===>
@@ -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
```
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/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()
diff --git a/crazy_functions/Latex输出PDF结果.py b/crazy_functions/Latex输出PDF结果.py
index 855cc1c..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]
@@ -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
diff --git a/crazy_functions/latex_utils.py b/crazy_functions/latex_utils.py
index d3d7b9c..eebce80 100644
--- a/crazy_functions/latex_utils.py
+++ b/crazy_functions/latex_utils.py
@@ -23,13 +23,67 @@ 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 set_transform_area(text, mask, pattern, flags=0):
"""
- Move caption area out of preserve area
+ Add a transform text area in this paper
"""
pattern_compile = re.compile(pattern, flags)
for res in pattern_compile.finditer(text):
- mask[res.regs[1][0]:res.regs[1][1]] = TRANSFORM
+ mask[res.span()[0] : res.span()[1]] = TRANSFORM
+ return text, mask
+
+
+def split_worker_careful_brace(text, mask, pattern, flags=0):
+ """
+ Move area into preserve area.
+ It is better to wrap the curly braces in the capture group, e.g., r"\\captioin(\{.*\})".
+ """
+ pattern_compile = re.compile(pattern, flags)
+ res = pattern_compile.search(text)
+
+ # 确保捕获组存在
+ if res and len(res.regs) > 1:
+ brace_level = 0
+ p = begin = end = res.regs[1][0]
+ for _ in range(1024 * 16):
+ if text[p] == "}" and brace_level == 1:
+ break
+ elif text[p] == "}":
+ brace_level -= 1
+ elif text[p] == "{":
+ brace_level += 1
+ p += 1
+ end = p
+ mask[begin + 1 : end] = PRESERVE
+ split_worker_careful_brace(text[end:], mask[end:], pattern, flags=flags)
+
+ return text, mask
+
+
+def split_worker_reverse_careful_brace(text, mask, pattern, flags=0):
+ """
+ Move area out of preserve area.
+ It is better to wrap the curly braces in the capture group, e.g., r"\\captioin(\{.*\})".
+ """
+ pattern_compile = re.compile(pattern, flags)
+ res = pattern_compile.search(text)
+
+ # 确保捕获组存在
+ if res and len(res.regs) > 1:
+ brace_level = 0
+ p = begin = end = res.regs[1][0]
+ for _ in range(1024 * 16):
+ if text[p] == "}" and brace_level == 1:
+ break
+ elif text[p] == "}":
+ brace_level -= 1
+ elif text[p] == "{":
+ brace_level += 1
+ p += 1
+ end = p
+ mask[begin + 1 : end] = TRANSFORM
+ split_worker_reverse_careful_brace(text[end:], mask[end:], pattern, flags=flags)
+
return text, mask
def split_worker_begin_end(text, mask, pattern, flags=0, limit_n_lines=42):
@@ -97,17 +151,19 @@ 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():
# 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)
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"(?
+ 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) # 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()
@@ -567,7 +668,7 @@ 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
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,
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"
}
-5. 这是一个能够“自我译解”的开源项目
-
-
