You may benefit from an embedding approach for semantic search. Not sure what an LLM would give you on top of that.

If the emergency is in a foreign country, being able to communicate with locals would likely be a benefit - and a domain specific trained model could translate better than general purpose translators.

In general, I think speech as input/output is under-explored. In the emergency scenario, in a stressful environment, having an expert in your ear you can talk to should work much better than having a big manual book to look up specific cases.

I think an LLM would give a "conversational" experience to search.

That's handy for situations where you might not really understand what you need to search for. Any search system that can ask you clarifying questions is going to be a big improvement.

Or where you need to combine several steps together but you don't yet know what those steps are.

There's probably other technologies that could do that, requiring lower resources but they'll come with different trade-offs around configuration.

Just having a Raspberry PI, a offline copy wikipedia and a RAG enabled small LLM would be quite useful or at least entertaining if you have to go off grid.