Embeddings, Vector Databases, Private Information Retrieval

This morning, we will discuss vector databases and private information retrieval. From embeddings to similarity search, retrieval-augmented generation, and privacy-preserving queries — it’s a world where math meets AI meets security. Do you need a specialized database, or will your SQL store do the trick? And how private is “private” really?

Come and share how (and if) you use vector databases. Do you rely on Pinecone, Weaviate, Milvus — or roll your own? Have you explored private information retrieval in production, or is it still in the “someday” pile? Ask about it, tell about it, or listen about it, sipping your coffee.

Time: 08:00 in the morning. I know it’s early. Early morning is the toughest time to stick to your commitments. It’s tempting to sleep in. But it’s a small group, and every person matters. If you signed up, please join — we count on you. If you can’t, update your RSVP on time.

Language: English 🇬🇧

Format: One topic, a bunch of friendly people, open discussion. There’s no speaker. There might be prepared questions for the round, but the discussion may derail — and that’s fine. Whatever happens is the only thing that could have happened.

Entry level: None. Join if you’ve never touched a vector DB and want to know what the fuss is about, or if you’ve built entire pipelines with them and want to talk shop.