dense-retrieval 开源项目推荐（210 个）

SeekStorm /SeekStorm

SeekStorm: vector & lexical search - in-process library & multi-tenancy server, in Rust.

nomic-ai /contrastors

Train Models Contrastively in Pytorch

PaddlePaddle /RocketQA

🚀 RocketQA, dense retrieval for information retrieval and question answering, including both Chinese and English state-of-the-art models.

texttron /tevatron

Tevatron - Unified Document Retrieval Toolkit across Scale, Language, and Modality. Demo in SIGIR 2023, SIGIR 2025.

ict-bigdatalab /awesome-pretrained-models-for-information-retrieval

A curated list of awesome papers related to pre-trained models for information retrieval (a.k.a., pretraining for IR).

texttron /hyde

HyDE: Precise Zero-Shot Dense Retrieval without Relevance Labels

SeanLee97 /AnglE

用英语训练并推断强有力的句子嵌入 |🔥 SOTA在STS和MTEB排行榜上

caiyinqiong /Semantic-Retrieval-Models

A curated list of awesome papers for Semantic Retrieval (TOIS Accepted: Semantic Models for the First-stage Retrieval: A Comprehensive Review).

luyug /Condenser

EMNLP 2021 - Pre-training architectures for dense retrieval

AmenRa /retriv

A Python Search Engine for Humans 🥸

Alibaba-NLP /Multi-CPR

[SIGIR 2022] Multi-CPR: A Multi Domain Chinese Dataset for Passage Retrieval

luyug /GC-DPR

Train Dense Passage Retriever (DPR) with a single GPU

ml4bio /Dense-Homolog-Retrieval

自然生物技术：利用深度密集反演实现蛋白质远程同源物的超高速、灵敏检测

jingtaozhan /RepCONC

WSDM'22 Best Paper: Learning Discrete Representations via Constrained Clustering for Effective and Efficient Dense Retrieval

microsoft /SimXNS

SimXNS is a research project for information retrieval. This repo contains official implementations by MSRA NLC team.

DevSinghSachan /art

Code and models for the paper "Questions Are All You Need to Train a Dense Passage Retriever (TACL 2023)"

sebastian-hofstaetter /tas-balanced-dense-retrieval

SIGIR 2021: Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling

jingtaozhan /disentangled-retriever

An easy-to-use python toolkit for flexibly adapting various neural ranking models to target domain.

McGill-NLP /topiocqa

Code and data for reproducing baselines for TopiOCQA, an open-domain conversational question-answering dataset

jingtaozhan /JPQ

CIKM'21: JPQ substantially improves the efficiency of Dense Retrieval with 30x compression ratio, 10x CPU speedup and 2x GPU speedup.