# What is Vespa? Definition and meaning

An engine that combines text, vector and structured search with on-node ranking.

## Definition

**Vespa**: An engine that combines text, vector and structured search with on-node ranking.

In short: Search and vector engine for large applications.

## When it is used

Large production search and recommendation systems.

## Where it fits

Vespa belongs to **Vector databases** in the [Generative AI and LLMs](/topics/generative-ai-llms) topic. These are the other terms in the same group:

- **[Weaviate](/glossary/weaviate)**: A vector database that stores objects with embeddings and supports hybrid and filtered search.
- **[ChromaDB](/glossary/chromadb)**: A simple embedding store that is easy to embed in an application.
- **[Milvus](/glossary/milvus)**: A distributed vector database built for billion-scale similarity search.
- **[Qdrant](/glossary/qdrant)**: A vector database with strong filtering, payloads and efficient indexing.
- **[FAISS](/glossary/faiss)**: Meta's library for nearest-neighbour search and clustering of dense vectors, with CPU and GPU indexes.
- **[pgvector](/glossary/pgvector)**: A PostgreSQL extension that stores embeddings and supports exact and approximate nearest-neighbour search.

## Learn more

The full guide to **[Vespa](/tools/vespa)** explains how it works, when to use it and how it compares with the alternatives, with examples. The [glossary](/glossary) lists every term on the site from A to Z.

Previous term: [Vertex AI](/glossary/vertex-ai) · Next term: [Vision-language-action models](/glossary/vision-language-action-models)
