Build Your First AI Search Application with Vespa

This hands-on workshop guides you through building your first Vespa application from scratch, covering data ingestion, schema design, ranking and querying, so you can see how Vespa works in practice.

Use the workshop for implementation guidance and sample code to:

• Deploy your first Vespa application.
• Feed and Index real data.
• Run queries using Vespa's query language.
• Understand Ranking and relevance
• Learn how hybrid retrieval works in production systems.

If you’re exploring how to build scalable AI search, recommendation, or RAG applications, the best way to learn Vespa is by doing.

Why Learn Vespa?

Modern AI Applications require much more than simple vector search.

Vespa enables you to:

• Combine text search, vector search, and structured filters.
• Apply machine-learned ranking models.
• Serve low-latecy queries at scale.
• Update data in real time without re-indexing.