Why it matters
LlamaIndex is a core RAG and agent orchestration framework. The people in this room are building the retrieval pipelines and agent runtimes where inference spend concentrates.
The tokenmaxxing angle
RAG pipelines built on LlamaIndex are token-heavy by design — embedding calls, retrieval re-ranking, and synthesis steps all add up. The practitioners here are the ones tuning those pipelines in production.
From the organizers
Event hosted by Rachel Eastwood and the LlamaIndex Community, featuring limited-edition LlamaIndex merchandise and a 'secret quest' accessible via QR code on 2nd Street, San Francisco.