diff --git a/dsRagAnything/Doc/长春市各区+各年级学生数量.xlsx b/dsRagAnything/Doc/长春市各区+各年级学生数量.xlsx new file mode 100644 index 00000000..b511235e Binary files /dev/null and b/dsRagAnything/Doc/长春市各区+各年级学生数量.xlsx differ diff --git a/dsRagAnything/Output/长春市各区+各年级学生数量.pdf b/dsRagAnything/Output/长春市各区+各年级学生数量.pdf new file mode 100644 index 00000000..510536a6 Binary files /dev/null and b/dsRagAnything/Output/长春市各区+各年级学生数量.pdf differ diff --git a/dsRagAnything/T1_Train.py b/dsRagAnything/T1_Train.py index f0c1fc20..95b09307 100644 --- a/dsRagAnything/T1_Train.py +++ b/dsRagAnything/T1_Train.py @@ -143,12 +143,13 @@ async def train(file_path, output_dir, working_dir): if __name__ == "__main__": # LightRag的数据库所在目录 - working_dir = "./Topic/HuangWanQiao" - + #working_dir = "./Topic/HuangWanQiao" + working_dir = "./Topic/Excel" # MinerU生成的临时文件目录 output_dir = "./Output" # 文档路径 - file_path = "./Doc/黄琬乔2023蓝桥杯省赛准考证.pdf" + #file_path = "./Doc/黄琬乔2023蓝桥杯省赛准考证.pdf" + file_path = "./Doc/长春市各区+各年级学生数量.xlsx" # 开始训练 asyncio.run(train(file_path, output_dir, working_dir))