xhluca/bm25s-quora-index

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

import bm25s
from bm25s.hf import BM25HF

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

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

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-quora-index", token=token)