SeekStorm - sub-millisecond full-text search library & multi-tenancy server in Rust

Fast lexical search implementing BM25 in Python

Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cross-encoders and more. Created by Prithivi Da, open for PRs & Collaborations.

Quranic Lexical/Semantic Search

Cross-platform Search Engine and File Explorer for Multimedia

Lexical Augmented Unified Retrieval Using Semantics

Intelligent Document Search for the Staatsarchiv Zurich.

An end-to-end private Opensearch cluster deployment example. This repo demonstrates various Keyword search functionalities available through Opensearch

KnoLo Core is a local-first knowledge base engine built for small language models (LLMs). It packages your documents into a compact .knolo file and enables fully deterministic querying — no embeddings, no vector databases, no cloud services required. Designed for on-device and edge LLM deployments.

RESTful API for Quranic Lexical Search

Simple lexicon matcher against a text

My implementation for a kaggle competition: https://www.kaggle.com/competitions/WattBot2025

An ultra-fast BM25 retriever with support for multiple variants and meta-data filtering.

🥭 Semango is a hybrid search engine that combines lexical (BM25) and semantic (vector) search. It ships with an MCP server, a simple HTTP API and optional embedded UI.

Lexical search based on partitioned index of hashed words in object storage

A Python-based assistant for Obsidian notes that provides powerful and efficient utilities to aid in knowledge management and research. Includes lexical search with BM25S.

Elasticsearch MCP Server with a Semantic-to-Lexical layer for Business rules

Overview of open-source lexical search libraries and servers

Baseline models for searching for movie plots from Wikipedia articles. Techniques include BM25 (lexical search), bi/cross-encoding (semantic search), and retrieval-augmented generation (RAG) using Mistal 7B through Fireworks.ai.

Benchmark comparing BM25, vector, and hybrid retrieval strategies using Claude agents and MCP tools