{"data":{"slug":"supervc-stack-vectorchord","name":"VectorChord","tagline":"Scalable, fast, and disk-friendly vector search in Postgres","github_url":"https://github.com/supervc-stack/VectorChord","owner":"supervc-stack","repo":"VectorChord","owner_avatar_url":"https://avatars.githubusercontent.com/u/284745899?v=4","primary_language":"Rust","stars":1758,"forks":71,"topics":["artificial-intelligence","llmops","postgresql","vector-database","vector-search"],"archived":false,"github_pushed_at":"2026-07-30T06:33:06+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/supervc-stack-vectorchord","markdown_url":"https://www.graphcanon.com/tools/supervc-stack-vectorchord.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/supervc-stack-vectorchord","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=supervc-stack-vectorchord","description":"Scalable, fast, and disk-friendly vector search in Postgres, the successor of pgvecto.rs.","homepage_url":"https://docs.vectorchord.ai/vectorchord/getting-started/overview.html","license":"Other","open_issues":17,"watchers":15,"ai_summary":"VectorChord is a vector database extension for PostgreSQL designed to provide efficient and scalable vector searches. It includes an all-in-one image with various extensions and supports creating indexes for quick retrieval.","readme_excerpt":"## Quick Start\n\nFor new users, we recommend using the Docker image to get started quickly. If you do not prefer Docker, please read [installation guide](https://docs.vectorchord.ai/vectorchord/getting-started/installation.html) for other installation methods.\n\n```bash\ndocker run \\\n  --name vectorchord-demo \\\n  -e POSTGRES_PASSWORD=mysecretpassword \\\n  -p 5432:5432 \\\n  -d ghcr.io/tensorchord/vchord-postgres:pg18-v1.1.1\n```\n\n> [!NOTE]\n> In addition to the base image with the VectorChord extension, we provide an all-in-one image, `tensorchord/vchord-suite:pg17-latest`. This comprehensive image includes all official TensorChord extensions, including `VectorChord`, `VectorChord-bm25` and `pg_tokenizer.rs` . Developers should select an image tag that is compatible with their extension's version, as indicated in [the support matrix](https://github.com/tensorchord/VectorChord-images?tab=readme-ov-file#support-matrix).\n\nThen you can connect to the database using the `psql` command line tool. The default username is `postgres`, and the default password is `mysecretpassword`.\n\n```bash\npsql -h localhost -p 5432 -U postgres\n```\n\nNow you can play with VectorChord!\n\nVectorChord depends on pgvector, including the vector representation. Since you can use them directly, your application can be easily migrated without pain!\n\n```sql\nCREATE EXTENSION IF NOT EXISTS vchord CASCADE;\n```\n\nSimilar to pgvector, you can create a table with vector column and insert some rows to it.\n\n```sql\nCREATE TABLE items (id bigserial PRIMARY KEY, embedding vector(3));\nINSERT INTO items (embedding) SELECT ARRAY[random(), random(), random()]::real[] FROM generate_series(1, 1000);\n```\n\nWith VectorChord, you can create `vchordrq` indexes.\n\n```SQL\nCREATE INDEX ON items USING vchordrq (embedding vector_l2_ops);\n```\n\nAnd then perform a vector search using `SELECT ... ORDER BY ... LIMIT ...`.\n\n```SQL\nSELECT * FROM items ORDER BY embedding <-> '[3,1,2]' LIMIT 5;\n```\n\nFor more usage, please read:\n\n- [Indexing](https://docs.vectorchord.ai/vectorchord/usage/indexing.html)\n- [Multi-Vector Retrieval](https://docs.vectorchord.ai/vectorchord/usage/indexing-with-maxsim-operators.html)\n- [Quantization Types](https://docs.vectorchord.ai/vectorchord/usage/quantization-types.html)\n- [Graph Index](https://docs.vectorchord.ai/vectorchord/usage/graph-index.html)\n- [Quantization Types](https://docs.vectorchord.ai/vectorchord/usage/quantization-types.html)\n- [Similarity Filter](https://docs.vectorchord.ai/vectorchord/usage/range-query.html)\n- [PostgreSQL Tuning](https://docs.vectorchord.ai/vectorchord/usage/performance-tuning.html)\n- [Monitoring](https://docs.vectorchord.ai/vectorchord/usage/monitoring.html)\n- [Fallback Parameters](https://docs.vectorchord.ai/vectorchord/usage/fallback-parameters.html)\n- [Measure Recall](https://docs.vectorchord.ai/vectorchord/usage/measure-recall.html)\n- [Prewarm](https://docs.vectorchord.ai/vectorchord/usage/prewarm.html)\n- [Prefilter](https://docs.vectorchord.ai/vectorchord/usage/prefilter.html)\n- [Prefetch](https://docs.vectorchord.ai/vectorchord/usage/prefetch.html)\n- [Rerank in Table](https://docs.vectorchord.ai/vectorchord/usage/rerank-in-table.html)\n- [Partitioning Tuning](https://docs.vectorchord.ai/vectorchord/usage/partitioning-tuning.html)\n- [External Build](https://docs.vectorchord.ai/vectorchord/usage/external-index-precomputation.html)\n\n---\n\n## License\n\nThis software is licensed under a dual license model:\n\n1. **GNU Affero General Public License v3 (AGPLv3)**: You may use, modify, and distribute this software under the terms of the AGPLv3.\n\n2. **Elastic License v2 (ELv2)**: You may also use, modify, and distribute this software under the Elastic License v2, which has specific restrictions.\n\nYou may choose either license based on your needs. We welcome any commercial collaboration or support, so please email us <vectorchord-inquiry@tensorchord.ai> with any questions or requests regarding the licenses.\n\n[cost-estimation]: https://github.com/user-","github_created_at":"2024-09-03T07:39:46+00:00","created_at":"2026-07-07T17:42:47.475314+00:00","updated_at":"2026-08-02T18:01:09.73256+00:00","categories":[{"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":"artificial-intelligence","name":"artificial-intelligence"},{"slug":"llmops","name":"llmops"},{"slug":"postgresql","name":"postgresql"},{"slug":"vector-database","name":"vector-database"},{"slug":"vector-search","name":"vector-search"}],"trust":{"provenance":{"is_fork":false,"github_id":851492630,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-02T18:01:08.916Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":0,"days_since_push":3,"last_release_at":"2026-02-28T04:04:07Z"},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T23:19:35.540Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-02T18:01:09.351Z"},"languages":{"value":["rust"],"source":"github.language","observed_at":"2026-08-02T18:01:09.351Z"},"license_spdx":{"value":"Other","source":"github.license","observed_at":"2026-08-02T18:01:09.351Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["- When you need efficient vector searches within a PostgreSQL database with compatibility to existing systems using pgvector","- For applications requiring an all-in-one Docker image that includes multiple extensions, such as `VectorChord`, `VectorChord-bm25`, and `pg_tokenizer.rs`"],"when_not_to_use":["- If you cannot use PostgreSQL or if your application already uses another database system with specific vector search capabilities","- When detailed customization beyond what VectorChord provides, such as deep integration with unique machine learning frameworks not natively supported by the extension, is required"],"source":"enrich:decision_facts","observed_at":"2026-07-12T11:04:02.698Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"__VectorChord__ - Scalable and disk-friendly vector search in PostgreSQL."}]}}