Decoder. plain-English AI glossary

LlamaIndex

● Core

Data framework for retrieving and indexing information to feed into LLMs; specializes in RAG.

Think of it like

The librarian; indexes your documents so the LLM can find what it needs.

Example

Index a PDF, then ask questions; LlamaIndex retrieves relevant chunks and passes them to Claude.

How it actually works

LlamaIndex focuses narrowly on data ingestion and retrieval. Supports many file types, vector stores, and LLMs. Built for RAG workflows.

For product teams

Narrower scope than LangChain but deep expertise; becoming part of the RAG stack.

For engineers

Good abstractions for chunking, embeddings, and retrieval. Pairs well with LangChain.

Read anything AI without the jargon

Look up any term in plain English, or save terms as you read with the free Chrome extension.

Open DecoderAdd to Chrome