LlamaIndex

Health v2 · maintenance only

Adoption not part of the score

52325 stars · 8226 forks observed · 2026-09-27

What it is AI-extracted, prompt v1, taxonomy v1, 2026-09-21, confidence 0.97

LlamaIndex is an open‑source framework for building LLM‑powered applications that ingest, parse, and index documents. It provides tools for OCR, structured extraction, vector storage, and retrieval‑augmented generation pipelines.

Use cases

• Parse PDFs, scans, or images into clean text for LLMs
• Extract structured JSON or tables from documents
• Build a RAG pipeline that searches a vector store of your documents
• Create document‑aware AI agents that can read and reason over files
• Index large corpora and perform semantic search over them

When to choose

• You need a unified SDK to handle document ingestion, OCR, and vector indexing
• Your application relies on LLMs for retrieval‑augmented generation or agentic workflows
• You want multi‑language support (Python, TypeScript, Go, Java) and cloud‑hosted parsing services
• You require built‑in layout extraction, metadata, and structured output capabilities

When to avoid

• You only need a simple PDF text extractor without LLM integration
• Your project is constrained to a single language runtime not supported by LlamaIndex
• You prefer a fully managed commercial document AI service with SLA guarantees

Facets

library · maturity active

parser vector-database search-engine rag artificial-intelligence large-language-models python go jvm cli llm document-agent ocr multi-agent llamaindex llama-hub llama-cloud agentic-ocr retrieval-augmented-generation data-engineering nlp nodejs

Member repositories

For agents

markdown · JSON · MCP: product_card(name="run-llama/llama_index")