Popular GitHub Repositories for Bm25

AdalFlow: The library to build & auto-optimize LLM applications.

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。

Easy-to-Use RAG Framework; CCF AIOps International Challenge 2024 Top3 Solution; CCF AIOps 国际挑战赛 2024 季军方案

Neural Search

Sentence-Transformers Information Retrieval example on Chinese

BestRAG: A library for hybrid RAG, combining dense, sparse, and late interaction methods for efficient document storage and search.

Contextual Retrieval solves this problem by prepending chunk-specific explanatory context to each chunk before embedding (“Contextual Embeddings”) and creating the BM25 index (“Contextual BM25”).

Build a Content-Based Movie Recommender System (TF-IDF, BM25, BERT)

Unsupervised tableQA and databaseQA on chinese finance question and tabular data

Anime Style Illustration Specific Image Search App with ViT Tagger x BM25/Doc2Vec

Python Project Sample for Demonstration

Semantic Search on Langchain Github Issues with Weaviate

Hybrid Search of full text and vector queries that execute against a search index containing both searchable plain text content and generated embeddings

This chat bot answers all your questions regarding menstruation ( hormonal changes , phases of menstruation and many more)

Experiments in the field of Semantic Search using BM-25 Algorithm, Mean of Word Vectors, along with state of the art Transformer based models namely USE and SBERT.

NLP based movies search engine (Graduation project)

DocChat is an AI-powered Multi-Agent RAG system using Docling for structured document parsing and BM25 + vector search retrievers to retrieve fact-checked answers from PDFs, DOCX, and text files, preventing hallucinations. ?

Baseline models for searching for movie plots from Wikipedia articles. Techniques include BM25 (lexical search), bi/cross-encoding (semantic search), and retrieval-augmented generation (RAG) using Mistal 7B through Fireworks.ai.

Machine Learning and NLP models for improving text-based recommendations on TripAdvisor, using BM25, TF-IDF, embeddings, and a Hybrid approach.