# Vespa

> Vespa is a big data serving engine with built-in vector search (ANN/HNSW), real-time ML serving, hybrid ranking (vector+lexical). Suited for search engines/apps like recommendations; vs Elasticsearch more ML-focused. Features: tensor compute, autoscaling.

- **URL:** https://vespa.ai/
- **Category:** Full Text Vector Search Engines
- **Tags:** Real Time Serving, Hybrid Ranking
- **Updated:** 2026-04-30 11:38
- **Canonical page:** https://vectordb.ever.works/items/vespa

## Details

## Overview

Vespa is an open-source big data serving engine designed for real-time computation over large datasets featuring vector search and ML inference.

## Features

- SQL-like queries (Vespa Query Language)
- Tensor compute for advanced ML operations
- Multi-phase ranking pipelines
- Hybrid search (vector, text, structured)
- Real-time updates and low-latency serving

## Use Cases

- Production search applications
- Personalized recommendation feeds
- RAG and large-scale AI systems

## Comparisons

| Tool | Vespa Difference |
|------|------------------|
| Elasticsearch | Native vector/tensor support |
| Milvus | Full serving platform with integrated ranking/ML |

## Pricing

Free and open-source (Apache 2.0 license).

---

_This Markdown mirror is generated by Ever Works for AI agents. The canonical HTML page is at https://vectordb.ever.works/items/vespa._