xhluca/bm25s-msmarco-index

BM25S Index

This is a BM25S index created with the bm25s library (version 0.0.1dev0), an ultra-fast implementation of BM25. It can be used for lexical retrieval tasks.

• BM25S GitHub Repository
• BM25S Technical Report

Installation

You can install the bm25s library with pip:

pip install "bm25s==0.1.3"

# Include extra dependencies like stemmer
pip install "bm25s[full]==0.1.3"

# 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:

import bm25s
from bm25s.hf import BM25HF

# Load the index
retriever = BM25HF.load_from_hub("xhluca/bm25s-msmarco-index", revision="main")

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

Saving a bm25s index

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

import bm25s
from bm25s.hf import BM25HF

# Create a BM25 index and add documents
retriever = BM25HF()
corpus = [
    "a cat is a feline and likes to purr",
    "a dog is the human's best friend and loves to play",
    "a bird is a beautiful animal that can fly",
    "a fish is a creature that lives in water and swims",
]
corpus_tokens = bm25s.tokenize(corpus)
retriever.index(corpus_tokens)

token = None  # You can get a token from the Hugging Face website
retriever.save_to_hub("xhluca/bm25s-msmarco-index", token=token)

Stats

This dataset was created using the following data:

Statistic	Value
Number of documents	8841823
Number of tokens	256970704
Average tokens per document	29.063090722354428

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