Fast lexical search implementing BM25 in Python using Numpy, Numba and Scipy
☆1,507Feb 17, 2026Updated 2 weeks ago
Alternatives and similar repositories for bm25s
Users that are interested in bm25s are comparing it to the libraries listed below
Sorting:
- Late Interaction Models Training & Retrieval☆732Feb 27, 2026Updated last week
- Baguetter is a flexible, efficient, and hackable search engine library implemented in Python. It's designed for quickly benchmarking, imp…☆206Aug 31, 2024Updated last year
- A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.☆1,602Dec 20, 2025Updated 2 months ago
- Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-…☆3,868May 17, 2025Updated 9 months ago
- Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.☆2,026Updated this week
- ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)☆3,787Oct 14, 2025Updated 4 months ago
- The Batched API provides a flexible and efficient way to process multiple requests in a batch, with a primary focus on dynamic batching o…☆159Jul 14, 2025Updated 7 months ago
- Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali☆2,688Feb 5, 2026Updated last month
- A Collection of BM25 Algorithms in Python☆1,316Oct 8, 2024Updated last year
- Fast, Accurate, Lightweight Python library to make State of the Art Embedding☆2,744Jan 9, 2026Updated last month
- Use late-interaction multi-modal models such as ColPali in just a few lines of code.☆845Jan 28, 2025Updated last year
- Fast State-of-the-Art Static Embeddings☆2,007Feb 28, 2026Updated last week
- Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts) @ NAACL 2024☆2,865Updated this week
- FastFit ⚡ When LLMs are Unfit Use FastFit ⚡ Fast and Effective Text Classification with Many Classes☆213Sep 18, 2025Updated 5 months ago
- minimal pytorch implementation of bm25 (with sparse tensors)☆104Oct 28, 2025Updated 4 months ago
- Structured Outputs☆13,488Updated this week
- SPLADE: sparse neural search (SIGIR21, SIGIR22)☆980May 3, 2024Updated last year
- The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.☆2,534Feb 24, 2026Updated last week
- A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.☆2,095Oct 16, 2025Updated 4 months ago
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆3,108Feb 23, 2026Updated last week
- ⚡️A Blazing-Fast Python Library for Ranking Evaluation, Comparison, and Fusion 🐍☆656Aug 7, 2025Updated 7 months ago
- Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.☆2,915Updated this week
- Efficient few-shot learning with Sentence Transformers☆2,688Dec 11, 2025Updated 2 months ago
- Bringing BERT into modernity via both architecture changes and scaling☆1,632Updated this week
- Fast Multimodal Semantic Deduplication & Filtering☆892Jan 20, 2026Updated last month
- Retrieval and Retrieval-augmented LLMs☆11,352Dec 15, 2025Updated 2 months ago
- MTEB: Massive Text Embedding Benchmark☆3,151Updated this week
- structured outputs for llms☆12,468Feb 25, 2026Updated last week
- Argilla is a collaboration tool for AI engineers and domain experts to build high-quality datasets☆4,884Updated this week
- A blazing fast inference solution for text embeddings models☆4,553Feb 25, 2026Updated last week
- DSPy: The framework for programming—not prompting—language models☆32,519Updated this week
- Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cro…☆946Jan 1, 2026Updated 2 months ago
- RankLLM is a Python toolkit for reproducible information retrieval research using rerankers, with a focus on listwise reranking.☆582Updated this week
- code for training & evaluating Contextual Document Embedding models☆201May 14, 2025Updated 9 months ago
- Tools for merging pretrained large language models.☆6,826Updated this week
- Tevatron - Unified Document Retrieval Toolkit across Scale, Language, and Modality. Demo in SIGIR 2023, SIGIR 2025.☆730Jan 26, 2026Updated last month
- A large-scale information-rich web dataset, featuring millions of real clicked query-document labels☆346Dec 16, 2024Updated last year
- Large Language Model Text Generation Inference☆10,788Jan 8, 2026Updated last month
- Full text search that feels like a numpy array☆303Feb 1, 2026Updated last month