Metadata-Version: 2.1
Name: beir
Version: 0.0.3
Summary: A Heterogeneous Benchmark for Information Retrieval
Home-page: https://github.com/beir-nlp/beir
Author: Nandan Thakur
Author-email: nandant@gmail.com
License: Apache License 2.0
Download-URL: https://github.com/beir-nlp/beir/archive/v0.0.1.zip
Keywords: Information Retrieval Transformer Networks BERT PyTorch IR NLP deep learning
Platform: UNKNOWN
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3.6
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.6
Description-Content-Type: text/markdown
Requires-Dist: sentence-transformers
Requires-Dist: pytrec-eval

# beir
A heterogeneous benchmark for Information Retrieval

## Installation

Install via pip:

```
pip install beir
```

If you want to build from source, use:

```
$ git clone https://github.com/beir-nlp/beir.git
$ pip install -e .
```

Tested with python versions 3.6 and 3.7
## Steps To Follow

1. Download datasets using ``datasets/download_data.py``
2. Evaluate using ``evaluate_model.py`` wherein set line 4 => ``data_path = "../datasets/{dataset-name}"``

