Add Qdrant 0.10 release article (for SEO)

This commit is contained in:
Kacper Łukawski
2022-12-06 12:29:45 +01:00
parent 5c53ca2afb
commit 05dfa3a97e
7 changed files with 116 additions and 0 deletions
@@ -0,0 +1,50 @@
---
title: Qdrant 0.10 released
short_description: A short review of all the features introduced in Qdrant 0.10
description: Qdrant 0.10 brings a lot of changes. Check out what's new!
preview_dir: /articles_data/qdrant-0-10-release/preview
small_preview_image: /articles_data/qdrant-0-10-release/new-svgrepo-com.svg
social_preview_image: /articles_data/qdrant-0-10-release/preview/social_preview.jpg
weight: 70
author: Kacper Łukawski
author_link: https://medium.com/@lukawskikacper
date: 2022-09-19T13:30:00+02:00
draft: false
---
Qdrant 0.10 is a new version that brings a lot of performance improvements, but also some new features which
were heavily requested by our users. Here is an overview of what has changed.
## Storing multiple vectors per object
Previously, if you wanted to use semantic search with multiple vectors per object, you had to create separate collections
for each vector type. This was even if the vectors shared some other attributes in the payload. With Qdrant 0.10, you can
now store all of these vectors together in the same collection, which allows you to share a single copy of the payload.
This makes it easier to use semantic search with multiple vector types, and reduces the amount of work you need to do to
set up your collections.
## Batch vector search
Previously, you had to send multiple requests to the Qdrant API to perform multiple non-related tasks. However, this
can cause significant network overhead and slow down the process, especially if you have a poor connection speed.
Fortunately, the [new batch search feature](https://blog.qdrant.tech/batch-vector-search-with-qdrant-8c4d598179d5) allows
you to avoid this issue. With just one API call, Qdrant will handle multiple search requests in the most efficient way
possible. This means that you can perform multiple tasks simultaneously without having to worry about network overhead
or slow performance.
## Built-in ARM support
To make our application accessible to ARM users, we have compiled it specifically for that platform. If it is not
compiled for ARM, the device will have to emulate it, which can slow down performance. To ensure the best possible
experience for ARM users, we have created Docker images specifically for that platform. Keep in mind that using
a limited set of processor instructions may affect the performance of your vector search. Therefore, [we have tested
both ARM and non-ARM architectures using similar setups to understand the potential impact on performance
](https://blog.qdrant.tech/qdrant-supports-arm-architecture-363e92aa5026).
## Full-text filtering
Qdrant is a vector database that allows you to quickly search for the nearest neighbors. However, you may need to apply
additional filters on top of the semantic search. Up until version 0.10, Qdrant only supported keyword filters. With the
release of Qdrant 0.10, [you can now use full-text filters](https://blog.qdrant.tech/qdrant-introduces-full-text-filters-and-indexes-9a032fcb5fa)
as well. This new filter type can be used on its own or in combination with other filter types to provide even more
flexibility in your searches.
@@ -0,0 +1,66 @@
<?xml version="1.0" encoding="iso-8859-1"?>
<!-- Generator: Adobe Illustrator 19.0.0, SVG Export Plug-In . SVG Version: 6.00 Build 0) -->
<svg version="1.1" id="Layer_1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" x="0px" y="0px"
viewBox="0 0 263.976 263.976" style="enable-background:new 0 0 263.976 263.976;" xml:space="preserve">
<g>
<g>
<g>
<path d="M234.475,93.137h-34.309l-54.913-75.693c-0.009-0.012-0.019-0.022-0.028-0.034c2.46-8.908-4.3-17.41-13.237-17.41
c-8.935,0-15.697,8.5-13.237,17.409c-0.009,0.012-0.019,0.023-0.028,0.035L63.81,93.137H29.502
c-14.205,0-25.761,11.556-25.761,25.761v119.317c0,14.205,11.557,25.761,25.761,25.761h204.973
c14.204,0,25.761-11.557,25.761-25.761V118.898C260.236,104.694,248.679,93.137,234.475,93.137z M130.067,27.352
c1.407,0.197,2.438,0.197,3.843,0l47.725,65.785H82.341L130.067,27.352z M245.236,238.216c0,5.934-4.827,10.761-10.761,10.761
H29.502c-5.934,0-10.761-4.828-10.761-10.761V118.898c0-5.934,4.828-10.761,10.761-10.761h204.973
c5.934,0,10.761,4.827,10.761,10.761V238.216z" fill="#fff"/>
<path d="M232.843,128.029c0-4.142-3.357-7.5-7.5-7.5H38.632c-4.142,0-7.5,3.358-7.5,7.5v101.056c0,4.142,3.358,7.5,7.5,7.5
h186.712c4.143,0,7.5-3.358,7.5-7.5V128.029z M217.843,221.585H46.132v-86.056h171.712V221.585z" fill="#fff"/>
<circle cx="27.674" cy="117.072" r="4.565" fill="#fff"/>
<circle cx="27.674" cy="240.042" r="4.565" fill="#fff"/>
<circle cx="236.301" cy="117.072" r="4.565" fill="#fff"/>
<circle cx="236.301" cy="240.042" r="4.565" fill="#fff"/>
<path d="M59.945,200.339c2.003,0,3.73-1.727,3.73-3.799v-28.666c23.229,32.231,22.363,32.466,25.282,32.466
c2.072,0,3.799-1.727,3.799-3.799v-40.133c0-2.003-1.727-3.73-3.799-3.73s-3.73,1.727-3.73,3.73v28.46l-22.312-30.877
c-1.174-1.658-3.523-2.003-5.25-0.829c-1.036,0.76-1.589,2.003-1.52,3.177c0,0.069,0,0.069,0,0.069v40.133
C56.146,198.612,57.804,200.339,59.945,200.339z" fill="#fff"/>
<path d="M108.647,200.339l0.069-0.069c0,0,0,0.069,0.138,0.069h22.381c2.003,0,3.799-1.727,3.799-3.799
c0-2.141-1.796-3.868-3.799-3.868h-18.72v-12.71h16.095c2.072,0,3.799-1.727,3.799-3.869c0-2.003-1.727-3.799-3.799-3.799
h-16.095v-12.641h18.72c2.003,0,3.799-1.727,3.799-3.868c0-2.142-1.796-3.799-3.799-3.799h-22.381c-0.138,0-0.138,0-0.138,0
h-0.069c-2.142,0-3.799,1.658-3.799,3.799v40.755C104.848,198.612,106.505,200.339,108.647,200.339z" fill="#fff"/>
<path d="M160.679,198.075c1.229,2.89,5.337,2.866,6.529-0.037l9.323-22.66l9.322,22.66c1.193,2.905,5.303,2.927,6.53,0.038
l17.438-41.06c0.764-1.799-0.075-3.876-1.874-4.64c-1.801-0.763-3.877,0.076-4.64,1.874l-14.129,33.269l-9.375-22.786
c-0.545-1.326-1.838-2.192-3.272-2.192c-1.436,0-2.727,0.867-3.272,2.192l-9.376,22.786l-14.129-33.27
c-1.833-4.31-8.341-1.535-6.514,2.766L160.679,198.075z" fill="#fff"/>
</g>
</g>
</g>
<g>
</g>
<g>
</g>
<g>
</g>
<g>
</g>
<g>
</g>
<g>
</g>
<g>
</g>
<g>
</g>
<g>
</g>
<g>
</g>
<g>
</g>
<g>
</g>
<g>
</g>
<g>
</g>
<g>
</g>
</svg>

After

Width:  |  Height:  |  Size: 2.9 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 13 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 22 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 81 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 39 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 66 KiB