​

LibreChat

Configure LibreChat, the open-source ChatGPT alternative, to use Eden AI for access to 200+ AI models.

​

Overview

LibreChat is a free, open-source AI chat platform that supports multiple providers. By connecting it to Eden AI, you get:

• 200+ models: Access OpenAI, Anthropic, Google, Cohere, and more through one interface
• Self-hosted: Full control over your data and infrastructure
• Cost savings: Leverage Eden AI’s competitive pricing
• Unified experience: Single chat interface for all providers

​

Prerequisites

• Docker and Docker Compose installed
• Eden AI API key from https://app.edenai.run
• Basic knowledge of environment variables

​

Installation

​

Option 1: Docker Compose (Recommended)

Clone LibreChat and set up with Docker:

​

Option 2: Manual Installation

​

Configuration

​

Step 1: Configure Environment Variables

Edit the .env file to add Eden AI configuration:

​

Step 2: Configure librechat.yaml

Create or edit librechat.yaml for advanced configuration:

​

Step 3: Start LibreChat

Access LibreChat at http://localhost:3080

​

Available Models

Configure which models appear in the LibreChat interface:

​

Features

​

Multi-Model Conversations

Switch between models mid-conversation:

1. Start a conversation with Claude
2. Click the model selector
3. Switch to GPT-4 or Gemini
4. Continue the conversation seamlessly

​

File Attachments

Upload files for vision-capable models:

​

Preset Prompts

Create custom prompts for common tasks:

​

Advanced Configuration

​

Custom Model Parameters

Configure temperature, max tokens, and other parameters:

​

User Authentication

Enable user registration and authentication:

​

Rate Limiting

Protect your API key with rate limiting:

​

Conversation History

Configure MongoDB for persistent conversations:

​

Docker Deployment

​

Production Docker Compose

​

Deploy to Production

​

Troubleshooting

​

Models Not Appearing

If models don’t show up in the interface:

1. Check librechat.yaml syntax:
   Copy

   # Validate YAML
   docker compose config
   
2. Verify API key:
   Copy

   # Test Eden AI endpoint
   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
     }'
   
3. Clear cache and restart:
   Copy

   docker compose down
   docker compose up -d
   

​

Authentication Errors

If you see 401 errors:

1. Check .env has correct API key
2. Ensure no extra spaces in the key
3. Verify OPENAI_REVERSE_PROXY URL is correct
4. Restart services after changing .env

​

Slow Responses

If responses are slow:

1. Use faster models for chat titles:
   Copy

   titleModel: "openai/gpt-3.5-turbo"
   
2. Disable unnecessary features:
   Copy

   summarize: false
   
3. Check your internet connection and Eden AI status

​

Connection Refused

If LibreChat can’t connect to MongoDB:

1. Check MongoDB is running:
   Copy

   docker compose ps mongodb
   
2. Verify MONGO_URI in .env:
   Copy

   MONGO_URI=mongodb://mongodb:27017/LibreChat
   
3. Check network connectivity:
   Copy

   docker compose logs mongodb
   

​

Security Best Practices

​

1. Secure API Keys

Never commit API keys to version control:

​

2. Use Environment-Specific Configs

​

3. Enable HTTPS

Use a reverse proxy like Nginx:

​

4. Implement Rate Limiting

Protect against abuse:

​

Cost Optimization

​

1. Use Appropriate Models

Configure cheaper models for simple tasks:

​

2. Monitor Usage

Track costs through Eden AI dashboard:

• View usage at https://app.edenai.run
• Set up billing alerts
• Review monthly reports

​

3. Limit Token Usage

​

Example Use Cases

​

1. Team Collaboration

Set up LibreChat for your team:

• Enable user registration for team members
• Configure multiple endpoints for different projects
• Use presets for common workflows (code review, documentation, etc.)

​

2. Customer Support

Deploy as an internal support tool:

• Create presets for support responses
• Use conversation history to maintain context
• Configure rate limits to prevent abuse

​

3. Development Assistant

Integrate with your development workflow:

• Code assistance with Claude or GPT-4
• Documentation generation with presets
• Bug analysis with vision models (screenshots)

​

Next Steps

• Open WebUI - Alternative chat interface
• Python SDK - Programmatic access
• API Reference - Complete API documentation
• Cost Management - Track spending