glowz/ragflow_api_test
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

更新主函数，添加PDF和TXT文件处理说明，注释掉文件选择和处理逻辑

Browse Source
This commit is contained in:
glowzz
2025-07-22 18:29:48 +08:00
parent 2cc9dbfcd0
commit 40211521a2
1 changed files with 14 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
src/add_chunk_cli_pdf_img.py
View File

@@ -157,19 +157,27 @@ def process_pdf_txt_pairs(pdf_dict, txt_dict, dataset):
process_txt_chunks(document, txt_path) process_txt_chunks(document, txt_path)
def main(): def main():
file_path = "g:\\11\\22\\规范\\"
pdf_dict, txt_dict = pair_pdf_and_txt(file_path, file_path) """主函数，处理PDF和TXT文件对
if not pdf_dict: dataset.id = bucket_name
print("未选择任何文件。") chunk_id = object_name
return """
file_path = "g:\\11\\22\\规范\\"
#pdf_dict, txt_dict = pair_pdf_and_txt(file_path, file_path)
# if not pdf_dict:
# print("未选择任何文件。")
# return
dataset = select_dataset(rag_object) dataset = select_dataset(rag_object)
print(f"选择的数据集: {dataset.name}")
print(f"选择的数据集id: {dataset.id}")
if not dataset: if not dataset:
print("未选择数据集。") print("未选择数据集。")
return return
process_pdf_txt_pairs(pdf_dict, txt_dict, dataset) #process_pdf_txt_pairs(pdf_dict, txt_dict, dataset)