mteb 2.8.1

Massive Text Embedding Benchmark

Stars: 3129, Watchers: 3129, Forks: 556, Open Issues: 255

The embeddings-benchmark/mteb repo was created 3 years ago and the last code push was 8 hours ago.
The project is very popular with an impressive 3129 github stars!

How to Install mteb

You can install mteb using pip

pip install mteb

or add it to a project with poetry

poetry add mteb

Package Details

Author

None

License

None

Homepage

None

PyPi:

https://pypi.org/project/mteb/

Documentation:

https://embeddings-benchmark.github.io/mteb/

GitHub Repo:

https://github.com/embeddings-benchmark/mteb

Classifiers

Related Packages

Errors

A list of common mteb errors.

Code Examples

Here are some mteb code examples and snippets.

GitHub Issues

The mteb package has 255 open issues on GitHub

• Tranvformers v5 removed mctct
• Tests transformers v5
• Test compatability with transformers v5
• [MAEB] Add qwen-omni models
• model: added Querit/Querit
• dataset: Add ERESS reranking task
• Made mteb.get_model compatible with CrossEncoders and SparseEncoders
• Add model: Qwen2.5/3-VL
• test run
• Fix support for datsets 4.5 with pandas 3
• Check support for pandas 3.0
• Update Leaderboard - Remove Memory Usage column and Add active Paramters column
• Load aggregated results from task results
• Add to_disk and from_disk to ModelResults
• rename bm25s to baseline/bm25s

See more issues on GitHub