llama-index-legacy

LlamaIndex is the leading document agent and OCR platform

No known security advisories. The current version has no OSV.dev malware reports and no critical or high-severity vulnerabilities.

llama-index-legacy has 2.4M monthly downloads and 51K GitHub stars. Version 0.9.48.post4 supports Python <4.0,>=3.8.1, first published in 2024.

It is actively maintained under a permissive license, last released in Nov 2024.

It is built on top of aiohttp, dataclasses-json and deprecated. It is used by 7 tracked packages, including llama-index-test-starter, tc-hivemind-backend and syftr.

GitHub topics include agents, application and data.

Shared Repository

This package shares its GitHub repository (run-llama/llama_index) with 3 other packages. Stars, forks, and other GitHub metrics reflect the entire repository.

llama-index-core (15.8M) llama-index (7.9M) llama-index-instrumentation (7.3M)

Downloads

Day

77.3K

Week

542.7K

Month

2.4M

Stars

50.7K

Forks

Issues

Version

Package Insights

Package Risks

No releases in 602 days despite active commits

click for breakdown

Actively Maintained

click for breakdown

Community Favorite

click for breakdown

click for breakdown

Score breakdown - each component scores 0-100, weighted by percentage

Maintenance

80

Popularity

95

Adoption

70

Community

80

Provenance

0

How the maintenance status was determined

Last commit

4 days ago

Monthly downloads

2,415,382

• Active

Activity within 30 days

Stable

Activity within 31-180 days

Minimal

Activity within 181-365 days, or no activity data

At Risk

No activity for > 365 days, but > 10,000 monthly downloads

Archived

Repository flagged as archived on GitHub

How the popularity category was determined

Monthly downloads

2,415,382

Stars

50,677

Stars per 1k downloads

20.98

Industry Standard

> 10,000,000 monthly downloads

Hidden Gem

< 0.5 stars per 1k downloads and > 100,000 monthly downloads

• Community Favorite

> 5 stars per 1k downloads

Rising Star

Balanced ratio of stars to downloads

Unknown

Fewer than 1,000 monthly downloads, or no star data

How download momentum is calculated

Week daily avg

77,535

Month daily avg

80,513

Momentum

-3.7%

((week_daily_avg - month_daily_avg) / month_daily_avg) * 100

click for breakdown

click for breakdown

Release Cadence

click for breakdown

Contributor Risk

click for breakdown

Python version support tiers

requires_python

<4.0,>=3.8.1

Cutting Edge

Minimum supported version is 3.12 or newer

• Modern

Minimum supported version is 3.9, 3.10, or 3.11

Legacy

Supports 3.8 or older (or Python 2)

Unknown

No requires_python specified or unparseable

License categories

License

MIT

• Permissive

MIT, Apache, BSD, ISC, Unlicense, CC0, etc.

Copyleft

GPL, LGPL, AGPL, MPL, EPL, etc.

Proprietary

Commercial, all rights reserved, custom EULAs

Unknown

No license specified, or none of the above match

How the release cadence was determined

Last release

606 days ago

Total releases

9

Releases/year

3.7

Rapid

Last release within 365 days and > 12 releases/year

Regular

Last release within 365 days

• Slow

Last release 366-730 days ago

Stalled

Last release > 730 days ago, or no releases

Unknown

No usable release date available

How contributor risk was determined

Contributors

1,893

Monthly downloads

2,415,382

High Load

≤ 2 contributors and ≥ 50,000 monthly downloads

Moderate Load

< 10 contributors and ≥ 500,000 monthly downloads

Low Load

< 25 contributors and ≥ 5,000,000 monthly downloads, or sole maintainer with ≥ 10,000 monthly downloads

• Balanced

Enough contributors for the package's popularity

Unknown

No contributor data available

Engagement

90

Issue Burden

3.7

per 1k stars

Discussions

15.5

per 1k stars

Fork Ratio

24.6%

contrib / forks

Stale Release

602d

PR Velocity

Quiet

Weekly Downloads

Last 7 days

542,748

Last 30 days

2,415,143

Peak day (2026-05-17)

88,273

2026-03-26 – 2026-07-03. Enable JavaScript for the interactive chart.

GitHub Stars

Current

50,646

Earliest (2026-01-14)

46,364

Change

+4,282

2026-01-14 – 2026-07-05. Enable JavaScript for the interactive chart.

Not all downloads include detailed metadata. Breakdowns reflect the subset that does.

Downloads by OS

Linux 76.2K

Windows 87

macOS 37

Python Versions

3.12

97.8% 74.4K

3.11

1.1% 838

3.10

0.9% 708

3.13

0.1% 64

3.9

0.1% 40

Top Countries

1.

US

75.4K

2.

AU

292

3.

SG

197

4.

IN

102

5.

HK

59

6.

DE

44

7.

GB

28

8.

CN

25

9.

JP

18

10.

BR

17

Dependencies

18

aiohttp <4.0.0,>=3.8.6
dataclasses-json
deprecated >=1.2.9.3
dirtyjson <2.0.0,>=1.0.8
fsspec >=2023.5.0
httpx
nest-asyncio <2.0.0,>=1.5.8
networkx >=3.0
nltk >=3.8.1
numpy
openai >=1.1.0
pandas
requests >=2.31.0
sqlalchemy >=1.4.49
tenacity <9.0.0,>=8.2.0
tiktoken >=0.3.3
typing-extensions >=4.5.0
typing-inspect >=0.8.0

15 optional dependencies

asyncpg[postgres]
beautifulsoup4[html]
gradientai[gradientai]
guidance[query-tools]
jsonpath-ng[query-tools]
langchain[langchain]
lm-format-enforcer[query-tools]
optimum[local-models]
pgvector[postgres]
psycopg2-binary[postgres]
rank-bm25[query-tools]
scikit-learn[query-tools]
sentencepiece[local-models]
spacy[query-tools]
transformers[local-models]

Used By

7

GitHub Topics

Tags from the package's GitHub repository describing what it does.

Agents Application Data Fine Tuning Framework Llamaindex Llm Rag Vector Database Multi Agents

Package Information

License

MIT

First Release

February 2, 2024

Last Release

1 year ago

Last Commit

5 days ago

Latest Version

0.9.48.post4

Total Releases

9

Contributors

1,893

Open PRs

298

Archived

No

Author

Jerry Liu

Python Versions

3 3.9 3.10 3.11 3.12

Wheels

py3

Keywords

LLM NLP RAG data devtools index retrieval

Tracking Since

January 6, 2026

Data Updated

July 5, 2026

Data Freshness

Fresh

Links

run-llama/llama_index