Run This Ai
EN DE

Vespa

The AI search platform for fast, accurate RAG and recommendations

★ 6,976 GitHub Apache-2.0 search-enginevector-searchragrecommendationai-searchvector-databasesemantic-search RAG & Knowledge

Overview

Vespa is the AI-powered search engine built for large-scale RAG, personalization, and recommendation systems. With 7k+ GitHub stars and years of production use at Yahoo, it combines vector search, tensor evaluation, and machine-learned model serving in a single platform. Vespa supports advanced features like real-time indexing, approximate nearest neighbor (ANN) search, multi-vector ranking with transformer models, grouping, and distributed serving across data centers. It is used by companies like Spotify, Wix, and Qwant for search, recommendations, and AI-powered data applications.

Requirements

Min vCPU
2
Min RAM
4096 MB
Min Disk
10 GB
Rec vCPU
4
Rec RAM
8192 MB
Rec Disk
20 GB

Recommended VPS

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
View plan

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
View plan

Hostinger · KVM 8

8 vCPU · 32256 MB · 400 GB

$20.00
View plan

Affiliate disclosure

Docker Compose

# Generated by Run This Ai — docker-compose.yml
services:
  vespa:
    image: vespaengine/vespa:latest
    restart: unless-stopped
    ports:
      - 8080:8080
    volumes:
      - ./data/vespa:/data

Best VPS for Vespa →

Related tools

Guides & articles