2025.8.15 v3.1.1 released
-
Bug Fixes:
- Added the missing methods
save_vector
,save_visual_info_list
,load_vector
, andload_visual_info_list
in thePP-ChatOCRv4
class. - Added the missing parameters
glossary
andllm_request_interval
to thetranslate
method in thePPDocTranslation
class.
- Added the missing methods
-
Documentation Improvements:
- Added a demo to the MCP documentation.
- Added information about the PaddlePaddle and PaddleOCR version used for performance metrics testing in the documentation.
- Fixed errors and omissions in the production line document translation.
-
Others:
- Changed the MCP server dependency to use the pure Python library
puremagic
instead ofpython-magic
to reduce installation issues. - Retested PP-OCRv5 performance metrics with PaddleOCR version 3.1.0 and updated the documentation.
- Changed the MCP server dependency to use the pure Python library
2025.8.15 v3.1.1 发布
-
bug修复:
- 补充
PP-ChatOCRv4
类缺失的save_vector
、save_visual_info_list
、load_vector、load_visual_info_list
方法。 - 补充
PPDocTranslation
类的translate
方法缺失的glossary 和
llm_request_interval 参数。
- 补充
-
文档优化:
- 补充 MCP 文档中的 demo。
- 补充文档中测试性能指标使用的飞桨框架与 PaddleOCR 版本。
- 修复文档翻译产线文档中的错漏。
-
其他:
- 修改 MCP 服务器依赖,使用纯 Python 库
puremagic
代替python-magic
,减少安装问题。 - 使用 3.1.0 版本 PaddleOCR 重新测试 PP-OCRv5 性能指标,更新文档。
- 修改 MCP 服务器依赖,使用纯 Python 库
Full Changelog: v3.1.0...v3.1.1