On-Device AI in Kotlin

New tutorials for Python and Kotlin demonstrate how to run a large language model (LLM) directly on a user's device, eliminating the need for servers or API keys. The guides start with basic chat exchanges and advance to multimodal input, speech-to-text, text-to-speech, voice activity detection, tool calling, and RAG. By running AI on-device, developers avoid the tradeoffs associated with cloud APIs, where requests are sent to remote servers for processing before returning a response.