# \[ANN\] IVFADC.jl inverse file system for billion-scale ANN search

**URL:** <https://discourse.julialang.org/t/ann-ivfadc-jl-inverse-file-system-for-billion-scale-ann-search/27025>\
**Category:** Package Announcements\
**Created:** [July 31, 2019, 10:14am UTC](https://discourse.julialang.org/t/ann-ivfadc-jl-inverse-file-system-for-billion-scale-ann-search/27025 "2019-07-31T10:14:16Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![zgornel](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/zgornel/32/217487_2.png) [@zgornel](https://discourse.julialang.org/u/zgornel)\
**Post date:** [July 31, 2019, 10:14am UTC](https://discourse.julialang.org/t/ann-ivfadc-jl-inverse-file-system-for-billion-scale-ann-search/27025/1 "2019-07-31T10:14:16Z")

</div>

[IVFADC.jl](https://github.com/zgornel/IVFADC.jl) is an inverse index for billion-scale ANN search.  
The package is still experimental and not registered; building and index and adding/deleting/searching points are the opperations supported.  
Facebook’s [FAISS](https://github.com/facebookresearch/faiss) implements it. The original publication can be found [here](https://lear.inrialpes.fr/pubs/2011/JDS11/jegou_searching_with_quantization.pdf)