dadashzadeh/2023_10_en_keywords_Cryptocurrency

pip install "bm25s==0.2.0"

# For huggingface hub usage
pip install huggingface_hub

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)

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)

# 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)

@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}, 
}