7e6fef53.png" width="700" >
</div>
- 多种大语言模型混合调用ChatGLM + OpenAI-GPT3.5 + [API2D](https://api2d.com/)-GPT4
- 多种大语言模型混合调用ChatGLM + OpenAI-GPT3.5 + GPT4
<div align="center">
<img src="https://user-images.githubusercontent.com/96192199/232537274-deca0563-7aa6-4b5d-94a2-b7c453c47794.png" width="700" >
</div>
@@ -308,9 +308,9 @@ Tip不指定文件直接点击 `载入对话历史存档` 可以查看历史h
<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/bc7ab234-ad90-48a0-8d62-f703d9e74665" width="500" >
</div>
8. OpenAI音频解析与总结
8. 基于mermaid的流图、脑图绘制
<div align="center">
<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/709ccf95-3aee-498a-934a-e1c22d3d5d5b" width="500" >
<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/c518b82f-bd53-46e2-baf5-ad1b081c1da4" width="500" >
</div>
9. Latex全文校对纠错
@@ -370,8 +370,8 @@ GPT Academic开发者QQ群`610599535`
1. `master` 分支: 主分支,稳定版
2. `frontier` 分支: 开发分支,测试版
3. 如何接入其他大模型:[接入其他大模型](request_llms/README.md)
3. 如何[接入其他大模型](request_llms/README.md)
4. 访问GPT-Academic的[在线服务并支持我们](https://github.com/binary-husky/gpt_academic/wiki/online)
### V参考与学习

查看文件

@@ -89,11 +89,14 @@ DEFAULT_FN_GROUPS = ['对话', '编程', '学术', '智能体']
LLM_MODEL = "gpt-3.5-turbo" # 可选 ↓↓↓
AVAIL_LLM_MODELS = ["gpt-3.5-turbo-1106","gpt-4-1106-preview","gpt-4-vision-preview",
"gpt-3.5-turbo-16k", "gpt-3.5-turbo", "azure-gpt-3.5",
"api2d-gpt-3.5-turbo", 'api2d-gpt-3.5-turbo-16k',
"gpt-4", "gpt-4-32k", "azure-gpt-4", "api2d-gpt-4",
"chatglm3", "moss", "claude-2"]
# P.S. 其他可用的模型还包括 ["zhipuai", "qianfan", "deepseekcoder", "llama2", "qwen", "gpt-3.5-turbo-0613", "gpt-3.5-turbo-16k-0613", "gpt-3.5-random"
# "spark", "sparkv2", "sparkv3", "chatglm_onnx", "claude-1-100k", "claude-2", "internlm", "jittorllms_pangualpha", "jittorllms_llama"]
"gemini-pro", "chatglm3", "moss", "claude-2"]
# P.S. 其他可用的模型还包括 [
# "qwen-turbo", "qwen-plus", "qwen-max"
# "zhipuai", "qianfan", "deepseekcoder", "llama2", "qwen-local", "gpt-3.5-turbo-0613",
# "gpt-3.5-turbo-16k-0613", "gpt-3.5-random", "api2d-gpt-3.5-turbo", 'api2d-gpt-3.5-turbo-16k',
# "spark", "sparkv2", "sparkv3", "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"
@@ -103,7 +106,11 @@ MULTI_QUERY_LLM_MODELS = "gpt-3.5-turbo&chatglm3"
# 选择本地模型变体只有当AVAIL_LLM_MODELS包含了对应本地模型时,才会起作用
# 如果你选择Qwen系列的模型,那么请在下面的QWEN_MODEL_SELECTION中指定具体的模型
# 也可以是具体的模型路径
QWEN_MODEL_SELECTION = "Qwen/Qwen-1_8B-Chat-Int8"
QWEN_LOCAL_MODEL_SELECTION = "Qwen/Qwen-1_8B-Chat-Int8"
# 接入通义千问在线大模型 https://dashscope.console.aliyun.com/
DASHSCOPE_API_KEY = "" # 阿里灵积云API_KEY
# 百度千帆LLM_MODEL="qianfan"
@@ -199,6 +206,10 @@ ANTHROPIC_API_KEY = ""
CUSTOM_API_KEY_PATTERN = ""
# Google Gemini API-Key
GEMINI_API_KEY = ''
# HUGGINGFACE的TOKEN,下载LLAMA时起作用 https://huggingface.co/docs/hub/security-tokens
HUGGINGFACE_ACCESS_TOKEN = "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"
@@ -284,6 +295,12 @@ NUM_CUSTOM_BASIC_BTN = 4
│ ├── ZHIPUAI_API_KEY
│ └── ZHIPUAI_MODEL
├── "qwen-turbo" 等通义千问大模型
│ └── DASHSCOPE_API_KEY
├── "Gemini"
│ └── GEMINI_API_KEY
└── "newbing" Newbing接口不再稳定,不推荐使用
├── NEWBING_STYLE
└── NEWBING_COOKIES
@@ -300,7 +317,7 @@ NUM_CUSTOM_BASIC_BTN = 4
├── "jittorllms_pangualpha"
├── "jittorllms_llama"
├── "deepseekcoder"
├── "qwen"
├── "qwen-local"
├── RWKV的支持见Wiki
└── "llama2"

查看文件

@@ -345,7 +345,7 @@ def get_crazy_functions():
"Color": "stop",
"AsButton": False,
"AdvancedArgs": True, # 调用时,唤起高级参数输入区默认False
"ArgsReminder": "支持任意数量的llm接口,用&符号分隔。例如chatglm&gpt-3.5-turbo&api2d-gpt-4", # 高级参数输入区的显示提示
"ArgsReminder": "支持任意数量的llm接口,用&符号分隔。例如chatglm&gpt-3.5-turbo&gpt-4", # 高级参数输入区的显示提示
"Function": HotReload(同时问询_指定模型)
},
})
@@ -356,7 +356,7 @@ def get_crazy_functions():
try:
from crazy_functions.图片生成 import 图片生成_DALLE2, 图片生成_DALLE3, 图片修改_DALLE2
function_plugins.update({
"图片生成_DALLE2 (先切换模型到openai或api2d": {
"图片生成_DALLE2 (先切换模型到gpt-*": {
"Group": "对话",
"Color": "stop",
"AsButton": False,
@@ -367,7 +367,7 @@ def get_crazy_functions():
},
})
function_plugins.update({
"图片生成_DALLE3 (先切换模型到openai或api2d": {
"图片生成_DALLE3 (先切换模型到gpt-*": {
"Group": "对话",
"Color": "stop",
"AsButton": False,
@@ -378,7 +378,7 @@ def get_crazy_functions():
},
})
function_plugins.update({
"图片修改_DALLE2 (先切换模型到openai或api2d": {
"图片修改_DALLE2 (先切换模型到gpt-*": {
"Group": "对话",
"Color": "stop",
"AsButton": False,

查看文件

@@ -139,6 +139,8 @@ def can_multi_process(llm):
if llm.startswith('gpt-'): return True
if llm.startswith('api2d-'): return True
if llm.startswith('azure-'): return True
if llm.startswith('spark'): return True
if llm.startswith('zhipuai'): return True
return False
def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
@@ -464,6 +466,9 @@ def read_and_clean_pdf_text(fp):
return True
else:
return False
# 对于某些PDF会有第一个段落就以小写字母开头,为了避免索引错误将其更改为大写
if starts_with_lowercase_word(meta_txt[0]):
meta_txt[0] = meta_txt[0].capitalize()
for _ in range(100):
for index, block_txt in enumerate(meta_txt):
if starts_with_lowercase_word(block_txt):

查看文件

@@ -250,8 +250,8 @@ def find_main_tex_file(file_manifest, mode):
else: # if len(canidates) >= 2 通过一些Latex模板中常见但通常不会出现在正文的单词,对不同latex源文件扣分,取评分最高者返回
canidates_score = []
# 给出一些判定模板文档的词作为扣分项
unexpected_words = ['\LaTeX', 'manuscript', 'Guidelines', 'font', 'citations', 'rejected', 'blind review', 'reviewers']
expected_words = ['\input', '\ref', '\cite']
unexpected_words = ['\\LaTeX', 'manuscript', 'Guidelines', 'font', 'citations', 'rejected', 'blind review', 'reviewers']
expected_words = ['\\input', '\\ref', '\\cite']
for texf in canidates:
canidates_score.append(0)
with open(texf, 'r', encoding='utf8', errors='ignore') as f:

查看文件

@@ -65,10 +65,10 @@ def cut(limit, get_token_fn, txt_tocut, must_break_at_empty_line, break_anyway=F
# 如果没有找到合适的切分点
if break_anyway:
# 是否允许暴力切分
prev, post = force_breakdown(txt_tocut, limit, get_token_fn)
prev, post = force_breakdown(remain_txt_to_cut, limit, get_token_fn)
else:
# 不允许直接报错
raise RuntimeError(f"存在一行极长的文本!{txt_tocut}")
raise RuntimeError(f"存在一行极长的文本!{remain_txt_to_cut}")
# 追加列表
res.append(prev); fin_len+=len(prev)

查看文件

@@ -104,7 +104,11 @@ def 图片生成_DALLE2(prompt, llm_kwargs, plugin_kwargs, chatbot, history, sys
web_port 当前软件运行的端口号
"""
history = [] # 清空历史,以免输入溢出
chatbot.append(("您正在调用“图像生成”插件。", "[Local Message] 生成图像, 请先把模型切换至gpt-*或者api2d-*。如果中文Prompt效果不理想, 请尝试英文Prompt。正在处理中 ....."))
if prompt.strip() == "":
chatbot.append((prompt, "[Local Message] 图像生成提示为空白,请在“输入区”输入图像生成提示。"))
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 界面更新
return
chatbot.append(("您正在调用“图像生成”插件。", "[Local Message] 生成图像, 请先把模型切换至gpt-*。如果中文Prompt效果不理想, 请尝试英文Prompt。正在处理中 ....."))
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 ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
resolution = plugin_kwargs.get("advanced_arg", '1024x1024')
@@ -121,7 +125,11 @@ def 图片生成_DALLE2(prompt, llm_kwargs, plugin_kwargs, chatbot, history, sys
@CatchException
def 图片生成_DALLE3(prompt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
history = [] # 清空历史,以免输入溢出
chatbot.append(("您正在调用“图像生成”插件。", "[Local Message] 生成图像, 请先把模型切换至gpt-*或者api2d-*。如果中文Prompt效果不理想, 请尝试英文Prompt。正在处理中 ....."))
if prompt.strip() == "":
chatbot.append((prompt, "[Local Message] 图像生成提示为空白,请在“输入区”输入图像生成提示。"))
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 界面更新
return
chatbot.append(("您正在调用“图像生成”插件。", "[Local Message] 生成图像, 请先把模型切换至gpt-*。如果中文Prompt效果不理想, 请尝试英文Prompt。正在处理中 ....."))
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 ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
resolution_arg = plugin_kwargs.get("advanced_arg", '1024x1024-standard-vivid').lower()

查看文件

@@ -229,4 +229,3 @@ services:
# 不使用代理网络拉取最新代码
command: >
bash -c "python3 -u main.py"

查看文件

@@ -1,2 +1 @@
# 此Dockerfile不再维护,请前往docs/GithubAction+ChatGLM+Moss

查看文件

@@ -341,4 +341,3 @@ https://github.com/oobabooga/one-click-installers
# المزيد:
https://github.com/gradio-app/gradio
https://github.com/fghrsh/live2d_demo

查看文件

@@ -355,4 +355,3 @@ https://github.com/oobabooga/one-click-installers
# More:
https://github.com/gradio-app/gradio
https://github.com/fghrsh/live2d_demo

查看文件

@@ -354,4 +354,3 @@ https://github.com/oobabooga/one-click-installers
# Plus
https://github.com/gradio-app/gradio
https://github.com/fghrsh/live2d_demo

查看文件

@@ -361,4 +361,3 @@ https://github.com/oobabooga/one-click-installers
# Weitere:
https://github.com/gradio-app/gradio
https://github.com/fghrsh/live2d_demo

查看文件

@@ -358,4 +358,3 @@ https://github.com/oobabooga/one-click-installers
# Altre risorse:
https://github.com/gradio-app/gradio
https://github.com/fghrsh/live2d_demo

查看文件

@@ -342,4 +342,3 @@ https://github.com/oobabooga/one-click-installers
# その他:
https://github.com/gradio-app/gradio
https://github.com/fghrsh/live2d_demo

查看文件

@@ -361,4 +361,3 @@ https://github.com/oobabooga/one-click-installers
# 더보기:
https://github.com/gradio-app/gradio
https://github.com/fghrsh/live2d_demo

查看文件

@@ -355,4 +355,3 @@ https://github.com/oobabooga/instaladores-de-um-clique
# Mais:
https://github.com/gradio-app/gradio
https://github.com/fghrsh/live2d_demo

查看文件

@@ -358,4 +358,3 @@ https://github.com/oobabooga/one-click-installers
# Больше:
https://github.com/gradio-app/gradio
https://github.com/fghrsh/live2d_demo

查看文件

@@ -7,13 +7,27 @@ sample = """
"""
import re
def preprocess_newbing_out(s):
pattern = r'\^(\d+)\^' # 匹配^数字^
pattern2 = r'\[(\d+)\]' # 匹配^数字^
sub = lambda m: '\['+m.group(1)+'\]' # 将匹配到的数字作为替换值
result = re.sub(pattern, sub, s) # 替换操作
if '[1]' in result:
result += '<br/><hr style="border-top: dotted 1px #44ac5c;"><br/><small>' + "<br/>".join([re.sub(pattern2, sub, r) for r in result.split('\n') if r.startswith('[')]) + '</small>'
pattern = r"\^(\d+)\^" # 匹配^数字^
pattern2 = r"\[(\d+)\]" # 匹配^数字^
def sub(m):
return "\\[" + m.group(1) + "\\]" # 将匹配到的数字作为替换值
result = re.sub(pattern, sub, s) # 替换操作
if "[1]" in result:
result += (
'<br/><hr style="border-top: dotted 1px #44ac5c;"><br/><small>'
+ "<br/>".join(
[
re.sub(pattern2, sub, r)
for r in result.split("\n")
if r.startswith("[")
]
)
+ "</small>"
)
return result
@@ -28,37 +42,39 @@ def close_up_code_segment_during_stream(gpt_reply):
str: 返回一个新的字符串,将输出代码片段的“后面的```”补上。
"""
if '```' not in gpt_reply:
if "```" not in gpt_reply:
return gpt_reply
if gpt_reply.endswith('```'):
if gpt_reply.endswith("```"):
return gpt_reply
# 排除了以上两个情况,我们
segments = gpt_reply.split('```')
segments = gpt_reply.split("```")
n_mark = len(segments) - 1
if n_mark % 2 == 1:
# print('输出代码片段中!')
return gpt_reply+'\n```'
return gpt_reply + "\n```"
else:
return gpt_reply
import markdown
from latex2mathml.converter import convert as tex2mathml
from functools import wraps, lru_cache
def markdown_convertion(txt):
"""
将Markdown格式的文本转换为HTML格式。如果包含数学公式,则先将公式转换为HTML格式。
"""
pre = '<div class="markdown-body">'
suf = '</div>'
suf = "</div>"
if txt.startswith(pre) and txt.endswith(suf):
# print('警告,输入了已经经过转化的字符串,二次转化可能出问题')
return txt # 已经被转化过,不需要再次转化
return txt # 已经被转化过,不需要再次转化
markdown_extension_configs = {
'mdx_math': {
'enable_dollar_delimiter': True,
'use_gitlab_delimiters': False,
"mdx_math": {
"enable_dollar_delimiter": True,
"use_gitlab_delimiters": False,
},
}
find_equation_pattern = r'<script type="math/tex(?:.*?)>(.*?)</script>'
@@ -72,19 +88,19 @@ def markdown_convertion(txt):
def replace_math_no_render(match):
content = match.group(1)
if 'mode=display' in match.group(0):
content = content.replace('\n', '</br>')
return f"<font color=\"#00FF00\">$$</font><font color=\"#FF00FF\">{content}</font><font color=\"#00FF00\">$$</font>"
if "mode=display" in match.group(0):
content = content.replace("\n", "</br>")
return f'<font color="#00FF00">$$</font><font color="#FF00FF">{content}</font><font color="#00FF00">$$</font>'
else:
return f"<font color=\"#00FF00\">$</font><font color=\"#FF00FF\">{content}</font><font color=\"#00FF00\">$</font>"
return f'<font color="#00FF00">$</font><font color="#FF00FF">{content}</font><font color="#00FF00">$</font>'
def replace_math_render(match):
content = match.group(1)
if 'mode=display' in match.group(0):
if '\\begin{aligned}' in content:
content = content.replace('\\begin{aligned}', '\\begin{array}')
content = content.replace('\\end{aligned}', '\\end{array}')
content = content.replace('&', ' ')
if "mode=display" in match.group(0):
if "\\begin{aligned}" in content:
content = content.replace("\\begin{aligned}", "\\begin{array}")
content = content.replace("\\end{aligned}", "\\end{array}")
content = content.replace("&", " ")
content = tex2mathml_catch_exception(content, display="block")
return content
else:
@@ -94,37 +110,58 @@ def markdown_convertion(txt):
"""
解决一个mdx_math的bug单$包裹begin命令时多余<script>
"""
content = content.replace('<script type="math/tex">\n<script type="math/tex; mode=display">', '<script type="math/tex; mode=display">')
content = content.replace('</script>\n</script>', '</script>')
content = content.replace(
'<script type="math/tex">\n<script type="math/tex; mode=display">',
'<script type="math/tex; mode=display">',
)
content = content.replace("</script>\n</script>", "</script>")
return content
if ('$' in txt) and ('```' not in txt): # 有$标识的公式符号,且没有代码段```的标识
if ("$" in txt) and ("```" not in txt): # 有$标识的公式符号,且没有代码段```的标识
# convert everything to html format
split = markdown.markdown(text='---')
convert_stage_1 = markdown.markdown(text=txt, extensions=['mdx_math', 'fenced_code', 'tables', 'sane_lists'], extension_configs=markdown_extension_configs)
split = markdown.markdown(text="---")
convert_stage_1 = markdown.markdown(
text=txt,
extensions=["mdx_math", "fenced_code", "tables", "sane_lists"],
extension_configs=markdown_extension_configs,
)
convert_stage_1 = markdown_bug_hunt(convert_stage_1)
# re.DOTALL: Make the '.' special character match any character at all, including a newline; without this flag, '.' will match anything except a newline. Corresponds to the inline flag (?s).
# 1. convert to easy-to-copy tex (do not render math)
convert_stage_2_1, n = re.subn(find_equation_pattern, replace_math_no_render, convert_stage_1, flags=re.DOTALL)
convert_stage_2_1, n = re.subn(
find_equation_pattern,
replace_math_no_render,
convert_stage_1,
flags=re.DOTALL,
)
# 2. convert to rendered equation
convert_stage_2_2, n = re.subn(find_equation_pattern, replace_math_render, convert_stage_1, flags=re.DOTALL)
convert_stage_2_2, n = re.subn(
find_equation_pattern, replace_math_render, convert_stage_1, flags=re.DOTALL
)
# cat them together
return pre + convert_stage_2_1 + f'{split}' + convert_stage_2_2 + suf
return pre + convert_stage_2_1 + f"{split}" + convert_stage_2_2 + suf
else:
return pre + markdown.markdown(txt, extensions=['fenced_code', 'codehilite', 'tables', 'sane_lists']) + suf
return (
pre
+ markdown.markdown(
txt, extensions=["fenced_code", "codehilite", "tables", "sane_lists"]
)
+ suf
)
sample = preprocess_newbing_out(sample)
sample = close_up_code_segment_during_stream(sample)
sample = markdown_convertion(sample)
with open('tmp.html', 'w', encoding='utf8') as f:
f.write("""
with open("tmp.html", "w", encoding="utf8") as f:
f.write(
"""
<head>
<title>My Website</title>
<link rel="stylesheet" type="text/css" href="style.css">
</head>
""")
"""
)
f.write(sample)

查看文件

@@ -61,4 +61,3 @@ VI 两种音频监听模式切换时,需要刷新页面才有效。
VII 非localhost运行+非https情况下无法打开录音功能的坑https://blog.csdn.net/weixin_39461487/article/details/109594434
## 5.点击函数插件区“实时音频采集” 或者其他音频交互功能

13
main.py
查看文件

@@ -15,7 +15,7 @@ help_menu_description = \
def main():
import gradio as gr
if gr.__version__ not in ['3.32.6']:
if gr.__version__ not in ['3.32.6', '3.32.7']:
raise ModuleNotFoundError("使用项目内置Gradio获取最优体验! 请运行 `pip install -r requirements.txt` 指令安装内置Gradio及其他依赖, 详情信息见requirements.txt.")
from request_llms.bridge_all import predict
from toolbox import format_io, find_free_port, on_file_uploaded, on_report_generated, get_conf, ArgsGeneralWrapper, load_chat_cookies, DummyWith
@@ -139,17 +139,17 @@ def main():
with gr.Row():
switchy_bt = gr.Button(r"请先从插件列表中选择", variant="secondary").style(size="sm")
with gr.Row():
with gr.Accordion("点击展开“文件上传区”。上传本地文件/压缩包供函数插件调用", open=False) as area_file_up:
with gr.Accordion("点击展开“文件下载区”", open=False) as area_file_up:
file_upload = gr.Files(label="任何文件, 推荐上传压缩文件(zip, tar)", file_count="multiple", elem_id="elem_upload")
with gr.Floating(init_x="0%", init_y="0%", visible=True, width=None, drag="forbidden"):
with gr.Floating(init_x="0%", init_y="0%", visible=True, width=None, drag="forbidden", elem_id="tooltip"):
with gr.Row():
with gr.Tab("上传文件", elem_id="interact-panel"):
gr.Markdown("请上传本地文件/压缩包供“函数插件区”功能调用。请注意: 上传文件后会自动把输入区修改为相应路径。")
file_upload_2 = gr.Files(label="任何文件, 推荐上传压缩文件(zip, tar)", file_count="multiple", elem_id="elem_upload_float")
with gr.Tab("更换模型 & Prompt", elem_id="interact-panel"):
with gr.Tab("更换模型", elem_id="interact-panel"):
md_dropdown = gr.Dropdown(AVAIL_LLM_MODELS, value=LLM_MODEL, label="更换LLM模型/请求源").style(container=False)
top_p = gr.Slider(minimum=-0, maximum=1.0, value=1.0, step=0.01,interactive=True, label="Top-p (nucleus sampling)",)
temperature = gr.Slider(minimum=-0, maximum=2.0, value=1.0, step=0.01, interactive=True, label="Temperature",)
@@ -161,10 +161,9 @@ def main():
checkboxes = gr.CheckboxGroup(["基础功能区", "函数插件区", "浮动输入区", "输入清除键", "插件参数区"],
value=["基础功能区", "函数插件区"], label="显示/隐藏功能区", elem_id='cbs').style(container=False)
checkboxes_2 = gr.CheckboxGroup(["自定义菜单"],
value=[], label="显示/隐藏自定义菜单", elem_id='cbs').style(container=False)
value=[], label="显示/隐藏自定义菜单", elem_id='cbsc').style(container=False)
dark_mode_btn = gr.Button("切换界面明暗 ☀", variant="secondary").style(size="sm")
dark_mode_btn.click(None, None, None, _js=js_code_for_toggle_darkmode,
)
dark_mode_btn.click(None, None, None, _js=js_code_for_toggle_darkmode)
with gr.Tab("帮助", elem_id="interact-panel"):
gr.Markdown(help_menu_description)

查看文件

@@ -28,6 +28,9 @@ from .bridge_chatglm3 import predict as chatglm3_ui
from .bridge_qianfan import predict_no_ui_long_connection as qianfan_noui
from .bridge_qianfan import predict as qianfan_ui
from .bridge_google_gemini import predict as genai_ui
from .bridge_google_gemini import predict_no_ui_long_connection as genai_noui
colors = ['#FF00FF', '#00FFFF', '#FF0000', '#990099', '#009999', '#990044']
class LazyloadTiktoken(object):
@@ -246,6 +249,22 @@ model_info = {
"tokenizer": tokenizer_gpt35,
"token_cnt": get_token_num_gpt35,
},
"gemini-pro": {
"fn_with_ui": genai_ui,
"fn_without_ui": genai_noui,
"endpoint": None,
"max_token": 1024 * 32,
"tokenizer": tokenizer_gpt35,
"token_cnt": get_token_num_gpt35,
},
"gemini-pro-vision": {
"fn_with_ui": genai_ui,
"fn_without_ui": genai_noui,
"endpoint": None,
"max_token": 1024 * 32,
"tokenizer": tokenizer_gpt35,
"token_cnt": get_token_num_gpt35,
},
}
# -=-=-=-=-=-=- api2d 对齐支持 -=-=-=-=-=-=-
@@ -431,14 +450,14 @@ if "chatglm_onnx" in AVAIL_LLM_MODELS:
})
except:
print(trimmed_format_exc())
if "qwen" in AVAIL_LLM_MODELS:
if "qwen-local" in AVAIL_LLM_MODELS:
try:
from .bridge_qwen import predict_no_ui_long_connection as qwen_noui
from .bridge_qwen import predict as qwen_ui
from .bridge_qwen_local import predict_no_ui_long_connection as qwen_local_noui
from .bridge_qwen_local import predict as qwen_local_ui
model_info.update({
"qwen": {
"fn_with_ui": qwen_ui,
"fn_without_ui": qwen_noui,
"qwen-local": {
"fn_with_ui": qwen_local_ui,
"fn_without_ui": qwen_local_noui,
"endpoint": None,
"max_token": 4096,
"tokenizer": tokenizer_gpt35,
@@ -447,16 +466,32 @@ if "qwen" in AVAIL_LLM_MODELS:
})
except:
print(trimmed_format_exc())
if "chatgpt_website" in AVAIL_LLM_MODELS: # 接入一些逆向工程https://github.com/acheong08/ChatGPT-to-API/
if "qwen-turbo" in AVAIL_LLM_MODELS or "qwen-plus" in AVAIL_LLM_MODELS or "qwen-max" in AVAIL_LLM_MODELS: # zhipuai
try:
from .bridge_chatgpt_website import predict_no_ui_long_connection as chatgpt_website_noui
from .bridge_chatgpt_website import predict as chatgpt_website_ui
from .bridge_qwen import predict_no_ui_long_connection as qwen_noui
from .bridge_qwen import predict as qwen_ui
model_info.update({
"chatgpt_website": {
"fn_with_ui": chatgpt_website_ui,
"fn_without_ui": chatgpt_website_noui,
"endpoint": openai_endpoint,
"max_token": 4096,
"qwen-turbo": {
"fn_with_ui": qwen_ui,
"fn_without_ui": qwen_noui,
"endpoint": None,
"max_token": 6144,
"tokenizer": tokenizer_gpt35,
"token_cnt": get_token_num_gpt35,
},
"qwen-plus": {
"fn_with_ui": qwen_ui,
"fn_without_ui": qwen_noui,
"endpoint": None,
"max_token": 30720,
"tokenizer": tokenizer_gpt35,
"token_cnt": get_token_num_gpt35,
},
"qwen-max": {
"fn_with_ui": qwen_ui,
"fn_without_ui": qwen_noui,
"endpoint": None,
"max_token": 28672,
"tokenizer": tokenizer_gpt35,
"token_cnt": get_token_num_gpt35,
}

查看文件

@@ -102,20 +102,25 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
result = ''
json_data = None
while True:
try: chunk = next(stream_response).decode()
try: chunk = next(stream_response)
except StopIteration:
break
except requests.exceptions.ConnectionError:
chunk = next(stream_response).decode() # 失败了,重试一次?再失败就没办法了。
if len(chunk)==0: continue
if not chunk.startswith('data:'):
error_msg = get_full_error(chunk.encode('utf8'), stream_response).decode()
chunk = next(stream_response) # 失败了,重试一次?再失败就没办法了。
chunk_decoded, chunkjson, has_choices, choice_valid, has_content, has_role = decode_chunk(chunk)
if len(chunk_decoded)==0: continue
if not chunk_decoded.startswith('data:'):
error_msg = get_full_error(chunk, stream_response).decode()
if "reduce the length" in error_msg:
raise ConnectionAbortedError("OpenAI拒绝了请求:" + error_msg)
else:
raise RuntimeError("OpenAI拒绝了请求" + error_msg)
if ('data: [DONE]' in chunk): break # api2d 正常完成
json_data = json.loads(chunk.lstrip('data:'))['choices'][0]
if ('data: [DONE]' in chunk_decoded): break # api2d 正常完成
# 提前读取一些信息 (用于判断异常)
if has_choices and not choice_valid:
# 一些垃圾第三方接口的出现这样的错误
continue
json_data = chunkjson['choices'][0]
delta = json_data["delta"]
if len(delta) == 0: break
if "role" in delta: continue

查看文件

@@ -0,0 +1,109 @@
# encoding: utf-8
# @Time : 2023/12/21
# @Author : Spike
# @Descr :
import json
import re
import os
import time
from request_llms.com_google import GoogleChatInit
from toolbox import get_conf, update_ui, update_ui_lastest_msg, have_any_recent_upload_image_files, trimmed_format_exc
proxies, TIMEOUT_SECONDS, MAX_RETRY = get_conf('proxies', 'TIMEOUT_SECONDS', 'MAX_RETRY')
timeout_bot_msg = '[Local Message] Request timeout. Network error. Please check proxy settings in config.py.' + \
'网络错误,检查代理服务器是否可用,以及代理设置的格式是否正确,格式须是[协议]://[地址]:[端口],缺一不可。'
def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=None,
console_slience=False):
# 检查API_KEY
if get_conf("GEMINI_API_KEY") == "":
raise ValueError(f"请配置 GEMINI_API_KEY。")
genai = GoogleChatInit()
watch_dog_patience = 5 # 看门狗的耐心, 设置5秒即可
gpt_replying_buffer = ''
stream_response = genai.generate_chat(inputs, llm_kwargs, history, sys_prompt)
for response in stream_response:
results = response.decode()
match = re.search(r'"text":\s*"((?:[^"\\]|\\.)*)"', results, flags=re.DOTALL)
error_match = re.search(r'\"message\":\s*\"(.*?)\"', results, flags=re.DOTALL)
if match:
try:
paraphrase = json.loads('{"text": "%s"}' % match.group(1))
except:
raise ValueError(f"解析GEMINI消息出错。")
buffer = paraphrase['text']
gpt_replying_buffer += buffer
if len(observe_window) >= 1:
observe_window[0] = gpt_replying_buffer
if len(observe_window) >= 2:
if (time.time() - observe_window[1]) > watch_dog_patience: raise RuntimeError("程序终止。")
if error_match:
raise RuntimeError(f'{gpt_replying_buffer} 对话错误')
return gpt_replying_buffer
def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream=True, additional_fn=None):
# 检查API_KEY
if get_conf("GEMINI_API_KEY") == "":
yield from update_ui_lastest_msg(f"请配置 GEMINI_API_KEY。", chatbot=chatbot, history=history, delay=0)
return
if "vision" in llm_kwargs["llm_model"]:
have_recent_file, image_paths = have_any_recent_upload_image_files(chatbot)
def make_media_input(inputs, image_paths):
for image_path in image_paths:
inputs = inputs + f'<br/><br/><div align="center"><img src="file={os.path.abspath(image_path)}"></div>'
return inputs
if have_recent_file:
inputs = make_media_input(inputs, image_paths)
chatbot.append((inputs, ""))
yield from update_ui(chatbot=chatbot, history=history)
genai = GoogleChatInit()
retry = 0
while True:
try:
stream_response = genai.generate_chat(inputs, llm_kwargs, history, system_prompt)
break
except Exception as e:
retry += 1
chatbot[-1] = ((chatbot[-1][0], trimmed_format_exc()))
yield from update_ui(chatbot=chatbot, history=history, msg="请求失败") # 刷新界面
return
gpt_replying_buffer = ""
gpt_security_policy = ""
history.extend([inputs, ''])
for response in stream_response:
results = response.decode("utf-8") # 被这个解码给耍了。。
gpt_security_policy += results
match = re.search(r'"text":\s*"((?:[^"\\]|\\.)*)"', results, flags=re.DOTALL)
error_match = re.search(r'\"message\":\s*\"(.*)\"', results, flags=re.DOTALL)
if match:
try:
paraphrase = json.loads('{"text": "%s"}' % match.group(1))
except:
raise ValueError(f"解析GEMINI消息出错。")
gpt_replying_buffer += paraphrase['text'] # 使用 json 解析库进行处理
chatbot[-1] = (inputs, gpt_replying_buffer)
history[-1] = gpt_replying_buffer
yield from update_ui(chatbot=chatbot, history=history)
if error_match:
history = history[-2] # 错误的不纳入对话
chatbot[-1] = (inputs, gpt_replying_buffer + f"对话错误,请查看message\n\n```\n{error_match.group(1)}\n```")
yield from update_ui(chatbot=chatbot, history=history)
raise RuntimeError('对话错误')
if not gpt_replying_buffer:
history = history[-2] # 错误的不纳入对话
chatbot[-1] = (inputs, gpt_replying_buffer + f"触发了Google的安全访问策略,没有回答\n\n```\n{gpt_security_policy}\n```")
yield from update_ui(chatbot=chatbot, history=history)
if __name__ == '__main__':
import sys
llm_kwargs = {'llm_model': 'gemini-pro'}
result = predict('Write long a story about a magic backpack.', llm_kwargs, llm_kwargs, [])
for i in result:
print(i)

查看文件

@@ -1,59 +1,62 @@
model_name = "Qwen"
cmd_to_install = "`pip install -r request_llms/requirements_qwen.txt`"
import time
import os
from toolbox import update_ui, get_conf, update_ui_lastest_msg
from toolbox import check_packages, report_exception
from toolbox import ProxyNetworkActivate, get_conf
from .local_llm_class import LocalLLMHandle, get_local_llm_predict_fns
model_name = 'Qwen'
def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
"""
⭐多线程方法
函数的说明请见 request_llms/bridge_all.py
"""
watch_dog_patience = 5
response = ""
from .com_qwenapi import QwenRequestInstance
sri = QwenRequestInstance()
for response in sri.generate(inputs, llm_kwargs, history, sys_prompt):
if len(observe_window) >= 1:
observe_window[0] = response
if len(observe_window) >= 2:
if (time.time()-observe_window[1]) > watch_dog_patience: raise RuntimeError("程序终止。")
return response
# ------------------------------------------------------------------------------------------------------------------------
# 🔌💻 Local Model
# ------------------------------------------------------------------------------------------------------------------------
class GetQwenLMHandle(LocalLLMHandle):
def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream = True, additional_fn=None):
"""
⭐单线程方法
函数的说明请见 request_llms/bridge_all.py
"""
chatbot.append((inputs, ""))
yield from update_ui(chatbot=chatbot, history=history)
def load_model_info(self):
# 🏃‍♂️🏃‍♂️🏃‍♂️ 子进程执行
self.model_name = model_name
self.cmd_to_install = cmd_to_install
# 尝试导入依赖,如果缺少依赖,则给出安装建议
try:
check_packages(["dashscope"])
except:
yield from update_ui_lastest_msg(f"导入软件依赖失败。使用该模型需要额外依赖,安装方法```pip install --upgrade dashscope```。",
chatbot=chatbot, history=history, delay=0)
return
def load_model_and_tokenizer(self):
# 🏃‍♂️🏃‍♂️🏃‍♂️ 子进程执行
# from modelscope import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.generation import GenerationConfig
with ProxyNetworkActivate('Download_LLM'):
model_id = get_conf('QWEN_MODEL_SELECTION')
self._tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True, resume_download=True)
# use fp16
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", trust_remote_code=True).eval()
model.generation_config = GenerationConfig.from_pretrained(model_id, trust_remote_code=True) # 可指定不同的生成长度、top_p等相关超参
self._model = model
# 检查DASHSCOPE_API_KEY
if get_conf("DASHSCOPE_API_KEY") == "":
yield from update_ui_lastest_msg(f"请配置 DASHSCOPE_API_KEY。",
chatbot=chatbot, history=history, delay=0)
return
return self._model, self._tokenizer
if additional_fn is not None:
from core_functional import handle_core_functionality
inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
def llm_stream_generator(self, **kwargs):
# 🏃‍♂️🏃‍♂️🏃‍♂️ 子进程执行
def adaptor(kwargs):
query = kwargs['query']
max_length = kwargs['max_length']
top_p = kwargs['top_p']
temperature = kwargs['temperature']
history = kwargs['history']
return query, max_length, top_p, temperature, history
# 开始接收回复
from .com_qwenapi import QwenRequestInstance
sri = QwenRequestInstance()
for response in sri.generate(inputs, llm_kwargs, history, system_prompt):
chatbot[-1] = (inputs, response)
yield from update_ui(chatbot=chatbot, history=history)
query, max_length, top_p, temperature, history = adaptor(kwargs)
for response in self._model.chat_stream(self._tokenizer, query, history=history):
yield response
def try_to_import_special_deps(self, **kwargs):
# import something that will raise error if the user does not install requirement_*.txt
# 🏃‍♂️🏃‍♂️🏃‍♂️ 主进程执行
import importlib
importlib.import_module('modelscope')
# ------------------------------------------------------------------------------------------------------------------------
# 🔌💻 GPT-Academic Interface
# ------------------------------------------------------------------------------------------------------------------------
predict_no_ui_long_connection, predict = get_local_llm_predict_fns(GetQwenLMHandle, model_name)
# 总结输出
if response == f"[Local Message] 等待{model_name}响应中 ...":
response = f"[Local Message] {model_name}响应异常 ..."
history.extend([inputs, response])
yield from update_ui(chatbot=chatbot, history=history)

查看文件

@@ -0,0 +1,59 @@
model_name = "Qwen_Local"
cmd_to_install = "`pip install -r request_llms/requirements_qwen_local.txt`"
from toolbox import ProxyNetworkActivate, get_conf
from .local_llm_class import LocalLLMHandle, get_local_llm_predict_fns
# ------------------------------------------------------------------------------------------------------------------------
# 🔌💻 Local Model
# ------------------------------------------------------------------------------------------------------------------------
class GetQwenLMHandle(LocalLLMHandle):
def load_model_info(self):
# 🏃‍♂️🏃‍♂️🏃‍♂️ 子进程执行
self.model_name = model_name
self.cmd_to_install = cmd_to_install
def load_model_and_tokenizer(self):
# 🏃‍♂️🏃‍♂️🏃‍♂️ 子进程执行
# from modelscope import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.generation import GenerationConfig
with ProxyNetworkActivate('Download_LLM'):
model_id = get_conf('QWEN_LOCAL_MODEL_SELECTION')
self._tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True, resume_download=True)
# use fp16
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", trust_remote_code=True).eval()
model.generation_config = GenerationConfig.from_pretrained(model_id, trust_remote_code=True) # 可指定不同的生成长度、top_p等相关超参
self._model = model
return self._model, self._tokenizer
def llm_stream_generator(self, **kwargs):
# 🏃‍♂️🏃‍♂️🏃‍♂️ 子进程执行
def adaptor(kwargs):
query = kwargs['query']
max_length = kwargs['max_length']
top_p = kwargs['top_p']
temperature = kwargs['temperature']
history = kwargs['history']
return query, max_length, top_p, temperature, history
query, max_length, top_p, temperature, history = adaptor(kwargs)
for response in self._model.chat_stream(self._tokenizer, query, history=history):
yield response
def try_to_import_special_deps(self, **kwargs):
# import something that will raise error if the user does not install requirement_*.txt
# 🏃‍♂️🏃‍♂️🏃‍♂️ 主进程执行
import importlib
importlib.import_module('modelscope')
# ------------------------------------------------------------------------------------------------------------------------
# 🔌💻 GPT-Academic Interface
# ------------------------------------------------------------------------------------------------------------------------
predict_no_ui_long_connection, predict = get_local_llm_predict_fns(GetQwenLMHandle, model_name)

查看文件

@@ -26,7 +26,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
from .com_sparkapi import SparkRequestInstance
sri = SparkRequestInstance()
for response in sri.generate(inputs, llm_kwargs, history, sys_prompt):
for response in sri.generate(inputs, llm_kwargs, history, sys_prompt, use_image_api=False):
if len(observe_window) >= 1:
observe_window[0] = response
if len(observe_window) >= 2:
@@ -52,7 +52,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
# 开始接收回复
from .com_sparkapi import SparkRequestInstance
sri = SparkRequestInstance()
for response in sri.generate(inputs, llm_kwargs, history, system_prompt):
for response in sri.generate(inputs, llm_kwargs, history, system_prompt, use_image_api=True):
chatbot[-1] = (inputs, response)
yield from update_ui(chatbot=chatbot, history=history)

228
request_llms/com_google.py 普通文件
查看文件

@@ -0,0 +1,228 @@
# encoding: utf-8
# @Time : 2023/12/25
# @Author : Spike
# @Descr :
import json
import os
import re
import requests
from typing import List, Dict, Tuple
from toolbox import get_conf, encode_image, get_pictures_list
proxies, TIMEOUT_SECONDS = get_conf("proxies", "TIMEOUT_SECONDS")
"""
========================================================================
第五部分 一些文件处理方法
files_filter_handler 根据type过滤文件
input_encode_handler 提取input中的文件,并解析
file_manifest_filter_html 根据type过滤文件, 并解析为html or md 文本
link_mtime_to_md 文件增加本地时间参数,避免下载到缓存文件
html_view_blank 超链接
html_local_file 本地文件取相对路径
to_markdown_tabs 文件list 转换为 md tab
"""
def files_filter_handler(file_list):
new_list = []
filter_ = [
"png",
"jpg",
"jpeg",
"bmp",
"svg",
"webp",
"ico",
"tif",
"tiff",
"raw",
"eps",
]
for file in file_list:
file = str(file).replace("file=", "")
if os.path.exists(file):
if str(os.path.basename(file)).split(".")[-1] in filter_:
new_list.append(file)
return new_list
def input_encode_handler(inputs, llm_kwargs):
if llm_kwargs["most_recent_uploaded"].get("path"):
image_paths = get_pictures_list(llm_kwargs["most_recent_uploaded"]["path"])
md_encode = []
for md_path in image_paths:
type_ = os.path.splitext(md_path)[1].replace(".", "")
type_ = "jpeg" if type_ == "jpg" else type_
md_encode.append({"data": encode_image(md_path), "type": type_})
return inputs, md_encode
def file_manifest_filter_html(file_list, filter_: list = None, md_type=False):
new_list = []
if not filter_:
filter_ = [
"png",
"jpg",
"jpeg",
"bmp",
"svg",
"webp",
"ico",
"tif",
"tiff",
"raw",
"eps",
]
for file in file_list:
if str(os.path.basename(file)).split(".")[-1] in filter_:
new_list.append(html_local_img(file, md=md_type))
elif os.path.exists(file):
new_list.append(link_mtime_to_md(file))
else:
new_list.append(file)
return new_list
def link_mtime_to_md(file):
link_local = html_local_file(file)
link_name = os.path.basename(file)
a = f"[{link_name}]({link_local}?{os.path.getmtime(file)})"
return a
def html_local_file(file):
base_path = os.path.dirname(__file__) # 项目目录
if os.path.exists(str(file)):
file = f'file={file.replace(base_path, ".")}'
return file
def html_local_img(__file, layout="left", max_width=None, max_height=None, md=True):
style = ""
if max_width is not None:
style += f"max-width: {max_width};"
if max_height is not None:
style += f"max-height: {max_height};"
__file = html_local_file(__file)
a = f'<div align="{layout}"><img src="{__file}" style="{style}"></div>'
if md:
a = f"![{__file}]({__file})"
return a
def to_markdown_tabs(head: list, tabs: list, alignment=":---:", column=False):
"""
Args:
head: 表头:[]
tabs: 表值:[[列1], [列2], [列3], [列4]]
alignment: :--- 左对齐, :---: 居中对齐, ---: 右对齐
column: True to keep data in columns, False to keep data in rows (default).
Returns:
A string representation of the markdown table.
"""
if column:
transposed_tabs = list(map(list, zip(*tabs)))
else:
transposed_tabs = tabs
# Find the maximum length among the columns
max_len = max(len(column) for column in transposed_tabs)
tab_format = "| %s "
tabs_list = "".join([tab_format % i for i in head]) + "|\n"
tabs_list += "".join([tab_format % alignment for i in head]) + "|\n"
for i in range(max_len):
row_data = [tab[i] if i < len(tab) else "" for tab in transposed_tabs]
row_data = file_manifest_filter_html(row_data, filter_=None)
tabs_list += "".join([tab_format % i for i in row_data]) + "|\n"
return tabs_list
class GoogleChatInit:
def __init__(self):
self.url_gemini = "https://generativelanguage.googleapis.com/v1beta/models/%m:streamGenerateContent?key=%k"
def generate_chat(self, inputs, llm_kwargs, history, system_prompt):
headers, payload = self.generate_message_payload(
inputs, llm_kwargs, history, system_prompt
)
response = requests.post(
url=self.url_gemini,
headers=headers,
data=json.dumps(payload),
stream=True,
proxies=proxies,
timeout=TIMEOUT_SECONDS,
)
return response.iter_lines()
def __conversation_user(self, user_input, llm_kwargs):
what_i_have_asked = {"role": "user", "parts": []}
if "vision" not in self.url_gemini:
input_ = user_input
encode_img = []
else:
input_, encode_img = input_encode_handler(user_input, llm_kwargs=llm_kwargs)
what_i_have_asked["parts"].append({"text": input_})
if encode_img:
for data in encode_img:
what_i_have_asked["parts"].append(
{
"inline_data": {
"mime_type": f"image/{data['type']}",
"data": data["data"],
}
}
)
return what_i_have_asked
def __conversation_history(self, history, llm_kwargs):
messages = []
conversation_cnt = len(history) // 2
if conversation_cnt:
for index in range(0, 2 * conversation_cnt, 2):
what_i_have_asked = self.__conversation_user(history[index], llm_kwargs)
what_gpt_answer = {
"role": "model",
"parts": [{"text": history[index + 1]}],
}
messages.append(what_i_have_asked)
messages.append(what_gpt_answer)
return messages
def generate_message_payload(
self, inputs, llm_kwargs, history, system_prompt
) -> Tuple[Dict, Dict]:
messages = [
# {"role": "system", "parts": [{"text": system_prompt}]}, # gemini 不允许对话轮次为偶数,所以这个没有用,看后续支持吧。。。
# {"role": "user", "parts": [{"text": ""}]},
# {"role": "model", "parts": [{"text": ""}]}
]
self.url_gemini = self.url_gemini.replace(
"%m", llm_kwargs["llm_model"]
).replace("%k", get_conf("GEMINI_API_KEY"))
header = {"Content-Type": "application/json"}
if "vision" not in self.url_gemini: # 不是vision 才处理history
messages.extend(
self.__conversation_history(history, llm_kwargs)
) # 处理 history
messages.append(self.__conversation_user(inputs, llm_kwargs)) # 处理用户对话
payload = {
"contents": messages,
"generationConfig": {
# "maxOutputTokens": 800,
"stopSequences": str(llm_kwargs.get("stop", "")).split(" "),
"temperature": llm_kwargs.get("temperature", 1),
"topP": llm_kwargs.get("top_p", 0.8),
"topK": 10,
},
}
return header, payload
if __name__ == "__main__":
google = GoogleChatInit()
# print(gootle.generate_message_payload('你好呀', {}, ['123123', '3123123'], ''))
# gootle.input_encode_handle('123123[123123](./123123), ![53425](./asfafa/fff.jpg)')

94
request_llms/com_qwenapi.py 普通文件
查看文件

@@ -0,0 +1,94 @@
from http import HTTPStatus
from toolbox import get_conf
import threading
import logging
timeout_bot_msg = '[Local Message] Request timeout. Network error.'
class QwenRequestInstance():
def __init__(self):
import dashscope
self.time_to_yield_event = threading.Event()
self.time_to_exit_event = threading.Event()
self.result_buf = ""
def validate_key():
DASHSCOPE_API_KEY = get_conf("DASHSCOPE_API_KEY")
if DASHSCOPE_API_KEY == '': return False
return True
if not validate_key():
raise RuntimeError('请配置 DASHSCOPE_API_KEY')
dashscope.api_key = get_conf("DASHSCOPE_API_KEY")
def generate(self, inputs, llm_kwargs, history, system_prompt):
# import _thread as thread
from dashscope import Generation
QWEN_MODEL = {
'qwen-turbo': Generation.Models.qwen_turbo,
'qwen-plus': Generation.Models.qwen_plus,
'qwen-max': Generation.Models.qwen_max,
}[llm_kwargs['llm_model']]
top_p = llm_kwargs.get('top_p', 0.8)
if top_p == 0: top_p += 1e-5
if top_p == 1: top_p -= 1e-5
self.result_buf = ""
responses = Generation.call(
model=QWEN_MODEL,
messages=generate_message_payload(inputs, llm_kwargs, history, system_prompt),
top_p=top_p,
temperature=llm_kwargs.get('temperature', 1.0),
result_format='message',
stream=True,
incremental_output=True
)
for response in responses:
if response.status_code == HTTPStatus.OK:
if response.output.choices[0].finish_reason == 'stop':
yield self.result_buf
break
elif response.output.choices[0].finish_reason == 'length':
self.result_buf += "[Local Message] 生成长度过长,后续输出被截断"
yield self.result_buf
break
else:
self.result_buf += response.output.choices[0].message.content
yield self.result_buf
else:
self.result_buf += f"[Local Message] 请求错误:状态码:{response.status_code},错误码:{response.code},消息:{response.message}"
yield self.result_buf
break
logging.info(f'[raw_input] {inputs}')
logging.info(f'[response] {self.result_buf}')
return self.result_buf
def generate_message_payload(inputs, llm_kwargs, history, system_prompt):
conversation_cnt = len(history) // 2
if system_prompt == '': system_prompt = 'Hello!'
messages = [{"role": "user", "content": system_prompt}, {"role": "assistant", "content": "Certainly!"}]
if conversation_cnt:
for index in range(0, 2*conversation_cnt, 2):
what_i_have_asked = {}
what_i_have_asked["role"] = "user"
what_i_have_asked["content"] = history[index]
what_gpt_answer = {}
what_gpt_answer["role"] = "assistant"
what_gpt_answer["content"] = history[index+1]
if what_i_have_asked["content"] != "":
if what_gpt_answer["content"] == "":
continue
if what_gpt_answer["content"] == timeout_bot_msg:
continue
messages.append(what_i_have_asked)
messages.append(what_gpt_answer)
else:
messages[-1]['content'] = what_gpt_answer['content']
what_i_ask_now = {}
what_i_ask_now["role"] = "user"
what_i_ask_now["content"] = inputs
messages.append(what_i_ask_now)
return messages

查看文件

@@ -72,12 +72,12 @@ class SparkRequestInstance():
self.result_buf = ""
def generate(self, inputs, llm_kwargs, history, system_prompt):
def generate(self, inputs, llm_kwargs, history, system_prompt, use_image_api=False):
llm_kwargs = llm_kwargs
history = history
system_prompt = system_prompt
import _thread as thread
thread.start_new_thread(self.create_blocking_request, (inputs, llm_kwargs, history, system_prompt))
thread.start_new_thread(self.create_blocking_request, (inputs, llm_kwargs, history, system_prompt, use_image_api))
while True:
self.time_to_yield_event.wait(timeout=1)
if self.time_to_yield_event.is_set():
@@ -86,7 +86,7 @@ class SparkRequestInstance():
return self.result_buf
def create_blocking_request(self, inputs, llm_kwargs, history, system_prompt):
def create_blocking_request(self, inputs, llm_kwargs, history, system_prompt, use_image_api):
if llm_kwargs['llm_model'] == 'sparkv2':
gpt_url = self.gpt_url_v2
elif llm_kwargs['llm_model'] == 'sparkv3':
@@ -94,10 +94,12 @@ class SparkRequestInstance():
else:
gpt_url = self.gpt_url
file_manifest = []
if llm_kwargs.get('most_recent_uploaded'):
if use_image_api and llm_kwargs.get('most_recent_uploaded'):
if llm_kwargs['most_recent_uploaded'].get('path'):
file_manifest = get_pictures_list(llm_kwargs['most_recent_uploaded']['path'])
gpt_url = self.gpt_url_img
if len(file_manifest) > 0:
print('正在使用讯飞图片理解API')
gpt_url = self.gpt_url_img
wsParam = Ws_Param(self.appid, self.api_key, self.api_secret, gpt_url)
websocket.enableTrace(False)
wsUrl = wsParam.create_url()

查看文件

@@ -5,4 +5,3 @@ accelerate
matplotlib
huggingface_hub
triton

查看文件

@@ -1,4 +1 @@
modelscope
transformers_stream_generator
auto-gptq
optimum
dashscope

查看文件

@@ -0,0 +1,5 @@
modelscope
transformers_stream_generator
auto-gptq
optimum
urllib3<2

查看文件

@@ -3,12 +3,14 @@
# """
def validate_path():
import os, sys
dir_name = os.path.dirname(__file__)
root_dir_assume = os.path.abspath(os.path.dirname(__file__) + '/..')
os.path.dirname(__file__)
root_dir_assume = os.path.abspath(os.path.dirname(__file__) + "/..")
os.chdir(root_dir_assume)
sys.path.append(root_dir_assume)
validate_path() # validate path so you can run from base directory
validate_path() # validate path so you can run from base directory
if __name__ == "__main__":
# from request_llms.bridge_newbingfree import predict_no_ui_long_connection
# from request_llms.bridge_moss import predict_no_ui_long_connection
@@ -18,19 +20,19 @@ if __name__ == "__main__":
# from request_llms.bridge_internlm import predict_no_ui_long_connection
# from request_llms.bridge_deepseekcoder import predict_no_ui_long_connection
# from request_llms.bridge_qwen_7B import predict_no_ui_long_connection
from request_llms.bridge_qwen import predict_no_ui_long_connection
from request_llms.bridge_qwen_local import predict_no_ui_long_connection
# from request_llms.bridge_spark import predict_no_ui_long_connection
# from request_llms.bridge_zhipu import predict_no_ui_long_connection
# from request_llms.bridge_chatglm3 import predict_no_ui_long_connection
llm_kwargs = {
'max_length': 4096,
'top_p': 1,
'temperature': 1,
"max_length": 4096,
"top_p": 1,
"temperature": 1,
}
result = predict_no_ui_long_connection( inputs="请问什么是质子?",
llm_kwargs=llm_kwargs,
history=["你好", "我好!"],
sys_prompt="")
print('final result:', result)
result = predict_no_ui_long_connection(
inputs="请问什么是质子?", llm_kwargs=llm_kwargs, history=["你好", "我好!"], sys_prompt=""
)
print("final result:", result)

查看文件

@@ -29,16 +29,20 @@ md = """
请随时告诉我您的需求,我会尽力提供帮助。如果您有任何问题或需要解答的议题,请随时提问。
"""
def validate_path():
import os, sys
dir_name = os.path.dirname(__file__)
root_dir_assume = os.path.abspath(os.path.dirname(__file__) + '/..')
os.path.dirname(__file__)
root_dir_assume = os.path.abspath(os.path.dirname(__file__) + "/..")
os.chdir(root_dir_assume)
sys.path.append(root_dir_assume)
validate_path() # validate path so you can run from base directory
validate_path() # validate path so you can run from base directory
from toolbox import markdown_convertion
html = markdown_convertion(md)
print(html)
with open('test.html', 'w', encoding='utf-8') as f:
with open("test.html", "w", encoding="utf-8") as f:
f.write(html)

查看文件

@@ -4,16 +4,28 @@
import os, sys
def validate_path(): dir_name = os.path.dirname(__file__); root_dir_assume = os.path.abspath(dir_name + '/..'); os.chdir(root_dir_assume); sys.path.append(root_dir_assume)
validate_path() # 返回项目根路径
def validate_path():
dir_name = os.path.dirname(__file__)
root_dir_assume = os.path.abspath(dir_name + "/..")
os.chdir(root_dir_assume)
sys.path.append(root_dir_assume)
validate_path() # 返回项目根路径
if __name__ == "__main__":
from tests.test_utils import plugin_test
# plugin_test(plugin='crazy_functions.函数动态生成->函数动态生成', main_input='交换图像的蓝色通道和红色通道', advanced_arg={"file_path_arg": "./build/ants.jpg"})
# plugin_test(plugin='crazy_functions.Latex输出PDF结果->Latex翻译中文并重新编译PDF', main_input="2307.07522")
plugin_test(plugin='crazy_functions.Latex输出PDF结果->Latex翻译中文并重新编译PDF', main_input="G:/SEAFILE_LOCAL/50503047/我的资料库/学位/paperlatex/aaai/Fu_8368_with_appendix")
plugin_test(
plugin="crazy_functions.Latex输出PDF结果->Latex翻译中文并重新编译PDF",
main_input="G:/SEAFILE_LOCAL/50503047/我的资料库/学位/paperlatex/aaai/Fu_8368_with_appendix",
)
# plugin_test(plugin='crazy_functions.虚空终端->虚空终端', main_input='修改api-key为sk-jhoejriotherjep')
@@ -61,4 +73,3 @@ if __name__ == "__main__":
# advanced_arg = {"advanced_arg":"--pre_seq_len=128 --learning_rate=2e-2 --num_gpus=1 --json_dataset='t_code.json' --ptuning_directory='/home/hmp/ChatGLM2-6B/ptuning' " }
# plugin_test(plugin='crazy_functions.chatglm微调工具->启动微调', main_input='build/dev.json', advanced_arg=advanced_arg)

查看文件

@@ -9,45 +9,52 @@ from functools import wraps
import sys
import os
def chat_to_markdown_str(chat):
result = ""
for i, cc in enumerate(chat):
result += f'\n\n{cc[0]}\n\n{cc[1]}'
if i != len(chat)-1:
result += '\n\n---'
result += f"\n\n{cc[0]}\n\n{cc[1]}"
if i != len(chat) - 1:
result += "\n\n---"
return result
def silence_stdout(func):
@wraps(func)
def wrapper(*args, **kwargs):
_original_stdout = sys.stdout
sys.stdout = open(os.devnull, 'w')
sys.stdout.reconfigure(encoding='utf-8')
sys.stdout = open(os.devnull, "w")
sys.stdout.reconfigure(encoding="utf-8")
for q in func(*args, **kwargs):
sys.stdout = _original_stdout
yield q
sys.stdout = open(os.devnull, 'w')
sys.stdout.reconfigure(encoding='utf-8')
sys.stdout = open(os.devnull, "w")
sys.stdout.reconfigure(encoding="utf-8")
sys.stdout.close()
sys.stdout = _original_stdout
return wrapper
def silence_stdout_fn(func):
@wraps(func)
def wrapper(*args, **kwargs):
_original_stdout = sys.stdout
sys.stdout = open(os.devnull, 'w')
sys.stdout.reconfigure(encoding='utf-8')
sys.stdout = open(os.devnull, "w")
sys.stdout.reconfigure(encoding="utf-8")
result = func(*args, **kwargs)
sys.stdout.close()
sys.stdout = _original_stdout
return result
return wrapper
class VoidTerminal():
class VoidTerminal:
def __init__(self) -> None:
pass
vt = VoidTerminal()
vt.get_conf = silence_stdout_fn(get_conf)
vt.set_conf = silence_stdout_fn(set_conf)
@@ -56,9 +63,27 @@ vt.get_plugin_handle = silence_stdout_fn(get_plugin_handle)
vt.get_plugin_default_kwargs = silence_stdout_fn(get_plugin_default_kwargs)
vt.get_chat_handle = silence_stdout_fn(get_chat_handle)
vt.get_chat_default_kwargs = silence_stdout_fn(get_chat_default_kwargs)
vt.chat_to_markdown_str = (chat_to_markdown_str)
proxies, WEB_PORT, LLM_MODEL, CONCURRENT_COUNT, AUTHENTICATION, CHATBOT_HEIGHT, LAYOUT, API_KEY = \
vt.get_conf('proxies', 'WEB_PORT', 'LLM_MODEL', 'CONCURRENT_COUNT', 'AUTHENTICATION', 'CHATBOT_HEIGHT', 'LAYOUT', 'API_KEY')
vt.chat_to_markdown_str = chat_to_markdown_str
(
proxies,
WEB_PORT,
LLM_MODEL,
CONCURRENT_COUNT,
AUTHENTICATION,
CHATBOT_HEIGHT,
LAYOUT,
API_KEY,
) = vt.get_conf(
"proxies",
"WEB_PORT",
"LLM_MODEL",
"CONCURRENT_COUNT",
"AUTHENTICATION",
"CHATBOT_HEIGHT",
"LAYOUT",
"API_KEY",
)
def plugin_test(main_input, plugin, advanced_arg=None, debug=True):
from rich.live import Live
@@ -69,9 +94,9 @@ def plugin_test(main_input, plugin, advanced_arg=None, debug=True):
plugin = vt.get_plugin_handle(plugin)
plugin_kwargs = vt.get_plugin_default_kwargs()
plugin_kwargs['main_input'] = main_input
plugin_kwargs["main_input"] = main_input
if advanced_arg is not None:
plugin_kwargs['plugin_kwargs'] = advanced_arg
plugin_kwargs["plugin_kwargs"] = advanced_arg
if debug:
my_working_plugin = (plugin)(**plugin_kwargs)
else:

查看文件

@@ -4,14 +4,25 @@
import os, sys
def validate_path(): dir_name = os.path.dirname(__file__); root_dir_assume = os.path.abspath(dir_name + '/..'); os.chdir(root_dir_assume); sys.path.append(root_dir_assume)
validate_path() # 返回项目根路径
def validate_path():
dir_name = os.path.dirname(__file__)
root_dir_assume = os.path.abspath(dir_name + "/..")
os.chdir(root_dir_assume)
sys.path.append(root_dir_assume)
validate_path() # 返回项目根路径
if __name__ == "__main__":
from tests.test_utils import plugin_test
plugin_test(plugin='crazy_functions.知识库问答->知识库文件注入', main_input="./README.md")
plugin_test(plugin="crazy_functions.知识库问答->知识库文件注入", main_input="./README.md")
plugin_test(plugin='crazy_functions.知识库问答->读取知识库作答', main_input="What is the installation method?")
plugin_test(
plugin="crazy_functions.知识库问答->读取知识库作答",
main_input="What is the installation method?",
)
plugin_test(plugin='crazy_functions.知识库问答->读取知识库作答', main_input="远程云服务器部署?")
plugin_test(plugin="crazy_functions.知识库问答->读取知识库作答", main_input="远程云服务器部署?")

查看文件

@@ -94,6 +94,10 @@
background-color: var(--block-background-fill) !important;
}
#cbsc {
background-color: var(--block-background-fill) !important;
}
#interact-panel .form {
border: hidden
}

查看文件

@@ -74,6 +74,7 @@ function toast_up(msg) {
m.style.cssText = "font-size: var(--text-md) !important; color: rgb(255, 255, 255); background-color: rgba(0, 0, 100, 0.6); padding: 10px 15px; margin: 0 0 0 -60px; border-radius: 4px; position: fixed; top: 50%; left: 50%; width: auto; text-align: center;";
document.body.appendChild(m);
}
function toast_down() {
var m = document.getElementById('toast_up');
if (m) {
@@ -81,6 +82,97 @@ function toast_down() {
}
}
function begin_loading_status() {
// Create the loader div and add styling
var loader = document.createElement('div');
loader.id = 'Js_File_Loading';
var C1 = document.createElement('div');
var C2 = document.createElement('div');
// var C3 = document.createElement('span');
// C3.textContent = '上传中...'
// C3.style.position = "fixed";
// C3.style.top = "50%";
// C3.style.left = "50%";
// C3.style.width = "80px";
// C3.style.height = "80px";
// C3.style.margin = "-40px 0 0 -40px";
C1.style.position = "fixed";
C1.style.top = "50%";
C1.style.left = "50%";
C1.style.width = "80px";
C1.style.height = "80px";
C1.style.borderLeft = "12px solid #00f3f300";
C1.style.borderRight = "12px solid #00f3f300";
C1.style.borderTop = "12px solid #82aaff";
C1.style.borderBottom = "12px solid #82aaff"; // Added for effect
C1.style.borderRadius = "50%";
C1.style.margin = "-40px 0 0 -40px";
C1.style.animation = "spinAndPulse 2s linear infinite";
C2.style.position = "fixed";
C2.style.top = "50%";
C2.style.left = "50%";
C2.style.width = "40px";
C2.style.height = "40px";
C2.style.borderLeft = "12px solid #00f3f300";
C2.style.borderRight = "12px solid #00f3f300";
C2.style.borderTop = "12px solid #33c9db";
C2.style.borderBottom = "12px solid #33c9db"; // Added for effect
C2.style.borderRadius = "50%";
C2.style.margin = "-20px 0 0 -20px";
C2.style.animation = "spinAndPulse2 2s linear infinite";
loader.appendChild(C1);
loader.appendChild(C2);
// loader.appendChild(C3);
document.body.appendChild(loader); // Add the loader to the body
// Set the CSS animation keyframes for spin and pulse to be synchronized
var styleSheet = document.createElement('style');
styleSheet.id = 'Js_File_Loading_Style';
styleSheet.textContent = `
@keyframes spinAndPulse {
0% { transform: rotate(0deg) scale(1); }
25% { transform: rotate(90deg) scale(1.1); }
50% { transform: rotate(180deg) scale(1); }
75% { transform: rotate(270deg) scale(0.9); }
100% { transform: rotate(360deg) scale(1); }
}
@keyframes spinAndPulse2 {
0% { transform: rotate(-90deg);}
25% { transform: rotate(-180deg);}
50% { transform: rotate(-270deg);}
75% { transform: rotate(-360deg);}
100% { transform: rotate(-450deg);}
}
`;
document.head.appendChild(styleSheet);
}
function cancel_loading_status() {
// remove the loader from the body
var loadingElement = document.getElementById('Js_File_Loading');
if (loadingElement) {
document.body.removeChild(loadingElement);
}
var loadingStyle = document.getElementById('Js_File_Loading_Style');
if (loadingStyle) {
document.head.removeChild(loadingStyle);
}
// create new listen event
let clearButton = document.querySelectorAll('div[id*="elem_upload"] button[aria-label="Clear"]');
for (let button of clearButton) {
button.addEventListener('click', function () {
setTimeout(function () {
register_upload_event();
}, 50);
});
}
}
// -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
// 第 2 部分: 复制按钮
@@ -94,8 +186,7 @@ function addCopyButton(botElement) {
const messageBtnColumnElement = botElement.querySelector('.message-btn-row');
if (messageBtnColumnElement) {
// Do something if .message-btn-column exists, for example, remove it
// messageBtnColumnElement.remove();
// if .message-btn-column exists
return;
}
@@ -154,32 +245,53 @@ function chatbotContentChanged(attempt = 1, force = false) {
// -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
function chatbotAutoHeight() {
// 自动调整高度
// 自动调整高度:立即
function update_height() {
var { panel_height_target, chatbot_height, chatbot } = get_elements(true);
if (panel_height_target != chatbot_height) {
var pixelString = panel_height_target.toString() + 'px';
var { height_target, chatbot_height, chatbot } = get_elements(true);
if (height_target != chatbot_height) {
var pixelString = height_target.toString() + 'px';
chatbot.style.maxHeight = pixelString; chatbot.style.height = pixelString;
}
}
// 自动调整高度:缓慢
function update_height_slow() {
var { panel_height_target, chatbot_height, chatbot } = get_elements();
if (panel_height_target != chatbot_height) {
new_panel_height = (panel_height_target - chatbot_height) * 0.5 + chatbot_height;
if (Math.abs(new_panel_height - panel_height_target) < 10) {
new_panel_height = panel_height_target;
var { height_target, chatbot_height, chatbot } = get_elements();
if (height_target != chatbot_height) {
// sign = (height_target - chatbot_height)/Math.abs(height_target - chatbot_height);
// speed = Math.max(Math.abs(height_target - chatbot_height), 1);
new_panel_height = (height_target - chatbot_height) * 0.5 + chatbot_height;
if (Math.abs(new_panel_height - height_target) < 10) {
new_panel_height = height_target;
}
// console.log(chatbot_height, panel_height_target, new_panel_height);
var pixelString = new_panel_height.toString() + 'px';
chatbot.style.maxHeight = pixelString; chatbot.style.height = pixelString;
}
}
monitoring_input_box()
update_height();
setInterval(function () {
update_height_slow()
}, 50); // 每100毫秒执行一次
window.addEventListener('resize', function() { update_height(); });
window.addEventListener('scroll', function() { update_height_slow(); });
setInterval(function () { update_height_slow() }, 50); // 每50毫秒执行一次
}
swapped = false;
function swap_input_area() {
// Get the elements to be swapped
var element1 = document.querySelector("#input-panel");
var element2 = document.querySelector("#basic-panel");
// Get the parent of the elements
var parent = element1.parentNode;
// Get the next sibling of element2
var nextSibling = element2.nextSibling;
// Swap the elements
parent.insertBefore(element2, element1);
parent.insertBefore(element1, nextSibling);
if (swapped) {swapped = false;}
else {swapped = true;}
}
function get_elements(consider_state_panel = false) {
@@ -191,19 +303,42 @@ function get_elements(consider_state_panel = false) {
const panel2 = document.querySelector('#basic-panel').getBoundingClientRect()
const panel3 = document.querySelector('#plugin-panel').getBoundingClientRect();
// const panel4 = document.querySelector('#interact-panel').getBoundingClientRect();
const panel5 = document.querySelector('#input-panel2').getBoundingClientRect();
const panel_active = document.querySelector('#state-panel').getBoundingClientRect();
if (consider_state_panel || panel_active.height < 25) {
document.state_panel_height = panel_active.height;
}
// 25 是chatbot的label高度, 16 是右侧的gap
var panel_height_target = panel1.height + panel2.height + panel3.height + 0 + 0 - 25 + 16 * 2;
var height_target = panel1.height + panel2.height + panel3.height + 0 + 0 - 25 + 16 * 2;
// 禁止动态的state-panel高度影响
panel_height_target = panel_height_target + (document.state_panel_height - panel_active.height)
var panel_height_target = parseInt(panel_height_target);
height_target = height_target + (document.state_panel_height - panel_active.height)
var height_target = parseInt(height_target);
var chatbot_height = chatbot.style.height;
// 交换输入区位置,使得输入区始终可用
if (!swapped){
if (panel1.top!=0 && (panel1.bottom + panel1.top)/2 < 0){ swap_input_area(); }
}
else if (swapped){
if (panel2.top!=0 && panel2.top > 0){ swap_input_area(); }
}
// 调整高度
const err_tor = 5;
if (Math.abs(panel1.left - chatbot.getBoundingClientRect().left) < err_tor){
// 是否处于窄屏模式
height_target = window.innerHeight * 0.6;
}else{
// 调整高度
const chatbot_height_exceed = 15;
const chatbot_height_exceed_m = 10;
b_panel = Math.max(panel1.bottom, panel2.bottom, panel3.bottom)
if (b_panel >= window.innerHeight - chatbot_height_exceed) {
height_target = window.innerHeight - chatbot.getBoundingClientRect().top - chatbot_height_exceed_m;
}
else if (b_panel < window.innerHeight * 0.75) {
height_target = window.innerHeight * 0.8;
}
}
var chatbot_height = parseInt(chatbot_height);
return { panel_height_target, chatbot_height, chatbot };
return { height_target, chatbot_height, chatbot };
}
@@ -217,9 +352,47 @@ var elem_upload_float = null;
var elem_input_main = null;
var elem_input_float = null;
var elem_chatbot = null;
var elem_upload_component_float = null;
var elem_upload_component = null;
var exist_file_msg = '⚠️请先删除上传区(左上方)中的历史文件,再尝试上传。'
function add_func_paste(input) {
function locate_upload_elems(){
elem_upload = document.getElementById('elem_upload')
elem_upload_float = document.getElementById('elem_upload_float')
elem_input_main = document.getElementById('user_input_main')
elem_input_float = document.getElementById('user_input_float')
elem_chatbot = document.getElementById('gpt-chatbot')
elem_upload_component_float = elem_upload_float.querySelector("input[type=file]");
elem_upload_component = elem_upload.querySelector("input[type=file]");
}
async function upload_files(files) {
let totalSizeMb = 0
elem_upload_component_float = elem_upload_float.querySelector("input[type=file]");
if (files && files.length > 0) {
// 执行具体的上传逻辑
if (elem_upload_component_float) {
for (let i = 0; i < files.length; i++) {
// 将从文件数组中获取的文件大小(单位为字节)转换为MB,
totalSizeMb += files[i].size / 1024 / 1024;
}
// 检查文件总大小是否超过20MB
if (totalSizeMb > 20) {
toast_push('⚠️文件夹大于 20MB 🚀上传文件中', 3000);
}
let event = new Event("change");
Object.defineProperty(event, "target", { value: elem_upload_component_float, enumerable: true });
Object.defineProperty(event, "currentTarget", { value: elem_upload_component_float, enumerable: true });
Object.defineProperty(elem_upload_component_float, "files", { value: files, enumerable: true });
elem_upload_component_float.dispatchEvent(event);
} else {
console.log(exist_file_msg);
toast_push(exist_file_msg, 3000);
}
}
}
function register_func_paste(input) {
let paste_files = [];
if (input) {
input.addEventListener("paste", async function (e) {
@@ -245,7 +418,7 @@ function add_func_paste(input) {
}
}
function add_func_drag(elem) {
function register_func_drag(elem) {
if (elem) {
const dragEvents = ["dragover"];
const leaveEvents = ["dragleave", "dragend", "drop"];
@@ -281,113 +454,74 @@ function add_func_drag(elem) {
}
}
async function upload_files(files) {
const uploadInputElement = elem_upload_float.querySelector("input[type=file]");
let totalSizeMb = 0
if (files && files.length > 0) {
// 执行具体的上传逻辑
if (uploadInputElement) {
for (let i = 0; i < files.length; i++) {
// 将从文件数组中获取的文件大小(单位为字节)转换为MB,
totalSizeMb += files[i].size / 1024 / 1024;
}
// 检查文件总大小是否超过20MB
if (totalSizeMb > 20) {
toast_push('⚠️文件夹大于 20MB 🚀上传文件中', 3000)
// return; // 如果超过了指定大小, 可以不进行后续上传操作
}
// 监听change事件, 原生Gradio可以实现
// uploadInputElement.addEventListener('change', function(){replace_input_string()});
let event = new Event("change");
Object.defineProperty(event, "target", { value: uploadInputElement, enumerable: true });
Object.defineProperty(event, "currentTarget", { value: uploadInputElement, enumerable: true });
Object.defineProperty(uploadInputElement, "files", { value: files, enumerable: true });
uploadInputElement.dispatchEvent(event);
} else {
toast_push(exist_file_msg, 3000)
}
}
}
function begin_loading_status() {
// Create the loader div and add styling
var loader = document.createElement('div');
loader.id = 'Js_File_Loading';
loader.style.position = "absolute";
loader.style.top = "50%";
loader.style.left = "50%";
loader.style.width = "60px";
loader.style.height = "60px";
loader.style.border = "16px solid #f3f3f3";
loader.style.borderTop = "16px solid #3498db";
loader.style.borderRadius = "50%";
loader.style.animation = "spin 2s linear infinite";
loader.style.transform = "translate(-50%, -50%)";
document.body.appendChild(loader); // Add the loader to the body
// Set the CSS animation keyframes
var styleSheet = document.createElement('style');
// styleSheet.type = 'text/css';
styleSheet.id = 'Js_File_Loading_Style'
styleSheet.innerText = `
@keyframes spin {
0% { transform: rotate(0deg); }
100% { transform: rotate(360deg); }
}`;
document.head.appendChild(styleSheet);
}
function cancel_loading_status() {
var loadingElement = document.getElementById('Js_File_Loading');
if (loadingElement) {
document.body.removeChild(loadingElement); // remove the loader from the body
}
var loadingStyle = document.getElementById('Js_File_Loading_Style');
if (loadingStyle) {
document.head.removeChild(loadingStyle);
}
let clearButton = document.querySelectorAll('div[id*="elem_upload"] button[aria-label="Clear"]');
for (let button of clearButton) {
button.addEventListener('click', function () {
setTimeout(function () {
register_upload_event();
}, 50);
function elem_upload_component_pop_message(elem) {
if (elem) {
const dragEvents = ["dragover"];
const leaveEvents = ["dragleave", "dragend", "drop"];
dragEvents.forEach(event => {
elem.addEventListener(event, function (e) {
e.preventDefault();
e.stopPropagation();
if (elem_upload_float.querySelector("input[type=file]")) {
toast_up('⚠️释放以上传文件')
} else {
toast_up(exist_file_msg)
}
});
});
}
}
function register_upload_event() {
elem_upload_float = document.getElementById('elem_upload_float')
const upload_component = elem_upload_float.querySelector("input[type=file]");
if (upload_component) {
upload_component.addEventListener('change', function (event) {
leaveEvents.forEach(event => {
elem.addEventListener(event, function (e) {
toast_down();
e.preventDefault();
e.stopPropagation();
});
});
elem.addEventListener("drop", async function (e) {
toast_push('正在上传中,请稍等。', 2000);
begin_loading_status();
});
}
}
function register_upload_event() {
locate_upload_elems();
if (elem_upload_float) {
_upload = document.querySelector("#elem_upload_float div.center.boundedheight.flex")
elem_upload_component_pop_message(_upload);
}
if (elem_upload_component_float) {
elem_upload_component_float.addEventListener('change', function (event) {
toast_push('正在上传中,请稍等。', 2000);
begin_loading_status();
});
}
if (elem_upload_component) {
elem_upload_component.addEventListener('change', function (event) {
toast_push('正在上传中,请稍等。', 2000);
begin_loading_status();
});
}else{
toast_push("oppps", 3000);
}
}
function monitoring_input_box() {
register_upload_event();
elem_upload = document.getElementById('elem_upload')
elem_upload_float = document.getElementById('elem_upload_float')
elem_input_main = document.getElementById('user_input_main')
elem_input_float = document.getElementById('user_input_float')
elem_chatbot = document.getElementById('gpt-chatbot')
if (elem_input_main) {
if (elem_input_main.querySelector("textarea")) {
add_func_paste(elem_input_main.querySelector("textarea"))
register_func_paste(elem_input_main.querySelector("textarea"))
}
}
if (elem_input_float) {
if (elem_input_float.querySelector("textarea")) {
add_func_paste(elem_input_float.querySelector("textarea"))
register_func_paste(elem_input_float.querySelector("textarea"))
}
}
if (elem_chatbot) {
add_func_drag(elem_chatbot)
register_func_drag(elem_chatbot)
}
}
@@ -441,8 +575,62 @@ function audio_fn_init() {
}
}
function minor_ui_adjustment() {
let cbsc_area = document.getElementById('cbsc');
cbsc_area.style.paddingTop = '15px';
var bar_btn_width = [];
// 自动隐藏超出范围的toolbar按钮
function auto_hide_toolbar() {
var qq = document.getElementById('tooltip');
var tab_nav = qq.getElementsByClassName('tab-nav');
if (tab_nav.length == 0){ return; }
var btn_list = tab_nav[0].getElementsByTagName('button')
if (btn_list.length == 0){ return; }
// 获取页面宽度
var page_width = document.documentElement.clientWidth;
// 总是保留的按钮数量
const always_preserve = 2;
// 获取最后一个按钮的右侧位置
var cur_right = btn_list[always_preserve-1].getBoundingClientRect().right;
if (bar_btn_width.length == 0){
// 首次运行,记录每个按钮的宽度
for (var i = 0; i < btn_list.length; i++) {
bar_btn_width.push(btn_list[i].getBoundingClientRect().width);
}
}
// 处理每一个按钮
for (var i = always_preserve; i < btn_list.length; i++) {
var element = btn_list[i];
var element_right = element.getBoundingClientRect().right;
if (element_right!=0){ cur_right = element_right; }
if (element.style.display === 'none') {
if ((cur_right + bar_btn_width[i]) < (page_width * 0.37)) {
// 恢复显示当前按钮
element.style.display = 'block';
// console.log('show');
return;
}else{
return;
}
} else {
if (cur_right > (page_width * 0.38)) {
// 隐藏当前按钮以及右侧所有按钮
for (var j = i; j < btn_list.length; j++) {
if (btn_list[j].style.display !== 'none') {
btn_list[j].style.display = 'none';
}
}
// console.log('show');
return;
}
}
}
}
setInterval(function () {
auto_hide_toolbar()
}, 200); // 每50毫秒执行一次
}
// -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
// 第 6 部分: JS初始化函数
@@ -450,6 +638,7 @@ function audio_fn_init() {
function GptAcademicJavaScriptInit(LAYOUT = "LEFT-RIGHT") {
audio_fn_init();
minor_ui_adjustment();
chatbotIndicator = gradioApp().querySelector('#gpt-chatbot > div.wrap');
var chatbotObserver = new MutationObserver(() => {
chatbotContentChanged(1);

查看文件

@@ -479,4 +479,3 @@
.dark .codehilite .vi { color: #89DDFF } /* Name.Variable.Instance */
.dark .codehilite .vm { color: #82AAFF } /* Name.Variable.Magic */
.dark .codehilite .il { color: #F78C6C } /* Literal.Number.Integer.Long */

查看文件

@@ -1,18 +1,26 @@
import os
import gradio as gr
from toolbox import get_conf
CODE_HIGHLIGHT, ADD_WAIFU, LAYOUT = get_conf('CODE_HIGHLIGHT', 'ADD_WAIFU', 'LAYOUT')
CODE_HIGHLIGHT, ADD_WAIFU, LAYOUT = get_conf("CODE_HIGHLIGHT", "ADD_WAIFU", "LAYOUT")
theme_dir = os.path.dirname(__file__)
def adjust_theme():
def adjust_theme():
try:
color_er = gr.themes.utils.colors.fuchsia
set_theme = gr.themes.Default(
primary_hue=gr.themes.utils.colors.orange,
neutral_hue=gr.themes.utils.colors.gray,
font=["Helvetica", "Microsoft YaHei", "ui-sans-serif", "sans-serif", "system-ui"],
font_mono=["ui-monospace", "Consolas", "monospace"])
font=[
"Helvetica",
"Microsoft YaHei",
"ui-sans-serif",
"sans-serif",
"system-ui",
],
font_mono=["ui-monospace", "Consolas", "monospace"],
)
set_theme.set(
# Colors
input_background_fill_dark="*neutral_800",
@@ -59,7 +67,7 @@ def adjust_theme():
button_cancel_text_color_dark="white",
)
with open(os.path.join(theme_dir, 'common.js'), 'r', encoding='utf8') as f:
with open(os.path.join(theme_dir, "common.js"), "r", encoding="utf8") as f:
js = f"<script>{f.read()}</script>"
# 添加一个萌萌的看板娘
@@ -69,21 +77,26 @@ def adjust_theme():
<script src="file=docs/waifu_plugin/jquery-ui.min.js"></script>
<script src="file=docs/waifu_plugin/autoload.js"></script>
"""
if not hasattr(gr, 'RawTemplateResponse'):
if not hasattr(gr, "RawTemplateResponse"):
gr.RawTemplateResponse = gr.routes.templates.TemplateResponse
gradio_original_template_fn = gr.RawTemplateResponse
def gradio_new_template_fn(*args, **kwargs):
res = gradio_original_template_fn(*args, **kwargs)
res.body = res.body.replace(b'</html>', f'{js}</html>'.encode("utf8"))
res.body = res.body.replace(b"</html>", f"{js}</html>".encode("utf8"))
res.init_headers()
return res
gr.routes.templates.TemplateResponse = gradio_new_template_fn # override gradio template
gr.routes.templates.TemplateResponse = (
gradio_new_template_fn # override gradio template
)
except:
set_theme = None
print('gradio版本较旧, 不能自定义字体和颜色')
print("gradio版本较旧, 不能自定义字体和颜色")
return set_theme
with open(os.path.join(theme_dir, 'contrast.css'), "r", encoding="utf-8") as f:
with open(os.path.join(theme_dir, "contrast.css"), "r", encoding="utf-8") as f:
advanced_css = f.read()
with open(os.path.join(theme_dir, 'common.css'), "r", encoding="utf-8") as f:
with open(os.path.join(theme_dir, "common.css"), "r", encoding="utf-8") as f:
advanced_css += f.read()

查看文件

@@ -303,4 +303,3 @@
.dark .codehilite .vi { color: #89DDFF } /* Name.Variable.Instance */
.dark .codehilite .vm { color: #82AAFF } /* Name.Variable.Magic */
.dark .codehilite .il { color: #F78C6C } /* Literal.Number.Integer.Long */

查看文件

@@ -1,17 +1,26 @@
import os
import gradio as gr
from toolbox import get_conf
CODE_HIGHLIGHT, ADD_WAIFU, LAYOUT = get_conf('CODE_HIGHLIGHT', 'ADD_WAIFU', 'LAYOUT')
theme_dir = os.path.dirname(__file__)
def adjust_theme():
CODE_HIGHLIGHT, ADD_WAIFU, LAYOUT = get_conf("CODE_HIGHLIGHT", "ADD_WAIFU", "LAYOUT")
theme_dir = os.path.dirname(__file__)
def adjust_theme():
try:
color_er = gr.themes.utils.colors.fuchsia
set_theme = gr.themes.Default(
primary_hue=gr.themes.utils.colors.orange,
neutral_hue=gr.themes.utils.colors.gray,
font=["Helvetica", "Microsoft YaHei", "ui-sans-serif", "sans-serif", "system-ui"],
font_mono=["ui-monospace", "Consolas", "monospace"])
font=[
"Helvetica",
"Microsoft YaHei",
"ui-sans-serif",
"sans-serif",
"system-ui",
],
font_mono=["ui-monospace", "Consolas", "monospace"],
)
set_theme.set(
# Colors
input_background_fill_dark="*neutral_800",
@@ -58,7 +67,7 @@ def adjust_theme():
button_cancel_text_color_dark="white",
)
with open(os.path.join(theme_dir, 'common.js'), 'r', encoding='utf8') as f:
with open(os.path.join(theme_dir, "common.js"), "r", encoding="utf8") as f:
js = f"<script>{f.read()}</script>"
# 添加一个萌萌的看板娘
@@ -68,21 +77,26 @@ def adjust_theme():
<script src="file=docs/waifu_plugin/jquery-ui.min.js"></script>
<script src="file=docs/waifu_plugin/autoload.js"></script>
"""
if not hasattr(gr, 'RawTemplateResponse'):
if not hasattr(gr, "RawTemplateResponse"):
gr.RawTemplateResponse = gr.routes.templates.TemplateResponse
gradio_original_template_fn = gr.RawTemplateResponse
def gradio_new_template_fn(*args, **kwargs):
res = gradio_original_template_fn(*args, **kwargs)
res.body = res.body.replace(b'</html>', f'{js}</html>'.encode("utf8"))
res.body = res.body.replace(b"</html>", f"{js}</html>".encode("utf8"))
res.init_headers()
return res
gr.routes.templates.TemplateResponse = gradio_new_template_fn # override gradio template
gr.routes.templates.TemplateResponse = (
gradio_new_template_fn # override gradio template
)
except:
set_theme = None
print('gradio版本较旧, 不能自定义字体和颜色')
print("gradio版本较旧, 不能自定义字体和颜色")
return set_theme
with open(os.path.join(theme_dir, 'default.css'), "r", encoding="utf-8") as f:
with open(os.path.join(theme_dir, "default.css"), "r", encoding="utf-8") as f:
advanced_css = f.read()
with open(os.path.join(theme_dir, 'common.css'), "r", encoding="utf-8") as f:
with open(os.path.join(theme_dir, "common.css"), "r", encoding="utf-8") as f:
advanced_css += f.read()

查看文件

@@ -2,29 +2,36 @@ import logging
import os
import gradio as gr
from toolbox import get_conf, ProxyNetworkActivate
CODE_HIGHLIGHT, ADD_WAIFU, LAYOUT = get_conf('CODE_HIGHLIGHT', 'ADD_WAIFU', 'LAYOUT')
CODE_HIGHLIGHT, ADD_WAIFU, LAYOUT = get_conf("CODE_HIGHLIGHT", "ADD_WAIFU", "LAYOUT")
theme_dir = os.path.dirname(__file__)
def dynamic_set_theme(THEME):
set_theme = gr.themes.ThemeClass()
with ProxyNetworkActivate('Download_Gradio_Theme'):
logging.info('正在下载Gradio主题,请稍等。')
if THEME.startswith('Huggingface-'): THEME = THEME.lstrip('Huggingface-')
if THEME.startswith('huggingface-'): THEME = THEME.lstrip('huggingface-')
with ProxyNetworkActivate("Download_Gradio_Theme"):
logging.info("正在下载Gradio主题,请稍等。")
if THEME.startswith("Huggingface-"):
THEME = THEME.lstrip("Huggingface-")
if THEME.startswith("huggingface-"):
THEME = THEME.lstrip("huggingface-")
set_theme = set_theme.from_hub(THEME.lower())
return set_theme
def adjust_theme():
try:
set_theme = gr.themes.ThemeClass()
with ProxyNetworkActivate('Download_Gradio_Theme'):
logging.info('正在下载Gradio主题,请稍等。')
THEME = get_conf('THEME')
if THEME.startswith('Huggingface-'): THEME = THEME.lstrip('Huggingface-')
if THEME.startswith('huggingface-'): THEME = THEME.lstrip('huggingface-')
with ProxyNetworkActivate("Download_Gradio_Theme"):
logging.info("正在下载Gradio主题,请稍等。")
THEME = get_conf("THEME")
if THEME.startswith("Huggingface-"):
THEME = THEME.lstrip("Huggingface-")
if THEME.startswith("huggingface-"):
THEME = THEME.lstrip("huggingface-")
set_theme = set_theme.from_hub(THEME.lower())
with open(os.path.join(theme_dir, 'common.js'), 'r', encoding='utf8') as f:
with open(os.path.join(theme_dir, "common.js"), "r", encoding="utf8") as f:
js = f"<script>{f.read()}</script>"
# 添加一个萌萌的看板娘
@@ -34,20 +41,26 @@ def adjust_theme():
<script src="file=docs/waifu_plugin/jquery-ui.min.js"></script>
<script src="file=docs/waifu_plugin/autoload.js"></script>
"""
if not hasattr(gr, 'RawTemplateResponse'):
if not hasattr(gr, "RawTemplateResponse"):
gr.RawTemplateResponse = gr.routes.templates.TemplateResponse
gradio_original_template_fn = gr.RawTemplateResponse
def gradio_new_template_fn(*args, **kwargs):
res = gradio_original_template_fn(*args, **kwargs)
res.body = res.body.replace(b'</html>', f'{js}</html>'.encode("utf8"))
res.body = res.body.replace(b"</html>", f"{js}</html>".encode("utf8"))
res.init_headers()
return res
gr.routes.templates.TemplateResponse = gradio_new_template_fn # override gradio template
except Exception as e:
gr.routes.templates.TemplateResponse = (
gradio_new_template_fn # override gradio template
)
except Exception:
set_theme = None
from toolbox import trimmed_format_exc
logging.error('gradio版本较旧, 不能自定义字体和颜色:', trimmed_format_exc())
logging.error("gradio版本较旧, 不能自定义字体和颜色:", trimmed_format_exc())
return set_theme
with open(os.path.join(theme_dir, 'common.css'), "r", encoding="utf-8") as f:
with open(os.path.join(theme_dir, "common.css"), "r", encoding="utf-8") as f:
advanced_css = f.read()

查看文件

@@ -197,12 +197,12 @@ footer {
}
textarea.svelte-1pie7s6 {
background: #e7e6e6 !important;
width: 96% !important;
width: 100% !important;
}
.dark textarea.svelte-1pie7s6 {
background: var(--input-background-fill) !important;
width: 96% !important;
width: 100% !important;
}
.dark input[type=number].svelte-1cl284s {
@@ -256,13 +256,13 @@ textarea.svelte-1pie7s6 {
max-height: 95% !important;
overflow-y: auto !important;
}*/
.app.svelte-1mya07g.svelte-1mya07g {
/* .app.svelte-1mya07g.svelte-1mya07g {
max-width: 100%;
position: relative;
padding: var(--size-4);
width: 100%;
height: 100%;
}
} */
.gradio-container-3-32-2 h1 {
font-weight: 700 !important;
@@ -508,12 +508,14 @@ ol:not(.options), ul:not(.options) {
[data-testid = "bot"] {
max-width: 85%;
border-bottom-left-radius: 0 !important;
box-shadow: 2px 2px 0px 1px rgba(0, 0, 0, 0.06);
background-color: var(--message-bot-background-color-light) !important;
}
[data-testid = "user"] {
max-width: 85%;
width: auto !important;
border-bottom-right-radius: 0 !important;
box-shadow: 2px 2px 0px 1px rgba(0, 0, 0, 0.06);
background-color: var(--message-user-background-color-light) !important;
}
.dark [data-testid = "bot"] {

查看文件

@@ -1,9 +1,11 @@
import os
import gradio as gr
from toolbox import get_conf
CODE_HIGHLIGHT, ADD_WAIFU, LAYOUT = get_conf('CODE_HIGHLIGHT', 'ADD_WAIFU', 'LAYOUT')
CODE_HIGHLIGHT, ADD_WAIFU, LAYOUT = get_conf("CODE_HIGHLIGHT", "ADD_WAIFU", "LAYOUT")
theme_dir = os.path.dirname(__file__)
def adjust_theme():
try:
set_theme = gr.themes.Soft(
@@ -50,7 +52,6 @@ def adjust_theme():
c900="#2B2B2B",
c950="#171717",
),
radius_size=gr.themes.sizes.radius_sm,
).set(
button_primary_background_fill="*primary_500",
@@ -75,7 +76,7 @@ def adjust_theme():
chatbot_code_background_color_dark="*neutral_950",
)
with open(os.path.join(theme_dir, 'common.js'), 'r', encoding='utf8') as f:
with open(os.path.join(theme_dir, "common.js"), "r", encoding="utf8") as f:
js = f"<script>{f.read()}</script>"
# 添加一个萌萌的看板娘
@@ -86,24 +87,29 @@ def adjust_theme():
<script src="file=docs/waifu_plugin/autoload.js"></script>
"""
with open(os.path.join(theme_dir, 'green.js'), 'r', encoding='utf8') as f:
with open(os.path.join(theme_dir, "green.js"), "r", encoding="utf8") as f:
js += f"<script>{f.read()}</script>"
if not hasattr(gr, 'RawTemplateResponse'):
if not hasattr(gr, "RawTemplateResponse"):
gr.RawTemplateResponse = gr.routes.templates.TemplateResponse
gradio_original_template_fn = gr.RawTemplateResponse
def gradio_new_template_fn(*args, **kwargs):
res = gradio_original_template_fn(*args, **kwargs)
res.body = res.body.replace(b'</html>', f'{js}</html>'.encode("utf8"))
res.body = res.body.replace(b"</html>", f"{js}</html>".encode("utf8"))
res.init_headers()
return res
gr.routes.templates.TemplateResponse = gradio_new_template_fn # override gradio template
gr.routes.templates.TemplateResponse = (
gradio_new_template_fn # override gradio template
)
except:
set_theme = None
print('gradio版本较旧, 不能自定义字体和颜色')
print("gradio版本较旧, 不能自定义字体和颜色")
return set_theme
with open(os.path.join(theme_dir, 'green.css'), "r", encoding="utf-8") as f:
with open(os.path.join(theme_dir, "green.css"), "r", encoding="utf-8") as f:
advanced_css = f.read()
with open(os.path.join(theme_dir, 'common.css'), "r", encoding="utf-8") as f:
with open(os.path.join(theme_dir, "common.css"), "r", encoding="utf-8") as f:
advanced_css += f.read()

查看文件

@@ -10,29 +10,33 @@ from toolbox import get_conf
-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
"""
def load_dynamic_theme(THEME):
adjust_dynamic_theme = None
if THEME == 'Chuanhu-Small-and-Beautiful':
if THEME == "Chuanhu-Small-and-Beautiful":
from .green import adjust_theme, advanced_css
theme_declaration = "<h2 align=\"center\" class=\"small\">[Chuanhu-Small-and-Beautiful主题]</h2>"
elif THEME == 'High-Contrast':
theme_declaration = (
'<h2 align="center" class="small">[Chuanhu-Small-and-Beautiful主题]</h2>'
)
elif THEME == "High-Contrast":
from .contrast import adjust_theme, advanced_css
theme_declaration = ""
elif '/' in THEME:
elif "/" in THEME:
from .gradios import adjust_theme, advanced_css
from .gradios import dynamic_set_theme
adjust_dynamic_theme = dynamic_set_theme(THEME)
theme_declaration = ""
else:
from .default import adjust_theme, advanced_css
theme_declaration = ""
return adjust_theme, advanced_css, theme_declaration, adjust_dynamic_theme
adjust_theme, advanced_css, theme_declaration, _ = load_dynamic_theme(get_conf('THEME'))
adjust_theme, advanced_css, theme_declaration, _ = load_dynamic_theme(get_conf("THEME"))
"""
@@ -42,26 +46,26 @@ cookie相关工具函数
-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
"""
def init_cookie(cookies, chatbot):
# 为每一位访问的用户赋予一个独一无二的uuid编码
cookies.update({'uuid': uuid.uuid4()})
cookies.update({"uuid": uuid.uuid4()})
return cookies
def to_cookie_str(d):
# Pickle the dictionary and encode it as a string
pickled_dict = pickle.dumps(d)
cookie_value = base64.b64encode(pickled_dict).decode('utf-8')
cookie_value = base64.b64encode(pickled_dict).decode("utf-8")
return cookie_value
def from_cookie_str(c):
# Decode the base64-encoded string and unpickle it into a dictionary
pickled_dict = base64.b64decode(c.encode('utf-8'))
pickled_dict = base64.b64decode(c.encode("utf-8"))
return pickle.loads(pickled_dict)
"""
-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
第 3 部分
@@ -114,5 +118,3 @@ js_code_for_persistent_cookie_init = """(persistent_cookie) => {
return getCookie("persistent_cookie");
}
"""

查看文件

@@ -11,8 +11,10 @@ import glob
import math
from latex2mathml.converter import convert as tex2mathml
from functools import wraps, lru_cache
pj = os.path.join
default_user_name = 'default_user'
"""
========================================================================
第一部分
@@ -26,6 +28,7 @@ default_user_name = 'default_user'
========================================================================
"""
class ChatBotWithCookies(list):
def __init__(self, cookie):
"""
@@ -67,18 +70,18 @@ def ArgsGeneralWrapper(f):
else:
user_name = default_user_name
cookies.update({
'top_p':top_p,
'top_p': top_p,
'api_key': cookies['api_key'],
'llm_model': llm_model,
'temperature':temperature,
'temperature': temperature,
'user_name': user_name,
})
llm_kwargs = {
'api_key': cookies['api_key'],
'llm_model': llm_model,
'top_p':top_p,
'top_p': top_p,
'max_length': max_length,
'temperature':temperature,
'temperature': temperature,
'client_ip': request.client.host,
'most_recent_uploaded': cookies.get('most_recent_uploaded')
}
@@ -103,8 +106,10 @@ def ArgsGeneralWrapper(f):
final_cookies = chatbot_with_cookie.get_cookies()
# len(args) != 0 代表“提交”键对话通道,或者基础功能通道
if len(args) != 0 and 'files_to_promote' in final_cookies and len(final_cookies['files_to_promote']) > 0:
chatbot_with_cookie.append(["检测到**滞留的缓存文档**,请及时处理。", "请及时点击“**保存当前对话**”获取所有滞留文档。"])
chatbot_with_cookie.append(
["检测到**滞留的缓存文档**,请及时处理。", "请及时点击“**保存当前对话**”获取所有滞留文档。"])
yield from update_ui(chatbot_with_cookie, final_cookies['history'], msg="检测到被滞留的缓存文档")
return decorated
@@ -129,6 +134,7 @@ def update_ui(chatbot, history, msg='正常', **kwargs): # 刷新界面
yield cookies, chatbot_gr, history, msg
def update_ui_lastest_msg(lastmsg, chatbot, history, delay=1): # 刷新界面
"""
刷新用户界面
@@ -147,6 +153,7 @@ def trimmed_format_exc():
replace_path = "."
return str.replace(current_path, replace_path)
def CatchException(f):
"""
装饰器函数,捕捉函数f中的异常并封装到一个生成器中返回,并显示到聊天当中。
@@ -164,9 +171,9 @@ def CatchException(f):
if len(chatbot_with_cookie) == 0:
chatbot_with_cookie.clear()
chatbot_with_cookie.append(["插件调度异常", "异常原因"])
chatbot_with_cookie[-1] = (chatbot_with_cookie[-1][0],
f"[Local Message] 插件调用出错: \n\n{tb_str} \n\n当前代理可用性: \n\n{check_proxy(proxies)}")
yield from update_ui(chatbot=chatbot_with_cookie, history=history, msg=f'异常 {e}') # 刷新界面
chatbot_with_cookie[-1] = (chatbot_with_cookie[-1][0], f"[Local Message] 插件调用出错: \n\n{tb_str} \n")
yield from update_ui(chatbot=chatbot_with_cookie, history=history, msg=f'异常 {e}') # 刷新界面
return decorated
@@ -209,6 +216,7 @@ def HotReload(f):
========================================================================
"""
def get_reduce_token_percent(text):
"""
* 此函数未来将被弃用
@@ -220,9 +228,9 @@ def get_reduce_token_percent(text):
EXCEED_ALLO = 500 # 稍微留一点余地,否则在回复时会因余量太少出问题
max_limit = float(match[0]) - EXCEED_ALLO
current_tokens = float(match[1])
ratio = max_limit/current_tokens
ratio = max_limit / current_tokens
assert ratio > 0 and ratio < 1
return ratio, str(int(current_tokens-max_limit))
return ratio, str(int(current_tokens - max_limit))
except:
return 0.5, '不详'
@@ -268,8 +276,6 @@ def regular_txt_to_markdown(text):
return text
def report_exception(chatbot, history, a, b):
"""
向chatbot中添加错误信息
@@ -352,7 +358,8 @@ def markdown_convertion(txt):
"""
解决一个mdx_math的bug单$包裹begin命令时多余<script>
"""
content = content.replace('<script type="math/tex">\n<script type="math/tex; mode=display">', '<script type="math/tex; mode=display">')
content = content.replace('<script type="math/tex">\n<script type="math/tex; mode=display">',
'<script type="math/tex; mode=display">')
content = content.replace('</script>\n</script>', '</script>')
return content
@@ -363,16 +370,16 @@ def markdown_convertion(txt):
if '```' in txt and '```reference' not in txt: return False
if '$' not in txt and '\\[' not in txt: return False
mathpatterns = {
r'(?<!\\|\$)(\$)([^\$]+)(\$)': {'allow_multi_lines': False}, #  $...$
r'(?<!\\)(\$\$)([^\$]+)(\$\$)': {'allow_multi_lines': True}, # $$...$$
r'(?<!\\)(\\\[)(.+?)(\\\])': {'allow_multi_lines': False}, # \[...\]
# r'(?<!\\)(\\\()(.+?)(\\\))': {'allow_multi_lines': False}, # \(...\)
# r'(?<!\\)(\\begin{([a-z]+?\*?)})(.+?)(\\end{\2})': {'allow_multi_lines': True}, # \begin...\end
# r'(?<!\\)(\$`)([^`]+)(`\$)': {'allow_multi_lines': False}, # $`...`$
r'(?<!\\|\$)(\$)([^\$]+)(\$)': {'allow_multi_lines': False}, #  $...$
r'(?<!\\)(\$\$)([^\$]+)(\$\$)': {'allow_multi_lines': True}, # $$...$$
r'(?<!\\)(\\\[)(.+?)(\\\])': {'allow_multi_lines': False}, # \[...\]
# r'(?<!\\)(\\\()(.+?)(\\\))': {'allow_multi_lines': False}, # \(...\)
# r'(?<!\\)(\\begin{([a-z]+?\*?)})(.+?)(\\end{\2})': {'allow_multi_lines': True}, # \begin...\end
# r'(?<!\\)(\$`)([^`]+)(`\$)': {'allow_multi_lines': False}, # $`...`$
}
matches = []
for pattern, property in mathpatterns.items():
flags = re.ASCII|re.DOTALL if property['allow_multi_lines'] else re.ASCII
flags = re.ASCII | re.DOTALL if property['allow_multi_lines'] else re.ASCII
matches.extend(re.findall(pattern, txt, flags))
if len(matches) == 0: return False
contain_any_eq = False
@@ -389,7 +396,7 @@ def markdown_convertion(txt):
def fix_markdown_indent(txt):
# fix markdown indent
if (' - ' not in txt) or ('. ' not in txt):
return txt # do not need to fix, fast escape
return txt # do not need to fix, fast escape
# walk through the lines and fix non-standard indentation
lines = txt.split("\n")
pattern = re.compile(r'^\s+-')
@@ -401,7 +408,7 @@ def markdown_convertion(txt):
stripped_string = line.lstrip()
num_spaces = len(line) - len(stripped_string)
if (num_spaces % 4) == 3:
num_spaces_should_be = math.ceil(num_spaces/4) * 4
num_spaces_should_be = math.ceil(num_spaces / 4) * 4
lines[i] = ' ' * num_spaces_should_be + stripped_string
return '\n'.join(lines)
@@ -409,7 +416,8 @@ def markdown_convertion(txt):
if is_equation(txt): # 有$标识的公式符号,且没有代码段```的标识
# convert everything to html format
split = markdown.markdown(text='---')
convert_stage_1 = markdown.markdown(text=txt, extensions=['sane_lists', 'tables', 'mdx_math', 'fenced_code'], extension_configs=markdown_extension_configs)
convert_stage_1 = markdown.markdown(text=txt, extensions=['sane_lists', 'tables', 'mdx_math', 'fenced_code'],
extension_configs=markdown_extension_configs)
convert_stage_1 = markdown_bug_hunt(convert_stage_1)
# 1. convert to easy-to-copy tex (do not render math)
convert_stage_2_1, n = re.subn(find_equation_pattern, replace_math_no_render, convert_stage_1, flags=re.DOTALL)
@@ -441,8 +449,7 @@ def close_up_code_segment_during_stream(gpt_reply):
segments = gpt_reply.split('```')
n_mark = len(segments) - 1
if n_mark % 2 == 1:
# print('输出代码片段中!')
return gpt_reply+'\n```'
return gpt_reply + '\n```' # 输出代码片段中!
else:
return gpt_reply
@@ -559,6 +566,7 @@ def file_already_in_downloadzone(file, user_path):
except:
return False
def promote_file_to_downloadzone(file, rename_file=None, chatbot=None):
# 将文件复制一份到下载区
import shutil
@@ -581,8 +589,10 @@ def promote_file_to_downloadzone(file, rename_file=None, chatbot=None):
if not os.path.exists(new_path): shutil.copyfile(file, new_path)
# 将文件添加到chatbot cookie中
if chatbot is not None:
if 'files_to_promote' in chatbot._cookies: current = chatbot._cookies['files_to_promote']
else: current = []
if 'files_to_promote' in chatbot._cookies:
current = chatbot._cookies['files_to_promote']
else:
current = []
if new_path not in current: # 避免把同一个文件添加多次
chatbot._cookies.update({'files_to_promote': [new_path] + current})
return new_path
@@ -605,8 +615,10 @@ def del_outdated_uploads(outdate_time_seconds, target_path_base=None):
for subdirectory in glob.glob(f'{user_upload_dir}/*'):
subdirectory_time = os.path.getmtime(subdirectory)
if subdirectory_time < one_hour_ago:
try: shutil.rmtree(subdirectory)
except: pass
try:
shutil.rmtree(subdirectory)
except:
pass
return
@@ -681,7 +693,7 @@ def on_file_uploaded(request: gradio.Request, files, chatbot, txt, txt2, checkbo
os.makedirs(target_path_base, exist_ok=True)
# 移除过时的旧文件从而节省空间&保护隐私
outdate_time_seconds = 3600 # 一小时
outdate_time_seconds = 3600 # 一小时
del_outdated_uploads(outdate_time_seconds, get_upload_folder(user_name))
# 逐个文件转移到目标路径
@@ -690,12 +702,7 @@ def on_file_uploaded(request: gradio.Request, files, chatbot, txt, txt2, checkbo
file_origin_name = os.path.basename(file.orig_name)
this_file_path = pj(target_path_base, file_origin_name)
shutil.move(file.name, this_file_path)
upload_msg += extract_archive(file_path=this_file_path, dest_dir=this_file_path+'.extract')
if "浮动输入区" in checkboxes:
txt, txt2 = "", target_path_base
else:
txt, txt2 = target_path_base, ""
upload_msg += extract_archive(file_path=this_file_path, dest_dir=this_file_path + '.extract')
# 整理文件集合 输出消息
moved_files = [fp for fp in glob.glob(f'{target_path_base}/**/*', recursive=True)]
@@ -703,7 +710,11 @@ def on_file_uploaded(request: gradio.Request, files, chatbot, txt, txt2, checkbo
chatbot.append(['我上传了文件,请查收',
f'[Local Message] 收到以下文件: \n\n{moved_files_str}' +
f'\n\n调用路径参数已自动修正到: \n\n{txt}' +
f'\n\n现在您点击任意函数插件时,以上文件将被作为输入参数'+upload_msg])
f'\n\n现在您点击任意函数插件时,以上文件将被作为输入参数' + upload_msg])
txt, txt2 = target_path_base, ""
if "浮动输入区" in checkboxes:
txt, txt2 = txt2, txt
# 记录近期文件
cookies.update({
@@ -732,34 +743,40 @@ def on_report_generated(cookies, files, chatbot):
chatbot.append(['报告如何远程获取?', f'报告已经添加到右侧“文件上传区”(可能处于折叠状态),请查收。{file_links}'])
return cookies, report_files, chatbot
def load_chat_cookies():
API_KEY, LLM_MODEL, AZURE_API_KEY = get_conf('API_KEY', 'LLM_MODEL', 'AZURE_API_KEY')
AZURE_CFG_ARRAY, NUM_CUSTOM_BASIC_BTN = get_conf('AZURE_CFG_ARRAY', 'NUM_CUSTOM_BASIC_BTN')
# deal with azure openai key
if is_any_api_key(AZURE_API_KEY):
if is_any_api_key(API_KEY): API_KEY = API_KEY + ',' + AZURE_API_KEY
else: API_KEY = AZURE_API_KEY
if is_any_api_key(API_KEY):
API_KEY = API_KEY + ',' + AZURE_API_KEY
else:
API_KEY = AZURE_API_KEY
if len(AZURE_CFG_ARRAY) > 0:
for azure_model_name, azure_cfg_dict in AZURE_CFG_ARRAY.items():
if not azure_model_name.startswith('azure'):
raise ValueError("AZURE_CFG_ARRAY中配置的模型必须以azure开头")
AZURE_API_KEY_ = azure_cfg_dict["AZURE_API_KEY"]
if is_any_api_key(AZURE_API_KEY_):
if is_any_api_key(API_KEY): API_KEY = API_KEY + ',' + AZURE_API_KEY_
else: API_KEY = AZURE_API_KEY_
if is_any_api_key(API_KEY):
API_KEY = API_KEY + ',' + AZURE_API_KEY_
else:
API_KEY = AZURE_API_KEY_
customize_fn_overwrite_ = {}
for k in range(NUM_CUSTOM_BASIC_BTN):
customize_fn_overwrite_.update({
"自定义按钮" + str(k+1):{
"Title": r"",
"Prefix": r"请在自定义菜单中定义提示词前缀.",
"Suffix": r"请在自定义菜单中定义提示词后缀",
"Title": r"",
"Prefix": r"请在自定义菜单中定义提示词前缀.",
"Suffix": r"请在自定义菜单中定义提示词后缀",
}
})
return {'api_key': API_KEY, 'llm_model': LLM_MODEL, 'customize_fn_overwrite': customize_fn_overwrite_}
def is_openai_api_key(key):
CUSTOM_API_KEY_PATTERN = get_conf('CUSTOM_API_KEY_PATTERN')
if len(CUSTOM_API_KEY_PATTERN) != 0:
@@ -768,14 +785,17 @@ def is_openai_api_key(key):
API_MATCH_ORIGINAL = re.match(r"sk-[a-zA-Z0-9]{48}$", key)
return bool(API_MATCH_ORIGINAL)
def is_azure_api_key(key):
API_MATCH_AZURE = re.match(r"[a-zA-Z0-9]{32}$", key)
return bool(API_MATCH_AZURE)
def is_api2d_key(key):
API_MATCH_API2D = re.match(r"fk[a-zA-Z0-9]{6}-[a-zA-Z0-9]{32}$", key)
return bool(API_MATCH_API2D)
def is_any_api_key(key):
if ',' in key:
keys = key.split(',')
@@ -785,8 +805,9 @@ def is_any_api_key(key):
else:
return is_openai_api_key(key) or is_api2d_key(key) or is_azure_api_key(key)
def what_keys(keys):
avail_key_list = {'OpenAI Key':0, "Azure Key":0, "API2D Key":0}
avail_key_list = {'OpenAI Key': 0, "Azure Key": 0, "API2D Key": 0}
key_list = keys.split(',')
for k in key_list:
@@ -803,6 +824,7 @@ def what_keys(keys):
return f"检测到: OpenAI Key {avail_key_list['OpenAI Key']} 个, Azure Key {avail_key_list['Azure Key']} 个, API2D Key {avail_key_list['API2D Key']}"
def select_api_key(keys, llm_model):
import random
avail_key_list = []
@@ -826,6 +848,7 @@ def select_api_key(keys, llm_model):
api_key = random.choice(avail_key_list) # 随机负载均衡
return api_key
def read_env_variable(arg, default_value):
"""
环境变量可以是 `GPT_ACADEMIC_CONFIG`(优先),也可以直接是`CONFIG`
@@ -856,7 +879,7 @@ def read_env_variable(arg, default_value):
env_arg = env_arg.strip()
if env_arg == 'True': r = True
elif env_arg == 'False': r = False
else: print('enter True or False, but have:', env_arg); r = default_value
else: print('Enter True or False, but have:', env_arg); r = default_value
elif isinstance(default_value, int):
r = int(env_arg)
elif isinstance(default_value, float):
@@ -880,12 +903,13 @@ def read_env_variable(arg, default_value):
print亮绿(f"[ENV_VAR] 成功读取环境变量{arg}")
return r
@lru_cache(maxsize=128)
def read_single_conf_with_lru_cache(arg):
from colorful import print亮红, print亮绿, print亮蓝
try:
# 优先级1. 获取环境变量作为配置
default_ref = getattr(importlib.import_module('config'), arg) # 读取默认值作为数据类型转换的参考
default_ref = getattr(importlib.import_module('config'), arg) # 读取默认值作为数据类型转换的参考
r = read_env_variable(arg, default_ref)
except:
try:
@@ -899,7 +923,7 @@ def read_single_conf_with_lru_cache(arg):
if arg == 'API_URL_REDIRECT':
oai_rd = r.get("https://api.openai.com/v1/chat/completions", None) # API_URL_REDIRECT填写格式是错误的,请阅读`https://github.com/binary-husky/gpt_academic/wiki/项目配置说明`
if oai_rd and not oai_rd.endswith('/completions'):
print亮红( "\n\n[API_URL_REDIRECT] API_URL_REDIRECT填错了。请阅读`https://github.com/binary-husky/gpt_academic/wiki/项目配置说明`。如果您确信自己没填错,无视此消息即可。")
print亮红("\n\n[API_URL_REDIRECT] API_URL_REDIRECT填错了。请阅读`https://github.com/binary-husky/gpt_academic/wiki/项目配置说明`。如果您确信自己没填错,无视此消息即可。")
time.sleep(5)
if arg == 'API_KEY':
print亮蓝(f"[API_KEY] 本项目现已支持OpenAI和Azure的api-key。也支持同时填写多个api-key,如API_KEY=\"openai-key1,openai-key2,azure-key3\"")
@@ -907,9 +931,9 @@ def read_single_conf_with_lru_cache(arg):
if is_any_api_key(r):
print亮绿(f"[API_KEY] 您的 API_KEY 是: {r[:15]}*** API_KEY 导入成功")
else:
print亮红( "[API_KEY] 您的 API_KEY 不满足任何一种已知的密钥格式,请在config文件中修改API密钥之后再运行。")
print亮红("[API_KEY] 您的 API_KEY 不满足任何一种已知的密钥格式,请在config文件中修改API密钥之后再运行。")
if arg == 'proxies':
if not read_single_conf_with_lru_cache('USE_PROXY'): r = None # 检查USE_PROXY,防止proxies单独起作用
if not read_single_conf_with_lru_cache('USE_PROXY'): r = None # 检查USE_PROXY,防止proxies单独起作用
if r is None:
print亮红('[PROXY] 网络代理状态未配置。无代理状态下很可能无法访问OpenAI家族的模型。建议检查USE_PROXY选项是否修改。')
else:
@@ -953,17 +977,20 @@ class DummyWith():
在上下文执行开始的情况下,__enter__()方法会在代码块被执行前被调用,
而在上下文执行结束时,__exit__()方法则会被调用。
"""
def __enter__(self):
return self
def __exit__(self, exc_type, exc_value, traceback):
return
def run_gradio_in_subpath(demo, auth, port, custom_path):
"""
把gradio的运行地址更改到指定的二次路径上
"""
def is_path_legal(path: str)->bool:
def is_path_legal(path: str) -> bool:
'''
check path for sub url
path: path to check
@@ -1039,14 +1066,15 @@ def clip_history(inputs, history, tokenizer, max_token_limit):
while n_token > max_token_limit:
where = np.argmax(everything_token)
encoded = tokenizer.encode(everything[where], disallowed_special=())
clipped_encoded = encoded[:len(encoded)-delta]
everything[where] = tokenizer.decode(clipped_encoded)[:-1] # -1 to remove the may-be illegal char
clipped_encoded = encoded[:len(encoded) - delta]
everything[where] = tokenizer.decode(clipped_encoded)[:-1] # -1 to remove the may-be illegal char
everything_token[where] = get_token_num(everything[where])
n_token = get_token_num('\n'.join(everything))
history = everything[1:]
return history
"""
========================================================================
第三部分
@@ -1058,6 +1086,7 @@ def clip_history(inputs, history, tokenizer, max_token_limit):
========================================================================
"""
def zip_folder(source_folder, dest_folder, zip_name):
import zipfile
import os
@@ -1089,15 +1118,18 @@ def zip_folder(source_folder, dest_folder, zip_name):
print(f"Zip file created at {zip_file}")
def zip_result(folder):
t = gen_time_str()
zip_folder(folder, get_log_folder(), f'{t}-result.zip')
return pj(get_log_folder(), f'{t}-result.zip')
def gen_time_str():
import time
return time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime())
def get_log_folder(user=default_user_name, plugin_name='shared'):
if user is None: user = default_user_name
PATH_LOGGING = get_conf('PATH_LOGGING')
@@ -1108,29 +1140,36 @@ def get_log_folder(user=default_user_name, plugin_name='shared'):
if not os.path.exists(_dir): os.makedirs(_dir)
return _dir
def get_upload_folder(user=default_user_name, tag=None):
PATH_PRIVATE_UPLOAD = get_conf('PATH_PRIVATE_UPLOAD')
if user is None: user = default_user_name
if tag is None or len(tag)==0:
if tag is None or len(tag) == 0:
target_path_base = pj(PATH_PRIVATE_UPLOAD, user)
else:
target_path_base = pj(PATH_PRIVATE_UPLOAD, user, tag)
return target_path_base
def is_the_upload_folder(string):
PATH_PRIVATE_UPLOAD = get_conf('PATH_PRIVATE_UPLOAD')
pattern = r'^PATH_PRIVATE_UPLOAD[\\/][A-Za-z0-9_-]+[\\/]\d{4}-\d{2}-\d{2}-\d{2}-\d{2}-\d{2}$'
pattern = pattern.replace('PATH_PRIVATE_UPLOAD', PATH_PRIVATE_UPLOAD)
if re.match(pattern, string): return True
else: return False
if re.match(pattern, string):
return True
else:
return False
def get_user(chatbotwithcookies):
return chatbotwithcookies._cookies.get('user_name', default_user_name)
class ProxyNetworkActivate():
"""
这段代码定义了一个名为TempProxy的空上下文管理器, 用于给一小段代码上代理
这段代码定义了一个名为ProxyNetworkActivate的空上下文管理器, 用于给一小段代码上代理
"""
def __init__(self, task=None) -> None:
self.task = task
if not task:
@@ -1158,12 +1197,14 @@ class ProxyNetworkActivate():
if 'HTTPS_PROXY' in os.environ: os.environ.pop('HTTPS_PROXY')
return
def objdump(obj, file='objdump.tmp'):
import pickle
with open(file, 'wb+') as f:
pickle.dump(obj, f)
return
def objload(file='objdump.tmp'):
import pickle, os
if not os.path.exists(file):
@@ -1171,6 +1212,7 @@ def objload(file='objdump.tmp'):
with open(file, 'rb') as f:
return pickle.load(f)
def Singleton(cls):
"""
一个单实例装饰器
@@ -1184,6 +1226,7 @@ def Singleton(cls):
return _singleton
"""
========================================================================
第四部分
@@ -1197,6 +1240,7 @@ def Singleton(cls):
========================================================================
"""
def set_conf(key, value):
from toolbox import read_single_conf_with_lru_cache, get_conf
read_single_conf_with_lru_cache.cache_clear()
@@ -1205,10 +1249,12 @@ def set_conf(key, value):
altered = get_conf(key)
return altered
def set_multi_conf(dic):
for k, v in dic.items(): set_conf(k, v)
return
def get_plugin_handle(plugin_name):
"""
e.g. plugin_name = 'crazy_functions.批量Markdown翻译->Markdown翻译指定语言'
@@ -1220,12 +1266,14 @@ def get_plugin_handle(plugin_name):
f_hot_reload = getattr(importlib.import_module(module, fn_name), fn_name)
return f_hot_reload
def get_chat_handle():
"""
"""
from request_llms.bridge_all import predict_no_ui_long_connection
return predict_no_ui_long_connection
def get_plugin_default_kwargs():
"""
"""
@@ -1234,9 +1282,9 @@ def get_plugin_default_kwargs():
llm_kwargs = {
'api_key': cookies['api_key'],
'llm_model': cookies['llm_model'],
'top_p':1.0,
'top_p': 1.0,
'max_length': None,
'temperature':1.0,
'temperature': 1.0,
}
chatbot = ChatBotWithCookies(llm_kwargs)
@@ -1252,6 +1300,7 @@ def get_plugin_default_kwargs():
}
return DEFAULT_FN_GROUPS_kwargs
def get_chat_default_kwargs():
"""
"""
@@ -1259,9 +1308,9 @@ def get_chat_default_kwargs():
llm_kwargs = {
'api_key': cookies['api_key'],
'llm_model': cookies['llm_model'],
'top_p':1.0,
'top_p': 1.0,
'max_length': None,
'temperature':1.0,
'temperature': 1.0,
}
default_chat_kwargs = {
"inputs": "Hello there, are you ready?",
@@ -1284,15 +1333,15 @@ def get_pictures_list(path):
def have_any_recent_upload_image_files(chatbot):
_5min = 5 * 60
if chatbot is None: return False, None # chatbot is None
if chatbot is None: return False, None # chatbot is None
most_recent_uploaded = chatbot._cookies.get("most_recent_uploaded", None)
if not most_recent_uploaded: return False, None # most_recent_uploaded is None
if not most_recent_uploaded: return False, None # most_recent_uploaded is None
if time.time() - most_recent_uploaded["time"] < _5min:
most_recent_uploaded = chatbot._cookies.get("most_recent_uploaded", None)
path = most_recent_uploaded['path']
file_manifest = get_pictures_list(path)
if len(file_manifest) == 0: return False, None
return True, file_manifest # most_recent_uploaded is new
return True, file_manifest # most_recent_uploaded is new
else:
return False, None # most_recent_uploaded is too old
@@ -1307,6 +1356,7 @@ def get_max_token(llm_kwargs):
from request_llms.bridge_all import model_info
return model_info[llm_kwargs['llm_model']]['max_token']
def check_packages(packages=[]):
import importlib.util
for p in packages:

查看文件

@@ -1,5 +1,5 @@
{
"version": 3.64,
"version": 3.65,
"show_feature": true,
"new_feature": "支持直接拖拽文件到上传区 <-> 支持将图片粘贴到输入区 <-> 修复若干隐蔽的内存BUG <-> 修复多用户冲突问题 <-> 接入Deepseek Coder <-> AutoGen多智能体插件测试版"
"new_feature": "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 <-> 修复若干隐蔽的内存BUG <-> 修复多用户冲突问题 <-> 接入Deepseek Coder <-> AutoGen多智能体插件测试版"
}