open-webui / open-webui

本文为原文前 6,000 字符的节选翻译，完整内容请查看原文。

Open WebUI 👋 Open WebUI is a home for AI, a self-hosted AI platform that’s extensible, feature-rich, user-friendly, and built to run entirely offline. With support for Ollama and OpenAI-compatible APIs, it gives you a powerful, provider-agnostic interface for both local and cloud-based models. Passionate about open-source AI? Join our team → TipLooking for an Enterprise Plan? – Speak with Our Sales Team Today! For more information, be sure to check out our Open WebUI Documentation.

Open WebUI 👋 Open WebUI 是一个 AI 之家，这是一个可扩展、功能丰富、用户友好且完全离线运行的自托管 AI 平台。通过对 Ollama 和兼容 OpenAI 的 API 的支持，它为你提供了一个强大的、与提供商无关的界面，适用于本地和云端模型。对开源 AI 充满热情？加入我们的团队 → 提示：正在寻找企业版计划？——立即与我们的销售团队联系！欲了解更多信息，请务必查看我们的 Open WebUI 文档。

Key Features of Open WebUI ⭐ 🚀 Effortless Setup: Install seamlessly via pip, uv, Docker, or Kubernetes (kubectl, kustomize, or helm), with :ollama and :cuda tagged images available for container deployments. 🤝 Broad Model & API Integration: Connect any OpenAI-compatible API alongside local Ollama models. Point the API URL at LMStudio, GroqCloud, Mistral, OpenRouter, vLLM, and more to mix and match providers freely. 🔐 Granular RBAC & User Groups: Administrators define detailed roles, groups, and permissions, giving each user exactly the access they need. Secure by default, with tailored experiences per group. 🧩 Plugin Support: Extend Open WebUI with Filters, Actions, Pipes, Tools, and Skills. Connect external services through MCP, MCPO, and OpenAPI tool servers. Build custom integrations, rate limits, approval flows, data connections, and more.

Open WebUI 的主要功能 ⭐ 🚀 轻松设置：通过 pip、uv、Docker 或 Kubernetes（kubectl、kustomize 或 helm）无缝安装，并提供 :ollama 和 :cuda 标签的镜像用于容器部署。🤝 广泛的模型与 API 集成：将任何兼容 OpenAI 的 API 与本地 Ollama 模型连接起来。将 API URL 指向 LMStudio、GroqCloud、Mistral、OpenRouter、vLLM 等，自由组合不同的提供商。🔐 细粒度的 RBAC 和用户组：管理员可以定义详细的角色、组和权限，为每个用户提供其所需的精确访问权限。默认安全，并为每个组提供定制的体验。🧩 插件支持：通过过滤器、动作、管道、工具和技能扩展 Open WebUI。通过 MCP、MCPO 和 OpenAPI 工具服务器连接外部服务。构建自定义集成、速率限制、审批流程、数据连接等。

🤖 Models & Agents: Wrap any base model with custom instructions, tools, and knowledge to build specialized agents. Supports dynamic variables, per-user/group access control, and community preset imports via Open WebUI Community. ⚡ Agentic Execution with Open Terminal: Give your agents a terminal and filesystem to carry out multi-step tasks. Let them analyze data, run scripts, fix errors, and produce files directly in chat. Scale to teams with Terminals (Enterprise) for per-user isolated environments, resource limits, and automatic lifecycle management. 📝 Notes: A dedicated workspace for content outside conversations. Draft with a rich editor, use AI to rewrite selected text, and attach notes to any chat for full-context injection. 📢 Channels: Real-time shared spaces where your team and AI models collaborate in one timeline. Tag models to draft or critique, with threads, reactions, pins, and access control.

🤖 模型与智能体：使用自定义指令、工具和知识封装任何基础模型，以构建专门的智能体。支持动态变量、按用户/组的访问控制，以及通过 Open WebUI 社区导入社区预设。⚡ 带有开放终端的智能体执行：为你的智能体提供终端和文件系统以执行多步骤任务。让他们在聊天中直接分析数据、运行脚本、修复错误并生成文件。通过终端（企业版）扩展到团队，实现用户隔离环境、资源限制和自动生命周期管理。📝 笔记：一个用于对话之外内容的专用工作区。使用富文本编辑器进行草拟，利用 AI 重写选定文本，并将笔记附加到任何聊天中以进行全上下文注入。📢 频道：实时共享空间，你的团队和 AI 模型可以在同一个时间轴上协作。标记模型进行草拟或评论，支持主题、反应、置顶和访问控制。

🧠 Persistent Memory: The AI remembers facts about you across conversations, carrying context from one chat to the next. ✅ Live Workflow & Message Flow: Watch the AI build and work through checklists in real time. Queue messages while the AI is still responding; they send automatically when it’s ready. 📅 Calendar & AI Scheduling: Built-in personal and shared calendars with month/week/day views, recurring events, color coding, attendees, and reminders. Models manage your schedule conversationally through native function calling. ⏱️ Automations: Schedule prompts to run on recurring schedules, with runs surfaced on your calendar and each completed run linking back to the chat it produced.

🧠 持久记忆：AI 会记住你在不同对话中的事实，将上下文从一个聊天带到下一个聊天。✅ 实时工作流与消息流：实时观察 AI 构建并完成清单。在 AI 仍在响应时排队消息；当它准备好时，消息会自动发送。📅 日历与 AI 日程安排：内置个人和共享日历，支持月/周/日视图、重复事件、颜色编码、参与者和提醒。模型通过原生函数调用以对话方式管理你的日程。⏱️ 自动化：安排提示词按重复时间表运行，运行记录会显示在你的日历上，并且每次完成的运行都会链接回它所产生的聊天。

📱 Responsive Design & PWA: Seamless experience across desktop, laptop, and mobile, with a Progressive Web App for native app-like feel and offline access on localhost. ✒️🔢 Full Markdown and LaTeX Support: Comprehensive Markdown and LaTeX capabilities for enriched interaction. 🎤📹 Hands-Free Voice/Video Call: Integrated voice and video calls with multiple Speech-to-Text providers (Local Whisper, OpenAI, Deepgram, Azure) and Text-to-Speech engines (Azure, ElevenLabs, OpenAI, Transformers, WebAPI). 💾 Persistent Artifact Storage: Built-in key-value storage API for artifacts, enabling journals, trackers, leaderboards, and collaborative tools with personal and shared data scopes.

📱 响应式设计与 PWA：在台式机、笔记本电脑和移动设备上提供无缝体验，并提供渐进式 Web 应用（PWA），带来类似原生应用的感觉和本地主机的离线访问。✒️🔢 全面的 Markdown 和 LaTeX 支持：全面的 Markdown 和 LaTeX 功能，用于丰富的交互。🎤📹 免提语音/视频通话：集成的语音和视频通话，支持多种语音转文字提供商（本地 Whisper、OpenAI、Deepgram、Azure）和文字转语音引擎（Azure、ElevenLabs、OpenAI、Transformers、WebAPI）。💾 持久化工件存储：内置用于工件的键值存储 API，支持日志、追踪器、排行榜以及具有个人和共享数据范围的协作工具。

📚 Local RAG Integration: Retrieval Augmented Generation backed by 9 vector databases and multiple content-extraction engines (Tika, Docling, Document Intelligence, Mistral OCR, PaddleOCR-vl, external loaders). Supports hybrid search (BM25 + vector) with reranking and full-context mode. Load documents into chat or pull them from your library with the # command. 🔍 Web Search for RAG: Search the web through dozens of providers including SearXNG, Google PSE, Brave Search, Kagi, Mojeek, Tavily, Perplexity, Firecrawl, serpstack, serper, Serply, DuckDuckGo, SearchApi, SerpApi, Bing, Jina, Exa, Sougou, Azure AI Search, and Ollama Cloud, injecting results directly into the conversation. 🌐 Web Browsing Capability: Pull websites into chat with the # command followed by a URL, or let the model fetch them on its own when needed.

📚 本地 RAG 集成：由 9 个向量数据库和多个内容提取引擎（Tika、Docling、Document Intelligence、Mistral OCR、PaddleOCR-vl、外部加载器）支持的检索增强生成。支持混合搜索（BM25 + 向量），具有重排序和全上下文模式。将文档加载到聊天中，或使用 # 命令从你的库中提取它们。🔍 用于 RAG 的网络搜索：通过数十个提供商搜索网络，包括 SearXNG、Google PSE、Brave Search、Kagi、Mojeek、Tavily、Perplexity、Firecrawl、serpstack、serper、Serply、DuckDuckGo、SearchApi、SerpApi、Bing、Jina、Exa、Sougou、Azure AI Search 和 Ollama Cloud，并将结果直接注入对话中。🌐 网络浏览能力：使用 # 命令后跟 URL 将网站拉入聊天，或者让模型在需要时自行获取。

🎨 Image Generation & Editing: Create and edit images with multiple engines including OpenAI DALL·E, Gemini, ComfyUI (local), and AUTOMATIC1111 (local), supporting both generation and prompt-based editing. ⚙️ Multi-Model Conversations: Engage several models at once, harnessing their individual strengths in parallel for the best possible responses. 📊 Usage Analytics & Model Evaluation: Admin dashboards track message volume, token consumption, and cost across users and models. Evaluate models with a built-in arena, A/B testing, and ELO-based leaderboards. 🗄️ Flexible Database & Storage: Choose SQLite (with optional encryption) or PostgreSQL, and store files locally or on S3, Google Cloud Storage, or Azure Blob Storage.

🎨 图像生成与编辑：使用多个引擎创建和编辑图像，包括 OpenAI DALL·E、Gemini、ComfyUI（本地）和 AUTOMATIC1111（本地），支持生成和基于提示词的编辑。⚙️ 多模型对话：同时参与多个模型，并行利用它们各自的优势以获得最佳响应。📊 使用分析与模型评估：管理仪表板跟踪跨用户和模型的消息量、Token 消耗和成本。通过内置竞技场、A/B 测试和基于 ELO 的排行榜来评估模型。🗄️ 灵活的数据库与存储：选择 SQLite（可选加密）或 PostgreSQL，并将文件存储在本地或 S3、Google Cloud Storage 或 Azure Blob Storage 上。

🧬 Advanced Vector Database Support: Pick from 9 vector databases: ChromaDB, PGVector, Qdrant, Milvus, Elasticsearch, OpenSearch, Pinecone, S3Vector, and Oracle 23ai. 🪪 Enterprise Authentication & Provisioning: Full LDAP/Active Directory integration, SSO via trusted headers and OAuth providers, and SCIM 2.0 automated provisioning for identity providers like Okta, Azure AD, and Google Workspace. ☁️ Cloud-Native File Integration: Native Google Drive and OneDrive/SharePoint file picking for seamless document import from enterprise cloud storage. 🔭 Production Observability: Built-in OpenTelemetry support for traces, metrics, and logs, plugging into your existing monitoring stack. ⚖️ Horizontal Scalability: Redis-backed session management and WebSocket support for multi-worker,

🧬 高级向量数据库支持：从 9 个向量数据库中选择：ChromaDB、PGVector、Qdrant、Milvus、Elasticsearch、OpenSearch、Pinecone、S3Vector 和 Oracle 23ai。🪪 企业身份验证与配置：完全的 LDAP/Active Directory 集成，通过受信任的标头和 OAuth 提供商进行 SSO，以及为 Okta、Azure AD 和 Google Workspace 等身份提供商提供 SCIM 2.0 自动配置。☁️ 云原生文件集成：原生的 Google Drive 和 OneDrive/SharePoint 文件选择器，用于从企业云存储无缝导入文档。🔭 生产可观测性：内置 OpenTelemetry 支持跟踪、指标和日志，可接入你现有的监控堆栈。⚖️ 水平扩展性：基于 Redis 的会话管理和 WebSocket 支持，适用于多工作节点。