User Guide
Discover how to get the most out of the RAG, Memory, MCP Servers, Full-Stack Mode, API, PWA, and BYOK features in Chat LLM.
Getting Started
Chat LLM offers advanced AI features to enhance your experience. Here's what you need to know:
What are the Key AI Features?
- RAG (Retrieval Augmented Generation): Enhances AI responses by incorporating knowledge from your documents
- Memory: Enables the AI to remember important information about you across multiple conversations
- MCP Servers: Specialized tools that extend your AI with external knowledge sources and capabilities
- Context7: An MCP server providing up-to-date technical documentation from public libraries for accurate development guidance
- Full-Stack Mode: Build complete web applications with AI-powered file editing, terminal, and live preview
- API: Provides programmatic access to Chat LLM features for building custom integrations and applications
- PWA (Progressive Web App): Allows installation as a standalone app
When to Use Each Feature
- Use RAG when you need the AI to reference specific documents or knowledge bases
- Use Memory when you want the AI to remember personal preferences or details across conversations
- Use MCP Servers when you need specialized tools or external knowledge sources for enhanced capabilities
- Use Context7 when you need up-to-date technical documentation and best practices for development
- Use Full-Stack Mode when you want to build complete web applications with AI-powered development tools
- Use API when you need programmatic access to Chat LLM features for custom applications
- Use PWA when you want to install Chat LLM as a standalone application on your device
Combining All Features
For the best experience, you can use all features together:
Example: Complete Technical Support Experience
- Memory knows you prefer detailed technical explanations
- RAG finds relevant technical documentation about your specific issue from your knowledge base
- MCP Servers provide specialized tools for extended capabilities
- Context7 adds up-to-date best practices and library documentation for production-ready solutions
- Full-Stack Mode enables AI to build and edit complete web applications with live preview
- Result: You receive a fully personalized, comprehensive, and actionable solution with best practices, executable code, and seamless access tailored to your specific problem
Click on each guide above to learn more about how to set up and use these powerful features.
RAG Guide
Learn how Retrieval Augmented Generation enhances the AI's responses by using additional information from your knowledge base.
MCP Servers Guide
Discover how MCP servers extend your AI with specialized tools and knowledge sources like Context7 for technical documentation and development best practices.
Memory Guide
Discover how the Memory feature allows the AI to remember information about you across conversations for more personalized interactions.
Full-Stack Mode Guide
Build complete web applications with AI-powered tools in Full-Stack Mode.
API Guide
Explore how to integrate with and extend Chat LLM's capabilities through our comprehensive API documentation and developer tools.
Context7 Guide
Learn how to leverage Context7 to provide the AI with up-to-date documentation from any public library, improving accuracy.
BYOK Guide
Learn how Bring Your Own Key (BYOK) enables access to advanced AI models by providing your own API keys for premium capabilities.
PWA Guide
Learn how to install the app on your device and enable push notifications for a native experience.
Image Generation Guide
Generate stunning AI images with multiple providers: OpenAI, Requesty, and ZAI.