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: 3 months 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 (about 2 years ago)
- Default Branch: main
- Last Pushed: 2024-10-29T22:07:35.000Z (8 months ago)
- Last Synced: 2024-10-30T00:40:09.742Z (8 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: 52
- Watchers: 8
- Forks: 6
- Open Issues: 10
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# TileDB Vector Search
_TileDB-Vector-Search_ is a C++ library and Python API for vector search built on top of the [TileDB Storage Engine](https://github.com/TileDB-Inc/TileDB).
Please see the following blog posts for background:
- [Why TileDB as a Vector Database](https://tiledb.com/blog/why-tiledb-as-a-vector-database)
- [TileDB Vector Search 101](https://tiledb.com/blog/tiledb-101-vector-search/)
We have released a [LangChain integration](https://python.langchain.com/docs/integrations/vectorstores/tiledb), with others to come soon.
# Quick Links
- [Build Instructions](https://tiledb-inc.github.io/TileDB-Vector-Search/documentation/Building.html)
- [Documentation](https://tiledb-inc.github.io/TileDB-Vector-Search/)
- [Python API reference](https://tiledb-inc.github.io/TileDB-Vector-Search/documentation/reference/)
# Quick Installation
Pre-built packages are available from [PyPI](https://pypi.org/project/tiledb-vector-search) using pip:
```
pip install tiledb-vector-search
```
Or from the [tiledb conda channel](https://anaconda.org/tiledb/tiledb-vector-search) using
[conda](https://conda.io/docs/) or [mamba](https://github.com/mamba-org/mamba#installation):
```
conda install -c tiledb -c conda-forge tiledb-vector-search
```
# Contributing
We welcome contributions. Please see [`Building`](./documentation/Building.md) 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](./LICENSE).