ToolsBuild with AIHungarian edition

LlamaIndex: build RAG answers from your own documents

A framework for building retrieval-augmented generation workflows, with documented file loading, indexing, and document-query examples.

Visit official website

LlamaIndex

Build document search

LlamaIndex connects an LLM application to documents. Its Python starter loads a folder with SimpleDirectoryReader, builds a VectorStoreIndex, and creates a query engine. It then exposes document search as an agent tool.

Keep the prototype inspectable

The directory reader supports file selection and custom metadata.

Choose a small folder whose contents you can inspect by hand. Try one question, open the retrieved text, and compare it with the response using our RAG checklist. We have not tested this tool here.

Keep exploring

Explore the collection

ArticlesBuild with AI

RAG with your own documents: check retrieval and citations before trusting an answer

A practical retrieval-augmented generation checklist with an invented policy example, expected source passages, and separate checks for retrieval and answers.

CurioFuse editorial · LlamaIndex documentation

VideosLearn & research

IBM explains RAG: what retrieval adds to an AI answer

Marina Danilevsky introduces RAG; the linked IBM Research companion explains retrieval, generation, and source checking.

IBM Technology23 Aug 2023

NewsBuild with AI

When should AI search again? Understanding agentic RAG

A second search helps when it fills a specific gap. A practical example shows how the retrieval loop works and when a simpler approach can be enough.

KDnuggets16 Oct 2026