Thread

Patterns for LLM systems: evals, RAG, fine-tuning, caching, guardrails

Eugene Yan (Anthropic) · x.com

The whole LLM-product stack in one thread; a map of every decision you will eventually face.

Open on x.com ↗

The question it answers

  1. How do founders ship their first AI feature (APIs, wrappers, RAG in plain terms)?

Read with it

  1. Video [1hr Talk] Intro to Large Language Models Andrej Karpathy
  2. Video Deep Dive into LLMs like ChatGPT Andrej Karpathy
  3. Video RAG Explained For Beginners KodeKloud
  4. Video Build and Deploy a RAG Chatbot with JavaScript, LangChain.js, Next.js freeCodeCamp (Ania Kubow)
  5. Free, thorough, and taught by the engineer who wrote much of LangChain's RAG tooling. freecodecamp.org Course Learn RAG from Scratch (Python tutorial from a LangChain engineer) freeCodeCamp (Lance Martin, LangChain)
  6. The follow-on course for when your prototype RAG needs to survive real users. freecodecamp.org Course Production RAG with LangChain and Vector Databases freeCodeCamp
eChai Partner Brands The partnership →