Skip to main content

​
Open WebUI

Configure Open WebUI (formerly Ollama WebUI) to use Eden AI for accessing 200+ AI models through a sleek interface.

​
Overview

Open WebUI is a self-hosted, feature-rich web interface for AI models. By connecting it to Eden AI, you get:
  • 200+ models: Access OpenAI, Anthropic, Google, Cohere, and more
  • Modern UI: Beautiful, responsive interface similar to ChatGPT
  • RAG support: Document upload and retrieval-augmented generation
  • Multi-user: User management with authentication
  • Self-hosted: Complete data privacy and control

​
Prerequisites

​
Quick Start

Run Open WebUI with a single command: Access Open WebUI at http://localhost:3000

​
Option 2: Docker Compose

Create a docker-compose.yml file:

​
Configuration

​
Initial Setup

  1. Open browser: Navigate to http://localhost:3000
  2. Create admin account: Register the first user (becomes admin)
  3. Configure models: Go to Settings → Models

​
Add Eden AI Models

In the Open WebUI interface:
  1. Click Settings (gear icon)
  2. Go to Models tab
  3. Add models in the format provider/model:

​
Environment Variables

Configure Open WebUI with environment variables:

​
Features

​
Chat with Multiple Models

  1. Select model: Click the model dropdown at the top
  2. Start chatting: Type your message
  3. Switch models: Change models mid-conversation
  4. Compare responses: Use split-screen to compare model outputs

​
Document Upload (RAG)

Upload documents for context-aware conversations: Usage:
  1. Click the + icon in chat
  2. Upload PDF, DOCX, TXT, or other documents
  3. Ask questions about the uploaded content
  4. The AI retrieves relevant sections automatically

​
Image Generation

Generate images using DALL-E or other providers: Usage: Type /imagine followed by your prompt in the chat. Enable web search for up-to-date information:

​
Voice Input

Enable voice-to-text:

​
Advanced Configuration

​
Multiple API Endpoints

Configure multiple providers:

​
Custom Model Metadata

Define model capabilities and pricing:

​
User Permissions

Configure role-based access:

​
Persistent Storage

Configure data persistence:

​
Security

​
Authentication

Enable and configure authentication:

​
HTTPS Setup

Use a reverse proxy for HTTPS:

​
Rate Limiting

Protect your API key:

​
Production Deployment

​
Full Production Stack

​
Backup Strategy

Backup your data regularly:

​
Troubleshooting

​
Models Not Appearing

If models don’t show up:
  1. Check API key: 
    docker compose logs open-webui | grep -i "api"
  2. Verify base URL: 
    docker compose exec open-webui env | grep OPENAI_API_BASE_URL
  3. Test endpoint manually: 
    curl -X POST https://api.edenai.run/v3/llm/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-3-5-sonnet-20241022",
    "messages": [{"role": "user", "content": "test"}],
    "stream": true
  }'
  4. Restart container: 
    docker compose restart open-webui

​
Authentication Issues

If you can’t log in:
  1. Reset admin password: 
    docker compose exec open-webui python manage.py reset-admin-password
  2. Check secret key: 
    docker compose exec open-webui env | grep WEBUI_SECRET_KEY

​
Performance Issues

If the UI is slow:
  1. Check resource usage: 
    docker stats open-webui
  2. Increase memory: 
    services:
  open-webui:
    deploy:
      resources:
        limits:
          memory: 4G
  3. Optimize database: 
    docker compose exec open-webui python manage.py optimize-db

​
RAG Not Working

If document upload fails:
  1. Check volume mounts: 
    docker compose exec open-webui ls -la /app/backend/uploads
  2. Verify embedding model: 
    docker compose exec open-webui env | grep RAG_EMBEDDING
  3. Check logs: 
    docker compose logs open-webui | grep -i "rag"

​
Cost Optimization

​
1. Use Appropriate Models

Configure cheaper models for embeddings:

​
2. Limit Token Usage

Set maximum tokens:

​
3. Monitor Usage

Track costs in Eden AI dashboard:

​
Example Workflows

​
1. Customer Support Bot

  • Upload support docs using RAG
  • Create templates for common queries
  • Use Claude Haiku for cost-effective responses

​
2. Code Assistant

  • Use GPT-4 or Claude for complex code
  • Enable file upload for code review
  • Configure presets for different languages

​
3. Research Assistant

  • Enable web search for current information
  • Use Gemini Pro for long context
  • RAG for internal documents

​
Next Steps