Skip to content

Core Concepts

Radkit is built on a few simple, powerful primitives. Understanding these concepts is key to using the library effectively.

This section covers the fundamental building blocks of Radkit:

  • Threads: Learn how to represent and manage the history of a conversation with an LLM.
  • Content: Understand how Radkit handles multi-modal message payloads, including text, images, and tool calls.
  • Events: See how individual messages are represented and associated with roles like user, assistant, and system.
  • LLM Providers: Discover how Radkit provides a unified interface for working with different LLM providers like Anthropic, OpenAI, and Gemini.