Download the PHP package filaforge/filament-opensource-chat without Composer

Filaforge Opensource Chat

A powerful Filament plugin that integrates various open-source AI chat capabilities directly into your admin panel.

Features

• Multi-Model Support: Chat with various open-source AI models
• Conversation Management: Save, organize, and continue chat conversations
• Model Selection: Choose from available open-source AI models
• Customizable Settings: Configure API endpoints, models, and chat parameters
• Real-time Chat: Live chat experience with streaming responses
• Conversation History: Keep track of all your AI conversations
• Export Conversations: Save and share chat transcripts
• Role-based Access: Configurable user permissions and access control
• Context Awareness: Maintain conversation context across sessions
• Local Deployment: Support for self-hosted AI models

Installation

1. Install via Composer

2. Publish & Migrate

3. Register Plugin

Add the plugin to your Filament panel provider:

Setup

Configuration

The plugin will automatically:

• Publish configuration files to config/opensource-chat.php
• Publish view files to resources/views/vendor/opensource-chat/
• Publish migration files to database/migrations/
• Register necessary routes and middleware

Open Source AI Configuration

Configure your open-source AI endpoints in the published config file:

Environment Variables

Add these to your .env file:

Getting API Keys

Fireworks AI

1. Visit Fireworks AI
2. Create an account and navigate to API keys
3. Generate a new API key
4. Copy the key to your .env file

Together AI

1. Visit Together AI
2. Sign up and go to API keys section
3. Create a new API key
4. Copy the key to your .env file

Local Models

For local deployment, you can use:

• Ollama: Local model serving
• LM Studio: Desktop AI model interface
• Custom endpoints: Your own AI model servers

Usage

Accessing Opensource Chat

1. Navigate to your Filament admin panel
2. Look for the "Opensource Chat" menu item
3. Start chatting with open-source AI models

Starting a Conversation

1. Select Provider: Choose from available AI providers
2. Select Model: Choose the specific AI model to use
3. Type Your Message: Enter your question or prompt
4. Send Message: Submit your message to the AI
5. View Response: See the AI's response in real-time
6. Continue Chat: Keep the conversation going

Managing Conversations

1. New Chat: Start a fresh conversation
2. Save Chat: Automatically save important conversations
3. Load Chat: Resume previous conversations
4. Export Chat: Download conversation transcripts
5. Delete Chat: Remove unwanted conversations

Advanced Features

• Provider Switching: Switch between different AI providers
• Model Selection: Choose from available models per provider
• Parameter Tuning: Adjust temperature, max tokens, and other settings
• Context Management: Maintain conversation context across sessions
• Streaming Responses: Real-time AI responses for better user experience

Troubleshooting

Common Issues

• API key errors: Verify your API keys are correct and have sufficient credits
• Connection failures: Check if the AI service endpoints are accessible
• Model not available: Ensure the selected model is available in your plan
• Rate limiting: Check your API rate limits and usage

Debug Steps

1. Check the plugin configuration:

2. Verify routes are registered:

3. Test API connectivity:

4. Check environment variables:

5. Clear caches:

6. Check logs for errors:

Provider-Specific Issues

Local Models

• Service not running: Ensure your local AI service is started
• Port conflicts: Check if the required ports are available
• Model not loaded: Verify the model is properly loaded in your service

Fireworks AI

• Authentication errors: Check API key and permissions
• Model availability: Ensure the model is available in your plan
• Rate limits: Monitor your API usage and limits

Together AI

• API key issues: Verify your Together AI API key
• Model access: Check if you have access to the selected model
• Service status: Check Together AI service status

Security Considerations

Access Control

• Role-based permissions: Restrict access to authorized users only
• API key security: Never expose API keys in client-side code
• User isolation: Ensure users can only access their own conversations
• Audit logging: Track all chat activities and API usage

Best Practices

• Use environment variables for API keys
• Implement proper user authentication
• Monitor API usage and costs
• Regularly rotate API keys
• Set appropriate rate limits
• Use HTTPS for external API calls

Performance Optimization

Local Deployment

• Resource allocation: Ensure sufficient RAM and CPU for models
• Model optimization: Use quantized models for better performance
• Caching: Implement response caching for common queries
• Load balancing: Use multiple model instances if needed

External APIs

• Connection pooling: Reuse HTTP connections when possible
• Request batching: Batch multiple requests when feasible
• Response caching: Cache responses to reduce API calls
• Fallback strategies: Implement fallback to local models

Uninstall

1. Remove Plugin Registration

Remove the plugin from your panel provider:

2. Roll Back Migrations (Optional)

3. Remove Published Assets (Optional)

4. Remove Package and Clear Caches

5. Clean Up Environment Variables

Remove these from your .env file:

Support

• Documentation: GitHub Repository
• Issues: GitHub Issues
• Discussions: GitHub Discussions

Contributing

We welcome contributions! Please see our Contributing Guide for details.

License

This plugin is open-sourced software licensed under the MIT license.

Made with ❤️ by the Filaforge Team