Skip to main content
Open WebUI is a feature-rich self-hosted AI platform that supports completely offline operation. Through Laozhang API, you can integrate various mainstream large language models into Open WebUI.

​
Quick Deployment

​
Docker Quick Start

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

​
Docker Compose Deployment

version: '3.6'

services:
  open-webui:
    image: ghcr.io/open-webui/open-webui:main
    container_name: open-webui
    ports:
      - "3000:8080"
    volumes:
      - open-webui:/app/backend/data
    environment:
      - OPENAI_API_BASE_URL=https://api.laozhang.ai
      - OPENAI_API_KEY=Your Laozhang API key
    restart: unless-stopped

volumes:
  open-webui:

​
Configure Laozhang API

​
Method 1: Environment Variable Configuration

Set environment variables during deployment: 
docker run -d -p 3000:8080 \
  -e OPENAI_API_BASE_URL=https://api.laozhang.ai \
  -e OPENAI_API_KEY=Your Laozhang API key \
  -v open-webui:/app/backend/data \
  --name open-webui \
  ghcr.io/open-webui/open-webui:main

​
Method 2: Interface Configuration

  1. Access Open WebUI management interface
  2. Go to Settings > Connections
  3. Configure in OpenAI API section:
    • API Base URL: https://api.laozhang.ai/v1
    • API Key: Enter your Laozhang API key
  4. Click save configuration
Configuration Key Points
  • API Base URL needs to include the /v1 suffix
  • API Key can be obtained from Laozhang API Console
  • Using environment variables is recommended for easier management and updates

​
Supported Models

Open WebUI supports the following model series through Laozhang API:
Model SeriesModel IDFeatures
GPT-4 Turbogpt-4-turbo-2024-04-09Latest GPT-4, balanced performance
Claude Sonnetclaude-sonnet-4-20250514Long text processing, creative writing
Gemini Progemini-2.5-proMultimodal capability, fast response
GPT-3.5 Turbogpt-3.5-turboEconomical and practical, daily conversation
FunctionRecommended ModelDescription
Vision Understandinggpt-4-vision-previewImage analysis and understanding
Code Generationgpt-4-turboProgramming assistance and code optimization
Reasoning Thinkingclaude-sonnet-4-20250514-thinkingShows thought process

​
Core Features

​
RAG (Retrieval Augmented Generation)

Open WebUI supports document upload and knowledge base features:
  1. Document Upload
    • Supports PDF, Word, Markdown and other formats
    • Automatic vectorization storage
    • Supports multilingual documents
  2. Knowledge Base Management
    • Create specialized knowledge bases
    • Document classification and tagging
    • Intelligent retrieval matching

​
OpenAI Compatible API

Open WebUI provides a complete OpenAI-compatible API: 
# Chat completion
curl -X POST "http://localhost:3000/api/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer Your Laozhang API key" \
  -d '{
    "model": "gpt-4-turbo",
    "messages": [
      {"role": "user", "content": "Hello, world!"}
    ]
  }'

​
Tool Integration

Supports external tools and plugins:
  • Web search
  • Code execution
  • Image generation
  • Document processing

​
Advanced Configuration

​
Multi-Model Configuration

Configure multiple model sources in docker-compose.yml: 
environment:
  - OPENAI_API_BASE_URL=https://api.laozhang.ai
  - OPENAI_API_KEY=Your Laozhang API key
  - ENABLE_OPENAI_API=true
  - ENABLE_OLLAMA_API=false

​
User Permission Management

environment:
  - ENABLE_SIGNUP=false
  - DEFAULT_USER_ROLE=user
  - WEBHOOK_URL=Your webhook address

​
Data Persistence

volumes:
  - open-webui:/app/backend/data
  - ./uploads:/app/backend/data/uploads
  - ./vector_db:/app/backend/data/vector_db

​
API Integration Examples

​
Python Integration

import requests

# Open WebUI API endpoint
api_url = "http://localhost:3000/api/chat/completions"

# Request configuration
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer Your Laozhang API key"
}

data = {
    "model": "gpt-4-turbo",
    "messages": [
        {"role": "user", "content": "Explain the basic principles of quantum computing"}
    ],
    "stream": False
}

# Send request
response = requests.post(api_url, headers=headers, json=data)
result = response.json()
print(result["choices"][0]["message"]["content"])

​
JavaScript Integration

const apiUrl = 'http://localhost:3000/api/chat/completions';

const requestData = {
  model: 'gpt-4-turbo',
  messages: [
    { role: 'user', content: 'Write a simple Python function' }
  ]
};

fetch(apiUrl, {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': 'Bearer Your Laozhang API key'
  },
  body: JSON.stringify(requestData)
})
.then(response => response.json())
.then(data => {
  console.log(data.choices[0].message.content);
});

​
Troubleshooting

​
Common Issues

Connection Failed
  • Check if API Base URL is correct: https://api.laozhang.ai/v1
  • Verify API Key validity
  • Confirm firewall settings
Model Unavailable
  • Check account balance
  • Confirm model is in service scope
  • View Laozhang API service status
Upload Failed
  • Check file format support
  • Confirm storage space is sufficient
  • Verify file size limits

​
Debug Logging

Enable debug mode: 
docker logs -f open-webui
View detailed logs: 
environment:
  - LOG_LEVEL=DEBUG
  - WEBUI_DEBUG=true

​
Best Practices

​
Performance Optimization

  1. Model Selection
    • Daily conversation uses GPT-3.5 Turbo
    • Complex tasks use GPT-4 Turbo
    • Long text processing uses Claude Sonnet
  2. Caching Strategy
    • Enable conversation caching
    • Set reasonable cache expiration time
    • Regularly clean unused cache
  3. Resource Management
    • Monitor memory usage
    • Set reasonable concurrency limits
    • Regularly backup user data

​
Security Configuration

environment:
  - ENABLE_ADMIN_EXPORT=false
  - ENABLE_ADMIN_CHAT_ACCESS=false
  - JWT_EXPIRES_IN=7d

​
Monitoring and Alerts

Integrate monitoring system: 
environment:
  - ENABLE_WEBHOOKS=true
  - WEBHOOK_URL=https://your-monitoring-url
Need more help? Please check Open WebUI Official Documentation or visit Laozhang API Official Website.
⌘I