Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
[EMNLP 2024: Demo Oral] RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation
| Date | Stars |
|---|---|
| 2026-07-31 | 312 |
| 2026-08-02 | 312 |
| 2026-08-06 | 312 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# <div align="center">RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation</div> <div align="center"> <a href="https://arxiv.org/abs/2408.11381" target="_blank"><img src=https://img.shields.io/badge/arXiv-b5212f.svg?logo=arxiv></a> <a href="https://huggingface.co/datasets/RAGLAB/data" target="_blank"><img src=https://img.shields.io/badge/%F0%9F%A4%97%20HuggingFace%20Datasets-27b3b4.svg></a> <a href="https://github.com/fate-ubw/RAGLAB/blob/main/LICENSE"><img alt="License" src="https://img.shields.io/badge/LICENSE-MIT-green"></a> <a><img alt="Static Badge" src="https://img.shields.io/badge/made_with-Python-blue"></a> </div> - RAGLAB is a modular, research-oriented open-source framework for Retrieval-Augmented Generation (RAG) algorithms. It offers reproductions of 6 existing RAG algorithms and a comprehensive evaluation system with 10 benchmark datasets, enabling fair comparisons between RAG algorithms and easy expansion for efficient development of new algorithms, datasets, and evaluation metrics.  # News - 2024.10.6: Our paper has been accepted by EMNLP 2024 System Demonstration.🎉 You can find our paper in [RAGLAB](https://arxiv.org/abs/2408.11381). - 2024.9.9: RAGLAB has open-sourced all log files and evaluation files in [evaluation results](https://huggingface.co/datasets/RAGLAB/raglab-eval_results)📌 - 2024.8.20: RAGLAB has open-sourced 4 models🤗: [llama3-8B-baseline](https://huggingface.co/RAGLAB/Llama3-8B-baseline) [selfrag-llama3-8b](https://huggingface.co/RAGLAB/selfrag_llama3-8B) [llama3-70B-adaptor](https://huggingface.co/RAGLAB/Llama3-70B-baseline-adapter) [selfrag-llama3-70B-adaptor](https://huggingface.co/RAGLAB/selfrag_llama3_70B-adapter) - 2024.8.6: RAGLAB is released🌈. # 🌟Features - **Comprehensive RAG Ecosystem:** Supports the entire RAG pipeline from data collection and training to auto-evaluation. - **Advanced Algorithm Implementations:** Reproduces 6 state-of-the-art RAG algorithms, with an easy-to-extend framework for developing new algorithms. - **Interact Mode & Evaluation Mode:** Interact Mode is specifically designed for quickly understanding algorithms. Evaluation Mode is specifically designed for reproducing paper results and scientific research. - **Fair Comparison Platform:** Provides benchmark results for 6 algorithms across 5 task types and 10 datasets. - **Efficient Retriever Client:** Offers local API for parallel access and caching, with average latency under 1 second. - **Versatile Generator Support:** Compatible with 70B+ models, VLLM, and quantization techniques. - **Flexible Instruction Lab:** Customizable instruction templates for various RAG scenarios. # 📎Related works - Interesting RAG applications - [Autosurvey](https://github.com/AutoSurveys/AutoSurvey) # 🔨Install environment - dev environment：pytorch:2.0.1-py3.10-cuda11.8.0-devel-ubuntu22.04 - [install miniconda](https://docs.anaconda.com/free/miniconda/index.html) - git clone RAGLAB ~~~bash https://github.com/fate-ubw/RAGLAB.git ~~~ - create environment from yml file ~~~bash cd RAGLAB conda env create -f environment.yml ~~~ - install flash-attn, en_core_web_sm, punkt manually ~~~bash pip install flash-attn==2.2 python -m spacy download en_core_web_sm python -m nltk.downloader punkt ~~~ # 🤗 Models <details> <summary>raglab need several models please download them</summary> ~~~bash cd RAGLAB mkdir model cd model mkdir output_models # retriever model mkdir colbertv2.0 huggingface-cli download colbert-ir/colbertv2.0 --local-dir colbertv2.0/ --local-dir-use-symlinks False mkdir contriever-msmarco huggingface-cli download facebook/contriever-msmarco --local-dir contriever-msmarco/ --local-dir-use-symlinks False # finetuned generator # 8B model mkdir Llama3-8B-baseline huggingface-cli download RAGLAB/Llama3-8B-baseline --local-dir Llama3-8B-baseline/ --local-dir-use-symlinks
Excerpt of 14,150 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:428d3517f9f60646, topic:rag, topic:retrieval-augmented-generation, desc:retrieval-augmented generation