LlamaIndex Workshop: Evaluation-Driven Development (EDD)

​In this workshop, we teach you how to do "Evaluation Driven Development" (EDD) to build LLM apps for production. This consists of the following:

1. ​Defining evaluation metrics (performance metrics like faithfulness/relevancy or system metrics like latency/cost)
2. ​Creating an evaluation dataset
3. ​Defining a baseline
4. ​Trying out different approaches

​We're excited to feature Wenqi Glantz, an open-source evangelist who has a series of wonderful blogs on this topic:

​https://levelup.gitconnected.com/evaluation-driven-development-the-swiss-army-knife-for-rag-pipelines-dba24218d47e

​https://levelup.gitconnected.com/exploring-zephyr-7b-alpha-through-the-lens-of-evaluation-driven-development-faf69e9d9ec7

apps build cost dataset development evaluation evaluation metrics feature latency llamaindex llm llm apps metrics performance production workshop