Streaming Chat API

Buildable now. The repo, the spec and the deployment steps are live — the written walkthrough for this one is still being drafted.

Everything so far has been a CLI. This project moves it to a FastAPI server that streams LLM responses over SSE, tracks token usage and cost per request in SQLite, and rate-limits callers per IP. This is the shape every real LLM-backed product takes — cost and abuse control aren’t optional extras, they’re the difference between a side project and something you could actually run.

Cost/latency tracking and rate-limiting are what interviewers and hiring managers actually probe for beyond 'can you call an LLM' — this project gives you concrete answers.

Clone this project, run it locally, and compare your output against the description above.

Streaming Chat API on GitHub ↗

The quiz isn't written yet

The project itself is ready to build — the repo, the spec and the deployment steps are all live. What's missing is the written quiz that goes with it, and the order those get written in is decided by which ones people actually ask for.

The assignment isn't written yet

The project itself is ready to build — the repo, the spec and the deployment steps are all live. What's missing is the written assignment that goes with it, and the order those get written in is decided by which ones people actually ask for.