最近更新内容
更新日志
v0.5.1
v0.5.1 - 2024-12-25
added
🔕 Notification Sound Toggle
Added a new setting under Settings > Interface to disable notification sounds, giving you greater control over your workspace environment and focus.
fixed
🔄 Non-Streaming Response Visibility
Resolved an issue where non-streaming responses were not displayed, ensuring all responses are now reliably shown in your conversations.
🖋️ Title Generation with OpenAI APIs
Fixed a bug preventing title generation when using OpenAI APIs, restoring the ability to automatically generate chat titles for smoother organization.
👥 Admin Panel User List
Addressed the issue where only 50 users were visible in the admin panel. You can now manage and view all users without restrictions.
🖼️ Image Generation Error
Fixed the issue causing 'get_automatic1111_api_auth()' errors in image generation, ensuring seamless creative workflows.
⚙️ Pipeline Settings Loading Issue
Resolved a problem where pipeline settings were stuck at the loading screen, restoring full configurability in the admin panel.
v0.5.0 - 2024-12-25
added
💬 True Asynchronous Chat Support
Create chats, navigate away, and return anytime with responses ready. Ideal for reasoning models and multi-agent workflows, enhancing multitasking like never before.
🔔 Chat Completion Notifications
Never miss a completed response. Receive instant in-UI notifications when a chat finishes in a non-active tab, keeping you updated while you work elsewhere.
🌐 Notification Webhook Integration
Get alerts via webhooks even when your tab is closed! Configure your webhook URL in Settings > Account and receive timely updates for long-running chats or external integration needs.
📚 Channels (Beta)
Explore Discord/Slack-style chat rooms designed for real-time collaboration between users and AIs. Build bots for channels and unlock asynchronous communication for proactive multi-agent workflows. Opt-in via Admin Settings > General. A Comprehensive Bot SDK tutorial (https://github.com/open-webui/bot) is incoming, so stay tuned!
🖼️ Client-Side Image Compression
Now compress images before upload (Settings > Interface), saving bandwidth and improving performance seamlessly.
🛠️ OAuth Management for User Groups
Enable group-level management via OAuth integration for enhanced control and scalability in collaborative environments.
✅ Structured Output for Ollama
Pass structured data output directly to Ollama, unlocking new possibilities for streamlined automation and precise data handling.
📜 Offline Swagger Documentation
Developer-friendly Swagger API docs are now available offline, ensuring full accessibility wherever you are.
📸 Quick Screen Capture Button
Effortlessly capture your screen with a single click from the message input menu.
🌍 i18n Updates
Improved and refined translations across several languages, including Ukrainian, German, Brazilian Portuguese, Catalan, and more, ensuring a seamless global user experience.
fixed
📋 Table Export to CSV
Resolved issues with CSV export where headers were missing or errors occurred due to values with commas, ensuring smooth and reliable data handling.
🔓 BYPASS_MODEL_ACCESS_CONTROL
Fixed an issue where users could see models but couldn’t use them with 'BYPASS_MODEL_ACCESS_CONTROL=True', restoring proper functionality for environments leveraging this setting.
changed
💡 API Key Authentication Restriction
Narrowed API key auth permissions to '/api/models' and '/api/chat/completions' for enhanced security and better API governance.
⚙️ Backend Overhaul for Performance
Major backend restructuring; a heads-up that some "Functions" using internal variables may face compatibility issues. Moving forward, websocket support is mandatory to ensure Open WebUI operates seamlessly.
removed
⚠️ Legacy Functionality Clean-Up
Deprecated outdated backend systems that were non-essential or overlapped with newer implementations, allowing for a leaner, more efficient platform.
v0.4.8 - 2024-12-07
added
🔓 Bypass Model Access Control
Introduced the 'BYPASS_MODEL_ACCESS_CONTROL' environment variable. Easily bypass model access controls for user roles when access control isn't required, simplifying workflows for trusted environments.
📝 Markdown in Banners
Now supports markdown for banners, enabling richer, more visually engaging announcements.
🌐 Internationalization Updates
Enhanced translations across multiple languages, further improving accessibility and global user experience.
🎨 Styling Enhancements
General UI style refinements for a cleaner and more polished interface.
📋 Rich Text Reliability
Improved the reliability and stability of rich text input across chats for smoother interactions.
fixed
💡 Tailwind Build Issue
Resolved a breaking bug caused by Tailwind, ensuring smoother builds and overall system reliability.
📚 Knowledge Collection Query Fix
Addressed API endpoint issues with querying knowledge collections, ensuring accurate and reliable information retrieval.
v0.4.7 - 2024-12-01
added
✨ Prompt Input Auto-Completion
Type a prompt and let AI intelligently suggest and complete your inputs. Simply press 'Tab' or swipe right on mobile to confirm. Available only with Rich Text Input (default setting). Disable via Admin Settings for full control.
🌍 Improved Translations
Enhanced localization for multiple languages, ensuring a more polished and accessible experience for international users.
fixed
🛠️ Tools Export Issue
Resolved a critical issue where exporting tools wasn’t functioning, restoring seamless export capabilities.
🔗 Model ID Registration
Fixed an issue where model IDs weren’t registering correctly in the model editor, ensuring reliable model setup and tracking.
🖋️ Textarea Auto-Expansion
Corrected a bug where textareas didn’t expand automatically on certain browsers, improving usability for multi-line inputs.
🔧 Ollama Embed Endpoint
Addressed the /ollama/embed endpoint malfunction, ensuring consistent performance and functionality.
changed
🎨 Knowledge Base Styling
Refined knowledge base visuals for a cleaner, more modern look, laying the groundwork for further enhancements in upcoming releases.
v0.4.6 - 2024-11-26
added
🌍 Enhanced Translations
Various language translations improved to make the WebUI more accessible and user-friendly worldwide.
fixed
✏️ Textarea Shifting Bug
Resolved the issue where the textarea shifted unexpectedly, ensuring a smoother typing experience.
⚙️ Model Configuration Modal
Fixed the issue where the models configuration modal introduced in 0.4.5 wasn’t working for some users.
🔍 Legacy Query Support
Restored functionality for custom query generation in RAG when using legacy prompts, ensuring both default and custom templates now work seamlessly.
⚡ Improved General Reliability
Various minor fixes improve platform stability and ensure a smoother overall experience across workflows.
2 个赞
又更了？
bug很多
更新日志
v0.5.1 - 2024-12-25
新增
通知声音开关：在“设置”>“界面”下添加了一个新设置，用于禁用通知声音，让您可以更好地控制您的工作环境和注意力。
修复
非流式响应可见性：解决了非流式响应不显示的问题，确保现在所有响应都能可靠地显示在您的对话中。
使用 OpenAI API 生成标题：修复了使用 OpenAI API 时无法生成标题的错误，恢复了自动生成聊天标题的功能，使组织更顺畅。
管理员面板用户列表：解决了管理员面板中只能看到 50 个用户的问题。您现在可以不受限制地管理和查看所有用户。
图像生成错误：修复了图像生成中导致“get_automatic1111_api_auth()”错误的的问题，确保无缝的创作流程。
流水线设置加载问题：解决了流水线设置卡在加载屏幕的问题，恢复了管理员面板中的完整可配置性。
v0.5.0 - 2024-12-25
新增
真正的异步聊天支持：创建聊天，离开，然后随时返回，响应已准备就绪。非常适合推理模型和多代理工作流程，前所未有地增强多任务处理能力。
聊天完成通知：不再错过已完成的响应。当聊天在非活动标签页中完成时，会收到即时的 UI 内通知，让您在其他地方工作时也能保持更新。
通知 Webhook 集成：即使您的标签页关闭，也能通过 webhooks 获得提醒！在“设置”>“帐户”中配置您的 webhook URL，并及时接收长时间运行的聊天或外部集成需求的更新。
频道（测试版）：探索 Discord/Slack 风格的聊天室，专为用户和 AI 之间的实时协作而设计。为频道构建机器人，并解锁异步通信，以实现主动的多代理工作流程。通过“管理员设置”>“常规”选择加入。即将推出全面的机器人 SDK 教程 (GitHub - open-webui/bot: beep boop 🤖 (experimental))，敬请期待！- 客户端图像压缩：现在可以在上传前压缩图像（“设置”>“界面”），无缝节省带宽并提高性能。
用户组的 OAuth 管理：通过 OAuth 集成启用组级管理，以增强协作环境中的控制和可扩展性。
Ollama 的结构化输出：将结构化数据输出直接传递给 Ollama，为简化的自动化和精确的数据处理解锁新的可能性。
离线 Swagger 文档：开发者友好的 Swagger API 文档现在可以离线使用，确保无论您身在何处都能完全访问。
快速屏幕捕获按钮：从消息输入菜单中单击一下即可轻松捕获您的屏幕。
i18n 更新：改进和完善了多种语言的翻译，包括乌克兰语、德语、巴西葡萄牙语、加泰罗尼亚语等，确保无缝的全球用户体验。
修复
表格导出到 CSV：解决了 CSV 导出中标题丢失或由于值中包含逗号而发生错误的问题，确保顺畅可靠的数据处理。
BYPASS_MODEL_ACCESS_CONTROL：修复了当“BYPASS_MODEL_ACCESS_CONTROL=True”时，用户可以看到模型但无法使用它们的问题，为利用此设置的环境恢复了适当的功能。
更改
API 密钥认证限制：将 API 密钥认证权限缩小到“/api/models”和“/api/chat/completions”，以增强安全性并改进 API 治理。- 后端重构以提高性能：主要的后端重构；请注意，某些使用内部变量的“函数”可能会面临兼容性问题。展望未来，强制要求支持 websocket，以确保 Open WebUI 无缝运行。
移除
遗留功能清理：弃用了非必要或与更新的实现重叠的过时的后端系统，从而实现更精简、更高效的平台。
v0.4.8 - 2024-12-07
新增
- 绕过模型访问控制：引入了“BYPASS_MODEL_ACCESS_CONTROL”环境变量。在不需要访问控制时，轻松绕过用户角色的模型访问控制，简化受信任环境的工作流程。
横幅中的 Markdown：现在支持横幅中的 markdown，从而实现更丰富、更具视觉吸引力的公告。- 国际化更新：增强了多种语言的翻译，进一步提高了可访问性和全球用户体验。
样式增强：常规 UI 样式改进，使界面更简洁、更美观。- 富文本可靠性：提高了聊天中富文本输入的可靠性和稳定性，以实现更顺畅的交互。
修复
- Tailwind 构建问题：解决了由 Tailwind 引起的破坏性错误，确保更顺畅的构建和整体系统可靠性。
- 知识库查询修复：解决了查询知识库的 API 端点问题，确保准确可靠的信息检索。
v0.4.7 - 2024-12-01
新增
提示输入自动完成：键入提示，让 AI 智能地建议并完成您的输入。只需在移动设备上按“Tab”键或向右滑动即可确认。仅适用于富文本输入（默认设置）。可通过管理员设置禁用以进行完全控制。- 改进的翻译：增强了多种语言的本地化，确保为国际用户提供更完善和更易于访问的体验。
修复
- 工具导出问题：解决了一个关键问题，即工具导出无法正常工作，恢复了无缝导出功能。
模型 ID 注册：修复了模型 ID 在模型编辑器中未正确注册的问题，确保可靠的模型设置和跟踪。- 文本区域自动扩展：更正了文本区域在某些浏览器上无法自动扩展的错误，提高了多行输入的可用性。
Ollama 嵌入端点：解决了 /ollama/embed 端点故障，确保一致的性能和功能。
更改
- 知识库样式：改进了知识库视觉效果，使其更简洁、更现代，为即将发布的版本中的进一步增强奠定了基础。
v0.4.6 - 2024-11-26
新增
- 增强的翻译：改进了各种语言的翻译，使 WebUI 在全球范围内更易于访问和用户友好。
修复
文本区域偏移错误：解决了文本区域意外偏移的问题，确保更顺畅的打字体验。- 模型配置模态框：修复了 0.4.5 中引入的模型配置模态框对某些用户不起作用的问题。
旧查询支持：在使用旧提示时，恢复了 RAG 中自定义查询生成的功能，确保默认和自定义模板现在都能无缝工作。
提高了一般可靠性：各种小修复提高了平台稳定性，并确保了跨工作流程的整体体验更加顺畅。
2 个赞
更新后，我的大多函数失效。
2 个赞
已经安装过的，可以保留配置更新吗，docker模式下
配置可以导出json
1 个赞
我在huggingface部署的openwebui更新了0.5.0后，流式输出特别慢，deepseek v3在我之前部署的0.4.7版本上发你好，开始输出后秒输出完成。在0.5.0上两个字两个字吐，打个招呼都要4,5秒 
1 个赞
我nas上docker部署5.0没问题
什么bug，我目前没有感受到问题
有人遇到了每10ms请求一次socket.io的问题，导致特别卡顿
1 个赞
据说outlet的问题会在即将发的0.5.2解决，我是想回退了0.4.8了，性能比原来卡太多了，而且api的o1思考4分钟还会报错net error
0.5.1的标题生成还没解决
昨天更新了，好象是快了一点
可以不用，但不能不更 
算了，能用就暂时不折腾了
还是等稳定再更好了，有好多bug，而且性能还变差了
据说解决了