Querying 3 billion vectors

Requirements are hard

Medium

Generative Agents Navigating Digital Libraries

In the rapidly evolving field of digital libraries, the development of large language models (LLMs) has opened up new possibilities for simulating user behavior. This innovation addresses the longstanding challenge in digital library research: the scarcity of publicly available datasets on user search patterns due to privacy concerns. In this context, we introduce Agent4DL, a user search behavior simulator specifically designed for digital library environments. Agent4DL generates realistic user profiles and dynamic search sessions that closely mimic actual search strategies, including querying, clicking, and stopping behaviors tailored to specific user profiles. Our simulator's accuracy in replicating real user interactions has been validated through comparisons with real user data. Notably, Agent4DL demonstrates competitive performance compared to existing user search simulators such as SimIIR 2.0, particularly in its ability to generate more diverse and context-aware user behaviors.

Publishing Progress: Oops

For the new year, I decided to expand the next batch of agents I’d query to represent my space opera novel. I’m excited to get this book out there; its themes of heroic scientific colla…

Alignment Scry | ExoPriors

The most powerful semantic search over alignment-adjacent documents. Fully embedded. Fully explorable.

Introducing pg_clickhouse: A Postgres extension for querying ClickHouse

Today, we’re pleased to release pg_clickhouse, an Apache 2-licensed PostgreSQL extension to transparently execute analytics queries on ClickHouse directly from PostgreSQL.