Explore Directory

TileDB Vector Search

Open source MIT Jupyter Notebook

Website GitHub

Stars

Forks

Issues

Watchers

4 months

Last Commit

Object Storage Vector Databases Database

About TileDB Vector Search

Cloud-native vector similarity search and storage with efficient, serverless scale-out

Platforms

Web Self-hosted Cloud

Languages

Jupyter Notebook

Links

Website Source Code

Need Help Installing TileDB Vector Search?

We provide expert installation service for this software. Our team will install, configure, and secure TileDB Vector Search on your server. plans start at just $30.

Hire an Expert

Alternatives to TileDB Vector Search

View All

SeekStorm

SeekStorm: vector & lexical search - in-process library & multi-tenancy server, in Rust.

1.9K

Azure Sql Db Vector Search

Samples about using vector in SQL Server and Azure SQL

CortexaDB

It is a simple, fast, and hard-durable embedded database designed specifically for AI agent memory. It provides a single-file-like experience (no server required) but with native support for vectors,

Vecdb

a vector embedding database with multiple storage engines and AI embedding integrations

Sochdb

SochDB is a high-performance embedded, ACID-compliant vector database purpose-built for AI agents and memory

Published by

tiledb-inc

Visit View Profile

TileDB Vector Search

View on GitHub

TileDB Vector Search

TileDB-Vector-Search is a C++ library and Python API for vector search built on top of the TileDB Storage Engine.

Please see the following blog posts for background:

We have released a LangChain integration, with others to come soon.

Quick Links

Quick Installation

Pre-built packages are available from PyPI using pip:

pip install tiledb-vector-search

Or from the tiledb conda channel using conda or mamba:

conda install -c tiledb -c conda-forge tiledb-vector-search

Contributing

We welcome contributions. Please see Building for development-build instructions. For large new features, please open an issue to discuss goals and approach in order to ensure a smooth PR integration and review process. All contributions must be licensed under the repository's MIT License.