20 Commits

Author	SHA1	Message	Date
shaohuzhang1	fa1aee6c3d	perf: Memory optimization (#4318)	2025-11-10 15:21:22 +08:00
CaptainB	d147b794ce	chore: replace split_text with smart_split_paragraph in pdf_split_handle.py	2025-10-27 14:23:42 +08:00
shaohuzhang1	d92dcd722b	fix: Add file name to prompt when processing images with doc (#4114)	2025-09-25 18:51:21 +08:00
CaptainB	4c9756839a	chore: normalize with_filter parameter to boolean in split handle files ... --bug=1057879 --user=刘瑞斌 【知识库】高级分段中自动清洗功能未生效 https://www.tapd.cn/62980211/s/1727744	2025-07-10 15:06:19 +08:00
CaptainB	aa901c7fc7	fix: update file URL paths to use relative references	2025-07-02 22:45:11 +08:00
CaptainB	0f1d57f0cb	feat: enhance error logging for file processing in CSV, XLS, and DOC handlers	2025-06-30 12:49:50 +08:00
CaptainB	82a2203be6	fix: handle string type for limit and improve error logging in pdf_split_handle ... --bug=1057493 --user=刘瑞斌 【知识库】上传文档，使用高级分段报错 https://www.tapd.cn/62980211/s/1720110	2025-06-30 12:47:47 +08:00
CaptainB	d49f448a5f	fix: correct image path replacement logic in zip_split_handle	2025-06-26 17:02:34 +08:00
CaptainB	37ac79dc5a	feat: import File model in zip_split_handle for enhanced functionality ... --bug=1057478 --user=刘瑞斌 【知识库】通用知识库上传ZIP文件，分段失败 https://www.tapd.cn/62980211/s/1719181	2025-06-26 16:56:28 +08:00
CaptainB	e24a2001c5	feat: refine regex patterns in text_split_handle for improved comment detection ... --bug=1057526 --user=刘瑞斌 【知识库】markdown文件导入知识库，分段详情中代码块展示异常 https://www.tapd.cn/62980211/s/1719131	2025-06-26 16:23:32 +08:00
CaptainB	a73e0b10f9	refactor: replace logging with maxkb_logger for consistent logging across modules	2025-06-25 17:00:18 +08:00
CaptainB	fe8f87834d	refactor: replace logging with maxkb_logger for consistent logging across modules	2025-06-25 16:46:50 +08:00
wxg0103	c253e8b696	refactor: remove print	2025-06-24 15:30:42 +08:00
CaptainB	45908b91ff	refactor: update dataset_id to knowledge_id in zip_split_handle.py and tools.py	2025-06-18 21:28:33 +08:00
CaptainB	c0b770f41e	refactor: update dataset_id to knowledge_id in zip_split_handle.py and tools.py	2025-06-18 21:15:53 +08:00
CaptainB	9a7281212d	fix: update image URL paths to use OSS endpoints	2025-06-12 15:49:54 +08:00
wxg0103	b8b14884bd	refactor: add application settings	2025-06-07 17:57:11 +08:00
wxg0103	93833849c1	refactor: file to oss	2025-06-06 11:42:31 +08:00
CaptainB	c3581be9bd	fix: rename image_name to file_name in zip_split_handle and remove workspace_id assignment in document	2025-05-13 12:47:59 +08:00
CaptainB	43bef216d5	refactor: reorganize file handling imports into a structured directory	2025-04-30 16:08:17 +08:00