DGDan Girelliniinengineering.fractional.ai·Feb 12 · 8 min readYour evals have a Rotten Tomatoes problemYou push a change to a prompt and your eval score drops from 0.91 to 0.84. Something got worse, but the score doesn’t tell you what. So you start re-running the pipeline, tweaking your inputs, pouring00
DGDan Girelliniinengineering.fractional.ai·Aug 30, 2024 · 3 min readTaming LLM Responses: Dynamic Pydantic Models for Flexible Structured OutputAs developers working with Large Language Models (LLMs), we often grapple with the challenge of constraining their outputs to meet our specific needs. In this post, I will share a technique I developed to enforce structured responses from LLMs, parti...00
