Open WebUI Has a Free API You Should Know About

#ai #llm #opensource #selfhosted

Open WebUI is an extensible, self-hosted AI interface that supports Ollama, OpenAI-compatible APIs, and more. It's the ChatGPT-like UI you can run on your own hardware.

Why Self-Host Your AI Chat

A company needed an internal AI assistant but couldn't send proprietary data to OpenAI. Open WebUI gave them a ChatGPT-like experience running entirely on their servers with local LLMs.

Key Features:

Multi-Model — Ollama, OpenAI, Anthropic, and any OpenAI-compatible API
RAG Built-In — Upload documents and chat with them
Multi-User — User management with role-based access
Customizable — Custom models, system prompts, and tools
Plugin System — Extend with custom tools and functions

Quick Start

docker run -d -p 3000:8080 \
  -v open-webui:/app/backend/data \
  --name open-webui \
  ghcr.io/open-webui/open-webui:main

With Ollama

# Start Ollama
ollama pull llama3

# Start Open WebUI connected to Ollama
docker run -d -p 3000:8080 \
  --add-host=host.docker.internal:host-gateway \
  -e OLLAMA_BASE_URL=http://host.docker.internal:11434 \
  ghcr.io/open-webui/open-webui:main

Why Choose Open WebUI

Data privacy — everything runs on your infrastructure
Multi-model — switch between models seamlessly
RAG built-in — document Q&A without extra setup
Team ready — multi-user with access controls

Check out Open WebUI docs to get started.

Need AI infrastructure? Check out my Apify actors or email spinov001@gmail.com for custom solutions.

DEV Community