weaviate/weaviate

Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database​.

What it solves

Weaviate is a cloud-native vector database designed to handle the storage and retrieval of both objects and their corresponding vector embeddings. It solves the problem of performing semantic search at scale, allowing users to find data based on meaning rather than just keywords, while still supporting traditional keyword filtering and hybrid search.

How it works

Weaviate stores data as objects and vectors. It provides a single query interface that combines vector similarity search, keyword filtering (BM25), and reranking. Users can either import pre-computed vectors or use integrated vectorizers from providers like OpenAI, Cohere, and HuggingFace to automatically vectorize data during import. The system is built in Go for high performance and supports horizontal scaling, multi-tenancy, and replication for production environments.

Who it’s for

Developers building AI-powered applications such as Retrieval-Augmented Generation (RAG) systems, semantic and image search engines, recommendation engines, chatbots, and content classification tools.

Highlights

  • Fast Search Performance: Millisecond response times over billions of vectors.
  • Flexible Vectorization: Support for both integrated model providers and custom pre-generated embeddings.
  • Advanced Hybrid Search: Combines semantic, keyword (BM25), and image search in one API call.
  • Integrated RAG & Reranking: Built-in generative search and reranking capabilities for Q&A and summarizers.
  • Production-Ready: Native support for multi-tenancy, RBAC authorization, and horizontal scaling.
  • Cost-Efficient: Includes vector compression and quantization to reduce memory usage.

Related

  • Project
    vearch/vearch

    Vearch is a cloud-native distributed vector database that enables efficient similarity search of embedding vectors for AI applications.

  • Project
    qdrant/qdrant

    A high-performance vector database and similarity search engine written in Rust, designed for storing and retrieving embeddings with advanced filtering and hybrid search capabilities.

  • Project
    rryam/VecturaKit

    VecturaKit is a Swift library that provides an on‑device vector database with hybrid vector + BM25 search. It supports multiple embedding back‑ends (Apple NaturalLanguage, OpenAI‑compatible APIs, swift‑embeddings models, and Apple MLX), custom storage/search plug‑ins, and CLI tools, enabling privacy‑first semantic search in iOS/macOS/watchOS/tvOS/visionOS apps.

  • Project
    Stevenic/vectra

    A local, file-backed, in-memory vector database that supports metadata filtering, cosine similarity, and local or API-based embeddings.

  • Project
    sqliteai/sqlite-vector

    A cross-platform SQLite extension that adds production-grade vector search and quantization to SQLite, enabling efficient semantic search and RAG on the edge and mobile devices.