AnswerDotAI / rerankers
A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.
☆1,375Updated 2 weeks ago
Alternatives and similar repositories for rerankers:
Users that are interested in rerankers are comparing it to the libraries listed below
- Fast lexical search implementing BM25 in Python using Numpy, Numba and Scipy☆1,102Updated last week
- Use late-interaction multi-modal models such as ColPali in just a few lines of code.☆768Updated 2 months ago
- Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cro…☆782Updated 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…☆2,620Updated last week
- Enforce the output format (JSON Schema, Regex etc) of a language model☆1,770Updated last month
- Fast Semantic Text Deduplication☆607Updated 3 weeks ago
- Code for explaining and evaluating late chunking (chunked pooling)☆366Updated 3 months ago
- In-Context Learning for eXtreme Multi-Label Classification (XMC) using only a handful of examples.☆417Updated last year
- Automated Evaluation of RAG Systems☆573Updated 2 weeks ago
- Sharing both practical insights and theoretical knowledge about LLM evaluation that we gathered while managing the Open LLM Leaderboard a…☆1,130Updated 3 months ago
- The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval☆1,178Updated 7 months ago
- Evaluate your LLM's response with Prometheus and GPT4 💯☆901Updated 3 weeks ago
- The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.☆1,698Updated this week
- Bringing BERT into modernity via both architecture changes and scaling☆1,314Updated 2 weeks ago
- High-performance retrieval engine for unstructured data☆1,316Updated this week
- Efficient Retrieval Augmentation and Generation Framework☆1,510Updated 3 months ago
- Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali☆2,038Updated 2 weeks ago
- Fast State-of-the-Art Static Embeddings☆1,281Updated this week
- Fast, Accurate, Lightweight Python library to make State of the Art Embedding☆1,941Updated this week
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends☆1,400Updated this week
- ☆849Updated 7 months ago
- Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-…☆3,386Updated 2 months ago
- RAGChecker: A Fine-grained Framework For Diagnosing RAG☆833Updated 4 months ago
- Framework for enhancing LLMs for RAG tasks using fine-tuning.☆737Updated last month
- DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. 🤖💤☆1,004Updated 2 months ago
- A lightweight library for generating synthetic instruction tuning datasets for your data without GPT.☆764Updated last month
- Superfast AI decision making and intelligent processing of multi-modal data.☆2,531Updated this week
- RankLLM is a Python toolkit for reproducible information retrieval research using rerankers, with a focus on listwise reranking.☆432Updated 2 weeks ago
- Optimizing inference proxy for LLMs☆2,150Updated last week
- Empowering RAG with a memory-based data interface for all-purpose applications!☆1,734Updated last month