mirror of
https://github.com/qdrant/landing_page.git
synced 2026-09-29 07:58:31 +02:00
Diana Errant
bcf5d219a0
-filtrable is a word, although not common and easily mistaken for an error -other issue is of grammatical nature in the recommendations section
25 lines
906 B
Markdown
25 lines
906 B
Markdown
---
|
|
title: Recommendations
|
|
icon: advertising
|
|
tabid: recommendations
|
|
landing_image: /content/images/recomendations_big.webp
|
|
landing_image_png: /content/images/recomendations_big.png
|
|
image: /content/images/solutions/recomendations.svg
|
|
image_caption: History-based Recommendations
|
|
default_link:
|
|
default_link_name:
|
|
weight: 30
|
|
short_description: |
|
|
User behavior can be represented as a semantic vector in a similar way as text or images.
|
|
Vector database allows you to create a real-time recommendation engine.
|
|
No MapReduce cluster required.
|
|
sitemapExclude: True
|
|
---
|
|
|
|
User behavior can be represented as a semantic vector is similar way as text or images.
|
|
This vector can represent user preferences, behavior patterns, or interest in the product.
|
|
|
|
|
|
|
|
With Qdrant vector database, user vectors can be updated in real-time, no need to deploy a MapReduce cluster.
|
|
Understand user behavior in real time. |