SeekStorm: vector & lexical search - in-process library & multi-tenancy server, in Rust.
-
Updated
Sep 8, 2026 - Rust
SeekStorm: vector & lexical search - in-process library & multi-tenancy server, in Rust.
Fast BM25 search in Python, powered by Numpy and Numba
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.
Knolo turns documents into a verifiable Knowledge Image (.knolo): one portable file you can mount, query, and prove. Deterministic retrieval, cryptographic roots, fail-closed verification. Local-first. No vector DB required.
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.
GenPark AI Agent Skill - Okapi BM25 sparse lexical search engine, Robertson-Spärck Jones IDF, and length normalization for hybrid RAG.
GenPark AI Agent Skill - Okapi BM25 sparse lexical search engine, Robertson-Spärck Jones IDF, and length normalization for hybrid RAG.
An end-to-end private Opensearch cluster deployment example. This repo demonstrates various Keyword search functionalities available through Opensearch
한국어 ASR 질의를 DB 용어로 안전하게 정규화하는 Foundry-first bounded agent. 로컬 발음 후보, Ollama 옵션, V1 호환.
Portable contracts and local-first runtimes for canonical data, retrieval, durable execution, and agent-facing AI.
My implementation for a kaggle competition: https://www.kaggle.com/competitions/WattBot2025
RESTful API for Quranic Lexical Search
Fastest and most accurate embeddable search library for MacOS / Apple Silicon
An ultra-fast BM25 retriever with support for multiple variants and meta-data filtering.
Elasticsearch MCP Server with a Semantic-to-Lexical layer for Business rules
🥭 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.
Reverse Wiktionary is a semantic lexical search app. This repository contains the online serving layer: FastAPI, Qdrant query integration, Redis-backed UI state, Docker/Nginx deployment files, and Azure beta deployment scripts. Offline artifact production and test harnesses live in companion repositories.
To associate your repository with the lexical-search topic, visit your repo's landing page and select "manage topics."