Skip to content
New this week26 prompts for Sora, Veo and Runway video workflows.
Explore video prompts→
AIPrompt123Prompt library

Search AIPrompt123

Search prompts, categories, platforms and repositories

RAG & memoryPythonMIT

run-llama/llama_index

LlamaIndex focuses on the data layer of LLM applications: ingestion, chunking, indexing, retrieval, query engines and agents over your own documents. It is a good fit when retrieval quality is the core problem, and it offers higher-level workflows alongside low-level primitives for teams that want control.

41.5k stars5.9k forks1.8k contributors720 open issuesUpdated

What it does

  • Ingests documents from files, APIs and databases into structured indexes.
  • Provides retrieval, reranking and query engines with citation support.
  • Supports agent workflows and multi-step query planning over private data.

Key features

  • Broad connector library for data sources and vector stores.
  • Advanced retrieval patterns including hybrid search and reranking.
  • Structured output and response synthesis with source nodes.
  • LlamaCloud and LlamaParse for complex documents.

How to install it

Commands are copied from the project documentation at the time of review. Check the repository for the current version.

Python
pip install llama-index

Install only the integration packages you need.

Alternatives to consider

llama_index is a strong default for rag & memory, but the right choice depends on your stack, licence constraints and how much control you need. These are the projects we compare most often.

LangChainHaystackRAGFlow

Prompts that pair with it

All prompts →
Verified Knowledge · FAQ

llama_index FAQ

Adoption questions we hear most often about this project.

Related repositories

RAG & memory · Python

A RAG engine with document parsing, chunking, retrieval and grounded citations.

64.0k6.1kApache-2.0

RAG & memory · Python

A memory layer for AI assistants that stores and retrieves user preferences across sessions.

42.0k4.3kApache-2.0