Simplicity and Metrics // Sam Bean // MLOps podcast #217 clip

Huge thank you to Zilliz for sponsoring this episode. Zilliz RAG - https://zilliz.com/vector-database-use-cases/llm-retrieval-augmented-generation

MLOps podcast #217 with Sam Bean, Software Engineer (Applied AI) at Rewind.ai, The Real E2E RAG Stack.

// Abstract
What does a fully operational LLM + Search stack look like when you're running your own retrieval and inference infrastructure? What does the flywheel really mean for RAG applications? How do you maintain the quality of your responses? How do you prune/dedupe documents to maintain your document quality? …

abstract applications applied ai e2e engineer flywheel inference infrastructure llm look mean mlops mlops podcast podcast quality rag responses retrieval running sam search software software engineer stack