LlamaIndex Expert Skill

LlamaIndex is an MIT-licensed Python framework for building LLM applications over your data. In 2026, it has evolved from a RAG indexing library into an event-driven workflow framework with integrated production runtime (llama-deploy), agent orchestration (AgentWorkflow), knowledge graph construction (PropertyGraphIndex), and OpenTelemetry-native observability.

The framework is organized around seven core primitives: Reader (data loaders), Document/Node (chunked content model), Index (data structures over Nodes), Retriever (relevant Node selection), Query Engine (retriever + synthesis), Agent (LLM with tools), and Workflow (event-driven orchestration).

Key Principles

These principles govern every decision when building with LlamaIndex. Read them before proceeding to the reference guides.

1. Decouple retrieval chunks from synthesis chunks. The embedding representation that retrieves well differs from the context representation that generates well. Use SentenceWindowNodeParser + MetadataReplacementNodePostProcessor for this pattern.
2. Rerank before you generate. Hybrid retrieval + reranker is the minimum viable production RAG configuration.
3. Agents are Workflows. FunctionAgent and AgentWorkflow are pre-configured Workflows. Drop to raw Workflow when you need custom control flow.
4. Graphs are not just vector stores. PropertyGraphIndex adds structural path traversal that vector similarity cannot provide — combine both for maximum retrieval quality.
5. Evaluate in the same process. Span-attached evaluation preserves the connection between the output and the retrieval context that produced it.

Where to Start

The pipeline has 9 phases from Ingest to Deploy. If you're joining mid-stream with existing work, find your entry point: