OSS Tanbou

LlamaIndex

View on GitHubProject website

LlamaIndex — compose document ingestion, retrieval, RAG, and agents

OSS scale score 323.6OSS health 96Update pace 38 commits/30d
About these scores

OSS scale score is an unbounded metric that log-compresses and weights Stars, Watchers, Forks, and Contributors. Discovery score is the current OSS scale score minus the score at discovery. Update pace is commits in the last 30 days, growth momentum is the OSS scale score difference within the recent observation window, and OSS health is a 0–100 rating based on available recency, Community Health, and release data.

Stars
52,236
Primary language
Python
License
MIT
Repository last updated
Sep 19, 2026

Overview

LlamaIndex is a Python OSS framework for ingesting data from documents, APIs, SQL, and other sources and composing indexes, retrievers, query engines, LLMs, embeddings, and vector stores into RAG and agent applications. Its core can be paired with more than 300 integration packages.

Features and best fit

Based on official documentation; not hands-on tested · Content checked:

Ingest and structure private data for LLM use

Data connectors load documents and other sources, which can then be indexed or structured for retrieval and context augmentation.

Sources: [2]

Swap retrievers, query engines, and provider integrations

LLMs, embedding models, vector stores, retrieval, and reranking components can be selected through modular integration packages.

Sources: [2][4]

For document-centric RAG, search, and agent applications

LlamaIndex fits applications that retrieve internal documents, PDFs, or database content and pass relevant context to LLMs or agents.

Sources: [2][4]

Separate the OSS framework from the LlamaParse product platform

The README says the OSS toolkit remains available while the company's current focus has shifted to LlamaParse, LiteParse, and document parsing/extraction. Decide which cloud services, if any, your architecture should depend on.

Sources: [2]

Official sources

  1. [1]run-llama/llama_index repository(2026-09-20)
  2. [2]LlamaIndex README(2026-09-20)
  3. [3]LlamaIndex MIT license(2026-09-20)
  4. [4]LlamaIndex OSS documentation(2026-09-20)
Supplemental curator note

LlamaIndex is useful when teams want composable ingestion, indexing, retrieval, and model integrations instead of building a RAG stack from scratch. Its README says the OSS framework remains available while the company's primary focus has shifted toward LlamaParse and document parsing/extraction.

Try it in 3 steps

  1. 1

    Install the LlamaIndex starter package

    Install the starter package containing core plus a representative set of integrations.

    python -m pip install llama-index
  2. 2

    Configure a model provider credential

    Follow the README minimal path first, or replace the provider with the integration you intend to use.

    export OPENAI_API_KEY="..."
  3. 3

    Index documents and query them

    Load documents with a reader, build an index, and verify the basic retrieval/query flow.

    VectorStoreIndex.from_documents(...) → index.as_query_engine().query(...)
Check the official README

Growth

Growth trends · Last 30 days

52,236 Stars

Trend data is still being collected.

Development activity

Last 90 days · weekly

Commits (last 30 days)
38
Open PRs
584
Issues opened
164
Issues closed
132
PRs opened
819
PRs merged
110

Issues

164 / 132

Jun 23Sep 20
Issues openedIssues closed

Pull requests

819 / 110

Jun 23Sep 20
PRs openedPRs merged

Maintenance

Median first response
13 min
Issue response rate
9% (9/100)

Based on up to the 100 newest issues opened by external users in the last 90 days. A first comment from an OWNER, MEMBER, or COLLABORATOR counts as a response; issues whose full comment history cannot be checked are excluded. The median and response rate update weekly.

Built with

Categories and tags

Categories

Tags

GitHub data

GitHub dataView detailed GitHub data
View on GitHub

GitHub Topics

  • agents
  • application
  • data
  • fine-tuning
  • framework
  • llamaindex
  • llm
  • rag
  • vector-database
  • multi-agents
Stars
52,236
Forks
8,177
Watchers
287
Open issues
220
Contributors
476
Primary language
Python
License
MIT
Repository last updated
Sep 19, 2026
Write a related article

Share a guide or use case for this OSS in Markdown. Articles are published after administrator approval.

Report incorrect information

Tell us if any listing information is incorrect or outdated.