AnswerDotAI / rerankersLinks
A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.
☆1,560Updated 4 months ago
Alternatives and similar repositories for rerankers
Users that are interested in rerankers are comparing it to the libraries listed below
Sorting:
- Fast lexical search implementing BM25 in Python using Numpy, Numba and Scipy☆1,358Updated last month
- Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cro…☆868Updated last month
- Use late-interaction multi-modal models such as ColPali in just a few lines of code.☆824Updated 8 months ago
- Automated Evaluation of RAG Systems☆664Updated 6 months ago
- Fast Semantic Text Deduplication & Filtering☆816Updated 2 weeks ago
- The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval☆1,434Updated last year
- Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-…☆3,713Updated 5 months ago
- The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.☆2,255Updated this week
- Code for explaining and evaluating late chunking (chunked pooling)☆453Updated 9 months ago
- Efficient Retrieval Augmentation and Generation Framework☆1,735Updated 9 months ago
- Enforce the output format (JSON Schema, Regex etc) of a language model☆1,943Updated last month
- Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali☆2,513Updated 2 weeks ago
- Fast, Accurate, Lightweight Python library to make State of the Art Embedding☆2,434Updated last month
- High-performance retrieval engine for unstructured data☆1,507Updated 2 months ago
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆2,903Updated this week
- Late Interaction Models Training & Retrieval☆626Updated this week
- Bringing BERT into modernity via both architecture changes and scaling☆1,546Updated 3 months ago
- Fast State-of-the-Art Static Embeddings☆1,863Updated last week
- A lightweight library for generating synthetic instruction tuning datasets for your data without GPT.☆795Updated 3 months ago
- A fast, lightweight and easy-to-use Python library for splitting text into semantically meaningful chunks.☆390Updated 2 months ago
- Evaluate your LLM's response with Prometheus and GPT4 💯☆1,005Updated 5 months ago
- ☆897Updated 11 months ago
- Use LOTUS to process all of your datasets with LLMs and embeddings. Enjoy up to 1000x speedups with fast, accurate query processing, that…☆1,323Updated last week
- Developer APIs to Accelerate LLM Projects☆1,727Updated last year
- DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. 🤖💤☆1,069Updated 8 months ago
- Framework for enhancing LLMs for RAG tasks using fine-tuning.☆750Updated 5 months ago
- A library for prompt engineering and optimization (SAMMO = Structure-aware Multi-Objective Metaprompt Optimization)☆732Updated 3 months ago
- Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts) @ NAACL 2024☆2,418Updated last week
- RankLLM is a Python toolkit for reproducible information retrieval research using rerankers, with a focus on listwise reranking.☆543Updated 2 weeks ago
- In-Context Learning for eXtreme Multi-Label Classification (XMC) using only a handful of examples.☆441Updated last year