Building RAG on Android
Why local retrieval-augmented generation is hard on a tablet, and how the pipeline is actually put together.
Writing
Engineering investigations rather than tutorials. Mental models that turned out to be wrong, and what replaced them.
Why local retrieval-augmented generation is hard on a tablet, and how the pipeline is actually put together.
Sharing one signed-in identity across several apps on the same device with AccountManager, and the lifecycle problems that come with it.
Dispatchers.IO is not a pool of IO threads. What the CoroutineScheduler really does, and the mental model that replaced mine.
If the thread is released while a request is in flight, what is actually waiting for the response? Coroutines, threads, sockets, and continuations, separated.