| | |
| | | import math |
| | | import os |
| | | from lang_flow import LangFlow |
| | | from markitdown import MarkItDown |
| | | |
| | | from knowledgebase.markitdown import MarkItDown |
| | | |
| | | from doc_to_docx import doc_to_docx |
| | | |
| | |
| | | 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) |
| | | text = result.text_content |
| | | out_file = dst_dir + file + '.md' |
| | | with open(out_file, 'w', encoding='utf-8') as f: |
| | | f.write(text) |
| | | return out_file |
| | | |
| | | |
| | |
| | | # 2.输入文档 |
| | | # 3.启动LangFlow |
| | | def main(): |
| | | # doc_dir = "D:\\workspace\\PythonProjects\\KnowledgeBase\\doc\\" |
| | | doc_dir = ".\\doc\\" |
| | | # 处理文档 |
| | | # process_docs(doc_dir) |
| | | # 文档转换为markdown |
| | | # md_file = to_markdown(doc_dir) |
| | | 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() |
| | | # 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) |
| | | |
| | | |
| | | def get_bit_mask(start, end): |
| | | bits = math.ceil((end + 1) / 8) * 8 |
| | | if bits == 0: |
| | | bits = 8 |
| | | mask = 0 |
| | | for i in range(start, end + 1): |
| | | mask |= 1 << (bits - i - 1) |
| | | return mask |
| | | |
| | | |
| | | if __name__ == '__main__': |
| | | main() |
| | | main() |