mirror of
https://github.com/qdrant/landing_page.git
synced 2026-10-03 01:48:32 +02:00
* replaced "vector database" with "vector search" across the website content # Conflicts: # qdrant-landing/content/headless/main/core-features.md # qdrant-landing/content/use-cases/_index.md * upd wording
32 lines
1.3 KiB
Markdown
32 lines
1.3 KiB
Markdown
---
|
|
title: RAG with Qdrant
|
|
description: RAG, powered by Qdrant's efficient data retrieval, elevates AI's capacity to generate rich, context-aware content across text, code, and multimedia, enhancing relevance and precision on a scalable platform. Discover why Qdrant is the perfect choice for your RAG project.
|
|
features:
|
|
- id: 0
|
|
icon:
|
|
src: /icons/outline/speedometer-blue.svg
|
|
alt: Speedometer
|
|
title: Highest RPS
|
|
description: Qdrant leads with top requests-per-second, outperforming alternative vector search in various datasets by up to 4x.
|
|
- id: 1
|
|
icon:
|
|
src: /icons/outline/time-blue.svg
|
|
alt: Time
|
|
title: Fast Retrieval
|
|
description: "Qdrant achieves the lowest latency, ensuring quicker response times in data retrieval: 3ms response for 1M Open AI embeddings."
|
|
- id: 2
|
|
icon:
|
|
src: /icons/outline/vectors-blue.svg
|
|
alt: Vectors
|
|
title: Multi-Vector Support
|
|
description: Integrate the strengths of multiple vectors per document, such as title and body, to create search experiences your customers admire.
|
|
- id: 3
|
|
icon:
|
|
src: /icons/outline/compression-blue.svg
|
|
alt: Compression
|
|
title: Built-in Compression
|
|
description: Significantly reduce memory usage, improve search performance and save up to 30x cost for high-dimensional vectors with Quantization.
|
|
sitemapExclude: true
|
|
---
|
|
|