73 Commits

Author	SHA1	Message	Date
shaohuzhang1	35b662a52d	perf: Optimize document extraction for complex table files (#3116)	2025-05-20 13:44:20 +08:00
CaptainB	8d503c8bf8	fix: update post_cell function to handle different newline characters in cell values ... --bug=1054683 --user=刘瑞斌 【github#2831】知识库上传excel、应用编排文档内容提取节点中上传excel，单元格中有换行，导入后没有在一个单元格里显示 https://www.tapd.cn/57709429/s/1690232	2025-04-24 16:05:09 +08:00
shaohuzhang1	0c14306889	fix: Docx segmented font title recognition (#2949)	2025-04-22 14:51:45 +08:00
CaptainB	3b24373cd0	fix: handle line breaks in cell content for markdown table formatting ... --bug=1054683 --user=刘瑞斌 【github#2831】知识库上传excel、应用编排文档内容提取节点中上传excel，单元格中有换行，导入后没有在一个单元格里显示 https://www.tapd.cn/57709429/s/1685274	2025-04-14 14:21:51 +08:00
CaptainB	560890f717	fix: limit chapter title length to 256 characters in pdf_split_handle.py ... --bug=1054363 --user=刘瑞斌 【知识库】导入PDF文档，分段标题长度超长时，没有自动截断 https://www.tapd.cn/57709429/s/1681044	2025-04-07 10:54:59 +08:00
CaptainB	675adeeb63	fix: exclude macOS specific files from zip processing ... --bug=1054264 --user=刘瑞斌 【知识库】QA问答对模式，导入在mac上压缩的zip文件，会出现2个乱码文档 https://www.tapd.cn/57709429/s/1681034	2025-04-07 10:37:06 +08:00
CaptainB	27bc01d442	fix: skip macOS specific metadata directories and files in zip parsing ... --bug=1054264 --user=刘瑞斌 【知识库】QA问答对模式，导入在mac上压缩的zip文件，会出现2个乱码文档 https://www.tapd.cn/57709429/s/1679674	2025-04-02 16:06:36 +08:00
shaohuzhang1	9750c6d605	fix: garbled zip import file names (#2747)	2025-03-31 16:22:39 +08:00
shaohuzhang1	55cdd0a708	fix: Zip with title cannot be parsed (#2683)	2025-03-26 10:31:31 +08:00
shaohuzhang1	5ec94860b2	perf: Enhance Word parsing (#2612)	2025-03-19 12:04:43 +08:00
shaohuzhang1	e420a01e0d	fix: Enterprise WeChat docking sub application cannot output thinking process (#2489)	2025-03-04 19:31:49 +08:00
shaohuzhang1	8c45e92ee4	feat: The OpenAI interface supports the thought process (#2392)	2025-02-25 14:22:51 +08:00
CaptainB	c524fbc0e4	fix: Fix excel merge cells header	2025-02-14 10:26:18 +08:00
CaptainB	89c08b4bb0	fix: Filter blank sheet ... --bug=1052097 --user=刘瑞斌 【github#2196】【应用编排】应用对话的时候上传带空白sheet的表格会报错 https://www.tapd.cn/57709429/s/1653414	2025-02-11 15:17:24 +08:00
shaohuzhang1	f16f417bd5	fix: The knowledge base table file upload is missing a header (#2185)	2025-02-10 10:22:23 +08:00
wxg0103	b90995d3aa	fix: defect of incorrect document names after importing CSV and docx files into the knowledge base ... --bug=1052039 --user=王孝刚 【知识库】-压缩文件中包含csv、docx文件时，导入到知识库后，文档名称包含文件夹名称 https://www.tapd.cn/57709429/s/1651752	2025-02-08 16:00:57 +08:00
shaohuzhang1	a3d6083188	fix: XLS, XLSX, CSV file upload lost data (#2150)	2025-02-07 15:13:14 +08:00
wxg0103	c5585da57d	feat: i18n	2025-01-14 09:46:21 +08:00
shaohuzhang1	a28de6feaf	feat: i18n (#2011)	2025-01-13 11:15:51 +08:00
shaohuzhang1	d9df013e33	fix: Part of the docx document is parsed incorrectly (#1981)	2025-01-06 14:37:51 +08:00
shaohuzhang1	832b0dbd63	feat: Knowledge base import supports zip, xls, xlsx, and csv formats, while knowledge base export supports zip format (#1869)	2024-12-18 18:00:19 +08:00
CaptainB	fb8b96779c	fix: 处理某些pdf中不包括目录和内部链接不能完整导入的问题	2024-12-06 10:49:37 +08:00
CaptainB	7346ef6a2c	fix: 过滤空白的sheet ... --bug=1049943 --user=刘瑞斌 【文档内容提取】-上传的excel中sheet为空时报错 https://www.tapd.cn/57709429/s/1625062	2024-12-04 16:30:43 +08:00
shaohuzhang1	6b4cee1412	fix: 修复对话使用api调用无法响应数据 (#1755)	2024-12-04 14:19:37 +08:00
shaohuzhang1	b6c65154c5	fix: 修复子应用表单调用无法调用问题 (#1741)	2024-12-03 15:23:53 +08:00
shaohuzhang1	b8aa4756c5	fix: 修复工作流节点输出等问题 (#1716)	2024-11-29 19:26:16 +08:00
CaptainB	78cd949f43	fix: 修复上传xlsx里的图片没在文档提取中显示的问题	2024-11-29 16:28:34 +08:00
CaptainB	2a07a50a60	fix: 修复文档提取doc图片没有保存和展示的问题	2024-11-28 16:17:23 +08:00
CaptainB	f638abdea2	fix: 修复文档提取doc图片没有保存和展示的问题	2024-11-28 15:07:21 +08:00
CaptainB	59f5c8ac76	fix: 修复文档提取报错没有显示的问题	2024-11-27 12:20:16 +08:00
CaptainB	64e8f4dc9f	chore: 文档内容无法提取的时候输出错误信息	2024-11-22 17:56:07 +08:00
CaptainB	e1df4b2857	fix: 处理PDF中出现 \0 字符报 Null characters are not allowed ... --bug=1048190 --user=刘瑞斌 【知识库】- 上传PDF文档 报错 ，关联issue #1468 https://www.tapd.cn/57709429/s/1611070	2024-11-18 12:46:37 +08:00
CaptainB	10e53f08e2	feat: 高级编排支持文件上传(WIP)	2024-11-14 14:24:36 +08:00
CaptainB	b57a619bdb	feat: 高级编排支持文件上传(WIP)	2024-11-14 13:36:16 +08:00
shaohuzhang1	22d9fdc42f	fix: 修复旧word文档图片无法正常识别 #1533	2024-11-06 14:20:10 +08:00
CaptainB	834ccaa35b	refactor: PDF分段强制按字数限制 ... --bug=1047568 --user=刘瑞斌 【github#1363】pdf 文件高级分段默认分段长度为500，但生成的段落长度超过29000字符 https://www.tapd.cn/57709429/s/1600183	2024-10-29 11:44:37 +08:00
shaohuzhang1	83d97439e4	fix: 修复导入word文档，有的图片导入不进去	2024-10-28 17:44:11 +08:00
CaptainB	76f63642e5	fix: 修复导入csv空行没有过滤的问题 ... --bug=1047841 --user=刘瑞斌 【知识库】上传csv格式的表格模版，第一行标题导入后分段显示不全 https://www.tapd.cn/57709429/s/1597113	2024-10-24 11:13:26 +08:00
wxg0103	d5bbf48d01	style: 优化样式	2024-10-18 15:51:03 +08:00
Henry-Shaw	33d63c8efe	fix: 修复知识库上传旧版本docx文件后，图片未正常识别导入的问题 (#1382)	2024-10-16 14:39:52 +08:00
CaptainB	e16e827028	fix: 处理文本前后的空白字符	2024-09-25 16:00:30 +08:00
CaptainB	6cacb5be71	fix: 处理不规范的pdf中前言部分没在目录中标识出来，导致不能正常识别的问题	2024-09-24 12:06:51 +08:00
shaohuzhang1	885ab5410a	fix: 修复【知识库】语雀导出的word，导入知识库是空白的 #1148	2024-09-20 19:37:22 +08:00
shaohuzhang1	49efb185e0	fix: 修复【模型设置】使用应用baseurl创建模型报错	2024-09-20 18:48:10 +08:00
shaohuzhang1	fda0bcb5d6	fix: 修复知识库导出后再导入，有一部分内容会丢失	2024-09-20 16:20:08 +08:00
CaptainB	3e3b77e34d	refactor: 处理纵向合并的单元格	2024-09-18 12:37:33 +08:00
CaptainB	746f587698	fix: 表格数据区分xls和xlsx	2024-09-12 10:49:31 +08:00
shaohuzhang1	b924958176	feat: 上传文档表格对支持xlsx文件单元格图片	2024-09-11 18:27:44 +08:00
shaohuzhang1	37445762b2	feat: 上传文档qa问答对支持xlsx文件单元格图片	2024-09-11 15:55:29 +08:00
shaohuzhang1	f9a76d7948	feat: 支持openai接口 #353 (#1128)	2024-09-09 14:47:25 +08:00