Redis

Vector databases have become the standard for building Retrieval Augmented Generation (RAG) systems, but on their own, they’re not enough to create a complete solution. While others race to catch up, Redis sets the standard with multi-tenancy, high availability, active-active replication, and durability—capabilities pure vector database vendors are still chasing. cc: Tyler Hutcherson

It’s time for “What’s New in Two”—swipe to see a roundup of new features and enhancements including the private preview of Redis 8.0-M03, the milestone release of RedisVL (0.4.0), and more. cc: Talon Miller

??Building AI apps using LangChain A new series from our friends at Redis on building AI applications using LangChain and Redis Covers RAG and semantic caching https://lnkd.in/gEfa4Xm3

RAG isn’t just a buzzword—it’s about using semantic search and AI to find and use information smarter and faster. Rini Vasan, an AI Product Marketing Manager at Redis, set out to build a Retrieval Augmented Generation (RAG) pipeline using the Redis Vector Library and also created a working AI assistant. Learn about her experience with RedisVL and start yours today: https://lnkd.in/gj2T4xsU?

Vector databases have been trending recently as they power modern search, recommendations, and AI-driven applications. Join Raphael De Lio in this video, as he breaks them all down using a simple analogy—planets in our solar system! You’ll learn: ? How vector databases store and compare data ?? ? Why AI isn’t required, but makes vector search more powerful ?? ? The role of embedding models in modern search & recommendations ?? ? How Redis delivers the fastest vector search on the market ?

Curious how to power personalized recommendations with content-based filtering? Justin Cechmanek, Senior Applied AI Engineer at Redis, breaks down content-based filtering—what it is, how it works, and why it matters. Plus, a step-by-step tutorial to build your own recommendation system using Redis. Get started: https://lnkd.in/dTcww57N

Don't miss the next session about semantic caching on March 12. The link to register is in the post below.

VentureBeat talked to our own Manvinder Singh about why agentic memory is so important for creating rich user experiences, and what devs building agents need to consider as they start integrating agents into workflows. “There are four high-level decisions you must make as you design a memory management architecture: Which type of memories do you store? How do you store and update memories? How do you retrieve relevant memories? How do you decay memories?” Read more here: https://lnkd.in/gHp_rydf

?? Redis 8.0-M03 is out. What’s in it for devs? ?? Boosted performance in single-core and multi-core environments. ?? New asynchronous I/O threading for improved efficiency. ?? Enhanced replication for faster, more reliable performance. ?? Latency improvements to PFCOUNT, PFMERGE, GET, EXISTS, LRANGE, HSET, and HGETALL. Get the full scoop in our latest blog: https://lnkd.in/gFPN_HRM

?? New video alert ?? Are you building #AI applications using LangChain? I just released a new series about developing AI apps with LangChain and Redis. In this series, I show how to implement: ?? Using Redis as a vector store for embeddings ?? Similarity search: with and without metadata filtering ?? Caching LLM responses with semantic cache ?? LLM memory session management with Redis ?? Resources you can use to learn more about AI Let's build!