For the uninitiated, LMQL is one of a few offerings in the AI space (amongst others like guidance and guardrails) that allows for finer control of the AIs output and allows you to guarantee some patterns which is hugely helpful for a whole variety of use cases (tool use, safe chatbots, parseable data)
Note, “safe chatbots” in this case doesn’t necessarily mean how people often think of it, it’s useful also for if say you need to make sure the chatbot doesn’t access (or hallucinate that it’s accessing) a different users data and returning it