# LlamaIndex

LlamaIndex is the leading document agent and OCR platform

Repository: https://github.com/run-llama/llama_index
Canonical: https://ross.abutalabs.com/products/llamaindex
Homepage: https://developers.llamaindex.ai
Language: Python
License: MIT
License Family: permissive
Topics: agents, application, data, fine-tuning, framework, llamaindex, llm, rag, vector-database, multi-agents
Last push: 2026-08-26T15:31:33+00:00

## Health v2 (maintenance only)
Score: 95/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 86, longevity 100
- inputs: {"age_days": 1400, "days_push": 7, "days_rel": 14, "gap_med": 4, "n_releases_24m": 116}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 51883, forks 8029 (observed 2026-08-28T04:12:11.981191+00:00)

## What it is
LlamaIndex is a Python (with a TypeScript variant) framework for building LLM-powered applications, centered on ingesting, indexing, and querying documents for retrieval-augmented generation and document agents. It provides data connectors, vector store integrations, query engines, and multi-agent orchestration.

## Use cases
- build a chatbot over my own documents
- index pdfs and query them with an llm
- build a rag pipeline with vector search
- create document agents that answer questions from files
- connect custom data sources to an llm
- fine-tune and evaluate llm applications
- build multi-agent workflows over enterprise data

## When to choose
- you need retrieval-augmented generation over private or unstructured data
- you want many prebuilt data connectors and vector store integrations
- you are building document Q&A, agents, or chat over your knowledge base in Python or TypeScript

## When to avoid
- you only need raw LLM API calls without retrieval or indexing
- you want a lightweight prompt library rather than a full data framework
- you need a non-Python/non-TypeScript runtime

## Facets
- artifact type: framework
- maturity: stable
- function: rag, agent-framework, llm-inference, vector-database, ocr, data-science, etl
- domain: large-language-models, machine-learning
- platform: python, cross-platform
- tags: llamaindex, document-indexing, llm-framework, data-connectors, query-engines, typescript, retrieval-augmented-generation, ai-agents, natural-language-processing, nodejs

## Member repositories
- run-llama/llama_index (main) score 95
- run-llama/llama-hub (plugin) score 10
- run-llama/LlamaIndexTS (sdk) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:11.981191+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:19:40.849924+00:00, confidence not recorded.
  - readme: https://github.com/run-llama/llama_index (fetched 2026-08-28T04:12:11.981191+00:00, sha 986105fabfcc)
- Data as of 2026-08-30T08:39:29.467469+00:00.