There are 2 repositories under bm25 topic.
Easy to use open source fast database for search | Good alternative to Elasticsearch now | Drop-in replacement for E in the ELK soon
The AI-native database built for LLM applications, providing incredibly fast full-text and vector search
A Collection of BM25 Algorithms in Python
Similarities: a toolkit for similarity calculation and semantic search. 相似度计算、匹配搜索工具包,支持亿级数据文搜文、文搜图、图搜图,python3开发,开箱即用。
Neural Search
对四种句子/文本相似度计算方法进行实验与比较
IResearch is a cross-platform, high-performance search analytics library written entirely in C++ with the focus on a pluggability of different ranking/similarity models
Emacs package that helps org-mode users (re)discover similar documents
Document Search Engine Tool
Fast Full Text Search based on BM25
Using business-level retrieval system (BM25) with Python in just a few lines.
Sentence-Transformers Information Retrieval example on Chinese
Python implementation of BM25 function for document retrieval
Improving the effectiveness Lucene's BM25 (and testing it using Yahoo! Answers and Stack Overflow collections)
Command-line tool that finds lexically similar documents in relation to a reference text file or ad-hoc query
Text Similarity using BM25 algorithm and WordNet
Build a Content-Based Movie Recommender System (TF-IDF, BM25, BERT)
Advanced model of Bm25 is Bm25+, which was implemented and compared with the baseline model (bm25)
Unsupervised tableQA and databaseQA on chinese finance question and tabular data
Bm25 Information retrieval model using python language
Well-tested implementation of the OkapiBM25 algorithm. Install the npm package!
A system for computing the most similar resume vectors given a query job vector. Built using an inverted index and BM25 retrieval model.
Search Engine Implemented in Python. Components : Web Crawler. Indexer. Parser. Page Ranking Algorithm