# Vespa.ai

> An AI Search Platform for building large-scale applications combining vector search, text search, machine-learned ranking, and real-time inference at enterprise scale.

Vespa.ai is an AI Search Platform designed for developing and operating large-scale applications that combine big data, vector search, machine-learned ranking, and real-time inference. It provides native tensor support for complex ranking and decisioning, enabling real-time AI applications like RAG, recommendation, and intelligent search at enterprise scale. Vespa supports querying, organizing, and making inferences across vectors, tensors, text, and structured data, scaling to billions of constantly changing data items with thousands of queries per second at sub-100ms latencies. The platform is open source at its core and also available as a fully managed cloud service.

- **Vector & Text Search** — *Combines leading open text search with a capable vector database, enabling hybrid search applications with superior relevance.*
- **Generative AI (RAG)** — *Supports hybrid search, relevance models, and multi-vector representations for high-quality retrieval-augmented generation pipelines.*
- **Recommendation & Personalization** — *Combines retrieval of eligible content with machine-learned model evaluation for recommendation, personalization, and ad targeting at any scale.*
- **Semi-Structured Navigation** — *Handles e-commerce and similar use cases that blend structured data, text, and images with seamless search and navigation.*
- **Personal/Private Search** — *Streaming search mode delivers full Vespa capabilities for personal data use cases at up to 20x lower cost than indexed search.*
- **Distributed Machine-Learned Ranking** — *Integrates distributed ML model inference directly into the serving layer for relevance ranking without external round-trips.*
- **Infinite Automated Scalability** — *Auto-scales to handle billions of documents and thousands of queries per second with continuous deployment and upgrades.*
- **Vespa Cloud** — *Fully managed cloud offering with strong security, operational monitoring, and support tiers for production deployments.*
- **Open Source Core** — *The Vespa engine is open source on GitHub, allowing self-hosting and community contributions alongside the managed cloud option.*

## Features
- Vector search
- Text search
- Hybrid search
- Machine-learned ranking
- Real-time inference
- RAG (Retrieval-Augmented Generation)
- Recommendation and personalization
- Streaming search for personal data
- Tensor formalism
- Distributed ML model inference
- Auto-scaling
- Continuous deployment
- Fully managed cloud (Vespa Cloud)
- Semi-structured navigation
- Visual retrieval

## Integrations
Voyage AI

## Platforms
WEB, API, CLI, DEVELOPER_SDK

## Pricing
Open Source, Open Source

## Links
- Website: https://vespa.ai
- Documentation: https://docs.vespa.ai
- Repository: https://github.com/vespa-engine/vespa
- EveryDev.ai: https://www.everydev.ai/tools/vespa-ai