Feat: Q&A format segmentation support (#668)

Co-authored-by: jyong <718720800@qq.com> Co-authored-by: StyleZhang <jasonapring2015@outlook.com>
2023-07-28 20:47:15 +08:00
parent aae2fb8a30
commit cf93d8d6e2
52 changed files with 2038 additions and 274 deletions
--- a/api/core/data_loader/loader/excel.py
+++ b/api/core/data_loader/loader/excel.py
@@ -39,7 +39,7 @@ class ExcelLoader(BaseLoader):
                    row_dict = dict(zip(keys, list(map(str, row))))
                    row_dict = {k: v for k, v in row_dict.items() if v}
                    item = ''.join(f'{k}:{v}\n' for k, v in row_dict.items())
-                    document = Document(page_content=item)
+                    document = Document(page_content=item, metadata={'source': self._file_path})
                    data.append(document)

        return data