Home Projects RankGPT
RankGPT
Python

RankGPT

Is ChatGPT Good at Search? LLMs as Re-Ranking Agent [EMNLP 2023 Outstanding Paper Award]

by sunnweiwei · GitHub
Stars
Forks
Trending
License
Created
Last commit
Category
Language
chatgptinformation-retrievallarge-language-modelsApache-2.0Python
View on GitHub
In plain words

Explore how ChatGPT can improve search results by ranking information more effectively.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
RankGPT — GitHub preview card
📈 Star history
670668
2026-07-202026-08-31
📈 Track RankGPT

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

Is ChatGPT Good at Search? LLMs as Re-Ranking Agent [EMNLP 2023 Outstanding Paper Award]

RankGPT has 670 stars on GitHub. It has been forked 66 times. RankGPT is written mainly in Python. It has been in active development since 2023. RankGPT is available under the Apache-2.0 license. Its main topics are chatgpt, information-retrieval, large-language-models, reranking.

Frequently asked questions

What is RankGPT?

Is ChatGPT Good at Search? LLMs as Re-Ranking Agent [EMNLP 2023 Outstanding Paper Award]

Is RankGPT open source?

RankGPT is an open-source project. It is released under the Apache-2.0 license.

Is RankGPT free?

Yes. RankGPT is free and open source — you can use, modify and self-host it.

What license does RankGPT use?

RankGPT is available under the Apache-2.0 license.

What language is RankGPT written in?

RankGPT is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — RankGPT

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=sunnweiwei-rankgpt)](https://olud.ai/project/sunnweiwei-rankgpt.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.