diff --git a/.gitignore b/.gitignore
index 987f0547..7a9c92b8 100644
--- a/.gitignore
+++ b/.gitignore
@@ -145,3 +145,4 @@ cradle*
debug*
private*
crazy_functions/test_project/pdf_and_word
+crazy_functions/test_samples
diff --git a/README.md b/README.md
index 9f0c4893..67aed4c3 100644
--- a/README.md
+++ b/README.md
@@ -32,20 +32,20 @@ If you like this project, please give it a Star. If you've come up with more use
一键中英互译 | 一键中英互译
一键代码解释 | 可以正确显示代码、解释代码
[自定义快捷键](https://www.bilibili.com/video/BV14s4y1E7jN) | 支持自定义快捷键
-[配置代理服务器](https://www.bilibili.com/video/BV1rc411W7Dr) | 支持配置代理服务器
-模块化设计 | 支持自定义高阶的函数插件与[函数插件],插件支持[热更新](https://github.com/binary-husky/chatgpt_academic/wiki/%E5%87%BD%E6%95%B0%E6%8F%92%E4%BB%B6%E6%8C%87%E5%8D%97)
+[配置代理服务器](https://www.bilibili.com/video/BV1rc411W7Dr) | 支持代理连接OpenAI/Google等,秒解锁ChatGPT互联网[实时信息聚合](https://www.bilibili.com/video/BV1om4y127ck/)能力
+模块化设计 | 支持自定义强大的[函数插件](https://github.com/binary-husky/chatgpt_academic/tree/master/crazy_functions),插件支持[热更新](https://github.com/binary-husky/chatgpt_academic/wiki/%E5%87%BD%E6%95%B0%E6%8F%92%E4%BB%B6%E6%8C%87%E5%8D%97)
[自我程序剖析](https://www.bilibili.com/video/BV1cj411A7VW) | [函数插件] [一键读懂](https://github.com/binary-husky/chatgpt_academic/wiki/chatgpt-academic%E9%A1%B9%E7%9B%AE%E8%87%AA%E8%AF%91%E8%A7%A3%E6%8A%A5%E5%91%8A)本项目的源代码
[程序剖析](https://www.bilibili.com/video/BV1cj411A7VW) | [函数插件] 一键可以剖析其他Python/C/C++/Java/Lua/...项目树
读论文 | [函数插件] 一键解读latex论文全文并生成摘要
-Latex全文翻译、润色 | [函数插件] 一键翻译或润色latex论文
+Latex全文[翻译](https://www.bilibili.com/video/BV1nk4y1Y7Js/)、[润色](https://www.bilibili.com/video/BV1FT411H7c5/) | [函数插件] 一键翻译或润色latex论文
批量注释生成 | [函数插件] 一键批量生成函数注释
chat分析报告生成 | [函数插件] 运行后自动生成总结汇报
-Markdown中英互译 | [函数插件] 看到上面5种语言的[README](https://github.com/binary-husky/chatgpt_academic/blob/master/docs/README_EN.md)了吗?
+Markdown[中英互译](https://www.bilibili.com/video/BV1yo4y157jV/) | [函数插件] 看到上面5种语言的[README](https://github.com/binary-husky/chatgpt_academic/blob/master/docs/README_EN.md)了吗?
[arxiv小助手](https://www.bilibili.com/video/BV1LM4y1279X) | [函数插件] 输入arxiv文章url即可一键翻译摘要+下载PDF
[PDF论文全文翻译功能](https://www.bilibili.com/video/BV1KT411x7Wn) | [函数插件] PDF论文提取题目&摘要+翻译全文(多线程)
-[谷歌学术统合小助手](https://www.bilibili.com/video/BV19L411U7ia) | [函数插件] 给定任意谷歌学术搜索页面URL,让gpt帮你选择有趣的文章
-公式/图片/表格显示 | 可以同时显示公式的tex形式和渲染形式,支持公式、代码高亮
-多线程函数插件支持 | 支持多线调用chatgpt,一键处理海量文本或程序
+[谷歌学术统合小助手](https://www.bilibili.com/video/BV19L411U7ia) | [函数插件] 给定任意谷歌学术搜索页面URL,让gpt帮你[写relatedworks](https://www.bilibili.com/video/BV1GP411U7Az/)
+公式/图片/表格显示 | 可以同时显示公式的[tex形式和渲染形式](https://user-images.githubusercontent.com/96192199/230598842-1d7fcddd-815d-40ee-af60-baf488a199df.png),支持公式、代码高亮
+多线程函数插件支持 | 支持多线调用chatgpt,一键处理[海量文本](https://www.bilibili.com/video/BV1FT411H7c5/)或程序
启动暗色gradio[主题](https://github.com/binary-husky/chatgpt_academic/issues/173) | 在浏览器url后面添加```/?__dark-theme=true```可以切换dark主题
[多LLM模型](https://www.bilibili.com/video/BV1wT411p7yf)支持,[API2D](https://api2d.com/)接口支持 | 同时被GPT3.5、GPT4和[清华ChatGLM](https://github.com/THUDM/ChatGLM-6B)伺候的感觉一定会很不错吧?
huggingface免科学上网[在线体验](https://huggingface.co/spaces/qingxu98/gpt-academic) | 登陆huggingface后复制[此空间](https://huggingface.co/spaces/qingxu98/gpt-academic)
@@ -183,6 +183,8 @@ docker run --rm -it --net=host --gpus=all gpt-academic bash
2. 使用WSL2(Windows Subsystem for Linux 子系统)
请访问[部署wiki-2](https://github.com/binary-husky/chatgpt_academic/wiki/%E4%BD%BF%E7%94%A8WSL2%EF%BC%88Windows-Subsystem-for-Linux-%E5%AD%90%E7%B3%BB%E7%BB%9F%EF%BC%89%E9%83%A8%E7%BD%B2)
+3. 如何在二级网址(如`http://localhost/subpath`)下运行
+请访问[FastAPI运行说明](docs/WithFastapi.md)
## 安装-代理配置
1. 常规方法
@@ -278,12 +280,15 @@ docker run --rm -it --net=host --gpus=all gpt-academic bash

+

+
## Todo 与 版本规划:
-- version 3.2+ (todo): 函数插件支持更多参数接口
+- version 3.3+ (todo): NewBing支持
+- version 3.2: 函数插件支持更多参数接口 (保存对话功能, 解读任意语言代码+同时询问任意的LLM组合)
- version 3.1: 支持同时问询多个gpt模型!支持api2d,支持多个apikey负载均衡
- version 3.0: 对chatglm和其他小型llm的支持
- version 2.6: 重构了插件结构,提高了交互性,加入更多插件
diff --git a/config.py b/config.py
index 6da37810..daad6eae 100644
--- a/config.py
+++ b/config.py
@@ -57,6 +57,9 @@ CONCURRENT_COUNT = 100
# [("username", "password"), ("username2", "password2"), ...]
AUTHENTICATION = []
-# 重新URL重新定向,实现更换API_URL的作用(常规情况下,不要修改!!)
+# 重新URL重新定向,实现更换API_URL的作用(常规情况下,不要修改!!)
# 格式 {"https://api.openai.com/v1/chat/completions": "重定向的URL"}
API_URL_REDIRECT = {}
+
+# 如果需要在二级路径下运行(常规情况下,不要修改!!)(需要配合修改main.py才能生效!)
+CUSTOM_PATH = "/"
diff --git a/crazy_functional.py b/crazy_functional.py
index 8e3ab6a8..8b8a3941 100644
--- a/crazy_functional.py
+++ b/crazy_functional.py
@@ -19,12 +19,25 @@ def get_crazy_functions():
from crazy_functions.解析项目源代码 import 解析一个Lua项目
from crazy_functions.解析项目源代码 import 解析一个CSharp项目
from crazy_functions.总结word文档 import 总结word文档
+ from crazy_functions.解析JupyterNotebook import 解析ipynb文件
+ from crazy_functions.对话历史存档 import 对话历史存档
function_plugins = {
"解析整个Python项目": {
"Color": "stop", # 按钮颜色
"Function": HotReload(解析一个Python项目)
},
+ "保存当前的对话": {
+ "AsButton":False,
+ "Function": HotReload(对话历史存档)
+ },
+ "[测试功能] 解析Jupyter Notebook文件": {
+ "Color": "stop",
+ "AsButton":False,
+ "Function": HotReload(解析ipynb文件),
+ "AdvancedArgs": True, # 调用时,唤起高级参数输入区(默认False)
+ "ArgsReminder": "若输入0,则不解析notebook中的Markdown块", # 高级参数输入区的显示提示
+ },
"批量总结Word文档": {
"Color": "stop",
"Function": HotReload(总结word文档)
@@ -168,7 +181,7 @@ def get_crazy_functions():
"AsButton": False, # 加入下拉菜单中
"Function": HotReload(Markdown英译中)
},
-
+
})
###################### 第三组插件 ###########################
@@ -181,7 +194,7 @@ def get_crazy_functions():
"Function": HotReload(下载arxiv论文并翻译摘要)
}
})
-
+
from crazy_functions.联网的ChatGPT import 连接网络回答问题
function_plugins.update({
"连接网络回答问题(先输入问题,再点击按钮,需要访问谷歌)": {
@@ -191,5 +204,25 @@ def get_crazy_functions():
}
})
+ from crazy_functions.解析项目源代码 import 解析任意code项目
+ function_plugins.update({
+ "解析项目源代码(手动指定和筛选源代码文件类型)": {
+ "Color": "stop",
+ "AsButton": False,
+ "AdvancedArgs": True, # 调用时,唤起高级参数输入区(默认False)
+ "ArgsReminder": "输入时用逗号隔开, *代表通配符, 加了^代表不匹配; 不输入代表全部匹配。例如: \"*.c, ^*.cpp, config.toml, ^*.toml\"", # 高级参数输入区的显示提示
+ "Function": HotReload(解析任意code项目)
+ },
+ })
+ from crazy_functions.询问多个大语言模型 import 同时问询_指定模型
+ function_plugins.update({
+ "询问多个GPT模型(手动指定询问哪些模型)": {
+ "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
+ "Function": HotReload(同时问询_指定模型)
+ },
+ })
###################### 第n组插件 ###########################
return function_plugins
diff --git a/crazy_functions/crazy_functions_test.py b/crazy_functions/crazy_functions_test.py
index 7b0f0725..6020fa2f 100644
--- a/crazy_functions/crazy_functions_test.py
+++ b/crazy_functions/crazy_functions_test.py
@@ -108,6 +108,13 @@ def test_联网回答问题():
print("当前问答:", cb[-1][-1].replace("\n"," "))
for i, it in enumerate(cb): print亮蓝(it[0]); print亮黄(it[1])
+def test_解析ipynb文件():
+ from crazy_functions.解析JupyterNotebook import 解析ipynb文件
+ txt = "crazy_functions/test_samples"
+ for cookies, cb, hist, msg in 解析ipynb文件(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+ print(cb)
+
+
# test_解析一个Python项目()
# test_Latex英文润色()
# test_Markdown中译英()
@@ -116,9 +123,8 @@ def test_联网回答问题():
# test_总结word文档()
# test_下载arxiv论文并翻译摘要()
# test_解析一个Cpp项目()
-
-test_联网回答问题()
-
+# test_联网回答问题()
+test_解析ipynb文件()
input("程序完成,回车退出。")
print("退出。")
\ No newline at end of file
diff --git a/crazy_functions/对话历史存档.py b/crazy_functions/对话历史存档.py
new file mode 100644
index 00000000..1b232de4
--- /dev/null
+++ b/crazy_functions/对话历史存档.py
@@ -0,0 +1,42 @@
+from toolbox import CatchException, update_ui
+from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+
+def write_chat_to_file(chatbot, file_name=None):
+ """
+ 将对话记录history以Markdown格式写入文件中。如果没有指定文件名,则使用当前时间生成文件名。
+ """
+ import os
+ import time
+ if file_name is None:
+ file_name = 'chatGPT对话历史' + time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime()) + '.html'
+ os.makedirs('./gpt_log/', exist_ok=True)
+ with open(f'./gpt_log/{file_name}', 'w', encoding='utf8') as f:
+ for i, contents in enumerate(chatbot):
+ for content in contents:
+ try: # 这个bug没找到触发条件,暂时先这样顶一下
+ if type(content) != str: content = str(content)
+ except:
+ continue
+ f.write(content)
+ f.write('\n\n')
+ f.write('
\n\n')
+
+ res = '对话历史写入:' + os.path.abspath(f'./gpt_log/{file_name}')
+ print(res)
+ return res
+
+@CatchException
+def 对话历史存档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+ """
+ txt 输入栏用户输入的文本,例如需要翻译的一段话,再例如一个包含了待处理文件的路径
+ llm_kwargs gpt模型参数,如温度和top_p等,一般原样传递下去就行
+ plugin_kwargs 插件模型的参数,暂时没有用武之地
+ chatbot 聊天显示框的句柄,用于显示给用户
+ history 聊天历史,前情提要
+ system_prompt 给gpt的静默提醒
+ web_port 当前软件运行的端口号
+ """
+
+ chatbot.append(("保存当前对话", f"[Local Message] {write_chat_to_file(chatbot)}"))
+ 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
+
diff --git a/crazy_functions/解析JupyterNotebook.py b/crazy_functions/解析JupyterNotebook.py
new file mode 100644
index 00000000..95a3d696
--- /dev/null
+++ b/crazy_functions/解析JupyterNotebook.py
@@ -0,0 +1,145 @@
+from toolbox import update_ui
+from toolbox import CatchException, report_execption, write_results_to_file
+fast_debug = True
+
+
+class PaperFileGroup():
+ def __init__(self):
+ self.file_paths = []
+ self.file_contents = []
+ self.sp_file_contents = []
+ self.sp_file_index = []
+ self.sp_file_tag = []
+
+ # count_token
+ from request_llm.bridge_all import model_info
+ enc = model_info["gpt-3.5-turbo"]['tokenizer']
+ def get_token_num(txt): return len(
+ enc.encode(txt, disallowed_special=()))
+ self.get_token_num = get_token_num
+
+ def run_file_split(self, max_token_limit=1900):
+ """
+ 将长文本分离开来
+ """
+ for index, file_content in enumerate(self.file_contents):
+ if self.get_token_num(file_content) < max_token_limit:
+ self.sp_file_contents.append(file_content)
+ self.sp_file_index.append(index)
+ self.sp_file_tag.append(self.file_paths[index])
+ else:
+ from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
+ segments = breakdown_txt_to_satisfy_token_limit_for_pdf(
+ file_content, self.get_token_num, max_token_limit)
+ for j, segment in enumerate(segments):
+ self.sp_file_contents.append(segment)
+ self.sp_file_index.append(index)
+ self.sp_file_tag.append(
+ self.file_paths[index] + f".part-{j}.txt")
+
+
+
+def parseNotebook(filename, enable_markdown=1):
+ import json
+
+ CodeBlocks = []
+ with open(filename, 'r', encoding='utf-8', errors='replace') as f:
+ notebook = json.load(f)
+ for cell in notebook['cells']:
+ if cell['cell_type'] == 'code' and cell['source']:
+ # remove blank lines
+ cell['source'] = [line for line in cell['source'] if line.strip()
+ != '']
+ CodeBlocks.append("".join(cell['source']))
+ elif enable_markdown and cell['cell_type'] == 'markdown' and cell['source']:
+ cell['source'] = [line for line in cell['source'] if line.strip()
+ != '']
+ CodeBlocks.append("Markdown:"+"".join(cell['source']))
+
+ Code = ""
+ for idx, code in enumerate(CodeBlocks):
+ Code += f"This is {idx+1}th code block: \n"
+ Code += code+"\n"
+
+ return Code
+
+
+def ipynb解释(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
+ from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
+
+ enable_markdown = plugin_kwargs.get("advanced_arg", "1")
+ try:
+ enable_markdown = int(enable_markdown)
+ except ValueError:
+ enable_markdown = 1
+
+ pfg = PaperFileGroup()
+
+ for fp in file_manifest:
+ file_content = parseNotebook(fp, enable_markdown=enable_markdown)
+ pfg.file_paths.append(fp)
+ pfg.file_contents.append(file_content)
+
+ # <-------- 拆分过长的IPynb文件 ---------->
+ pfg.run_file_split(max_token_limit=1024)
+ n_split = len(pfg.sp_file_contents)
+
+ inputs_array = [r"This is a Jupyter Notebook file, tell me about Each Block in Chinese. Focus Just On Code." +
+ r"If a block starts with `Markdown` which means it's a markdown block in ipynbipynb. " +
+ r"Start a new line for a block and block num use Chinese." +
+ f"\n\n{frag}" for frag in pfg.sp_file_contents]
+ inputs_show_user_array = [f"{f}的分析如下" for f in pfg.sp_file_tag]
+ sys_prompt_array = ["You are a professional programmer."] * n_split
+
+ gpt_response_collection = yield from request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
+ inputs_array=inputs_array,
+ inputs_show_user_array=inputs_show_user_array,
+ llm_kwargs=llm_kwargs,
+ chatbot=chatbot,
+ history_array=[[""] for _ in range(n_split)],
+ sys_prompt_array=sys_prompt_array,
+ # max_workers=5, # OpenAI所允许的最大并行过载
+ scroller_max_len=80
+ )
+
+ # <-------- 整理结果,退出 ---------->
+ block_result = " \n".join(gpt_response_collection)
+ chatbot.append(("解析的结果如下", block_result))
+ history.extend(["解析的结果如下", block_result])
+ yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+ # <-------- 写入文件,退出 ---------->
+ res = write_results_to_file(history)
+ chatbot.append(("完成了吗?", res))
+ yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+@CatchException
+def 解析ipynb文件(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+ chatbot.append([
+ "函数插件功能?",
+ "对IPynb文件进行解析。Contributor: codycjy."])
+ yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+ history = [] # 清空历史
+ import glob
+ import os
+ if os.path.exists(txt):
+ project_folder = txt
+ else:
+ if txt == "":
+ txt = '空空如也的输入栏'
+ report_execption(chatbot, history,
+ a=f"解析项目: {txt}", b=f"找不到本地项目或无权访问: {txt}")
+ yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+ return
+ if txt.endswith('.ipynb'):
+ file_manifest = [txt]
+ else:
+ file_manifest = [f for f in glob.glob(
+ f'{project_folder}/**/*.ipynb', recursive=True)]
+ if len(file_manifest) == 0:
+ report_execption(chatbot, history,
+ a=f"解析项目: {txt}", b=f"找不到任何.ipynb文件: {txt}")
+ yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+ return
+ yield from ipynb解释(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, )
diff --git a/crazy_functions/解析项目源代码.py b/crazy_functions/解析项目源代码.py
index 375b87ae..bfa473ae 100644
--- a/crazy_functions/解析项目源代码.py
+++ b/crazy_functions/解析项目源代码.py
@@ -11,7 +11,7 @@ def 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
history_array = []
sys_prompt_array = []
report_part_1 = []
-
+
assert len(file_manifest) <= 512, "源文件太多(超过512个), 请缩减输入文件的数量。或者,您也可以选择删除此行警告,并修改代码拆分file_manifest列表,从而实现分批次处理。"
############################## <第一步,逐个文件分析,多线程> ##################################
for index, fp in enumerate(file_manifest):
@@ -63,10 +63,10 @@ def 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
current_iteration_focus = ', '.join([os.path.relpath(fp, project_folder) for index, fp in enumerate(this_iteration_file_manifest)])
i_say = f'根据以上分析,对程序的整体功能和构架重新做出概括。然后用一张markdown表格整理每个文件的功能(包括{previous_iteration_files_string})。'
inputs_show_user = f'根据以上分析,对程序的整体功能和构架重新做出概括,由于输入长度限制,可能需要分组处理,本组文件为 {current_iteration_focus} + 已经汇总的文件组。'
- this_iteration_history = copy.deepcopy(this_iteration_gpt_response_collection)
+ this_iteration_history = copy.deepcopy(this_iteration_gpt_response_collection)
this_iteration_history.append(last_iteration_result)
result = yield from request_gpt_model_in_new_thread_with_ui_alive(
- inputs=i_say, inputs_show_user=inputs_show_user, llm_kwargs=llm_kwargs, chatbot=chatbot,
+ inputs=i_say, inputs_show_user=inputs_show_user, llm_kwargs=llm_kwargs, chatbot=chatbot,
history=this_iteration_history, # 迭代之前的分析
sys_prompt="你是一个程序架构分析师,正在分析一个项目的源代码。")
report_part_2.extend([i_say, result])
@@ -222,8 +222,8 @@ def 解析一个Golang项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
yield from 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
-
-
+
+
@CatchException
def 解析一个Lua项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
history = [] # 清空历史,以免输入溢出
@@ -243,9 +243,9 @@ def 解析一个Lua项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何lua文件: {txt}")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
- yield from 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
-
-
+ yield from 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
+
+
@CatchException
def 解析一个CSharp项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
history = [] # 清空历史,以免输入溢出
@@ -263,4 +263,45 @@ def 解析一个CSharp项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何CSharp文件: {txt}")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
- yield from 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
+ yield from 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
+
+
+@CatchException
+def 解析任意code项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+ txt_pattern = plugin_kwargs.get("advanced_arg")
+ txt_pattern = txt_pattern.replace(",", ",")
+ # 将要匹配的模式(例如: *.c, *.cpp, *.py, config.toml)
+ pattern_include = [_.lstrip(" ,").rstrip(" ,") for _ in txt_pattern.split(",") if _ != "" and not _.strip().startswith("^")]
+ if not pattern_include: pattern_include = ["*"] # 不输入即全部匹配
+ # 将要忽略匹配的文件后缀(例如: ^*.c, ^*.cpp, ^*.py)
+ pattern_except_suffix = [_.lstrip(" ^*.,").rstrip(" ,") for _ in txt_pattern.split(" ") if _ != "" and _.strip().startswith("^*.")]
+ pattern_except_suffix += ['zip', 'rar', '7z', 'tar', 'gz'] # 避免解析压缩文件
+ # 将要忽略匹配的文件名(例如: ^README.md)
+ pattern_except_name = [_.lstrip(" ^*,").rstrip(" ,").replace(".", "\.") for _ in txt_pattern.split(" ") if _ != "" and _.strip().startswith("^") and not _.strip().startswith("^*.")]
+ # 生成正则表达式
+ pattern_except = '/[^/]+\.(' + "|".join(pattern_except_suffix) + ')$'
+ pattern_except += '|/(' + "|".join(pattern_except_name) + ')$' if pattern_except_name != [] else ''
+
+ history.clear()
+ import glob, os, re
+ if os.path.exists(txt):
+ project_folder = txt
+ else:
+ if txt == "": txt = '空空如也的输入栏'
+ report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
+ yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+ return
+ # 若上传压缩文件, 先寻找到解压的文件夹路径, 从而避免解析压缩文件
+ maybe_dir = [f for f in glob.glob(f'{project_folder}/*') if os.path.isdir(f)]
+ if len(maybe_dir)>0 and maybe_dir[0].endswith('.extract'):
+ extract_folder_path = maybe_dir[0]
+ else:
+ extract_folder_path = project_folder
+ # 按输入的匹配模式寻找上传的非压缩文件和已解压的文件
+ file_manifest = [f for pattern in pattern_include for f in glob.glob(f'{extract_folder_path}/**/{pattern}', recursive=True) if "" != extract_folder_path and \
+ os.path.isfile(f) and (not re.search(pattern_except, f) or pattern.endswith('.' + re.search(pattern_except, f).group().split('.')[-1]))]
+ if len(file_manifest) == 0:
+ report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何文件: {txt}")
+ yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+ return
+ yield from 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
\ No newline at end of file
diff --git a/crazy_functions/询问多个大语言模型.py b/crazy_functions/询问多个大语言模型.py
index c28f2aae..5cf239e1 100644
--- a/crazy_functions/询问多个大语言模型.py
+++ b/crazy_functions/询问多个大语言模型.py
@@ -25,6 +25,35 @@ def 同时问询(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
retry_times_at_unknown_error=0
)
+ history.append(txt)
+ history.append(gpt_say)
+ yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
+
+
+@CatchException
+def 同时问询_指定模型(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+ """
+ txt 输入栏用户输入的文本,例如需要翻译的一段话,再例如一个包含了待处理文件的路径
+ llm_kwargs gpt模型参数,如温度和top_p等,一般原样传递下去就行
+ plugin_kwargs 插件模型的参数,如温度和top_p等,一般原样传递下去就行
+ chatbot 聊天显示框的句柄,用于显示给用户
+ history 聊天历史,前情提要
+ system_prompt 给gpt的静默提醒
+ 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((txt, "正在同时咨询ChatGPT和ChatGLM……"))
+ 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
+
+ # llm_kwargs['llm_model'] = 'chatglm&gpt-3.5-turbo&api2d-gpt-3.5-turbo' # 支持任意数量的llm接口,用&符号分隔
+ llm_kwargs['llm_model'] = plugin_kwargs.get("advanced_arg", 'chatglm&gpt-3.5-turbo') # 'chatglm&gpt-3.5-turbo' # 支持任意数量的llm接口,用&符号分隔
+ gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
+ inputs=txt, inputs_show_user=txt,
+ llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
+ sys_prompt=system_prompt,
+ retry_times_at_unknown_error=0
+ )
+
history.append(txt)
history.append(gpt_say)
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
\ No newline at end of file
diff --git a/crazy_functions/谷歌检索小助手.py b/crazy_functions/谷歌检索小助手.py
index 94ef2563..b9e1f8e3 100644
--- a/crazy_functions/谷歌检索小助手.py
+++ b/crazy_functions/谷歌检索小助手.py
@@ -70,6 +70,7 @@ def 谷歌检索小助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
# 尝试导入依赖,如果缺少依赖,则给出安装建议
try:
import arxiv
+ import math
from bs4 import BeautifulSoup
except:
report_execption(chatbot, history,
@@ -80,25 +81,26 @@ def 谷歌检索小助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
# 清空历史,以免输入溢出
history = []
-
meta_paper_info_list = yield from get_meta_information(txt, chatbot, history)
+ batchsize = 5
+ for batch in range(math.ceil(len(meta_paper_info_list)/batchsize)):
+ if len(meta_paper_info_list[:batchsize]) > 0:
+ i_say = "下面是一些学术文献的数据,提取出以下内容:" + \
+ "1、英文题目;2、中文题目翻译;3、作者;4、arxiv公开(is_paper_in_arxiv);4、引用数量(cite);5、中文摘要翻译。" + \
+ f"以下是信息源:{str(meta_paper_info_list[:batchsize])}"
- if len(meta_paper_info_list[:10]) > 0:
- i_say = "下面是一些学术文献的数据,请从中提取出以下内容。" + \
- "1、英文题目;2、中文题目翻译;3、作者;4、arxiv公开(is_paper_in_arxiv);4、引用数量(cite);5、中文摘要翻译。" + \
- f"以下是信息源:{str(meta_paper_info_list[:10])}"
+ inputs_show_user = f"请分析此页面中出现的所有文章:{txt},这是第{batch+1}批"
+ gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
+ inputs=i_say, inputs_show_user=inputs_show_user,
+ llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
+ sys_prompt="你是一个学术翻译,请从数据中提取信息。你必须使用Markdown表格。你必须逐个文献进行处理。"
+ )
- inputs_show_user = f"请分析此页面中出现的所有文章:{txt}"
- gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
- inputs=i_say, inputs_show_user=inputs_show_user,
- llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
- sys_prompt="你是一个学术翻译,请从数据中提取信息。你必须使用Markdown格式。你必须逐个文献进行处理。"
- )
+ history.extend([ f"第{batch+1}批", gpt_say ])
+ meta_paper_info_list = meta_paper_info_list[batchsize:]
- history.extend([ "第一批", gpt_say ])
- meta_paper_info_list = meta_paper_info_list[10:]
-
- chatbot.append(["状态?", "已经全部完成"])
+ chatbot.append(["状态?",
+ "已经全部完成,您可以试试让AI写一个Related Works,例如您可以继续输入Write a \"Related Works\" section about \"你搜索的研究领域\" for me."])
msg = '正常'
yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
res = write_results_to_file(history)
diff --git a/docs/WithFastapi.md b/docs/WithFastapi.md
new file mode 100644
index 00000000..188b5271
--- /dev/null
+++ b/docs/WithFastapi.md
@@ -0,0 +1,43 @@
+# Running with fastapi
+
+We currently support fastapi in order to solve sub-path deploy issue.
+
+1. change CUSTOM_PATH setting in `config.py`
+
+``` sh
+nano config.py
+```
+
+2. Edit main.py
+
+```diff
+ auto_opentab_delay()
+ - demo.queue(concurrency_count=CONCURRENT_COUNT).launch(server_name="0.0.0.0", server_port=PORT, auth=AUTHENTICATION, favicon_path="docs/logo.png")
+ + demo.queue(concurrency_count=CONCURRENT_COUNT)
+
+ - # 如果需要在二级路径下运行
+ - # CUSTOM_PATH, = get_conf('CUSTOM_PATH')
+ - # if CUSTOM_PATH != "/":
+ - # from toolbox import run_gradio_in_subpath
+ - # run_gradio_in_subpath(demo, auth=AUTHENTICATION, port=PORT, custom_path=CUSTOM_PATH)
+ - # else:
+ - # demo.launch(server_name="0.0.0.0", server_port=PORT, auth=AUTHENTICATION, favicon_path="docs/logo.png")
+
+ + 如果需要在二级路径下运行
+ + CUSTOM_PATH, = get_conf('CUSTOM_PATH')
+ + if CUSTOM_PATH != "/":
+ + from toolbox import run_gradio_in_subpath
+ + run_gradio_in_subpath(demo, auth=AUTHENTICATION, port=PORT, custom_path=CUSTOM_PATH)
+ + else:
+ + demo.launch(server_name="0.0.0.0", server_port=PORT, auth=AUTHENTICATION, favicon_path="docs/logo.png")
+
+if __name__ == "__main__":
+ main()
+```
+
+
+3. Go!
+
+``` sh
+python main.py
+```
diff --git a/main.py b/main.py
index 6ec26a57..d100d4f9 100644
--- a/main.py
+++ b/main.py
@@ -45,7 +45,7 @@ def main():
gr_L1 = lambda: gr.Row().style()
gr_L2 = lambda scale: gr.Column(scale=scale)
- if LAYOUT == "TOP-DOWN":
+ if LAYOUT == "TOP-DOWN":
gr_L1 = lambda: DummyWith()
gr_L2 = lambda scale: gr.Row()
CHATBOT_HEIGHT /= 2
@@ -89,9 +89,12 @@ def main():
with gr.Row():
with gr.Accordion("更多函数插件", open=True):
dropdown_fn_list = [k for k in crazy_fns.keys() if not crazy_fns[k].get("AsButton", True)]
- with gr.Column(scale=1):
+ with gr.Row():
dropdown = gr.Dropdown(dropdown_fn_list, value=r"打开插件列表", label="").style(container=False)
- with gr.Column(scale=1):
+ with gr.Row():
+ plugin_advanced_arg = gr.Textbox(show_label=True, label="高级参数输入区", visible=False,
+ placeholder="这里是特殊函数插件的高级参数输入区").style(container=False)
+ with gr.Row():
switchy_bt = gr.Button(r"请先从插件列表中选择", variant="secondary")
with gr.Row():
with gr.Accordion("点击展开“文件上传区”。上传本地文件可供红色函数插件调用。", open=False) as area_file_up:
@@ -101,7 +104,7 @@ def main():
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",)
max_length_sl = gr.Slider(minimum=256, maximum=4096, value=512, step=1, interactive=True, label="Local LLM MaxLength",)
- checkboxes = gr.CheckboxGroup(["基础功能区", "函数插件区", "底部输入区", "输入清除键"], value=["基础功能区", "函数插件区"], label="显示/隐藏功能区")
+ checkboxes = gr.CheckboxGroup(["基础功能区", "函数插件区", "底部输入区", "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")
md_dropdown = gr.Dropdown(AVAIL_LLM_MODELS, value=LLM_MODEL, label="更换LLM模型/请求源").style(container=False)
gr.Markdown(description)
@@ -123,11 +126,12 @@ def main():
ret.update({area_input_secondary: gr.update(visible=("底部输入区" in a))})
ret.update({clearBtn: gr.update(visible=("输入清除键" in a))})
ret.update({clearBtn2: gr.update(visible=("输入清除键" in a))})
+ ret.update({plugin_advanced_arg: gr.update(visible=("插件参数区" in a))})
if "底部输入区" in a: ret.update({txt: gr.update(value="")})
return ret
- checkboxes.select(fn_area_visibility, [checkboxes], [area_basic_fn, area_crazy_fn, area_input_primary, area_input_secondary, txt, txt2, clearBtn, clearBtn2] )
+ checkboxes.select(fn_area_visibility, [checkboxes], [area_basic_fn, area_crazy_fn, area_input_primary, area_input_secondary, txt, txt2, clearBtn, clearBtn2, plugin_advanced_arg] )
# 整理反复出现的控件句柄组合
- input_combo = [cookies, max_length_sl, md_dropdown, txt, txt2, top_p, temperature, chatbot, history, system_prompt]
+ input_combo = [cookies, max_length_sl, md_dropdown, txt, txt2, top_p, temperature, chatbot, history, system_prompt, plugin_advanced_arg]
output_combo = [cookies, chatbot, history, status]
predict_args = dict(fn=ArgsGeneralWrapper(predict), inputs=input_combo, outputs=output_combo)
# 提交按钮、重置按钮
@@ -154,14 +158,19 @@ def main():
# 函数插件-下拉菜单与随变按钮的互动
def on_dropdown_changed(k):
variant = crazy_fns[k]["Color"] if "Color" in crazy_fns[k] else "secondary"
- return {switchy_bt: gr.update(value=k, variant=variant)}
- dropdown.select(on_dropdown_changed, [dropdown], [switchy_bt] )
+ ret = {switchy_bt: gr.update(value=k, variant=variant)}
+ if crazy_fns[k].get("AdvancedArgs", False): # 是否唤起高级插件参数区
+ ret.update({plugin_advanced_arg: gr.update(visible=True, label=f"插件[{k}]的高级参数说明:" + crazy_fns[k].get("ArgsReminder", [f"没有提供高级参数功能说明"]))})
+ else:
+ ret.update({plugin_advanced_arg: gr.update(visible=False, label=f"插件[{k}]不需要高级参数。")})
+ return ret
+ dropdown.select(on_dropdown_changed, [dropdown], [switchy_bt, plugin_advanced_arg] )
def on_md_dropdown_changed(k):
return {chatbot: gr.update(label="当前模型:"+k)}
md_dropdown.select(on_md_dropdown_changed, [md_dropdown], [chatbot] )
# 随变按钮的回调函数注册
def route(k, *args, **kwargs):
- if k in [r"打开插件列表", r"请先从插件列表中选择"]: return
+ if k in [r"打开插件列表", r"请先从插件列表中选择"]: return
yield from ArgsGeneralWrapper(crazy_fns[k]["Function"])(*args, **kwargs)
click_handle = switchy_bt.click(route,[switchy_bt, *input_combo, gr.State(PORT)], output_combo)
click_handle.then(on_report_generated, [file_upload, chatbot], [file_upload, chatbot])
@@ -179,7 +188,7 @@ def main():
print(f"如果浏览器没有自动打开,请复制并转到以下URL:")
print(f"\t(亮色主题): http://localhost:{PORT}")
print(f"\t(暗色主题): http://localhost:{PORT}/?__dark-theme=true")
- def open():
+ def open():
time.sleep(2) # 打开浏览器
webbrowser.open_new_tab(f"http://localhost:{PORT}/?__dark-theme=true")
threading.Thread(target=open, name="open-browser", daemon=True).start()
@@ -189,5 +198,13 @@ def main():
auto_opentab_delay()
demo.queue(concurrency_count=CONCURRENT_COUNT).launch(server_name="0.0.0.0", share=False, favicon_path="docs/logo.png")
+ # 如果需要在二级路径下运行
+ # CUSTOM_PATH, = get_conf('CUSTOM_PATH')
+ # if CUSTOM_PATH != "/":
+ # from toolbox import run_gradio_in_subpath
+ # run_gradio_in_subpath(demo, auth=AUTHENTICATION, port=PORT, custom_path=CUSTOM_PATH)
+ # else:
+ # demo.launch(server_name="0.0.0.0", server_port=PORT, auth=AUTHENTICATION, favicon_path="docs/logo.png")
+
if __name__ == "__main__":
main()
diff --git a/request_llm/README.md b/request_llm/README.md
index 973adea1..4a912d10 100644
--- a/request_llm/README.md
+++ b/request_llm/README.md
@@ -1,4 +1,4 @@
-# 如何使用其他大语言模型(v3.0分支测试中)
+# 如何使用其他大语言模型
## ChatGLM
@@ -15,7 +15,7 @@ LLM_MODEL = "chatglm"
---
-## Text-Generation-UI (TGUI)
+## Text-Generation-UI (TGUI,调试中,暂不可用)
### 1. 部署TGUI
``` sh
diff --git a/request_llm/bridge_all.py b/request_llm/bridge_all.py
index d1bc5189..311dc6f4 100644
--- a/request_llm/bridge_all.py
+++ b/request_llm/bridge_all.py
@@ -1,12 +1,12 @@
"""
- 该文件中主要包含2个函数
+ 该文件中主要包含2个函数,是所有LLM的通用接口,它们会继续向下调用更底层的LLM模型,处理多模型并行等细节
- 不具备多线程能力的函数:
- 1. predict: 正常对话时使用,具备完备的交互功能,不可多线程
+ 不具备多线程能力的函数:正常对话时使用,具备完备的交互功能,不可多线程
+ 1. predict(...)
- 具备多线程调用能力的函数
- 2. predict_no_ui_long_connection:在实验过程中发现调用predict_no_ui处理长文档时,和openai的连接容易断掉,这个函数用stream的方式解决这个问题,同样支持多线程
+ 具备多线程调用能力的函数:在函数插件中被调用,灵活而简洁
+ 2. predict_no_ui_long_connection(...)
"""
import tiktoken
from functools import lru_cache
@@ -210,7 +210,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history, sys_prompt, obser
return_string_collect.append( f"【{str(models[i])} 说】: {future.result()} " )
window_mutex[-1] = False # stop mutex thread
- res = '
\n\n---\n\n'.join(return_string_collect)
+ res = '
\n\n---\n\n'.join(return_string_collect)
return res
diff --git a/request_llm/bridge_chatglm.py b/request_llm/bridge_chatglm.py
index 7af28356..fb44043c 100644
--- a/request_llm/bridge_chatglm.py
+++ b/request_llm/bridge_chatglm.py
@@ -32,6 +32,7 @@ class GetGLMHandle(Process):
return self.chatglm_model is not None
def run(self):
+ # 子进程执行
# 第一次运行,加载参数
retry = 0
while True:
@@ -53,17 +54,24 @@ class GetGLMHandle(Process):
self.child.send('[Local Message] Call ChatGLM fail 不能正常加载ChatGLM的参数。')
raise RuntimeError("不能正常加载ChatGLM的参数!")
- # 进入任务等待状态
while True:
+ # 进入任务等待状态
kwargs = self.child.recv()
+ # 收到消息,开始请求
try:
for response, history in self.chatglm_model.stream_chat(self.chatglm_tokenizer, **kwargs):
self.child.send(response)
+ # # 中途接收可能的终止指令(如果有的话)
+ # if self.child.poll():
+ # command = self.child.recv()
+ # if command == '[Terminate]': break
except:
self.child.send('[Local Message] Call ChatGLM fail.')
+ # 请求处理结束,开始下一个循环
self.child.send('[Finish]')
def stream_chat(self, **kwargs):
+ # 主进程执行
self.parent.send(kwargs)
while True:
res = self.parent.recv()
@@ -92,8 +100,8 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
# chatglm 没有 sys_prompt 接口,因此把prompt加入 history
history_feedin = []
+ history_feedin.append(["What can I do?", sys_prompt])
for i in range(len(history)//2):
- history_feedin.append(["What can I do?", sys_prompt] )
history_feedin.append([history[2*i], history[2*i+1]] )
watch_dog_patience = 5 # 看门狗 (watchdog) 的耐心, 设置5秒即可
@@ -130,11 +138,17 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
if "PreProcess" in core_functional[additional_fn]: inputs = core_functional[additional_fn]["PreProcess"](inputs) # 获取预处理函数(如果有的话)
inputs = core_functional[additional_fn]["Prefix"] + inputs + core_functional[additional_fn]["Suffix"]
+ # 处理历史信息
history_feedin = []
+ history_feedin.append(["What can I do?", system_prompt] )
for i in range(len(history)//2):
- history_feedin.append(["What can I do?", system_prompt] )
history_feedin.append([history[2*i], history[2*i+1]] )
+ # 开始接收chatglm的回复
for response in glm_handle.stream_chat(query=inputs, history=history_feedin, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']):
chatbot[-1] = (inputs, response)
- yield from update_ui(chatbot=chatbot, history=history)
\ No newline at end of file
+ yield from update_ui(chatbot=chatbot, history=history)
+
+ # 总结输出
+ history.extend([inputs, response])
+ yield from update_ui(chatbot=chatbot, history=history)
diff --git a/request_llm/bridge_chatgpt.py b/request_llm/bridge_chatgpt.py
index c1a900b1..5e32f452 100644
--- a/request_llm/bridge_chatgpt.py
+++ b/request_llm/bridge_chatgpt.py
@@ -21,7 +21,7 @@ import importlib
# config_private.py放自己的秘密如API和代理网址
# 读取时首先看是否存在私密的config_private配置文件(不受git管控),如果有,则覆盖原config文件
-from toolbox import get_conf, update_ui, is_any_api_key, select_api_key, what_keys
+from toolbox import get_conf, update_ui, is_any_api_key, select_api_key, what_keys, clip_history
proxies, API_KEY, TIMEOUT_SECONDS, MAX_RETRY = \
get_conf('proxies', 'API_KEY', 'TIMEOUT_SECONDS', 'MAX_RETRY')
@@ -145,7 +145,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
yield from update_ui(chatbot=chatbot, history=history, msg="api-key不满足要求") # 刷新界面
return
- history.append(inputs); history.append(" ")
+ history.append(inputs); history.append("")
retry = 0
while True:
@@ -198,14 +198,17 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
chunk_decoded = chunk.decode()
error_msg = chunk_decoded
if "reduce the length" in error_msg:
- chatbot[-1] = (chatbot[-1][0], "[Local Message] Reduce the length. 本次输入过长,或历史数据过长. 历史缓存数据现已释放,您可以请再次尝试.")
- history = [] # 清除历史
+ if len(history) >= 2: history[-1] = ""; history[-2] = "" # 清除当前溢出的输入:history[-2] 是本次输入, history[-1] 是本次输出
+ history = clip_history(inputs=inputs, history=history, tokenizer=model_info[llm_kwargs['llm_model']]['tokenizer'],
+ max_token_limit=(model_info[llm_kwargs['llm_model']]['max_token'])) # history至少释放二分之一
+ chatbot[-1] = (chatbot[-1][0], "[Local Message] Reduce the length. 本次输入过长, 或历史数据过长. 历史缓存数据已部分释放, 您可以请再次尝试. (若再次失败则更可能是因为输入过长.)")
+ # history = [] # 清除历史
elif "does not exist" in error_msg:
- chatbot[-1] = (chatbot[-1][0], f"[Local Message] Model {llm_kwargs['llm_model']} does not exist. 模型不存在,或者您没有获得体验资格.")
+ chatbot[-1] = (chatbot[-1][0], f"[Local Message] Model {llm_kwargs['llm_model']} does not exist. 模型不存在, 或者您没有获得体验资格.")
elif "Incorrect API key" in error_msg:
- chatbot[-1] = (chatbot[-1][0], "[Local Message] Incorrect API key. OpenAI以提供了不正确的API_KEY为由,拒绝服务.")
+ chatbot[-1] = (chatbot[-1][0], "[Local Message] Incorrect API key. OpenAI以提供了不正确的API_KEY为由, 拒绝服务.")
elif "exceeded your current quota" in error_msg:
- chatbot[-1] = (chatbot[-1][0], "[Local Message] You exceeded your current quota. OpenAI以账户额度不足为由,拒绝服务.")
+ chatbot[-1] = (chatbot[-1][0], "[Local Message] You exceeded your current quota. OpenAI以账户额度不足为由, 拒绝服务.")
elif "bad forward key" in error_msg:
chatbot[-1] = (chatbot[-1][0], "[Local Message] Bad forward key. API2D账户额度不足.")
elif "Not enough point" in error_msg:
diff --git a/toolbox.py b/toolbox.py
index d2c9e6ec..c9dc2070 100644
--- a/toolbox.py
+++ b/toolbox.py
@@ -24,23 +24,23 @@ def ArgsGeneralWrapper(f):
"""
装饰器函数,用于重组输入参数,改变输入参数的顺序与结构。
"""
- def decorated(cookies, max_length, llm_model, txt, txt2, top_p, temperature, chatbot, history, system_prompt, *args):
+ def decorated(cookies, max_length, llm_model, txt, txt2, top_p, temperature, chatbot, history, system_prompt, plugin_advanced_arg, *args):
txt_passon = txt
if txt == "" and txt2 != "": txt_passon = txt2
# 引入一个有cookie的chatbot
cookies.update({
- 'top_p':top_p,
+ 'top_p':top_p,
'temperature':temperature,
})
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,
}
plugin_kwargs = {
- # 目前还没有
+ "advanced_arg": plugin_advanced_arg,
}
chatbot_with_cookie = ChatBotWithCookies(cookies)
chatbot_with_cookie.write_list(chatbot)
@@ -219,7 +219,7 @@ def markdown_convertion(txt):
return content
else:
return tex2mathml_catch_exception(content)
-
+
def markdown_bug_hunt(content):
"""
解决一个mdx_math的bug(单$包裹begin命令时多余\n', '')
return content
-
+
if ('$' in txt) and ('```' not in txt): # 有$标识的公式符号,且没有代码段```的标识
# convert everything to html format
@@ -248,7 +248,7 @@ def markdown_convertion(txt):
def close_up_code_segment_during_stream(gpt_reply):
"""
在gpt输出代码的中途(输出了前面的```,但还没输出完后面的```),补上后面的```
-
+
Args:
gpt_reply (str): GPT模型返回的回复字符串。
@@ -511,7 +511,7 @@ class DummyWith():
它的作用是……额……没用,即在代码结构不变得情况下取代其他的上下文管理器。
上下文管理器是一种Python对象,用于与with语句一起使用,
以确保一些资源在代码块执行期间得到正确的初始化和清理。
- 上下文管理器必须实现两个方法,分别为 __enter__()和 __exit__()。
+ 上下文管理器必须实现两个方法,分别为 __enter__()和 __exit__()。
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。
"""
@@ -520,3 +520,83 @@ class DummyWith():
def __exit__(self, exc_type, exc_value, traceback):
return
+
+def run_gradio_in_subpath(demo, auth, port, custom_path):
+ def is_path_legal(path: str)->bool:
+ '''
+ check path for sub url
+ path: path to check
+ return value: do sub url wrap
+ '''
+ if path == "/": return True
+ if len(path) == 0:
+ print("ilegal custom path: {}\npath must not be empty\ndeploy on root url".format(path))
+ return False
+ if path[0] == '/':
+ if path[1] != '/':
+ print("deploy on sub-path {}".format(path))
+ return True
+ return False
+ print("ilegal custom path: {}\npath should begin with \'/\'\ndeploy on root url".format(path))
+ return False
+
+ if not is_path_legal(custom_path): raise RuntimeError('Ilegal custom path')
+ import uvicorn
+ import gradio as gr
+ from fastapi import FastAPI
+ app = FastAPI()
+ if custom_path != "/":
+ @app.get("/")
+ def read_main():
+ return {"message": f"Gradio is running at: {custom_path}"}
+ app = gr.mount_gradio_app(app, demo, path=custom_path)
+ uvicorn.run(app, host="0.0.0.0", port=port) # , auth=auth
+
+
+def clip_history(inputs, history, tokenizer, max_token_limit):
+ """
+ reduce the length of history by clipping.
+ this function search for the longest entries to clip, little by little,
+ until the number of token of history is reduced under threshold.
+ 通过裁剪来缩短历史记录的长度。
+ 此函数逐渐地搜索最长的条目进行剪辑,
+ 直到历史记录的标记数量降低到阈值以下。
+ """
+ import numpy as np
+ from request_llm.bridge_all import model_info
+ def get_token_num(txt):
+ return len(tokenizer.encode(txt, disallowed_special=()))
+ input_token_num = get_token_num(inputs)
+ if input_token_num < max_token_limit * 3 / 4:
+ # 当输入部分的token占比小于限制的3/4时,裁剪时
+ # 1. 把input的余量留出来
+ max_token_limit = max_token_limit - input_token_num
+ # 2. 把输出用的余量留出来
+ max_token_limit = max_token_limit - 128
+ # 3. 如果余量太小了,直接清除历史
+ if max_token_limit < 128:
+ history = []
+ return history
+ else:
+ # 当输入部分的token占比 > 限制的3/4时,直接清除历史
+ history = []
+ return history
+
+ everything = ['']
+ everything.extend(history)
+ n_token = get_token_num('\n'.join(everything))
+ everything_token = [get_token_num(e) for e in everything]
+
+ # 截断时的颗粒度
+ delta = max(everything_token) // 16
+
+ 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
+ everything_token[where] = get_token_num(everything[where])
+ n_token = get_token_num('\n'.join(everything))
+
+ history = everything[1:]
+ return history
diff --git a/version b/version
index bb462e21..a2a877b7 100644
--- a/version
+++ b/version
@@ -1,5 +1,5 @@
{
- "version": 3.1,
+ "version": 3.2,
"show_feature": true,
- "new_feature": "添加支持清华ChatGLM和GPT-4 <-> 改进架构,支持与多个LLM模型同时对话 <-> 添加支持API2D(国内,可支持gpt4)<-> 支持多API-KEY负载均衡(并列填写,逗号分割) <-> 添加输入区文本清除按键"
+ "new_feature": "保存对话功能 <-> 解读任意语言代码+同时询问任意的LLM组合 <-> 添加联网(Google)回答问题插件 <-> 修复ChatGLM上下文BUG <-> 添加支持清华ChatGLM和GPT-4 <-> 改进架构,支持与多个LLM模型同时对话 <-> 添加支持API2D(国内,可支持gpt4)"
}