AI-Powered Search & Analytics: Running Embeddings Natively in SurrealDB

We’re excited to bring together the SurrealDB community for our first virtual meetup!

Whether you’re joining from New York, San Francisco, or anywhere in the world, this is an opportunity to connect, learn, and discover the power of multi-model databases.

What to Expect

In this session, we explore AI-Powered Search & Analytics: Running Embeddings Natively in SurrealDB. Discover how to run an embedding model directly within your database to unlock powerful AI-driven search and analytics capabilities.

Key Highlights:

• Why Embeddings Matter in RAG: Understand the role of embeddings in Retrieval-Augmented Generation (RAG) and why they are crucial for improving search and retrieval in AI-driven applications.
• What Are Embeddings? Learn the fundamentals of embeddings—how they work, their mathematical representations, and how they capture semantic meaning.
• Creating Embeddings: Explore different approaches to generating embeddings, including model selection, training, and fine-tuning.
• Using Embeddings in Databases: See how embeddings integrate with SurrealDB to enable efficient vector searches, similarity matching, and real-time data retrieval.
• Eliminating API Calls for Faster Performance: Learn how to streamline your architecture by processing embeddings directly in the database, reducing dependency on external API calls.

Whether you’re a SurrealDB user or exploring ML-powered databases, this session will equip you with the knowledge to build high-performance, next-gen applications.

Agenda

12:00 - 12:15
Introduction / Meet the Community

12:00 - 12:45
AI-Powered Search & Analytics: Running Embeddings Natively in SurrealDB
In this talk, we explore how to run an embedding model directly within your database, unlocking powerful AI-driven search and analytics capabilities. We begin with an introduction to SurrealDB, a multi-model database that simplifies real-time data processing and vector storage. You’ll learn how embeddings can enhance search relevance, recommendation systems, and semantic queries, all while leveraging the efficiency of SurrealDB’s native features. Whether you’re working with AI-powered applications or looking to optimize database-driven machine learning workflows, this session will provide practical insights and a hands-on approach to integrating embedding models seamlessly.

12:45 - 13:00
Q&A