xhluca / bm25sLinks
Fast lexical search implementing BM25 in Python using Numpy, Numba and Scipy
☆1,444Updated last week
Alternatives and similar repositories for bm25s
Users that are interested in bm25s are comparing it to the libraries listed below
Sorting:
- A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.☆1,584Updated 2 weeks ago
- Late Interaction Models Training & Retrieval☆677Updated 2 weeks ago
- Fast Semantic Text Deduplication & Filtering☆861Updated this week
- Bringing BERT into modernity via both architecture changes and scaling☆1,602Updated 6 months ago
- Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cro…☆910Updated this week
- SPLADE: sparse neural search (SIGIR21, SIGIR22)☆960Updated last year
- RankLLM is a Python toolkit for reproducible information retrieval research using rerankers, with a focus on listwise reranking.☆562Updated last week
- Easily embed, cluster and semantically label text datasets☆587Updated last year
- ⚡️A Blazing-Fast Python Library for Ranking Evaluation, Comparison, and Fusion 🐍☆630Updated 4 months ago
- Use late-interaction multi-modal models such as ColPali in just a few lines of code.☆836Updated 11 months ago
- Automated Evaluation of RAG Systems☆682Updated 9 months ago
- Code for explaining and evaluating late chunking (chunked pooling)☆481Updated last year
- Fast State-of-the-Art Static Embeddings☆1,964Updated this week
- A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.☆2,040Updated 2 months ago
- A fast, lightweight and easy-to-use Python library for splitting text into semantically meaningful chunks.☆519Updated 2 months ago
- Efficient Retrieval Augmentation and Generation Framework☆1,756Updated 11 months ago
- Enforce the output format (JSON Schema, Regex etc) of a language model☆1,977Updated 4 months ago
- Train Models Contrastively in Pytorch☆770Updated 9 months ago
- The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval☆1,513Updated last year
- Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts) @ NAACL 2024☆2,658Updated 2 weeks ago
- Evaluate your LLM's response with Prometheus and GPT4 💯☆1,025Updated 8 months ago
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆3,008Updated last week
- The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.☆2,416Updated this week
- Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'☆1,635Updated last month
- Train and Infer Powerful Sentence Embeddings with AnglE | 🔥 SOTA on STS and MTEB Leaderboard☆569Updated 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-…☆3,805Updated 7 months ago
- A Collection of BM25 Algorithms in Python☆1,289Updated last year
- DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. 🤖💤☆1,086Updated 11 months ago
- Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.☆2,000Updated this week
- A lightweight library for generating synthetic instruction tuning datasets for your data without GPT.☆817Updated 5 months ago