DSPy: Transforming Language Model Calls into Smart Pipelines // Omar Khattab // #194

Agentic Conversations (formally mlops.community) · Dec 5, 2023 · 1h 5m · transcript

MLOps podcast #194 with Omar Khattab, PhD Candidate at Stanford, DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines.

// Abstract

The ML community is rapidly exploring techniques for prompting language models (LMs) and for stacking them into pipelines that solve complex tasks. Unfortunately, existing LM pipelines are typically implemented using hard-coded "prompt templates", i.e., lengthy strings discovered via trial and error. Toward a more systematic approach for developing and optimizing LM pipelines, we introduce DSPy, a programming model that abstracts LM…