diff --git a/crazy_functional.py b/crazy_functional.py index 45570616..83915813 100644 --- a/crazy_functional.py +++ b/crazy_functional.py @@ -112,6 +112,7 @@ def get_crazy_functions(): "Group": "学术", "Color": "stop", "AsButton": False, + "AdvancedArgs": True, "Info": "批量总结word文档 | 输入参数为路径", "Function": HotReload(总结文件), }, @@ -347,18 +348,6 @@ def get_crazy_functions(): "Function": HotReload(Latex翻译中文并重新编译PDF), # 当注册Class后，Function旧接口仅会在“虚空终端”中起作用 "Class": Arxiv_Localize, # 新一代插件需要注册Class }, - "📚Arxiv论文交互对话（输入arxivID）": { - "Group": "学术", - "Color": "stop", - "AsButton": False, - "AdvancedArgs": True, - "ArgsReminder": r"如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 " - r"例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: " - r'If the term "agent" is used in this section, it should be translated to "智能体". ', - "Info": "Arixv论文精细翻译 | 输入参数arxiv论文的ID，比如1812.10695", - "Function": HotReload(Arxiv_论文对话), # 当注册Class后，Function旧接口仅会在“虚空终端”中起作用 - "Class": Arxiv_Localize, # 新一代插件需要注册Class - }, "📚本地Latex论文精细翻译（上传Latex项目）[需Latex]": { "Group": "学术", "Color": "stop", diff --git a/crazy_functions/rag_fns/rag_file_support.py b/crazy_functions/rag_fns/rag_file_support.py index 98ba3bee..dd2137f3 100644 --- a/crazy_functions/rag_fns/rag_file_support.py +++ b/crazy_functions/rag_fns/rag_file_support.py @@ -1,22 +1,56 @@ import os from llama_index.core import SimpleDirectoryReader -supports_format = ['.csv', '.docx', '.epub', '.ipynb', '.mbox', '.md', '.pdf', '.txt', '.ppt', - '.pptm', '.pptx'] +supports_format = ['.csv', '.docx','.doc', '.epub', '.ipynb', '.mbox', '.md', '.pdf', '.txt', '.ppt', + '.pptm', '.pptx','.py', '.xls', '.xlsx', '.html', '.json', '.xml', '.yaml', '.yml' ,'.m'] +def read_docx_doc(file_path): + if file_path.split(".")[-1] == "docx": + from docx import Document + doc = Document(file_path) + file_content = "\n".join([para.text for para in doc.paragraphs]) + else: + try: + import win32com.client + word = win32com.client.Dispatch("Word.Application") + word.visible = False + # 打开文件 + doc = word.Documents.Open(os.getcwd() + '/' + file_path) + # file_content = doc.Content.Text + doc = word.ActiveDocument + file_content = doc.Range().Text + doc.Close() + word.Quit() + except: + raise RuntimeError('请先将.doc文档转换为.docx文档。') + return file_content # 修改后的 extract_text 函数，结合 SimpleDirectoryReader 和自定义解析逻辑 +import os + def extract_text(file_path): _, ext = os.path.splitext(file_path.lower()) # 使用 SimpleDirectoryReader 处理它支持的文件格式 - if ext in supports_format: + if ext in ['.docx', '.doc']: + return read_docx_doc(file_path) + else: + # 尝试读取文件为纯文本 try: - reader = SimpleDirectoryReader(input_files=[file_path]) - documents = reader.load_data() - if len(documents) > 0: - return documents[0].text + with open(file_path, 'r', encoding='utf-8') as f: + return f.read() + except UnicodeDecodeError: + # 如果遇到解码错误，说明文件不是纯文本 + print(f"Error: {file_path} is not a valid text file.") except Exception as e: - pass + # 捕获其他可能的异常 + print(f"Error reading file {file_path}: {e}") + try: + reader = SimpleDirectoryReader(input_files=[file_path]) + documents = reader.load_data() + if len(documents) > 0: + return documents[0].text + except Exception as e: + pass return None diff --git a/crazy_functions/总结文档.py b/crazy_functions/总结文档.py index 3ba142d1..afb5ede9 100644 --- a/crazy_functions/总结文档.py +++ b/crazy_functions/总结文档.py @@ -14,6 +14,8 @@ def 文档总结(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatb for index, fp in enumerate(file_manifest): file_content = extract_text(fp) # private_upload里面的文件名在解压zip后容易出现乱码（rar和7z格式正常），故可以只分析文章内容，不输入文件名 + if file_content==None: + continue from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit from request_llms.bridge_all import model_info max_token = model_info[llm_kwargs['llm_model']]['max_token'] @@ -21,8 +23,8 @@ def 文档总结(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatb paper_fragments = breakdown_text_to_satisfy_token_limit(txt=file_content, limit=TOKEN_LIMIT_PER_FRAGMENT, llm_model=llm_kwargs['llm_model']) this_paper_history = [] for i, paper_frag in enumerate(paper_fragments): - i_say = f'请对下面的内容用中文做概述，文件名是{os.path.relpath(fp, project_folder)}，内容是 ```{paper_frag}```' - i_say_show_user = f'请对下面的内容片段做概述: {os.path.abspath(fp)}的第{i+1}/{len(paper_fragments)}个片段。' + i_say = f'请对下面的内容用中文做概述，文件名是{os.path.relpath(fp, project_folder)}，做概述时请注意以下要求：{plugin_kwargs['advanced_arg']}：内容是 ```{paper_frag}```' + i_say_show_user = f'请对下面的内容片段做概述，做概述时请注意以下要求：{plugin_kwargs['advanced_arg']}: {os.path.abspath(fp)}的第{i+1}/{len(paper_fragments)}个片段。' gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive( inputs=i_say, inputs_show_user=i_say_show_user, @@ -38,7 +40,7 @@ def 文档总结(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatb # 已经对该文章的所有片段总结完毕，如果文章被切分了， if len(paper_fragments) > 1: - i_say = f"根据以上的对话，总结文件{os.path.abspath(fp)}的主要内容。" + i_say = f"根据以上的对话，总结时请注意以下要求：{plugin_kwargs['advanced_arg']}，总结文件{os.path.abspath(fp)}的主要内容。" gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive( inputs=i_say, inputs_show_user=i_say, @@ -67,7 +69,6 @@ def 总结文件(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt import glob, os # 基本信息：功能、贡献者 - supports_format = ["pdf", "docx", "txt", "md"] # 假设支持的文件格式 chatbot.append([ "函数插件功能？", f"批量总结各类文件。函数插件贡献者: JasonGuo1 and BoyinLiu。支持的文件类型包括：{', '.join(supports_format)}。" @@ -87,10 +88,8 @@ def 总结文件(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt return # 搜索需要处理的文件清单 - file_manifest = [] - for ext in supports_format: - file_manifest += [f for f in glob.glob(f'{project_folder}/**/*{ext}', recursive=True)] + file_manifest = [f for f in glob.glob(f'{project_folder}/**', recursive=True) if os.path.isfile(f)] # 如果没找到任何文件 if len(file_manifest) == 0: