embedding-search 开源项目推荐（20 个）

dingodb /dingo

A multi-modal vector database that supports upserts and vector queries using unified SQL (MySQL-Compatible) on structured and unstructured data, while meeting the requirements of high concurrency and ultra-low latency.

VQLite /VQLite

VQLite - Simple and Lightweight Vector Search Engine based on Google ScaNN

dannyl1u /doppelganger

Github Issues + AI 代码审查的相似性检测

yousef-rafat /Magna

Magna is an AI-powered embedding similarity search tool for searching within large documents.

DavidBelicza /semantic-search

👀 Semantic search over PDF, Markdown, and source code; chunks and indexes files into AI embeddings in a vector database for meaning-based search.

DataCanvasIO /dingo

A multi-modal vector database that supports upserts and vector queries using unified SQL (MySQL-Compatible) on structured and unstructured data, while meeting the requirements of high concurrency and ultra-low latency.

rajathshttgr /zoro-db

Vector Search Engine for the next generation of AI applications

lightfeed /sdk

用于搜索和筛选 Web 数据的 Lightfeed SDK

yousefkhaled2005 /distributed-vector-engine

High-performance distributed vector database & embedding search engine in Rust, Python, TypeScript, and Go with SIMD HNSW indexing.

dmae3 /redisearch-embedding-search-sample

Embedding Search sample with RediSearch

akarauser /pixel-match

Image Search

sunsided /firestorm

该项目在 GitHub 上没有填写描述

TCA166 /static-embed-db

Solution for static embedding search

vitistatyagi /Sentence-embedding-search

The project demonstrates the fundamental concept behind semantic search, where similarity is based on meaning rather than exact keyword matches.

scriptstar /vector-db-benchmark

A production-grade benchmarking suite that evaluates vector databases (Qdrant, Milvus, Weaviate, ChromaDB, Pinecone, SQLite, TopK) for music semantic search applications. Features automated performance testing, statistical analysis across 15-20 iterations, real-time web UI for database comparison, and comprehensive reporting with production.

1055I3 /protseq_retriever

Context-aware protein sequence retrieval and refinement system. Features embedding-based similarity search, biological context refinement, and structured LLM extraction.

mohdwaseem /rag-chat

A full-stack Retrieval-Augmented Generation (RAG) chatbot application with multi-language support

dmae3 /voyager-sample

Embedding Search sample with Voyager

sakshammaurya /production-rag-api

Production-style RAG API built with FastAPI, PostgreSQL and pgvector, featuring PDF ingestion, semantic retrieval, grounded answers, citations and evaluation.

wzhongyou /flux

轻量级向量数据库召回引擎。C++17 实现，自研 HNSW / IVF / BM25，单二进制部署，HTTP API 即开即用。