See what we think

If you’re a developer or vibe coder you’re probably already familiar with AI-powered coding assistants like Augment Code. These tools have a number of features, but they are all working ...

Redis is now available to use natively on Windows. We’ve partnered with Memurai to develop Memurai Enterprise Edition, a fully compatible and officially supported Windows port of Redis t...

As GenAI applications evolve—think agents, copilots, and chatbots—developers need more than just a connection to an LLM. These applications demand fast, cost-efficient inference. By defa...

Least Frequently Used (LFU) and Least Recently Used (LRU) are two of the most common cache eviction policies for determining which data to evict when a cache fills up. Without a policy i...

Retrieval-augmented generation (RAG) has rapidly become the go-to pattern for combining large language models (LLMs) with up-to-date, domain-specific knowledge. By grounding generative o...

Redis 8 is now available for preview on Redis Cloud Essentials. Starting today, you can create a Redis 8 database and experience the power of our most performant Redis version yet. Whet...

In the previous blog posts on grid search and bayesian optimization with the retrieval optimizer we made things easy by pulling pre-defined and formatted data. However, let’s say you hav...

In the last article, we introduced the retrieval optimizer, why it matters for eval driven development (EDD) and how to get started with a basic grid search. Often selecting the right se...

One of the most valuable pieces of feedback I’ve ever received as an engineer came as an intern. I was debugging some data issues and, truthfully, didn’t really know what was going on. W...

Fraudsters don’t wait—and neither can your systems. Financial crime is faster, smarter, and more coordinated than ever. Every delayed response is a potential breach, a lost customer, or...

ChatGPT launched in 2022, triggering the current AI wave, and in 2023, enterprises invested $2.3 billion in AI – an amount easily cleared by the $13.8 billion spent in 2024. But while c...

In today's AI-driven landscape, the difference between retrieving relevant information and irrelevant noise can make or break your application's value proposition. Whether you're buildin...

Large language models are powerful, but they forget quickly. For AI agents and assistants to be truly useful, they need memory: the ability to retain instructions, recall facts, and carr...

A cache hit ratio is a simple concept. It’s the proportion of data requests served from a cache, measured against total requests received by the cache. The former includes the “hits” (wh...

Welcome to “What’s new in two,” your quick hit of Redis releases you might have missed in the past month. We’re covering the latest developments from June and expanding on what I covered...

Every few weeks, a new GenAI model arrives—smarter, faster, cheaper, and poised to outshine the rest. The claims stay the same, even as the names change. In just the past few weeks alone...

The key to better retrieval, lower latency, and higher accuracy LLM chunking is the process of breaking large amounts of data into smaller, self-contained pieces of data (chunks) befor...

From branches to smartphones Today, a bank’s most important branch fits in the palm of your hand. Mobile apps have revolutionized banking, turning time-consuming tasks—like depositing c...

Caching is the process of storing copies of data in temporary storage, allowing new requests for that data to be served more quickly. Without that temporary storage – the cache – request...

As developers build increasingly advanced GenAI apps like chatbots, agents, and copilots, the infrastructure behind them needs to keep up. Connecting to a large language model is just th...

Do you know Kevin Bacon? The six degrees of separation rule says that if you map the right social connections, all people are six or fewer handshakes away from each other—including Kevin...