xhluca / bm25sLinks
Fast lexical search implementing BM25 in Python using Numpy, Numba and Scipy
☆1,335Updated 3 weeks ago
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.☆1,543Updated 4 months ago
- Late Interaction Models Training & Retrieval☆608Updated this week
- Fast Semantic Text Deduplication & Filtering☆810Updated 3 weeks ago
- Bringing BERT into modernity via both architecture changes and scaling☆1,525Updated 3 months ago
- Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cro…☆863Updated 2 weeks ago
- SPLADE: sparse neural search (SIGIR21, SIGIR22)☆912Updated last year
- Easily embed, cluster and semantically label text datasets☆576Updated last year
- RankLLM is a Python toolkit for reproducible information retrieval research using rerankers, with a focus on listwise reranking.☆536Updated 2 weeks ago
- Automated Evaluation of RAG Systems☆658Updated 6 months ago
- A fast, lightweight and easy-to-use Python library for splitting text into semantically meaningful chunks.☆375Updated last month
- ⚡️A Blazing-Fast Python Library for Ranking Evaluation, Comparison, and Fusion 🐍☆594Updated last month
- Use late-interaction multi-modal models such as ColPali in just a few lines of code.☆826Updated 8 months ago
- Efficient Retrieval Augmentation and Generation Framework☆1,719Updated 8 months ago
- Code for explaining and evaluating late chunking (chunked pooling)☆453Updated 9 months ago
- Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts) @ NAACL 2024☆2,359Updated last week
- Evaluate your LLM's response with Prometheus and GPT4 💯☆995Updated 5 months ago
- A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.☆1,963Updated 3 months ago
- The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval☆1,425Updated last year
- Enforce the output format (JSON Schema, Regex etc) of a language model☆1,930Updated last month
- Train Models Contrastively in Pytorch☆749Updated 6 months ago
- Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'☆1,596Updated 8 months ago
- The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.☆2,231Updated this week
- Train and Infer Powerful Sentence Embeddings with AnglE | 🔥 SOTA on STS and MTEB Leaderboard☆555Updated 6 months ago
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆2,899Updated this week
- Fast State-of-the-Art Static Embeddings☆1,846Updated 2 weeks ago
- Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.☆2,645Updated this week
- DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. 🤖💤☆1,062Updated 7 months ago
- Fast, Accurate, Lightweight Python library to make State of the Art Embedding☆2,400Updated last month
- MTEB: Massive Text Embedding Benchmark☆2,859Updated this week
- HyDE: Precise Zero-Shot Dense Retrieval without Relevance Labels☆554Updated 9 months ago