lexical-search 开源项目推荐（63 个）

SeekStorm /SeekStorm

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

xhluca /bm25s

Fast BM25 search in Python, powered by Numpy and Numba

PrithivirajDamodaran /FlashRank

轻量级且超快速的搜索和检索流程重新排名。 支持基于大型语言模型（LLM）、交叉编码器等的列表和成对排名重排序。 由Prithivi Da创作，开放公关与合作。

ahr9n /quranic-search-v2

Quranic Lexical/Semantic Search

HiveForensics-AI /knolo-core

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.

Fl0k3n /kfe

Cross-platform Search Engine and File Explorer for Multimedia

mosuka /laurus

Lexically Augmented Unified Retrieval Using Semantics

initial-d /ngram-store

NGramStore: a general-purpose backend for learned n-gram embeddings — compression, storage and exact lookup. FastText and Engram/TinyEngram are application examples.

minhqdao /fortran-mcp

Local MCP server providing curated Fortran documentation for AI-assisted development

machinelearningZH /ai-search_staatsarchiv

Intelligent Document Search for the Staatsarchiv Zurich.

Univeracity /vyral

用于规范数据、检索、持久执行和面向智能体的 AI 的可移植契约与本地优先运行时。

aws-samples /sample-for-amazon-opensearch-service-tutorials-101

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

hyeonsangjeon /pronunciation-mapper

한국어 ASR 질의를 DB 용어로 안전하게 정규화하는 Foundry-first bounded agent. 로컬 발음 후보, Ollama 옵션, V1 호환.

anubhavmaity /wattbot

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

zepdb /zeppelin-embed

Fastest and most accurate embeddable search library for MacOS / Apple Silicon

ahr9n /quran-lexical-search-api

RESTful API for Quranic Lexical Search

Rohith-2 /bm25-fusion

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

omarkamali /semango

🥭 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.

rbeg1 /odigo-elastic-s2l-mcp

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

Nikoo-Asadnejad /Security-Knowledge-Assistant

A local RAG assistant that will answer LLM security questions using retrieved OWASP documentation