diff --git a/.gitignore b/.gitignore index 1bb5ae1..76a9c2b 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 e409d56..a77ffc8 100644 --- a/README.md +++ b/README.md @@ -173,6 +173,8 @@ 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 @@ -268,6 +270,8 @@ docker run --rm -it --net=host --gpus=all gpt-academic bash
+ +
diff --git a/config.py b/config.py index e24c68b..b2727da 100644 --- a/config.py +++ b/config.py @@ -56,3 +56,10 @@ CONCURRENT_COUNT = 100 # 设置用户名和密码（不需要修改）（相关功能不稳定，与gradio版本和网络都相关，如果本地使用不建议加这个） # [("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!!） +# 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 eb245f2..f49dc23 100644 --- a/crazy_functional.py +++ b/crazy_functional.py @@ -20,6 +20,7 @@ def get_crazy_functions(): 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.辅助回答 import 猜你想问 + from crazy_functions.解析JupyterNotebook import 解析ipynb文件 function_plugins = { "猜你想问": { "Function": HotReload(猜你想问) @@ -28,6 +29,11 @@ def get_crazy_functions(): "Color": "stop", # 按钮颜色 "Function": HotReload(解析一个Python项目) }, + "[测试功能] 解析Jupyter Notebook文件": { + "Color": "stop", + "AsButton":False, + "Function": HotReload(解析ipynb文件), + }, "批量总结Word文档": { "Color": "stop", "Function": HotReload(总结word文档) @@ -172,7 +178,7 @@ def get_crazy_functions(): "AsButton": False, # 加入下拉菜单中 "Function": HotReload(Markdown英译中) }, - + }) ###################### 第三组插件 ########################### @@ -185,7 +191,7 @@ 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）": { @@ -195,5 +201,25 @@ 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 7b0f072..6020fa2 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/解析JupyterNotebook.py b/crazy_functions/解析JupyterNotebook.py new file mode 100644 index 0000000..3c9948b --- /dev/null +++ b/crazy_functions/解析JupyterNotebook.py @@ -0,0 +1,140 @@ +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 + + pfg = PaperFileGroup() + + print(file_manifest) + for fp in file_manifest: + file_content = parseNotebook(fp, enable_markdown=1) + 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 375b87a..bfa473a 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 fb78145..2939d04 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/docs/WithFastapi.md b/docs/WithFastapi.md new file mode 100644 index 0000000..188b527 --- /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 833720b..55bd680 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 @@ -88,9 +88,12 @@ 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: @@ -100,7 +103,7 @@ 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) @@ -122,11 +125,12 @@ 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 @@ -153,14 +157,19 @@ 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]) @@ -178,7 +187,7 @@ 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() @@ -188,5 +197,13 @@ def main(): 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") + # 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 973adea..4a912d1 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 c5219d4..2dd790c 100644 --- a/request_llm/bridge_all.py +++ b/request_llm/bridge_all.py @@ -1,16 +1,17 @@ """ - 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 wraps, lru_cache +from functools import lru_cache from concurrent.futures import ThreadPoolExecutor +from toolbox import get_conf from request_llm.bridge_chatgpt import predict_no_ui_long_connection as chatgpt_noui from request_llm.bridge_chatgpt import predict as chatgpt_ui @@ -42,18 +43,37 @@ class LazyloadTiktoken(object): def decode(self, *args, **kwargs): encoder = self.get_encoder(self.model) return encoder.decode(*args, **kwargs) - + +# Endpoint 重定向 +API_URL_REDIRECT, = get_conf("API_URL_REDIRECT") +openai_endpoint = "https://api.openai.com/v1/chat/completions" +api2d_endpoint = "https://openai.api2d.net/v1/chat/completions" +# 兼容旧版的配置 +try: + API_URL, = get_conf("API_URL") + if API_URL != "https://api.openai.com/v1/chat/completions": + openai_endpoint = API_URL + print("警告！API_URL配置选项将被弃用，请更换为API_URL_REDIRECT配置") +except: + pass +# 新版配置 +if openai_endpoint in API_URL_REDIRECT: openai_endpoint = API_URL_REDIRECT[openai_endpoint] +if api2d_endpoint in API_URL_REDIRECT: api2d_endpoint = API_URL_REDIRECT[api2d_endpoint] + + +# 获取tokenizer tokenizer_gpt35 = LazyloadTiktoken("gpt-3.5-turbo") tokenizer_gpt4 = LazyloadTiktoken("gpt-4") get_token_num_gpt35 = lambda txt: len(tokenizer_gpt35.encode(txt, disallowed_special=())) get_token_num_gpt4 = lambda txt: len(tokenizer_gpt4.encode(txt, disallowed_special=())) + model_info = { # openai "gpt-3.5-turbo": { "fn_with_ui": chatgpt_ui, "fn_without_ui": chatgpt_noui, - "endpoint": "https://api.openai.com/v1/chat/completions", + "endpoint": openai_endpoint, "max_token": 4096, "tokenizer": tokenizer_gpt35, "token_cnt": get_token_num_gpt35, @@ -62,7 +82,7 @@ model_info = { "gpt-4": { "fn_with_ui": chatgpt_ui, "fn_without_ui": chatgpt_noui, - "endpoint": "https://api.openai.com/v1/chat/completions", + "endpoint": openai_endpoint, "max_token": 8192, "tokenizer": tokenizer_gpt4, "token_cnt": get_token_num_gpt4, @@ -72,7 +92,7 @@ model_info = { "api2d-gpt-3.5-turbo": { "fn_with_ui": chatgpt_ui, "fn_without_ui": chatgpt_noui, - "endpoint": "https://openai.api2d.net/v1/chat/completions", + "endpoint": api2d_endpoint, "max_token": 4096, "tokenizer": tokenizer_gpt35, "token_cnt": get_token_num_gpt35, @@ -81,7 +101,7 @@ model_info = { "api2d-gpt-4": { "fn_with_ui": chatgpt_ui, "fn_without_ui": chatgpt_noui, - "endpoint": "https://openai.api2d.net/v1/chat/completions", + "endpoint": api2d_endpoint, "max_token": 8192, "tokenizer": tokenizer_gpt4, "token_cnt": get_token_num_gpt4, @@ -190,7 +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 7af2835..8eef322 100644 --- a/request_llm/bridge_chatglm.py +++ b/request_llm/bridge_chatglm.py @@ -92,8 +92,8 @@ 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 @@ -131,10 +131,13 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp inputs = core_functional[additional_fn]["Prefix"] + inputs + core_functional[additional_fn]["Suffix"] 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]] ) 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) + + history.extend([inputs, response]) + yield from update_ui(chatbot=chatbot, history=history) \ No newline at end of file diff --git a/request_llm/bridge_chatgpt.py b/request_llm/bridge_chatgpt.py index 2d8a8bc..98bb74f 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 +from toolbox import get_conf, update_ui, is_any_api_key, select_api_key, what_keys proxies, API_KEY, TIMEOUT_SECONDS, MAX_RETRY = \ get_conf('proxies', 'API_KEY', 'TIMEOUT_SECONDS', 'MAX_RETRY') @@ -118,7 +118,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp """ if is_any_api_key(inputs): chatbot._cookies['api_key'] = inputs - chatbot.append(("输入已识别为openai的api_key", "api_key已导入")) + chatbot.append(("输入已识别为openai的api_key", what_keys(inputs))) yield from update_ui(chatbot=chatbot, history=history, msg="api_key已导入") # 刷新界面 return elif not is_any_api_key(chatbot._cookies['api_key']): @@ -141,7 +141,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp try: headers, payload = generate_payload(inputs, llm_kwargs, history, system_prompt, stream) except RuntimeError as e: - chatbot[-1] = (inputs, f"您提供的api-key不满足要求，不包含任何可用于{llm_kwargs['llm_model']}的api-key。") + chatbot[-1] = (inputs, f"您提供的api-key不满足要求，不包含任何可用于{llm_kwargs['llm_model']}的api-key。您可能选择了错误的模型或请求源。") yield from update_ui(chatbot=chatbot, history=history, msg="api-key不满足要求") # 刷新界面 return diff --git a/toolbox.py b/toolbox.py index 7dc72c5..3147ce9 100644 --- a/toolbox.py +++ b/toolbox.py @@ -32,23 +32,23 @@ 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, top_p, temperature, - chatbot, history, system_prompt, models, ipaddr: gr.Request, *args): + chatbot, history, system_prompt, plugin_advanced_arg, models, ipaddr: gr.Request, *args): """""" # 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, 'ipaddr': ipaddr.client.host } plugin_kwargs = { - # 目前还没有 + "advanced_arg": plugin_advanced_arg, } chatbot_with_cookie = ChatBotWithCookies(cookies) chatbot_with_cookie.write_list(chatbot) @@ -237,7 +237,7 @@ 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 @@ -266,7 +266,7 @@ 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。 @@ -473,6 +473,19 @@ def is_any_api_key(key): else: return is_openai_api_key(key) or is_api2d_key(key) +def what_keys(keys): + avail_key_list = {'OpenAI Key':0, "API2D Key":0} + key_list = keys.split(',') + + for k in key_list: + if is_openai_api_key(k): + avail_key_list['OpenAI Key'] += 1 + + for k in key_list: + if is_api2d_key(k): + avail_key_list['API2D Key'] += 1 + + return f"检测到： OpenAI Key {avail_key_list['OpenAI Key']} 个，API2D Key {avail_key_list['API2D Key']} 个" def select_api_key(keys, llm_model): import random @@ -488,7 +501,7 @@ def select_api_key(keys, llm_model): if is_api2d_key(k): avail_key_list.append(k) if len(avail_key_list) == 0: - raise RuntimeError(f"您提供的api-key不满足要求，不包含任何可用于{llm_model}的api-key。") + raise RuntimeError(f"您提供的api-key不满足要求，不包含任何可用于{llm_model}的api-key。您可能选择了错误的模型或请求源。") api_key = random.choice(avail_key_list) # 随机负载均衡 return api_key @@ -539,7 +552,7 @@ 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。 """ @@ -550,7 +563,33 @@ class DummyWith(): return -if __name__ == '__main__': - private_upload = './private_upload' - for r, d, f in os.walk(private_upload): - print(r, f) +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 \ No newline at end of file diff --git a/version b/version index bb462e2..ec50d82 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": "现函数插件可读取高级参数（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）" }