慣性聚合 高效追讀感興趣之博客、新聞、科技資訊
閱原文 以慣性聚合開啟

推薦訂閱源

L
LangChain Blog
宝玉的分享
宝玉的分享
酷 壳 – CoolShell
酷 壳 – CoolShell
N
Netflix TechBlog - Medium
F
Fortinet All Blogs
T
Tailwind CSS Blog
Google DeepMind News
Google DeepMind News
Jina AI
Jina AI
J
Java Code Geeks
Recent Announcements
Recent Announcements
The Cloudflare Blog
D
DataBreaches.Net
Hugging Face - Blog
Hugging Face - Blog
WordPress大学
WordPress大学
Vercel News
Vercel News
月光博客
月光博客
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
Microsoft Azure Blog
Microsoft Azure Blog
雷峰网
雷峰网
H
Help Net Security
博客园 - Franky
S
SegmentFault 最新的问题
T
The Blog of Author Tim Ferriss
博客园_首页
C
Check Point Blog
腾讯CDC
美团技术团队
Martin Fowler
Martin Fowler
The GitHub Blog
The GitHub Blog
M
MIT News - Artificial intelligence
Apple Machine Learning Research
Apple Machine Learning Research
P
Proofpoint News Feed
U
Unit 42
人人都是产品经理
人人都是产品经理
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
Engineering at Meta
Engineering at Meta
M
Microsoft Research Blog - Microsoft Research
阮一峰的网络日志
阮一峰的网络日志
G
Google Developers Blog
Stack Overflow Blog
Stack Overflow Blog
B
Blog
Last Week in AI
Last Week in AI
博客园 - 三生石上(FineUI控件)
博客园 - 聂微东
云风的 BLOG
云风的 BLOG
H
Hackread – Cybersecurity News, Data Breaches, AI and More
李成银的技术随笔
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
博客园 - 叶小钗
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知

DEV Community

Constitutional Exception Committees: A Pattern for AI Agent Constraint Governance Veltrix's Treasure Hunt Engine: Optimized for Long-Term Survival, Not Just Scalability Build a streaming UI without overcomplicating it The Cost of Kernel CVE Patching Frequency in SLA Commitments Gemma 4 Runs on a Raspberry Pi. Let That Sink In. The Git Filesystem - Recreating the Content-Addressable Database Why I Still Believe Our Event-Driven Architecture Was The Right Call For Veltrix Local RAG: Chat With Your Documents (Open Source, Private) GGUF & Modelfile: The Power User's Guide to Local LLMs What Excited Me Most at Google I/O 2026 OSS assemble! Kilo Code is launching on Product Hunt. Join the launch! https://www.producthunt.com/products/kilocode Your Organizational AI Adoption Metrics Are Lying (Plus How to Measure Real Adoption) Building a Production-Grade MLOps Home Lab on Windows — K8s, LLM, RAG & GitLab CI The Moment I Realized AI Agents are Changing Software Forever Prisma Generator NestJS DTO — pluggable DTOs with annotations and custom generators I Spent a Month Testing Decentralized Poker Sites. Here's What Actually Works. DeepSeek-R1: The $0 o1 Alternative You Can Run Right Now The PHP Stack I Built TrustGate On — And Why I'd Do It Differently Today Building High-Throughput Data Pipelines: Why Chaining Encryption and Compression is a Performance Killer Optic is dead. A 2026 migration guide for OpenAPI breaking changes Smart Blind Stick, Mini Project The NSA just published an MCP security playbook. We created Agent Trust Transport Protocol ATTP - Implement today with MCPS Symfony 8 AWS Secrets Bundle Canlı TV Platformu Geliştirirken Öğrendiğim Teknik Dersler: Streaming, Flussonic ve Performans Gemma 4 Is Powerful — But Production AI Still Needs Governance What RepoSignal Surfaced in React — and Why Review Alone Doesn't Catch Everything LeetCode Solution: 1752. Check if Array Is Sorted and Rotated Breaking the Matrix at 15: How I Built a Cyber-Aesthetic AI Assistant Core Powered by Gemma 4 Разработка Android Kiosk приложения No More Manual Test Writing: How I Used Gemma 4 to Turn a GitHub Repo Into a Full Test Suite 🎯 Trafik Cezaları Platformları Geliştirirken Öğrendiğim Teknik Dersler The Myth of Low Latency: Why Event Meshes Make Your System Slow Building EIDOLON OS — A Local-First AI Cognitive Operating System qrrot - database with AI I Built a Local Gemma 4 Reviewer for Merchant Registry Evidence Compass v1.1.0 · we shipped a memory plugin that catches its own consumption drift How to build your first MCP server in 10 minutes Expo SDK 56 Is Out, and a Few Things Finally Clicked Into Place Building a 100ms Browser-Native WebSocket Clipboard Cómo solucionar `docker run` con `Exited (1)` en Raspberry Pi Why Claude Code Sessions Diverge: A Mechanism Catalog When One AI Agent Is Not Enough: A Practical Delegation Pattern for Enterprise Systems Cómo solucionar el bucle infinito en `useEffect` con objetos y arrays 🛢️ The Dangote Chain: What a Blockchain-Native Refinery IPO Would Look Like Build a "Where to Watch" feature in 50 lines with the StreamWatchHub API Gemma 4 on Android: Tricks for Faster On-Device Inference Your AI agent has amnesia. You've just normalized it. 🚀 Reviving My Women Safety System – From Idea to Real-Time Smart Safety Solution I built an AI that reviews every PR automatically (because nobody was reviewing mine) 🌿 Git Mastery: The Complete Developer Guide
开网页界面:汝之本地ChatGPT
Lingdas1 · 2026-05-24 · via DEV Community

Lingdas1

开放式网络界面:汝之本地ChatGPT

化汝之本地大语言模型为精美、功能完备之网络界面——若ChatGPT,然全然运行于汝之机器。

开放式网络界面为何物?

开放式网络界面乃Ollama之自托管网络界面。其予汝:

  • 🖥️ 浏览器中ChatGPT式之对话界面
  • 🔄 谈话中途切换模型
  • 📁 上传文牍,与之论谈(RAG)
  • 🖼️ 图像生成(由Automatic1111 / ComfyUI)
  • 🎤 声音输入,文转音
  • 👥 多人支持(与家人或团队共享)
  • 📱 适于手机(可在手机浏览器运行)
  • 🔌 图像、网络搜索等插件

最妙者: 乃通乎汝之本地Ollama之实例——永无数据离汝之机。


须知之备

  • ✅ Ollama已安装且可用(参看入门)。
  • ✅ 至少引一模型(如qwen2.5:7b)。
  • ✅ Docker已安装(推荐)。OR Python 3.11以上。

选项A:以Docker安装(推荐——仅需两分钟)

Docker乃最简之法。一令即可毕:

docker run -d \
  -p 3000:8080 \
  -v open-webui:/app/backend/data \
  -e OLLAMA_BASE_URL=http://host.docker.internal:11434 \
  --name open-webui \
  --restart always \
  ghcr.io/open-webui/open-webui:main

切换全屏模式 退出全屏模式

此举所为:

  • -p 3000:8080 — 使之可于http://localhost:3000
  • -v open-webui:/app/backend/data — 即便重启,亦存吾之私语
  • -e OLLAMA_BASE_URL — 告之吾之Ollama所运行之处
  • --restart always — 自启于机之启动

验其运行

# Check logs — you should see "Application startup complete"
docker logs open-webui --tail 20

入全景模式 出全景模式

乃启 http://localhost:3000 于浏览器中.

初用乎? 造一账户。无虑也——唯局域之用。汝之数据存于汝之机。


选项二:以 pip 安装(不使用 Docker)

若无 Docker,则:

# Install
pip install open-webui

# Run
open-webui serve

入全景模式 出全屏模式

则启之http://localhost:8080.


所见所感

既登录,Open WebUI之貌与感,类ChatGPT。

Open WebUI Interface

要旨所在:

其功用何在
对话面板(左) 汝之交谈往迹
模型选择器(上) 于所有下载之模型间切换
对话输入(下) 书汝之讯
回形针图标 上传文书
设置之轮 配置模型参数、RAG、声音

可玩之趣

1. 聊天中途易模型

于顶置下拉菜单,可于对话中易模型。各模型皆见同聊之史.

  • 始以qwen2.5:7b为泛聊
  • 需硬思时,易为deepseek-r1:14b
  • 转至codellama以处理代码之事

2. 上传文书(内置RAG)

点击回形针图标,上传PDF、Word文档或文本文件。模型即可就其内容作答

应用场景:

  • 上传研究论文并提问
  • 上传公司手册
  • 上传教材章节以助研习

三. 呼声输入

点击麦克风之象,以声代笔。此法可行于Chrome与Edge。

四. 定制模型之行止

于设置→模型,可调:

  • 温度: 0.2(精微)至1.0(奇诡)
  • 语境之长: 模型所忆几何
  • 系统提示:模型之人格

高级:连接其他服务

图像生成

Open WebUI可集成本地图像生成器:

# Add Automatic1111 (Stable Diffusion)
docker run -d \
  -p 7860:7860 \
  -v sd-models:/models \
  --gpus all \
  asd/stable-diffusion-webui:latest

进入全屏模式 退出全屏模式

然后在Open WebUI设置→图像生成中配置。

网络检索(实验性)

于设置→网络检索中启用网络检索。开启WebUI,应答疑问时将搜索互联网。


生产部署

带HTTPS

为安全远程访问(VPN或隧道后):

# Using Caddy as a reverse proxy
docker run -d \
  -p 443:443 \
  -v open-webui:/app/backend/data \
  -e OLLAMA_BASE_URL=http://ollama:11434 \
  -e WEBUI_SECRET_KEY=your-secret-here \
  --name open-webui \
  ghcr.io/open-webui/open-webui:main

进入全屏模式 退出全屏模式

多用户部署

開放式網絡用戶介面,自帶多用戶支援。每用戶:

  • 獲其獨自之對話史
  • 不得見他用人之對話
  • 得選自所引之任何模型

欲增用戶者:往設置→管理面板→用戶→創造用戶.


排錯

問題 原由 解法
"连接被拒" Ollama未运行 首启 Ollama:ollama serve
本地3000端口空白页 容器未启动 docker start open-webui
无可供之模型 未引模型 ollama pull qwen2.5:7b
迟滞之文牍也&一 嵌入模型未载入 首份文档上传,加载嵌入需时更久
端口三千已占用 又有他务用之 更易其端口也-p 8080:8080且用之http://localhost:8080
容器不启 Docker未运行 启 Docker 桌面或 Docker 守护

资源


次步:既得图形界面,可试设本地RAG——令尔之LLM答尔之自有文书之问。

其部分之本地大模型指南 — 独立硬件运行人工智能之权威宝典。