beir 2.0.0

A Heterogeneous Benchmark for Information Retrieval

Stars: 1357, Watchers: 1357, Forks: 165, Open Issues: 68

The beir-cellar/beir repo was created 3 years ago and the last code push was 3 weeks ago.
The project is very popular with an impressive 1357 github stars!

How to Install beir

You can install beir using pip

pip install beir

or add it to a project with poetry

poetry add beir

Package Details

Author

Nandan Thakur

License

Apache License 2.0

Homepage

https://github.com/beir-cellar/beir

PyPi:

https://pypi.org/project/beir/

GitHub Repo:

https://github.com/beir-cellar/beir

Classifiers

• Scientific/Engineering/Artificial Intelligence

Related Packages

Errors

A list of common beir errors.

Code Examples

Here are some beir code examples and snippets.

GitHub Issues

The beir package has 68 open issues on GitHub

• evaluate_anserini_bm25.py retrieves 1000 documents for each query no matter which k I set in payload
• adding a simple implementation of ColBERT
• No module named 'tensorflow_text'
• Adding the ANTIQUE dataset to BEIR
• fix: typing issue raising warnings in mypy and pylance
• Support for custom retrievers: common base type for EvaluateRetrieval's retriever param
• Evaluation codes for ColBERT
• Rerank scores lower than vanilla dense IR?

See more issues on GitHub