mirror of
https://github.com/qdrant/landing_page.git
synced 2026-09-27 15:08:30 +02:00
27 lines
1.2 KiB
Markdown
27 lines
1.2 KiB
Markdown
---
|
|
title: Semantic Text Search
|
|
tabid: textsearch
|
|
icon: paper
|
|
landing_image: /content/images/semantic_search_big.webp
|
|
landing_image_png: /content/images/semantic_search_big.png
|
|
image: /content/images/solutions/semantic_text_search.svg
|
|
image_caption: Neural Text Search
|
|
default_link: https://qdrant.to/semantic-search-demo
|
|
default_link_name: Demo
|
|
weight: 20
|
|
short_description: |
|
|
The vector search uses **semantic embeddings** instead of keywords and works best with short texts.
|
|
With Qdrant, you can build and deploy semantic neural search on your data in minutes.
|
|
Check out our [demo](https://qdrant.to/semantic-search-demo)!
|
|
sitemapExclude: True
|
|
---
|
|
|
|
Full-text search does not always provide the desired result.
|
|
Documents may have too few keywords, or queries might be too large.
|
|
|
|
One way to overcome these problems is a neural network-based semantic search, which can be used in conjunction with traditional search.
|
|
The neural search uses **semantic embeddings** to find texts with similar meaning.
|
|
|
|
With Qdrant vector search engine, you can build and deploy semantic neural search on your data in minutes!
|
|
Compare the results of a semantic and full-text search in our demo.
|