v0.2.10
Release Notes - Version 0.2.10
New Features:
- Model Enhancements:
- Added support for the
gpt-4o-minimodel to improve performance. - Introduced new model options including
glm-4variants and versioned Claude models. - Enhanced model selection options for media processing nodes.
- Added support for the
- Workflow Improvements:
- Added versioning for workflow and workflow run records.
- User Interface Updates:
- Added dynamic model family management UI with translations.
- Enhanced settings view with endpoint configurations and LLMs.
- Integration and Compatibility:
- Integrated the
python-vectorveinpackage for improved functionality.
- Integrated the
Improvements:
- Performance Optimization:
- Removed unused multimodal model checks.
- Updated default model to
gpt-4o-minifor better performance.
- Code Quality and Maintenance:
- Refactored hashing to support key ignoring in objects.
- Refactored Azure and Local LLM settings for better structure.
- Removed deprecated
Baichuan2-Turbo-192koption from templates.
Important Notes:
- Settings Structure Change:
- Starting from this version, the structure of user settings will be changed. Old configuration information will be saved in the
settings_v1.jsonfile in the software directory. It is recommended that users back up their database before running the new version.
- Starting from this version, the structure of user settings will be changed. Old configuration information will be saved in the
新特性:
- 模型增强:
- 添加对
gpt-4o-mini模型的支持以提升性能。 - 引入新的模型选项,包括
glm-4变体和版本化的 Claude 模型。 - 增强媒体处理节点的模型选择选项。
- 添加对
- 工作流改进:
- 为工作流和工作流运行记录添加版本控制。
- 用户界面更新:
- 添加动态模型家族管理 UI 并进行翻译。
- 增强设置视图,添加端点配置和 LLM 支持。
- 集成和兼容性:
- 集成
python-vectorvein包以精简项目代码。
- 集成
改进:
- 性能优化:
- 移除未使用的多模态模型检查。
- 将默认模型更新为
gpt-4o-mini以提升性能。
- 代码质量和维护:
- 重构哈希处理以支持对象中的键忽略。
- 重构 Azure 和本地 LLM 设置以提升结构化。
- 从模板中移除已弃用的
Baichuan2-Turbo-192k选项。
重要提示:
- 设置结构变更:
- 从本版本开始,用户设置的结构将进行变更。旧的配置项信息将被保存在软件目录的
settings_v1.json文件中。建议用户在运行新版本前先备份数据库。
- 从本版本开始,用户设置的结构将进行变更。旧的配置项信息将被保存在软件目录的