A Python Search Engine for Humans 🥸

Unified Learned Sparse Retrieval Framework

SPRINT Toolkit helps you evaluate diverse neural sparse models easily using a single click on any IR dataset.

Fast search index for SPLADE sparse retrieval models implemented in Python using Numpy and Numba

Lite weight wrapper for the independent implementation of SPLADE++ models for search & retrieval pipelines. Models and Library created by Prithivi Da, For PRs and Collaboration checkout the readme.

🚀 Engram-PEFT: An unofficial implementation of DeepSeek Engram. Inject high-capacity conditional memory into LLMs via sparse retrieval PEFT without increasing inference FLOPs / DeepSeek Engram 架构的非官方实现。通过参数高效微调 (PEFT) 为大语言模型注入超大规模条件记忆，支持稀疏更新且不增加推理开销。

Provides a minimal PyTorch implementation of SPLADE

Optimised BAAI/bge-m3 serving with dense + sparse + ColBERT embeddings, async dynamic batching and pipeline GPU inference

OctoVector AI is a high-performance RAG system that combines dense and sparse retrieval with fusion and cross-encoder reranking to deliver precise, context-aware answers.

A controlled experiment evaluating whether hybrid (dense + sparse) retrieval surfaces evidence that dense-only RAG systems misrank—without changing generation behavior.

a grounded, constraint-aware conversational retrieval engine built for the SHL Product Catalog.

Semantic Hybrid Search with Sentence-Transformers + FAISS. Ask any question in plain English. Get the most relevant Wikipedia passages back — ranked by meaning, not just keywords.

A personal knowledge base that ingests PDFs and markdown notes, then answers questions using a hybrid search system combining dense vector search and BM25 with a side by side dashboard showing how each retrieval method performs on any given query.

RAG routing research prototype: Feature-based classifiers learn when to use cheap vs full retrieval/LLM paths based on retrieval difficulty

A Systematic Cross-domain Evaluation of Document Retrievers