| | |
|---|
| | | import os |
|---|
| | | from lang_flow import LangFlow |
|---|
| | | from markitdown import MarkItDown |
|---|
| | | |
|---|
| | | from doc_to_docx import doc_to_docx |
|---|
| | | |
|---|
| | | |
|---|
| | | def process_docs(directory): |
|---|
| | | # 遍历目录下的所有文件 |
|---|
| | | for filename in os.listdir(directory): |
|---|
| | | # 判断是否为 doc 文件 |
|---|
| | | if filename.endswith(".doc"): |
|---|
| | | # 转换为 docx |
|---|
| | | doc_to_docx(directory + filename, directory + filename.replace(".doc", ".docx")) |
|---|
| | | |
|---|
| | | |
|---|
| | | md = MarkItDown() |
|---|
| | | |
|---|
| | | |
|---|
| | | def to_markdown(dst_dir: str): |
|---|
| | | text = '' |
|---|
| | | # 遍历文件夹下的所有文件 |
|---|
| | | for file in os.listdir(dst_dir): |
|---|
| | | # 判断是否为 docx 文件 |
|---|
| | | if file.endswith(".docx"): |
|---|
| | | # 转换为 md |
|---|
| | | result = md.convert(dst_dir + file) |
|---|
| | | text += '\n\n' + result.text_content |
|---|
| | | out_file = dst_dir + 'docs.md' |
|---|
| | | with open(out_file, 'w', encoding='utf-8') as f: |
|---|
| | | f.write(text) |
|---|
| | | return out_file |
|---|
| | | |
|---|
| | | |
|---|
| | | # 1.解析文档 |
|---|
| | | # 2.输入文档 |
|---|
| | | # 3.启动LangFlow |
|---|
| | | def main(): |
|---|
| | | # doc_dir = "D:\\workspace\\PythonProjects\\KnowledgeBase\\doc\\" |
|---|
| | | # 处理文档 |
|---|
| | | # process_docs(doc_dir) |
|---|
| | | # 文档转换为markdown |
|---|
| | | # md_file = to_markdown(doc_dir) |
|---|
| | | |
|---|
| | | md_file = 'D:\\workspace\\PythonProjects\\KnowledgeBase\\doc\\test.md' |
|---|
| | | # 启动大模型处理流程 |
|---|
| | | ret_text = LangFlow([md_file]).run() |
|---|
| | | # 保存结果 |
|---|
| | | # with open('D:\\workspace\\PythonProjects\\KnowledgeBase\\doc\\test.text', 'w', encoding='utf-8') as f: |
|---|
| | | # f.write(ret_text) |
|---|
| | | |
|---|
| | | if __name__ == '__main__': |
|---|
| | | main() |
|---|
