---
language: en
library_name: bm25s
tags:
- bm25
- bm25s
- retrieval
- search
- lexical
---

# BM25S Index

This is a BM25S index created with the [`bm25s` library](https://github.com/xhluca/bm25s) (version `0.2.0`), an ultra-fast implementation of BM25. It can be used for lexical retrieval tasks.

BM25S Related Links:

* 🏠[Homepage](https://bm25s.github.io)
* 💻[GitHub Repository](https://github.com/xhluca/bm25s)
* 🤗[Blog Post](https://huggingface.co/blog/xhluca/bm25s)
* 📝[Technical Report](https://arxiv.org/abs/2407.03618)


## Installation

You can install the `bm25s` library with `pip`:

```bash
pip install "bm25s==0.2.0"

# For huggingface hub usage
pip install huggingface_hub
```

## Loading a `bm25s` index

You can use this index for information retrieval tasks. Here is an example:

```python
import bm25s
from bm25s.hf import BM25HF

# Load the index
retriever = BM25HF.load_from_hub("dadashzadeh/2023_10_en_keywords_Cryptocurrency")

# You can retrieve now
query = "a cat is a feline"
results = retriever.retrieve(bm25s.tokenize(query), k=3)
```

## Saving a `bm25s` index

You can save a `bm25s` index to the Hugging Face Hub. Here is an example:

```python
import bm25s
from bm25s.hf import BM25HF

corpus = [
    "northwest bank",
    "misfits market",
    "merrick bank login",
    "marketing",
    "market place",
    "jetblue customer service",
    "internal revenue service",
    "how to make money online",
    "gordon food service",
    "futures market",
    "frontier airlines customer service",
    "food banks near me",
    "first convenience bank",
    "eastern bank",
    "dollar bank",
]

retriever = BM25HF(corpus=corpus)
retriever.index(bm25s.tokenize(corpus))

token = None  # You can get a token from the Hugging Face website
retriever.save_to_hub("dadashzadeh/2023_10_en_keywords_Cryptocurrency", token=token)
```

## Advanced usage

You can leverage more advanced features of the BM25S library during `load_from_hub`:

```python
# Load corpus and index in memory-map (mmap=True) to reduce memory
retriever = BM25HF.load_from_hub("dadashzadeh/2023_10_en_keywords_Cryptocurrency", load_corpus=True, mmap=True)

# Load a different branch/revision
retriever = BM25HF.load_from_hub("dadashzadeh/2023_10_en_keywords_Cryptocurrency", revision="main")

# Change directory where the local files should be downloaded
retriever = BM25HF.load_from_hub("dadashzadeh/2023_10_en_keywords_Cryptocurrency", local_dir="/path/to/dir")

# Load private repositories with a token:
retriever = BM25HF.load_from_hub("dadashzadeh/2023_10_en_keywords_Cryptocurrency", token=token)
```

## Stats

This dataset was created using the following data: 497 keywords Cryptocurrency (semrush)

| Statistic | Value |
| --- | --- |
| Number of documents | 602959 |
| Number of tokens | 2414020 |
| Average tokens per document | 4.0 |

## Parameters

The index was created with the following parameters:

| Parameter | Value |
| --- | --- |
| k1 | `1.5` |
| b | `0.75` |
| delta | `0.5` |
| method | `lucene` |
| idf method | `lucene` |

## Citation

To cite `bm25s`, please use the following bibtex:

```
@misc{lu_2024_bm25s,
      title={BM25S: Orders of magnitude faster lexical search via eager sparse scoring}, 
      author={Xing Han Lù},
      year={2024},
      eprint={2407.03618},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2407.03618}, 
}
```