flâneur

High-Level Concepts - LlamaIndex 🦙 0.8.49

docs.llamaindex.ai · 903 words · saved by 1 readers

If you haven’t, install and complete starter tutorial before you read this. It will make a lot more sense! LlamaIndex helps you build LLM-powered applications (e.g. Q&A, chatbot, and agents) over custom data. In this high-level concepts guide, you will learn: the retrieval augmented generation (RAG) paradigm for combining LLM with custom data, key concepts and modules in LlamaIndex for composing your own RAG pipeline. Retrieval augmented generation (RAG) is a paradigm for augmenting LLM with custom data. It generally consists of two stages: indexing stage: preparing a knowledge base, and querying stage: retrieving relevant context from the knowledge to assist the LLM in responding to a question LlamaIndex provides the essential toolkit for making both steps super easy. Let’s explore each stage in detail. LlamaIndex helps you prepare the knowledge base with a suite of data connectors and indexes. Data Connectors: A data connector (i.e. Reader) ingests data from different data sources an

High-Level Concepts | Developer Documentation Skip to content LlamaIndex Framework Getting Started High-Level Concepts Copy Markdown Open in Claude Open in ChatGPT Open in Cursor Copy Markdown View as Markdown High-Level Concepts This is a quick guide to the high-level concepts you’ll encounter frequently when building LLM applications. Large Language Models (LLMs) Section titled “Large Language Models (LLMs)” LLMs are the fundamental innovation that launched LlamaIndex. They are an artificial intelligence (AI) computer system that can understand, generate, and manipulate natural language, inc

related reading