vespa-engine/vespa

★ 6,912JavaAudience · developerComplexity · 4/5LicenseSetup · hard

Mindmap

mindmap
  root((vespa))
    What it does
      Real-time search
      AI-based ranking
      Vector similarity
    Tech stack
      Java
      C++
      Maven build
    Use cases
      Search engines
      Recommendation
      Personalization
    Deployment
      Cloud service
      Self-hosted
      Pre-built releases

mindmap root((vespa)) What it does Real-time search AI-based ranking Vector similarity Tech stack Java C++ Maven build Use cases Search engines Recommendation Personalization Deployment Cloud service Self-hosted Pre-built releases

Click or tap to explore — scroll the page freely

Things people build with this

USE CASE 1

Build a real-time product recommendation engine that ranks results using machine learning models.

USE CASE 2

Create a large-scale text search engine that handles hundreds of thousands of queries per second.

USE CASE 3

Power a personalization system that continuously updates rankings as new user data arrives.

USE CASE 4

Combine vector similarity search with traditional keyword search in a single query.

Tech stack

JavaC++Maven

Getting it running

Difficulty · hard Time to first run · 1h+

Full source build requires AlmaLinux 8, most users should use the managed cloud service or pre-built releases instead.

Use freely for any purpose including commercial, as long as you keep the copyright notice. (Apache 2.0)

In plain English

Vespa is a platform for searching, ranking, and organizing large collections of data in real time. It is built to handle use cases like search engines, recommendation systems, and personalization features at scale, where millions of data items need to be searched and scored within a fraction of a second while the data itself is continuously changing. At its core, Vespa stores structured data, text, and numerical vectors. Vectors are a format used in machine learning to represent content like documents or product descriptions as lists of numbers, which allows similarity-based search. Vespa can evaluate models over that data at query time, meaning it can combine traditional text matching with AI-based ranking in a single query rather than requiring a separate processing step. The project has been in development for many years and runs in production at large internet services handling hundreds of thousands of queries per second. All code in the repository is open source under the Apache 2.0 license. A new release is made from the main branch every weekday morning. Vespa can be used through a managed cloud service at vespa.ai, which includes a free trial, or by running your own Vespa instance. Documentation, a getting-started guide, and sample applications are available at docs.vespa.ai. Building from source is only needed for contributors, most users work with pre-built releases. The codebase is primarily Java with some C++. A full build requires AlmaLinux 8, though the Java modules alone can be built on any platform with Java 17 and Maven 3.8 or newer. The project maintains a blog and a Slack community for users, and welcomes external contributions.

Copy-paste prompts

Prompt 1

Show me how to set up a Vespa application schema that stores both text fields and embedding vectors for hybrid search.

Prompt 2

Write a Vespa ranking profile that combines BM25 text matching with dot-product vector similarity using a linear combination.

Prompt 3

Create a Python script that continuously feeds product catalog updates into a running Vespa instance via its document API.

Prompt 4

How do I configure Vespa to load and run a custom ONNX model for re-ranking search results at query time?

Prompt 5

Walk me through deploying Vespa on a single machine, indexing sample documents, and running a YQL search query.

Open on GitHub → Explain another repo

← vespa-engine on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.