Skip to main content

A persistent implementation of BM25 retrieval.

Project description

persistent_bm25

persistent_bm25 is a Python package that provides a persistent implementation of BM25 retrieval.

Installation

You can install it via pip:

pip install persistent_bm25

Usage

from persistent_bm25 import PersistentBM25Retriever
from langchain_core.documents import Document
docs = [
    Document(page_content="LangChain makes AI powerful"),
    Document(page_content="BM25 is a ranking function for search"),
]

# Create retriever
bm25_retriever = PersistentBM25Retriever.from_documents(docs)
bm25_retriever.persist("./bm25_retriever")

loaded_bm25_retriever = PersistentBM25Retriever.from_persist_dir("./bm25_retriever")

results = loaded_bm25_retriever.get_relevant_documents("AI search")
print(results)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

bm25_retriever-0.1.tar.gz (2.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

bm25_retriever-0.1-py3-none-any.whl (2.7 kB view details)

Uploaded Python 3

File details

Details for the file bm25_retriever-0.1.tar.gz.

File metadata

  • Download URL: bm25_retriever-0.1.tar.gz
  • Upload date:
  • Size: 2.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.7

File hashes

Hashes for bm25_retriever-0.1.tar.gz
Algorithm Hash digest
SHA256 4ee8d8dbe042c494fbe679421a1973bf33cdecc1f34f0b85dacc063a92a80b1d
MD5 384b78b4a9d9876dd7cd5e0283424b00
BLAKE2b-256 a55af01c1bb03a67288e89939610aa37e722f72ae284d25d259e86e62586bdee

See more details on using hashes here.

File details

Details for the file bm25_retriever-0.1-py3-none-any.whl.

File metadata

  • Download URL: bm25_retriever-0.1-py3-none-any.whl
  • Upload date:
  • Size: 2.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.7

File hashes

Hashes for bm25_retriever-0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 495866534456ac481bb0efe52c74c18d425973c916e864866c59219989ce8e4a
MD5 42e7e7eb4b6c876dcf45e086fc57c355
BLAKE2b-256 b210b4c0559e499de9d4ac83f1e586b0a885caf56a2883bed4b71994d391ce32

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page