Tools · SPBoucher
Menu

Weaviate

by Weaviate B.V. · Database

Open-source vector database in Go with pluggable vectorizer modules, hybrid BM25 and vector search, multi-tenancy and a managed cloud

BSD-3-Clause licenseOpen sourceFreemiumUsage-basedEnterpriseSelf-hostedCloudSelf-hostable
Visit official site Compare

Link verified Nov 2, 2026

Overview

Weaviate is a vector database written in Go by Weaviate B.V. Objects are stored in classes (collections) with a schema, each carrying one or more vectors; search combines HNSW nearest-neighbor retrieval with BM25 keyword scoring in a single hybrid query and supports filters, grouping and generative or reranking modules. A distinguishing feature is the module system: vectorizer modules call OpenAI, Cohere, Google, Hugging Face or local models so that the database embeds objects on write and queries on read, which removes that step from application code.

The server exposes REST, gRPC and GraphQL APIs with clients for Python, TypeScript, Go and Java, supports multi-tenancy with per-tenant shards, replication and horizontal scaling, and offers vector compression options. Most of the repository is BSD-3-Clause; code under the wl directory is proprietary and enabled with an enterprise license key. Weaviate Cloud provides managed serverless and dedicated clusters.

Weaviate suits teams who want embedding generation, hybrid retrieval and RAG helpers in one service. Trade-offs are a heavier schema model than minimal stores, dependence on module configuration for embeddings, and enterprise-only features behind the commercial license.

Capabilities

  • HNSW vector search with filters and hybrid BM25 fusion
  • Vectorizer, reranker and generative modules calling external or local models
  • REST, gRPC and GraphQL APIs
  • Multi-tenancy with isolated shards
  • Replication and horizontal scaling
  • Vector compression (PQ, BQ, SQ)

Typical workflows

  1. RAG backend that embeds documents on ingest
  2. Hybrid search for product or document catalogs
  3. Multi-tenant SaaS search with per-customer isolation

Strengths

  • Embedding generation handled by modules
  • Hybrid search in one query
  • Managed cloud and self-hosted options

Limitations

  • Enterprise features are proprietary (wl directory)
  • Schema and module configuration add setup effort
  • GraphQL API has a learning curve

Prerequisites

  • Docker, Kubernetes or Weaviate Cloud
  • API keys for external vectorizer modules if used

Who it is for

  • Developers building RAG and semantic search
  • Teams needing multi-tenant vector search

Alternatives & comparison

  • Chroma

    Open-source embedding database with a minimal Python and JavaScript API, usable in-process, as a server or through Chroma Cloud

    Open sourceOpen source
  • Milvus

    Open-source vector database from Zilliz with Lite, Standalone and Distributed deployments, many index types and GPU acceleration

    Open sourceOpen source
  • pgvector

    PostgreSQL extension adding vector types, distance operators and HNSW/IVFFlat indexes for similarity search inside the database

    Open sourceOpen source
  • Pinecone

    Fully managed, proprietary vector database service with serverless indexes, namespaces, metadata filtering and integrated embedding and reranking

    ProprietaryFreemium
  • Qdrant

    Open-source vector search engine written in Rust with filterable HNSW indexes, sparse and multi-vector support, REST/gRPC APIs and a managed cloud

    Open sourceOpen source
Compare Weaviate with its alternatives →

Sources & verification

Primary sources consulted for this record. Claims are tied to the fields each source supports; the automated link checker re-verifies every URL on a schedule.

  • License
    Weaviate LICENSE

    https://github.com/weaviate/weaviate/blob/main/LICENSE

    Supports: license_spdx, source_model

    BSD-3-Clause outside the wl directory; wl directory is proprietary enterprise code

    checked Nov 1, 2026
  • Official documentation
    Weaviate Documentation

    https://docs.weaviate.io/weaviate

    Supports: capabilities, interfaces, languages

    checked Nov 1, 2026
  • Official site
    Weaviate

    https://weaviate.io/

    Supports: name, summary

    checked Nov 1, 2026
  • Pricing page
    Weaviate pricing

    https://weaviate.io/pricing

    Supports: pricing_model

    checked Nov 1, 2026
  • Repository
    weaviate/weaviate

    https://github.com/weaviate/weaviate

    Supports: repo_url

    checked Nov 1, 2026
Confidence
High
Reviewed
Nov 1, 2026
Links
Broken · Nov 2, 2026

Spotted an error?

Broken link, outdated license, wrong category, or a tool that no longer exists? Tell us; reports are reviewed by the editor.

Elasticsearch

Elastic N.V. · Vector databases

In-depth entry

Distributed search and analytics engine on Apache Lucene with full-text, aggregations, vector search and ES|QL; triple-licensed AGPL, SSPL and Elastic License

AGPL-3.0-only OR SSPL-1.0 OR Elastic-2.0Open sourceFreeSelf-hostedNov 2, 2026

Meilisearch

Meili SAS · Vector databases

Rust search engine for application search-as-you-type with typo tolerance, faceting and hybrid semantic search; MIT core plus BSL enterprise parts

MIT AND BUSL-1.1Open sourceFreeSelf-hostedNov 2, 2026

OpenSearch

OpenSearch Software Foundation (Linux Foundation) · Vector databases

Apache-2.0 search and analytics suite forked from Elasticsearch and Kibana, governed by the OpenSearch Software Foundation

Apache-2.0Open sourceFreeSelf-hostedBroken

Typesense

Typesense, Inc. · Vector databases

GPL-licensed in-memory search engine in C++ offering typo-tolerant instant search, faceting, vector and hybrid search, with Typesense Cloud hosting

GPL-3.0Open sourceFreeSelf-hostedNov 2, 2026