Slush is happening right now, it's one of the core startup conferences in Europe, you cannot miss it if you're a founder or investor.
I've created a RAG chatbot based on Slush's 700+ events, 6.2k+ companies.
To be precise, right now there's 7048 documents in the chat.
Slush actually has a great data model so I was able to export clean documents. That are easy to chunk and thus have good semantics.
It's great for finding after party events 😉 After all, why are we are embedding at all?