Reimagining LLM-Powered Unstructured Data Analysis with DocETL

DocETL is an open-source system for building LLM-powered data processing pipelines, offering declarative operators and powerful optimization for complex document analysis tasks

Lightweight Nudges for More Accurate Retrieval in RAG Pipelines

Make your retrieval pipelines more effective with this novel and lightweight fine-tuning approach

Introducing Data People

Reimagining the next generation of intelligent, usable, and efficient data infrastructure