From aeddf6b461d58eb7c755b1ed1d8ce2810cdf752f Mon Sep 17 00:00:00 2001 From: binary-husky <96192199+binary-husky@users.noreply.github.com> Date: Sun, 11 Jun 2023 10:20:49 +0800 Subject: [PATCH 01/17] =?UTF-8?q?Update=20Latex=E8=BE=93=E5=87=BAPDF?= =?UTF-8?q?=E7=BB=93=E6=9E=9C.py?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- crazy_functions/Latex输出PDF结果.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/crazy_functions/Latex输出PDF结果.py b/crazy_functions/Latex输出PDF结果.py index 855cc1c..6592c9a 100644 --- a/crazy_functions/Latex输出PDF结果.py +++ b/crazy_functions/Latex输出PDF结果.py @@ -146,7 +146,7 @@ def Latex英文纠错加PDF对比(txt, llm_kwargs, plugin_kwargs, chatbot, histo from .latex_utils import Latex精细分解与转化, 编译Latex except Exception as e: chatbot.append([ f"解析项目: {txt}", - f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"]) + f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"]) yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 return @@ -216,7 +216,7 @@ def Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, from .latex_utils import Latex精细分解与转化, 编译Latex except Exception as e: chatbot.append([ f"解析项目: {txt}", - f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"]) + f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"]) yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 return From 3ecf2977a86abaf49ddaf112a196bc7f8fcb6717 Mon Sep 17 00:00:00 2001 From: binary-husky Date: Sun, 11 Jun 2023 18:23:54 +0800 Subject: [PATCH 02/17] =?UTF-8?q?=E4=BF=AE=E5=A4=8Dcaption=E7=BF=BB?= =?UTF-8?q?=E8=AF=91?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- crazy_functions/latex_utils.py | 59 +++++++++++++++++++++++++++------- 1 file changed, 47 insertions(+), 12 deletions(-) diff --git a/crazy_functions/latex_utils.py b/crazy_functions/latex_utils.py index d3d7b9c..afaae22 100644 --- a/crazy_functions/latex_utils.py +++ b/crazy_functions/latex_utils.py @@ -29,7 +29,15 @@ def split_worker_reverse_caption(text, mask, pattern, flags=0): """ pattern_compile = re.compile(pattern, flags) for res in pattern_compile.finditer(text): - mask[res.regs[1][0]:res.regs[1][1]] = TRANSFORM + brace_level = 0 + p = begin = end = res.regs[1][0] + for _ in range(1024*16): + if text[p] == '}' and brace_level == 0: break + elif text[p] == '}': brace_level -= 1 + elif text[p] == '{': brace_level += 1 + p += 1 + end = p + mask[begin:end] = TRANSFORM return text, mask def split_worker_begin_end(text, mask, pattern, flags=0, limit_n_lines=42): @@ -97,6 +105,7 @@ def 寻找Latex主文件(file_manifest, mode): else: continue raise RuntimeError('无法找到一个主Tex文件（包含documentclass关键字）') + def rm_comments(main_file): new_file_remove_comment_lines = [] for l in main_file.splitlines(): @@ -108,6 +117,7 @@ def rm_comments(main_file): main_file = '\n'.join(new_file_remove_comment_lines) main_file = re.sub(r'(? 0 and node_string.count('\_') > final_tex.count('\_'): # walk and replace any _ without \ final_tex = re.sub(r"(? lps = LatexPaperSplit() - res = lps.split(merged_content, project_folder) # 消耗时间的函数 + res = lps.split(merged_content, project_folder, opts) # 消耗时间的函数 # <-------- 拆分过长的latex片段 ----------> pfg = LatexPaperFileGroup() From 790a1cf12a2a98811ccb4c38568f21b120049f7a Mon Sep 17 00:00:00 2001 From: binary-husky Date: Sun, 11 Jun 2023 20:12:25 +0800 Subject: [PATCH 03/17] =?UTF-8?q?=E6=B7=BB=E5=8A=A0=E4=B8=80=E4=BA=9B?= =?UTF-8?q?=E6=8F=90=E7=A4=BA?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- crazy_functions/latex_utils.py | 28 ++++++++++++++++++++++++---- 1 file changed, 24 insertions(+), 4 deletions(-) diff --git a/crazy_functions/latex_utils.py b/crazy_functions/latex_utils.py index afaae22..89ca7a5 100644 --- a/crazy_functions/latex_utils.py +++ b/crazy_functions/latex_utils.py @@ -23,9 +23,26 @@ def split_worker(text, mask, pattern, flags=0): mask[res.span()[0]:res.span()[1]] = PRESERVE return text, mask -def split_worker_reverse_caption(text, mask, pattern, flags=0): +def split_worker_careful_brace(text, mask, pattern, flags=0): """ - Move caption area out of preserve area + Move area into preserve area + """ + pattern_compile = re.compile(pattern, flags) + for res in pattern_compile.finditer(text): + brace_level = -1 + p = begin = end = res.regs[0][0] + for _ in range(1024*16): + if text[p] == '}' and brace_level == 0: break + elif text[p] == '}': brace_level -= 1 + elif text[p] == '{': brace_level += 1 + p += 1 + end = p+1 + mask[begin:end] = PRESERVE + return text, mask + +def split_worker_reverse_careful_brace(text, mask, pattern, flags=0): + """ + Move area out of preserve area """ pattern_compile = re.compile(pattern, flags) for res in pattern_compile.finditer(text): @@ -274,7 +291,8 @@ def split_subprocess(txt, project_folder, return_dict, opts): text, mask = split_worker(text, mask, r"\\vspace\{(.*?)\}") text, mask = split_worker(text, mask, r"\\hspace\{(.*?)\}") text, mask = split_worker(text, mask, r"\\end\{(.*?)\}") - text, mask = split_worker_reverse_caption(text, mask, r"\\caption\{(.*?)\}", re.DOTALL) + text, mask = split_worker_careful_brace(text, mask, r"\\hl\{(.*?)\}", re.DOTALL) + text, mask = split_worker_reverse_careful_brace(text, mask, r"\\caption\{(.*?)\}", re.DOTALL) root = convert_to_linklist(text, mask) # 修复括号 @@ -504,6 +522,8 @@ def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin f.write(merged_content) # <-------- 精细切分latex文件 ----------> + chatbot.append((f"Latex文件融合完成", f'[Local Message] 正在精细切分latex文件，这需要一段时间计算，文档越长耗时越长，请耐心等待。')) + yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 lps = LatexPaperSplit() res = lps.split(merged_content, project_folder, opts) # 消耗时间的函数 @@ -602,7 +622,7 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f current_dir = os.getcwd() n_fix = 1 max_try = 32 - chatbot.append([f"正在编译PDF文档", f'编译已经开始。当前工作路径为{work_folder}，如果程序停顿5分钟以上，则大概率是卡死在Latex里面了。不幸卡死时请直接去该路径下取回翻译结果，或者重启之后再度尝试 ...']); yield from update_ui(chatbot=chatbot, history=history) + chatbot.append([f"正在编译PDF文档", f'编译已经开始。当前工作路径为{work_folder}，如果程序停顿5分钟以上，请直接去该路径下取回翻译结果，或者重启之后再度尝试 ...']); yield from update_ui(chatbot=chatbot, history=history) chatbot.append([f"正在编译PDF文档", '...']); yield from update_ui(chatbot=chatbot, history=history); time.sleep(1); chatbot[-1] = list(chatbot[-1]) # 刷新界面 yield from update_ui_lastest_msg('编译已经开始...', chatbot, history) # 刷新Gradio前端界面 From 9fd212652ed0e80d3e55b9b72461fc24d3837ce1 Mon Sep 17 00:00:00 2001 From: binary-husky Date: Mon, 12 Jun 2023 09:45:59 +0800 Subject: [PATCH 04/17] =?UTF-8?q?=E4=B8=93=E4=B8=9A=E8=AF=8D=E6=B1=87?= =?UTF-8?q?=E5=A3=B0=E6=98=8E?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- crazy_functions/Latex输出PDF结果.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/crazy_functions/Latex输出PDF结果.py b/crazy_functions/Latex输出PDF结果.py index 6592c9a..2e9a30b 100644 --- a/crazy_functions/Latex输出PDF结果.py +++ b/crazy_functions/Latex输出PDF结果.py @@ -5,7 +5,7 @@ pj = os.path.join ARXIV_CACHE_DIR = os.path.expanduser(f"~/arxiv_cache/") # =================================== 工具函数 =============================================== -沙雕GPT啊别犯这些低级翻译错误 = 'You must to translate "agent" to "智能体". ' +专业词汇声明 = 'If the term "agent" is used in this section, it should be translated to "智能体". ' def switch_prompt(pfg, mode): """ Generate prompts and system prompts based on the mode for proofreading or translating. @@ -25,7 +25,7 @@ def switch_prompt(pfg, mode): f"\n\n{frag}" for frag in pfg.sp_file_contents] sys_prompt_array = ["You are a professional academic paper writer." for _ in range(n_split)] elif mode == 'translate_zh': - inputs_array = [r"Below is a section from an English academic paper, translate it into Chinese." + 沙雕GPT啊别犯这些低级翻译错误 + + inputs_array = [r"Below is a section from an English academic paper, translate it into Chinese. " + 专业词汇声明 + r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " + r"Answer me only with the translated text:" + f"\n\n{frag}" for frag in pfg.sp_file_contents] From 9ac3d0d65dfd1ae4209a28139d133057a3c22e39 Mon Sep 17 00:00:00 2001 From: OverKit <78402478+OverKit@users.noreply.github.com> Date: Mon, 12 Jun 2023 10:09:52 +0800 Subject: [PATCH 05/17] check letter % after removing spaces or tabs in the left --- crazy_functions/latex_utils.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/crazy_functions/latex_utils.py b/crazy_functions/latex_utils.py index 89ca7a5..53894ca 100644 --- a/crazy_functions/latex_utils.py +++ b/crazy_functions/latex_utils.py @@ -127,7 +127,7 @@ def rm_comments(main_file): new_file_remove_comment_lines = [] for l in main_file.splitlines(): # 删除整行的空注释 - if l.startswith("%") or (l.startswith(" ") and l.lstrip().startswith("%")): + if l.lstrip().startswith("%"): pass else: new_file_remove_comment_lines.append(l) From c365ea9f579acb88ffd756c3483c5c29fc2b57c3 Mon Sep 17 00:00:00 2001 From: binary-husky <96192199+binary-husky@users.noreply.github.com> Date: Tue, 13 Jun 2023 16:13:19 +0800 Subject: [PATCH 06/17] Update README.md --- README.md | 47 ++++++++++++++++++++++------------------------- 1 file changed, 22 insertions(+), 25 deletions(-) diff --git a/README.md b/README.md index d4d6858..581d3d5 100644 --- a/README.md +++ b/README.md @@ -228,7 +228,7 @@ docker-compose up 1. 对话保存功能。在函数插件区调用 `保存当前的对话` 即可将当前对话保存为可读+可复原的html文件， 另外在函数插件区（下拉菜单）调用 `载入对话历史存档` ，即可还原之前的会话。 -Tip：不指定文件直接点击 `载入对话历史存档` 可以查看历史html存档缓存，点击 `删除所有本地对话历史记录` 可以删除所有html存档缓存。 +Tip：不指定文件直接点击 `载入对话历史存档` 可以查看历史html存档缓存。
@@ -251,38 +251,33 @@ 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 -5. 这是一个能够“自我译解”的开源项目 -
- -
- -6. 译解其他开源项目，不在话下 +5. 译解其他开源项目
-7. 装饰[live2d](https://github.com/fghrsh/live2d_demo)的小功能（默认关闭，需要修改`config.py`） +6. 装饰[live2d](https://github.com/fghrsh/live2d_demo)的小功能（默认关闭，需要修改`config.py`）
-8. 新增MOSS大语言模型支持 +7. 新增MOSS大语言模型支持
-9. OpenAI图像生成 +8. OpenAI图像生成
-10. OpenAI音频解析与总结 +9. OpenAI音频解析与总结
-11. Latex全文校对纠错 +10. Latex全文校对纠错
===> @@ -310,30 +305,32 @@ gpt_academic开发者QQ群-2：610599535 - 已知问题 - 某些浏览器翻译插件干扰此软件前端的运行 - - 官方Gradio目前有很多兼容性Bug，请务必使用requirement.txt安装Gradio + - 官方Gradio目前有很多兼容性Bug，请务必使用`requirement.txt`安装Gradio ## 参考与学习 ``` -代码中参考了很多其他优秀项目中的设计，主要包括： +代码中参考了很多其他优秀项目中的设计，顺序不分先后： -# 项目1：清华ChatGLM-6B: +# 清华ChatGLM-6B: https://github.com/THUDM/ChatGLM-6B -# 项目2：清华JittorLLMs: +# 清华JittorLLMs: https://github.com/Jittor/JittorLLMs -# 项目3：Edge-GPT: -https://github.com/acheong08/EdgeGPT - -# 项目4：ChuanhuChatGPT: -https://github.com/GaiZhenbiao/ChuanhuChatGPT - -# 项目5：ChatPaper: +# ChatPaper: https://github.com/kaixindelele/ChatPaper -# 更多： +# Edge-GPT: +https://github.com/acheong08/EdgeGPT + +# ChuanhuChatGPT: +https://github.com/GaiZhenbiao/ChuanhuChatGPT + +# Oobabooga one-click installer: +https://github.com/oobabooga/one-click-installers + +# More： https://github.com/gradio-app/gradio https://github.com/fghrsh/live2d_demo -https://github.com/oobabooga/one-click-installers ``` From c40ebfc21f39b995b3f0437b387d5ee561759327 Mon Sep 17 00:00:00 2001 From: qingxu fu <505030475@qq.com> Date: Wed, 14 Jun 2023 09:50:15 +0800 Subject: [PATCH 07/17] =?UTF-8?q?=E5=B0=86gpt-3.5-16k=E4=BD=9C=E4=B8=BA?= =?UTF-8?q?=E5=8A=A0=E5=85=A5=E6=94=AF=E6=8C=81=E5=88=97=E8=A1=A8?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- config.py | 2 +- request_llm/bridge_all.py | 9 +++++++++ 2 files changed, 10 insertions(+), 1 deletion(-) diff --git a/config.py b/config.py index 14b089e..87e0ec9 100644 --- a/config.py +++ b/config.py @@ -46,7 +46,7 @@ MAX_RETRY = 2 # 模型选择是 (注意: LLM_MODEL是默认选中的模型, 同时它必须被包含在AVAIL_LLM_MODELS切换列表中 ) LLM_MODEL = "gpt-3.5-turbo" # 可选 ↓↓↓ -AVAIL_LLM_MODELS = ["gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "moss", "newbing", "newbing-free", "stack-claude"] +AVAIL_LLM_MODELS = ["gpt-3.5-turbo-16k", "gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "moss", "newbing", "newbing-free", "stack-claude"] # P.S. 其他可用的模型还包括 ["newbing-free", "jittorllms_rwkv", "jittorllms_pangualpha", "jittorllms_llama"] # 本地LLM模型如ChatGLM的执行方式 CPU/GPU diff --git a/request_llm/bridge_all.py b/request_llm/bridge_all.py index b6efe21..a27407c 100644 --- a/request_llm/bridge_all.py +++ b/request_llm/bridge_all.py @@ -83,6 +83,15 @@ model_info = { "tokenizer": tokenizer_gpt35, "token_cnt": get_token_num_gpt35, }, + + "gpt-3.5-turbo-16k": { + "fn_with_ui": chatgpt_ui, + "fn_without_ui": chatgpt_noui, + "endpoint": openai_endpoint, + "max_token": 1024*16, + "tokenizer": tokenizer_gpt35, + "token_cnt": get_token_num_gpt35, + }, "gpt-4": { "fn_with_ui": chatgpt_ui, From 8c62f21aa6b0c68bdc795f315f5d325b1384161b Mon Sep 17 00:00:00 2001 From: qingxu fu <505030475@qq.com> Date: Wed, 14 Jun 2023 09:57:09 +0800 Subject: [PATCH 08/17] =?UTF-8?q?3.41=E5=A2=9E=E5=8A=A0gpt-3.5-16k?= =?UTF-8?q?=E7=9A=84=E6=94=AF=E6=8C=81?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- version | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/version b/version index 669c708..ceb909a 100644 --- a/version +++ b/version @@ -1,5 +1,5 @@ { - "version": 3.4, + "version": 3.41, "show_feature": true, - "new_feature": "新增最强Arxiv论文翻译插件 <-> 修复gradio复制按钮BUG <-> 修复PDF翻译的BUG, 新增HTML中英双栏对照 <-> 添加了OpenAI图片生成插件 <-> 添加了OpenAI音频转文本总结插件 <-> 通过Slack添加对Claude的支持" + "new_feature": "增加gpt-3.5-16k的支持 <-> 新增最强Arxiv论文翻译插件 <-> 修复gradio复制按钮BUG <-> 修复PDF翻译的BUG, 新增HTML中英双栏对照 <-> 添加了OpenAI图片生成插件 <-> 添加了OpenAI音频转文本总结插件 <-> 通过Slack添加对Claude的支持" } From 73d4a1ff4b41548b6d6b5ea4c321fa2e81fe55ce Mon Sep 17 00:00:00 2001 From: binary-husky <96192199+binary-husky@users.noreply.github.com> Date: Wed, 14 Jun 2023 10:15:47 +0800 Subject: [PATCH 09/17] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 581d3d5..39b37ea 100644 --- a/README.md +++ b/README.md @@ -47,7 +47,7 @@ chat分析报告生成 | [函数插件] 运行后自动生成总结汇报 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```/?__theme=dark```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、[清华ChatGLM](https://github.com/THUDM/ChatGLM-6B)、[复旦MOSS](https://github.com/OpenLMLab/MOSS)同时伺候的感觉一定会很不错吧？ +[多LLM模型](https://www.bilibili.com/video/BV1wT411p7yf)支持 | 同时被GPT3.5、GPT4、[清华ChatGLM](https://github.com/THUDM/ChatGLM-6B)、[复旦MOSS](https://github.com/OpenLMLab/MOSS)同时伺候的感觉一定会很不错吧？ 更多LLM模型接入，支持[huggingface部署](https://huggingface.co/spaces/qingxu98/gpt-academic) | 加入Newbing接口(新必应)，引入清华[Jittorllms](https://github.com/Jittor/JittorLLMs)支持[LLaMA](https://github.com/facebookresearch/llama)，[RWKV](https://github.com/BlinkDL/ChatRWKV)和[盘古α](https://openi.org.cn/pangu/) 更多新功能展示(图像生成等) …… | 见本文档结尾处 …… From ef752838b06a4898ba23ea34dd349be6a51a199e Mon Sep 17 00:00:00 2001 From: Skyzayre <120616113+Skyzayre@users.noreply.github.com> Date: Thu, 15 Jun 2023 02:07:43 +0800 Subject: [PATCH 10/17] Update README.md --- README.md | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/README.md b/README.md index 39b37ea..c3dd52a 100644 --- a/README.md +++ b/README.md @@ -16,7 +16,7 @@ To translate this project to arbitary language with GPT, read and run [`multi_la > > 1.请注意只有**红颜色**标识的函数插件（按钮）才支持读取文件，部分插件位于插件区的**下拉菜单**中。另外我们以**最高优先级**欢迎和处理任何新插件的PR！ > -> 2.本项目中每个文件的功能都在自译解[`self_analysis.md`](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)详细说明。随着版本的迭代，您也可以随时自行点击相关函数插件，调用GPT重新生成项目的自我解析报告。常见问题汇总在[`wiki`](https://github.com/binary-husky/chatgpt_academic/wiki/%E5%B8%B8%E8%A7%81%E9%97%AE%E9%A2%98)当中。[安装方法](#installation)。 +> 2.本项目中每个文件的功能都在自译解[`self_analysis.md`](https://github.com/binary-husky/gpt_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)详细说明。随着版本的迭代，您也可以随时自行点击相关函数插件，调用GPT重新生成项目的自我解析报告。常见问题汇总在[`wiki`](https://github.com/binary-husky/gpt_academic/wiki/%E5%B8%B8%E8%A7%81%E9%97%AE%E9%A2%98)当中。[安装方法](#installation)。 > > 3.本项目兼容并鼓励尝试国产大语言模型chatglm和RWKV, 盘古等等。支持多个api-key共存，可在配置文件中填写如`API_KEY="openai-key1,openai-key2,api2d-key3"`。需要临时更换`API_KEY`时，在输入区输入临时的`API_KEY`然后回车键提交后即可生效。 @@ -31,13 +31,13 @@ To translate this project to arbitary language with GPT, read and run [`multi_la 一键中英互译 | 一键中英互译 一键代码解释 | 显示代码、解释代码、生成代码、给代码加注释 [自定义快捷键](https://www.bilibili.com/video/BV14s4y1E7jN) | 支持自定义快捷键 -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 +模块化设计 | 支持自定义强大的[函数插件](https://github.com/binary-husky/gpt_academic/tree/master/crazy_functions)，插件支持[热更新](https://github.com/binary-husky/gpt_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/gpt_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、[翻译](https://www.bilibili.com/video/BV1KT411x7Wn)论文 | [函数插件] 一键解读latex/pdf论文全文并生成摘要 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 -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？ +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/gpt_academic/blob/master/docs/README_EN.md)了吗？ chat分析报告生成 | [函数插件] 运行后自动生成总结汇报 [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） [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 @@ -46,7 +46,7 @@ chat分析报告生成 | [函数插件] 运行后自动生成总结汇报 ⭐Arxiv论文精细翻译 | [函数插件] 一键[以超高质量翻译arxiv论文](https://www.bilibili.com/video/BV1dz4y1v77A/)，迄今为止最好的论文翻译工具⭐ 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```/?__theme=dark```可以切换dark主题 +启动暗色gradio[主题](https://github.com/binary-husky/gpt_academic/issues/173) | 在浏览器url后面添加```/?__theme=dark```可以切换dark主题 [多LLM模型](https://www.bilibili.com/video/BV1wT411p7yf)支持 | 同时被GPT3.5、GPT4、[清华ChatGLM](https://github.com/THUDM/ChatGLM-6B)、[复旦MOSS](https://github.com/OpenLMLab/MOSS)同时伺候的感觉一定会很不错吧？ 更多LLM模型接入，支持[huggingface部署](https://huggingface.co/spaces/qingxu98/gpt-academic) | 加入Newbing接口(新必应)，引入清华[Jittorllms](https://github.com/Jittor/JittorLLMs)支持[LLaMA](https://github.com/facebookresearch/llama)，[RWKV](https://github.com/BlinkDL/ChatRWKV)和[盘古α](https://openi.org.cn/pangu/) 更多新功能展示(图像生成等) …… | 见本文档结尾处 …… @@ -91,8 +91,8 @@ chat分析报告生成 | [函数插件] 运行后自动生成总结汇报 1. 下载项目 ```sh -git clone https://github.com/binary-husky/chatgpt_academic.git -cd chatgpt_academic +git clone https://github.com/binary-husky/.git +cd gpt_academic ``` 2. 配置API_KEY @@ -150,8 +150,8 @@ python main.py 1. 仅ChatGPT（推荐大多数人选择） ``` sh -git clone https://github.com/binary-husky/chatgpt_academic.git # 下载项目 -cd chatgpt_academic # 进入路径 +git clone https://github.com/binary-husky/gpt_academic.git # 下载项目 +cd gpt_academic # 进入路径 nano config.py # 用任意文本编辑器编辑config.py, 配置 “Proxy”， “API_KEY” 以及 “WEB_PORT” (例如50923) 等 docker build -t gpt-academic . # 安装 @@ -188,10 +188,10 @@ docker-compose up 按照`config.py`中的说明配置API_URL_REDIRECT即可。 4. 远程云服务器部署（需要云服务器知识与经验）。 -请访问[部署wiki-1](https://github.com/binary-husky/chatgpt_academic/wiki/%E4%BA%91%E6%9C%8D%E5%8A%A1%E5%99%A8%E8%BF%9C%E7%A8%8B%E9%83%A8%E7%BD%B2%E6%8C%87%E5%8D%97) +请访问[部署wiki-1](https://github.com/binary-husky/gpt_academic/wiki/%E4%BA%91%E6%9C%8D%E5%8A%A1%E5%99%A8%E8%BF%9C%E7%A8%8B%E9%83%A8%E7%BD%B2%E6%8C%87%E5%8D%97) 5. 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) +请访问[部署wiki-2](https://github.com/binary-husky/gpt_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) 6. 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) @@ -220,7 +220,7 @@ docker-compose up 编写强大的函数插件来执行任何你想得到的和想不到的任务。 本项目的插件编写、调试难度很低，只要您具备一定的python基础知识，就可以仿照我们提供的模板实现自己的插件功能。 -详情请参考[函数插件指南](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)。 +详情请参考[函数插件指南](https://github.com/binary-husky/gpt_academic/wiki/%E5%87%BD%E6%95%B0%E6%8F%92%E4%BB%B6%E6%8C%87%E5%8D%97)。 --- # Latest Update From 6d849eeb121b9f88821d7e46cad95c32bb9a12a9 Mon Sep 17 00:00:00 2001 From: qingxu fu <505030475@qq.com> Date: Fri, 16 Jun 2023 17:33:03 +0800 Subject: [PATCH 11/17] =?UTF-8?q?=E4=BF=AE=E5=A4=8DLangchain=E6=8F=92?= =?UTF-8?q?=E4=BB=B6=E7=9A=84bug?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- crazy_functions/Langchain知识库.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/crazy_functions/Langchain知识库.py b/crazy_functions/Langchain知识库.py index 5b09d3b..31c459a 100644 --- a/crazy_functions/Langchain知识库.py +++ b/crazy_functions/Langchain知识库.py @@ -30,7 +30,7 @@ def 知识库问答(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_pro ) yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 from .crazy_utils import try_install_deps - try_install_deps(['zh_langchain==0.2.0']) + try_install_deps(['zh_langchain==0.2.1']) # < --------------------读取参数--------------- > if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg") @@ -84,7 +84,7 @@ def 读取知识库作答(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst chatbot.append(["依赖不足", "导入依赖失败。正在尝试自动安装，请查看终端的输出或耐心等待..."]) yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 from .crazy_utils import try_install_deps - try_install_deps(['zh_langchain==0.2.0']) + try_install_deps(['zh_langchain==0.2.1']) # < ------------------- --------------- > kai = knowledge_archive_interface() From bb864c631376320f8847b36e4a75a38edbb23176 Mon Sep 17 00:00:00 2001 From: qingxu fu <505030475@qq.com> Date: Fri, 16 Jun 2023 17:33:19 +0800 Subject: [PATCH 12/17] =?UTF-8?q?=E5=A2=9E=E5=8A=A0=E4=B8=80=E4=BA=9B?= =?UTF-8?q?=E6=8F=90=E7=A4=BA=E6=96=87=E5=AD=97?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- crazy_functions/latex_utils.py | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/crazy_functions/latex_utils.py b/crazy_functions/latex_utils.py index 53894ca..78eec29 100644 --- a/crazy_functions/latex_utils.py +++ b/crazy_functions/latex_utils.py @@ -165,17 +165,23 @@ def merge_tex_files(project_foler, main_file, mode): main_file = rm_comments(main_file) if mode == 'translate_zh': + # find paper documentclass pattern = re.compile(r'\\documentclass.*\n') match = pattern.search(main_file) + assert match is not None, "Cannot find documentclass statement!" position = match.end() add_ctex = '\\usepackage{ctex}\n' add_url = '\\usepackage{url}\n' if '{url}' not in main_file else '' main_file = main_file[:position] + add_ctex + add_url + main_file[position:] - # 2 fontset=windows + # fontset=windows import platform if platform.system() != 'Windows': main_file = re.sub(r"\\documentclass\[(.*?)\]{(.*?)}", r"\\documentclass[\1,fontset=windows]{\2}",main_file) main_file = re.sub(r"\\documentclass{(.*?)}", r"\\documentclass[fontset=windows]{\1}",main_file) + # find paper abstract + pattern = re.compile(r'\\begin\{abstract\}.*\n') + match = pattern.search(main_file) + assert match is not None, "Cannot find paper abstract section!" return main_file @@ -418,6 +424,7 @@ class LatexPaperSplit(): if mode == 'translate_zh': pattern = re.compile(r'\\begin\{abstract\}.*\n') match = pattern.search(result_string) + assert match is not None, "Cannot find paper abstract section!" position = match.end() result_string = result_string[:position] + self.msg + msg + self.msg_declare + result_string[position:] return result_string From 2bb13b4677b3bd403b950c97036a2753cda5ec8b Mon Sep 17 00:00:00 2001 From: binary-husky <96192199+binary-husky@users.noreply.github.com> Date: Sun, 18 Jun 2023 15:44:42 +0800 Subject: [PATCH 13/17] Update README.md --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index c3dd52a..f079086 100644 --- a/README.md +++ b/README.md @@ -160,6 +160,7 @@ docker run --rm -it --net=host gpt-academic #（最后一步-选择2）在macOS/windows环境下，只能用-p选项将容器上的端口(例如50923)暴露给主机上的端口 docker run --rm -it -e WEB_PORT=50923 -p 50923:50923 gpt-academic ``` +P.S. 如果需要Latex功能，请见另一个[Dockerfile](https://github.com/binary-husky/gpt_academic/blob/master/docs/Dockerfile%2BNoLocal%2BLatex) 2. ChatGPT + ChatGLM + MOSS（需要熟悉Docker） From 4bafbb3562f249b9b10a3595ac9f859762a52377 Mon Sep 17 00:00:00 2001 From: binary-husky <96192199+binary-husky@users.noreply.github.com> Date: Sun, 18 Jun 2023 15:54:23 +0800 Subject: [PATCH 14/17] =?UTF-8?q?Update=20Latex=E8=BE=93=E5=87=BAPDF?= =?UTF-8?q?=E7=BB=93=E6=9E=9C.py?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- crazy_functions/Latex输出PDF结果.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/crazy_functions/Latex输出PDF结果.py b/crazy_functions/Latex输出PDF结果.py index 2e9a30b..6c89751 100644 --- a/crazy_functions/Latex输出PDF结果.py +++ b/crazy_functions/Latex输出PDF结果.py @@ -205,7 +205,7 @@ def Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, # <-------------- information about this plugin -------------> chatbot.append([ "函数插件功能？", - "对整个Latex项目进行翻译, 生成中文PDF。函数插件贡献者: Binary-Husky。注意事项: 目前仅支持GPT3.5/GPT4，其他模型转化效果未知。目前对机器学习类文献转化效果最好，其他类型文献转化效果未知。"]) + "对整个Latex项目进行翻译, 生成中文PDF。函数插件贡献者: Binary-Husky。注意事项: 此插件Windows支持最佳，Linux下必须使用Docker安装，详见项目主README.md。目前仅支持GPT3.5/GPT4，其他模型转化效果未知。目前对机器学习类文献转化效果最好，其他类型文献转化效果未知。"]) yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 From 8d7ee975a012a9b258408ddcf9a59ea4a29a752d Mon Sep 17 00:00:00 2001 From: binary-husky <96192199+binary-husky@users.noreply.github.com> Date: Sun, 18 Jun 2023 16:10:45 +0800 Subject: [PATCH 15/17] Update README.md --- README.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index f079086..182a49b 100644 --- a/README.md +++ b/README.md @@ -113,6 +113,8 @@ conda activate gptac_venv # 激活anaconda环境 python -m pip install -r requirements.txt # 这个步骤和pip安装一样的步骤 ``` +P.S. 如果需要依赖Latex的插件功能，请见Wiki +
如果需要支持清华ChatGLM/复旦MOSS作为后端，请点击展开此处

@@ -160,7 +162,7 @@ docker run --rm -it --net=host gpt-academic #（最后一步-选择2）在macOS/windows环境下，只能用-p选项将容器上的端口(例如50923)暴露给主机上的端口 docker run --rm -it -e WEB_PORT=50923 -p 50923:50923 gpt-academic ``` -P.S. 如果需要Latex功能，请见另一个[Dockerfile](https://github.com/binary-husky/gpt_academic/blob/master/docs/Dockerfile%2BNoLocal%2BLatex) +P.S. 如果需要依赖Latex的插件功能，请见Wiki 2. ChatGPT + ChatGLM + MOSS（需要熟悉Docker） From 29c6bfb6cb08f58a0e5fba8540ef56cf36277cf6 Mon Sep 17 00:00:00 2001 From: binary-husky <96192199+binary-husky@users.noreply.github.com> Date: Sun, 18 Jun 2023 16:12:06 +0800 Subject: [PATCH 16/17] Update README.md --- README.md | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 182a49b..6e461c2 100644 --- a/README.md +++ b/README.md @@ -113,11 +113,16 @@ conda activate gptac_venv # 激活anaconda环境 python -m pip install -r requirements.txt # 这个步骤和pip安装一样的步骤 ``` -P.S. 如果需要依赖Latex的插件功能，请见Wiki -

如果需要支持清华ChatGLM/复旦MOSS作为后端，请点击展开此处

+ +

如果需要依赖Latex的插件功能（如Arxiv文献翻译），请点击展开此处 +

+ 请见[Wiki](https://github.com/binary-husky/gpt_academic/wiki/%E5%A6%82%E4%BD%95%E4%BD%BF%E7%94%A8Latex%E7%9B%B8%E5%85%B3%E6%8F%92%E4%BB%B6%EF%BC%88arxiv%E6%96%87%E7%AB%A0%E7%BF%BB%E8%AF%91%EF%BC%89) +

+
+ 【可选步骤】如果需要支持清华ChatGLM/复旦MOSS作为后端，需要额外安装更多依赖（前提条件：熟悉Python + 用过Pytorch + 电脑配置够强）： ```sh # 【可选步骤I】支持清华ChatGLM。清华ChatGLM备注：如果遇到"Call ChatGLM fail 不能正常加载ChatGLM的参数" 错误，参考如下： 1：以上默认安装的为torch+cpu版，使用cuda需要卸载torch重新安装torch+cuda； 2：如因本机配置不够无法加载模型，可以修改request_llm/bridge_chatglm.py中的模型精度, 将 AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True) 都修改为 AutoTokenizer.from_pretrained("THUDM/chatglm-6b-int4", trust_remote_code=True) From a06e43c96b9f6c199b0d440d5db2e7247224a18b Mon Sep 17 00:00:00 2001 From: binary-husky <96192199+binary-husky@users.noreply.github.com> Date: Sun, 18 Jun 2023 16:15:37 +0800 Subject: [PATCH 17/17] Update README.md --- README.md | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/README.md b/README.md index 6e461c2..c69bfb5 100644 --- a/README.md +++ b/README.md @@ -113,16 +113,10 @@ conda activate gptac_venv # 激活anaconda环境 python -m pip install -r requirements.txt # 这个步骤和pip安装一样的步骤 ``` +
如果需要支持清华ChatGLM/复旦MOSS作为后端，请点击展开此处

- -

如果需要依赖Latex的插件功能（如Arxiv文献翻译），请点击展开此处 -

- 请见[Wiki](https://github.com/binary-husky/gpt_academic/wiki/%E5%A6%82%E4%BD%95%E4%BD%BF%E7%94%A8Latex%E7%9B%B8%E5%85%B3%E6%8F%92%E4%BB%B6%EF%BC%88arxiv%E6%96%87%E7%AB%A0%E7%BF%BB%E8%AF%91%EF%BC%89) -

-
- 【可选步骤】如果需要支持清华ChatGLM/复旦MOSS作为后端，需要额外安装更多依赖（前提条件：熟悉Python + 用过Pytorch + 电脑配置够强）： ```sh # 【可选步骤I】支持清华ChatGLM。清华ChatGLM备注：如果遇到"Call ChatGLM fail 不能正常加载ChatGLM的参数" 错误，参考如下： 1：以上默认安装的为torch+cpu版，使用cuda需要卸载torch重新安装torch+cuda； 2：如因本机配置不够无法加载模型，可以修改request_llm/bridge_chatglm.py中的模型精度, 将 AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True) 都修改为 AutoTokenizer.from_pretrained("THUDM/chatglm-6b-int4", trust_remote_code=True)