{"data":{"slug":"weaviate-weaviate","name":"weaviate","tagline":"An open-source vector database for vector search and structured filtering","github_url":"https://github.com/weaviate/weaviate","owner":"weaviate","repo":"weaviate","owner_avatar_url":"https://avatars.githubusercontent.com/u/37794290?v=4","primary_language":"Go","stars":16819,"forks":1403,"topics":["approximate-nearest-neighbor-search","generative-search","grpc","hnsw","hybrid-search","image-search","information-retrieval","mlops","nearest-neighbor-search","neural-search","recommender-system","search-engine","semantic-search","semantic-search-engine","similarity-search","vector-database","vector-search","vector-search-engine","vectors","weaviate"],"archived":false,"github_pushed_at":"2026-09-18T08:26:37+00:00","maintenance_label":"Very active","stars_delta_30d":138,"url":"https://www.graphcanon.com/tools/weaviate-weaviate","markdown_url":"https://www.graphcanon.com/tools/weaviate-weaviate.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/weaviate-weaviate","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=weaviate-weaviate","description":"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​.","homepage_url":"https://weaviate.io/developers/weaviate/","license":"Other","open_issues":735,"watchers":141,"ai_summary":"Weaviate is an open-source vector database that supports vector search and structured filtering, offering fault tolerance and scalability. It supports deployment via Docker, Kubernetes, and cloud services.","readme_excerpt":"## Installation\n\nWeaviate offers multiple installation and deployment options:\n\n- [Docker](https://docs.weaviate.io/deploy/installation-guides/docker-installation)\n- [Kubernetes](https://docs.weaviate.io/deploy/installation-guides/k8s-installation)\n- [Weaviate Cloud](https://console.weaviate.cloud)\n\nSee the [installation docs](https://docs.weaviate.io/deploy) for more deployment options, such as [AWS](https://docs.weaviate.io/deploy/installation-guides/aws-marketplace) and [GCP](https://docs.weaviate.io/deploy/installation-guides/gcp-marketplace).\n\n---\n\n## Getting started\n\nYou can easily start Weaviate and a local vector embedding model with [Docker](https://docs.docker.com/desktop/).\nCreate a `docker-compose.yml` file:\n\n```yml\nservices:\n  weaviate:\n    image: cr.weaviate.io/semitechnologies/weaviate:1.36.0\n    ports:\n      - \"8080:8080\"\n      - \"50051:50051\"\n    environment:\n      ENABLE_MODULES: text2vec-model2vec\n      MODEL2VEC_INFERENCE_API: http://text2vec-model2vec:8080\n\n  # A lightweight embedding model that will generate vectors from objects during import\n  text2vec-model2vec:\n    image: cr.weaviate.io/semitechnologies/model2vec-inference:minishlab-potion-base-32M\n```\n\nStart Weaviate and the embedding service with:\n\n```bash\ndocker compose up -d\n```\n\nInstall the Python client (or use another [client library](#client-libraries-and-apis)):\n\n```bash\npip install -U weaviate-client\n```\n\nThe following Python example shows how easy it is to populate a Weaviate database with data, create vector embeddings and perform semantic search:\n\n```python\nimport weaviate\nfrom weaviate.classes.config import Configure, DataType, Property\n\n---\n\n## License\n\nBSD 3-Clause License. See [LICENSE](./LICENSE) for details.","github_created_at":"2016-03-30T15:03:17+00:00","created_at":"2026-07-07T17:43:41.021121+00:00","updated_at":"2026-09-20T04:31:29.755603+00:00","categories":[{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"},{"slug":"vector-databases","name":"Vector Databases","url":"https://www.graphcanon.com/categories/vector-databases","markdown_url":"https://www.graphcanon.com/categories/vector-databases.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/vector-databases"}],"tags":[{"slug":"approximate-nearest-neighbor-search","name":"approximate-nearest-neighbor-search"},{"slug":"grpc","name":"grpc"},{"slug":"hnsw","name":"hnsw"},{"slug":"hybrid-search","name":"hybrid-search"},{"slug":"image-search","name":"image-search"},{"slug":"information-retrieval","name":"information retrieval"},{"slug":"mlops","name":"mlops"},{"slug":"nearest-neighbor-search","name":"nearest-neighbor-search"}],"trust":{"provenance":{"is_fork":false,"github_id":55072677,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-18T08:32:03.572Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":30,"days_since_push":0,"last_release_at":"2026-09-15T20:18:04Z","stars_delta_30d":138,"open_issues_delta_30d":115},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":11,"high_count":0,"last_scan_at":"2026-09-18T08:32:06.175Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-18T08:32:02.455Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-09-18T08:32:02.455Z","managed_saas":false},"languages":{"value":["go","python"],"source":"github.language+pyproject.toml","observed_at":"2026-09-18T08:32:02.455Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-09-18T08:32:02.455Z"},"license_spdx":{"value":"Other","source":"github.license","observed_at":"2026-09-18T08:32:02.455Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need a vector database that supports both vector search and structured filtering, as Weaviate uniquely combines these capabilities.","If you require a cloud-native database with fault tolerance and scalability, Weaviate is designed to meet these needs.","For projects that need deployment flexibility, Weaviate supports Docker, Kubernetes, and cloud services, making it suitable for various deployment environments."],"when_not_to_use":["If your project strictly requires a proprietary solution, Weaviate, being open-source under the BSD 3-Clause License, may not be the best fit.","If your application does not require vector search or structured filtering, Weaviate's specialized capabilities might be overkill.","For teams that prefer a different programming language, Weaviate is primarily developed in Go, which might not align with all development environments."],"source":"enrich:decision_facts","observed_at":"2026-09-18T10:12:48.922Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Weaviate is an open-source vector database that supports vector search and structured filtering, offering fault tolerance and scalability. It supports deployment via Docker, Kubernetes, and cloud services."}]}}