惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

S
SegmentFault 最新的问题
爱范儿
爱范儿
博客园 - 三生石上(FineUI控件)
Microsoft Security Blog
Microsoft Security Blog
Google DeepMind News
Google DeepMind News
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
GbyAI
GbyAI
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
V
V2EX
酷 壳 – CoolShell
酷 壳 – CoolShell
量子位
博客园_首页
T
Tailwind CSS Blog
aimingoo的专栏
aimingoo的专栏
A
About on SuperTechFans
T
The Blog of Author Tim Ferriss
Stack Overflow Blog
Stack Overflow Blog
Recent Announcements
Recent Announcements
P
Proofpoint News Feed
博客园 - 司徒正美
有赞技术团队
有赞技术团队
Engineering at Meta
Engineering at Meta
Last Week in AI
Last Week in AI
MongoDB | Blog
MongoDB | Blog

DEV Community

Authentication Security Deep Dive: From Brute Force to Salted Hashing (With Java Examples) Why AI Systems Don’t Fail — They Drift Spilling beans for how i learn for exam😁"Reinforcement Learning Cheat Sheet" I Replaced Chrome with Safari for AI Browser Automation. Here's What Broke (and What Finally Worked) How Python Borrows Other People's Work The $40 Architecture: Processing 1 Billion API Requests with 99.99% Uptime Vibe Coding: A Workflow Guide (From Zero to SaaS) Most webhook security guides protect the wrong side. The scary part is delivery. Headless CMS for TanStack Start: Build a Blog with Cosmic EU Age Verification App "Hacked in 2 Minutes" — What Actually Happened Comfy Cloud’s delete function does not actually remove files Running AI Models on GPU Cloud Servers: A Beginner Guide Event-driven media intelligence with AWS Step Functions and Bedrock I scored 500 AI prompts across 8 quality dimensions — here's what broke How to Call Google Gemini API from Next.js (Free Tier, No Backend Needed) The Portal Protocol: Reclaiming Human Connection in the Age of AI How to Fix Your Team's Scattered Knowledge Problem With a Self-Hosted Forum Intro to tc Cloud Functors: A Graph-First Mental Model for the Modern Cloud Designing Multi-Tenant Backends With Both Ownership and Team Access I Built a Neumorphic CSS Library with 77+ Components — Here's What I Learned PostgreSQL Performance Optimization: Why Connection Pooling Is Critical at Scale Cómo construí un SaaS multi-rubro para gestionar expensas en Argentina con FastAPI + Vue 3 🚀 I Built an Ethical Hacking Scanner Tool – Open Source Project I Replaced /usage and /context in Claude Code With a Single Statusline A Pythonic Way to Handle Emails (IMAP/SMTP) with Auto-Discovery and AI-Ready Design I Collected 8.9 Million Polymarket Price Points — Here's What I Found About How Markets Really Move EcoTrack AI — Carbon Footprint Tracker & Dashboard Everyone's Using AI. No One Agrees How. 5 self-hosted ebook managers worth trying in 2026 Building Your First AI Agent with LangChain: From Chatbot to Autonomous Assistant
The simplest self-hosted RAG you'll ever set up (Apache 2...
retrovirusre · 2026-05-21 · via DEV Community

retrovirusretro

Most RAG tools make you choose between simplicity and power. MaxKB doesn't try to be powerful — it tries to be simple, and it nails it.

20K+ GitHub stars. Apache 2.0. Almost no English content. Here's the guide.


What is MaxKB?

MaxKB (Max Knowledge Base) is a knowledge base Q&A system by the 1Panel team. It connects to any OpenAI-compatible API — including Ollama — and lets you upload documents, ask questions, and embed a chat widget into any website.

That last part is the killer feature: MaxKB generates a JavaScript snippet that drops a chat widget into any HTML page. One script tag. No iframe, no backend changes needed. Apache 2.0 means you can embed this in commercial products with no restrictions.


Setup

3 commands, under 5 minutes.

Clone the repo, copy .env.example to .env, then docker compose up -d. Open localhost:8081admin / admin123 → Settings → Model Provider → Ollama → http://ollama:11434.

Create a knowledge base, upload a PDF, start asking questions. That's the entire setup.

Full docker-compose: maxkb-english-guide


Embed Widget

MaxKB generates a JavaScript snippet — drop it into any HTML page and a chat widget appears bottom-right. No iframe, no backend changes. This is what makes MaxKB unique among RAG tools: it's designed to be embedded.

Go to: Application → your app → Embed → copy the script tag → paste into any HTML page.


API

Works from Python, JavaScript, curl, n8n — anything that speaks HTTP. POST your question to /api/application/{app_id}/chat/completions with a Bearer token. Returns {"content": "the answer"}.

Full Python + JavaScript examples in the repo.


MaxKB vs the Alternatives

MaxKB WeKnora FastGPT RAGFlow
Setup time ⚡ 3 min 5 min 10 min 15 min
License Apache 2.0 MIT Custom* Apache 2.0
Embed widget
Autonomous agent
PDF table parsing Basic Basic Good Excellent
Commercial embed

*FastGPT prohibits SaaS resale.

Pick MaxKB when: working knowledge base in 5 minutes, embed widget needed, Apache 2.0 matters.

Pick something else when: complex PDFs → RAGFlow · pipeline builder → FastGPT · multi-hop reasoning → WeKnora


Supported LLM Providers

MaxKB works with any OpenAI-compatible API: Ollama (local, free), OpenAI, Groq, Together, or Anthropic via LiteLLM proxy.


Full Guide

github.com/retrovirusretro/maxkb-english-guide

Part of a broader series:
chinese-ai-tools-english-guide


MaxKB is the tool I recommend to people who just want RAG working quickly without reading 40 pages of docs.