A look at how to augment LLM results with retrieval augemented generation (RAG) and vector search, directly from BigQuery.

Amazon OpenSearch is a popular fully managed analytics engine that makes it easier for customers to do interactive log analytics, real-time application monitoring, and semantic and keyword searches. It can also be used as a vector engine that helps organizations build and augment GenAI applications without managing infrastructure (we’ll talk about this in future blogs). Additionally, the service provides a reliable, scalable infrastructure designed to handle massive data volumes.

While controversial in functional programming, dependency injection can be a useful pattern in Elixir for managing dependencies and improving testability. In this, the first part of a two-part series, we will cover the basic concepts, core principles, and types of dependency injection. We'll explore its benefits in terms of modularity, testability, and maintainability. Then, we will look into a specific scenario where dependency injection can be beneficial, in this case, testing.

A database schema, or DB schema, is an abstract design representing how your data is stored in a database. Database schemas can be visually represented using schema diagrams, such as the one below: A database schema diagram visually describes the following: Database schemas are at the heart of every scalable, high-performance database. They’re the blueprint that defines how a database stores and organizes data, its components’ relationships, and its response to queries.

LLM evaluation is the process of assessing the performance and capabilities of LLMs. This helps determine how well the model understands and generates language, ensuring that it meets the specific needs of applications. There are multiple ways to perform LLM evaluation, each with different advantages. In this blog post, we explain the role of LLM evaluation in AI lifecycles and the different types of LLM evaluation methods. In the end, we show a demo of a chatbot that was developed with crowdsourcing.

Imagine transforming raw business data into actionable insights with minimal effort. This is the value proposition of automated analytics, a form of data analytics fast becoming more accessible among modern business intelligence (BI) and analytics software solution vendors. Independent software vendors (ISVs) and enterprise organizations at the cusp of investing in analytics struggle with manual data processes that are time-consuming and prone to errors.

Ruby on Rails has long been celebrated for its ‘convention over configuration’ philosophy, simplifying web development for countless programmers. However, what if you’ve started with a lean Rails API-only application and now find yourself needing a front-end? This isn’t uncommon, especially with the rise of JavaScript frameworks and SPAs.

We’re excited to announce that Ably LiveSync is now in public alpha! LiveSync is a state synchronisation product that allows you to watch changes to your database and publish them reliably to millions of frontend clients, enabling those clients to stay up to date with the latest changes in realtime.

Today we’re excited to announce an expansion of our partnership with Microsoft to deliver a seamless and efficient interoperability experience between Snowflake and Microsoft Fabric OneLake, in preview later this year. This will enable our joint customers to experience bidirectional data access between Snowflake and Microsoft Fabric, with a single copy of data with OneLake in Fabric.