# 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​.

Repository: https://github.com/weaviate/weaviate
Canonical: https://ross.abutalabs.com/products/weaviate
Homepage: https://weaviate.io/developers/weaviate/
Language: Go
License: BSD-3-Clause
License Family: permissive
Topics: search-engine, semantic-search, semantic-search-engine, vector-search, vector-search-engine, vector-database, approximate-nearest-neighbor-search, image-search, hnsw, information-retrieval, mlops, nearest-neighbor-search, neural-search, recommender-system, similarity-search, vectors, generative-search, hybrid-search, weaviate, grpc
Last push: 2026-08-26T21:58:09+00:00

## Health v2 (maintenance only)
Score: 95/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 100
- inputs: {"age_days": 3808, "days_push": 7, "days_rel": 6, "gap_med": 1.0, "n_releases_24m": 291}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 16754, forks 1377 (observed 2026-08-28T04:11:17.146978+00:00)

## What it is
Weaviate is an open-source, cloud-native vector database written in Go that stores both objects and vector embeddings, combining vector similarity search with structured filtering, hybrid keyword search, and integrated RAG. It supports automatic vectorization via model provider integrations (OpenAI, Cohere, Hugging Face, etc.) or importing pre-computed embeddings, with multi-tenancy, replication, and RBAC for production deployments.

## Use cases
- build a semantic search engine over documents
- store and query vector embeddings with metadata filtering
- build a RAG pipeline with retrieval and generative models
- power a recommendation engine with similarity search
- search images by visual similarity
- build a chatbot with persistent vector memory
- run hybrid keyword plus vector search
- self-host a scalable vector database on Kubernetes

## When to choose
- you need a production-grade vector database with filtering, replication, and multi-tenancy
- you want integrated embedding and generative model providers in one query interface
- you need hybrid search combining BM25-style keyword and vector similarity
- you plan to scale to billions of vectors on Docker or Kubernetes

## When to avoid
- you only need a lightweight in-process vector index for a small dataset
- your workload is purely relational/SQL with no similarity search
- you need a fully embedded database with no server component (embedded mode is experimental)
- you want to avoid telemetry or cloud service dependencies entirely

## Facets
- artifact type: service
- maturity: stable
- function: vector-database, search-engine, database, rag, llm-inference
- domain: databases, machine-learning, artificial-intelligence, developer-tools
- platform: cloud, self-hosted, go, cross-platform
- tags: semantic-search, vector-search, hnsw, hybrid-search, embeddings, multi-tenancy, grpc, recommender-systems, similarity-search, search, retrieval-augmented-generation, docker, kubernetes

## Member repositories
- weaviate/weaviate (main) score 95

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:17.146978+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:04:45.732267+00:00, confidence not recorded.
  - readme: https://github.com/weaviate/weaviate (fetched 2026-08-28T04:11:17.146978+00:00, sha 7734b780ad63)
  - homepage: https://weaviate.io/developers/weaviate/ (fetched 2026-08-29T08:02:03.368021+00:00, sha 9a931e88e75e)
  - site_page: https://docs.weaviate.io/weaviate/model-providers (fetched 2026-08-29T08:02:03.377199+00:00, sha ce9b295f9c7c)
  - site_page: https://docs.weaviate.io/weaviate/release-notes (fetched 2026-08-29T08:02:03.379036+00:00, sha 967d577d596a)
  - site_page: https://docs.weaviate.io/weaviate/quickstart (fetched 2026-08-29T08:02:03.380729+00:00, sha 8bb384fa2f3a)
  - site_page: https://docs.weaviate.io/deploy (fetched 2026-08-29T08:02:03.383138+00:00, sha 6763e0f41055)
  - site_page: https://docs.weaviate.io/deploy/installation-guides/docker-installation (fetched 2026-08-29T08:02:03.386580+00:00, sha 3a2e1c2fb8b7)
  - site_page: https://docs.weaviate.io/deploy/installation-guides/k8s-installation (fetched 2026-08-29T08:02:03.388327+00:00, sha 98fb352a446b)
  - site_page: https://docs.weaviate.io/deploy/installation-guides/embedded (fetched 2026-08-29T08:02:03.390190+00:00, sha cf7258403575)
  - site_page: https://weaviate.io/product/integrations (fetched 2026-08-29T08:02:03.384690+00:00, sha a78b2d911a9b)
- Data as of 2026-08-30T08:39:29.467469+00:00.