Beyond Buzzwords: Practical Vector Search and RAG for Developers

In this workshop we'll dive deep into integrating vector search into your applications. Over the course of this workshop, you'll not only grasp the core principles behind vector search but also cut through the buzzwords to understand its practical applications. We'll explore when vector search is the right tool for the job—and when it's not—so you can make informed decisions in your projects.

By the end of the workshop, you'll have hands-on experience as we build a fully functioning application together, leveraging vector search to elevate the user experience. We'll also cover how to effectively test and optimize your implementation to ensure it meets real-world demands. Whether you're new to the concept or looking to refine your skills, this workshop will equip you with the knowledge and tools to integrate vector search confidently into your development workflow.

Key takeaways:

• - Cut through the buzz and understand vector search's real-world applications to make informed choices in your projects.
• - Gain hands-on experience building an application with vector search to enhance user experience practically.
• - Learn best practices for testing and optimizing vector search implementations for robust, real-world performance.

SQLite in Node.js From Inside Out

SQLite is having its Renaissance. It's being used in many projects and companies. Bun runtime has its implementation of sqlite, Turso is a product on top of SQLite, and the Ruby on Rails framework dropped all its dependency on Redis in favor o SQLite for things like Caching and Queues.

Node.js version 22.5.0 introduced the `node:sqlite` module. It's an experimental module that allows you to use SQLite in a very Node.js way, without any external dependency.

In this workshop, you will learn how to use SQLite in Node.js. We will explore the current `node:sqlite` features and how to use them. We will also explore the future of SQLite in Node.js.

Building a RAG System in Node.js: Vector Databases, Embeddings & Chunking

Large Language Models (LLMs) are powerful, but they often lack real-time knowledge. Retrieval-Augmented Generation (RAG) bridges this gap by fetching relevant information from external sources before generating responses. In this workshop, we’ll explore how to build an efficient RAG pipeline in Node.js using RSS feeds as a data source. We’ll compare different vector databases (FAISS, pgvector, Elasticsearch), embedding methods, and testing strategies. We’ll also cover the crucial role of chunking—splitting and structuring data effectively for better retrieval performance.

Prerequisites

- Good understanding of JavaScript or TypeScript

- Experience with Node.js and API development

- Basic knowledge of databases and LLMs is helpful but not required

Agenda

📢 Introduction to RAG

💻 Demo - Example Application (RAG with RSS Feeds)

📕 Vector Databases (FAISS, pgvector, Elasticsearch) & Embeddings

🛠️ Chunking Strategies for Better Retrieval

🔬 Testing & Evaluating RAG Pipelines (Precision, Recall, Performance)

🏊‍♀️ Performance & Optimization Considerations

🥟 Summary & Q&A