https://github.com/TileDB-Inc/TileDB-Vector-Search
Cloud-native vector similarity search and storage with efficient, serverless scale-out
https://github.com/TileDB-Inc/TileDB-Vector-Search
approximate-nearest-neighbor-search embedding-database information-retrieval nearest-neighbor-search python-package tensor-database vector-database vector-search vector-similarity-search
Last synced: 25 days ago
JSON representation
Cloud-native vector similarity search and storage with efficient, serverless scale-out
- Host: GitHub
- URL: https://github.com/TileDB-Inc/TileDB-Vector-Search
- Owner: TileDB-Inc
- License: mit
- Created: 2023-04-13T16:37:50.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2025-12-10T22:01:34.000Z (7 months ago)
- Last Synced: 2025-12-10T22:29:39.191Z (7 months ago)
- Topics: approximate-nearest-neighbor-search, embedding-database, information-retrieval, nearest-neighbor-search, python-package, tensor-database, vector-database, vector-search, vector-similarity-search
- Language: Jupyter Notebook
- Homepage: https://tiledb-inc.github.io/TileDB-Vector-Search/
- Size: 86.1 MB
- Stars: 67
- Watchers: 7
- Forks: 10
- Open Issues: 16
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-vector-databases - TileDB Vector Search - TileDB Vector Search is a scalable open-source vector database that stores and performs approximate nearest neighbor searches on high-dimensional dense and sparse vectors using TileDB's multi-dimensional array storage for petabyte-scale data. Key features include Vamana graph and IVF-PQ indexing, metadata filtering, multi-tenancy, serverless scalability on object stores like S3, and APIs in Python/C++ with gRPC support. Suited for RAG pipelines, recommendation systems, and anomaly detection; excels in sparse vector efficiency and cost savings compared to Milvus or Pinecone, while scaling better than Faiss for large production deployments. ([Read more](/details/tiledb-vector-search.md)) `Open Source` `Scalable ANN` `2026 Production` `Production Use` `2026 Ready` (Core Vector Databases)