Redis

Make the most of your downtime this Thanksgiving weekend. In just 75 minutes, learn how to build a semantic cache to make your AI agents faster. Check out the Redis course built with DeepLearning.AI. Your future self will be extra thankful. https://lnkd.in/gxGSKuwj

Redis Open Source 8.4 is GA today. It’s faster, more scalable, and now has hybrid search. It’s the most advanced version of Redis yet, continuing our mission to make Redis faster, simpler, and more powerful. New features in 8.4 include: 🔎 Hybrid Search: Combines full-text and vector results in one query, powering more accurate AI, RAG, and semantic search experiences. 📈 Performance improvements: With multi-threaded I/O, improved memory handling, and smarter JSON storage that deliver over 30% higher throughput and up to 91% lower memory use. ⚛️ Atomic Slot Migration (ASM): Enables easier, more reliable cluster scaling. 💬 Stream enhancements: Allow clients to process new and pending messages in a single step. 🔑 Atomic key operations: Provide safer, script-free key updates and expirations. Read more here: https://lnkd.in/ghGUD6tc  Download Redis 8.4 here: https://lnkd.in/gYcp3gcv

🔍 Reduce LLM Calls with Vector Similarity Search – Design Patterns for Faster, Cheaper and Greener AI One of my absolute highlights at Codemotion Milano 2025 some weeks ago was the talk by Raphael De Lio (Redis). It was a perfect mix of technical clarity and practical impact. The idea: Instead of sending every query through an LLM, he showed how semantic routing, vector similarity search (VSS), and semantic caching can dramatically reduce token usage, latency, and energy consumption, while keeping quality and context intact. The three use cases he presented: text classification, function calling, and caching responses. It's a mindset shift: don't scale by calling bigger models, but by calling them smarter. Efficiency here isn't just optimisation, it's responsibility. Highly recommend the material: Presentation: https://lnkd.in/dMYA2y2k Paper: arxiv.org/abs/2504.02268 Thanks, Raphael, for a talk that connects technical depth with a vision for sustainable Al infrastructure! #Codemotion #Redis #Al #LLM #VectorSearch #SemanticCaching #AlEngineering #ResponsibleAl

Redis 🤝 Google Cloud We recently announced the general availability of Google Cloud Spanner support in Redis Data Integration for both self-managed and Redis Cloud on GCP deployments. With this integration, enterprises can now: ⤷ Sync data between Redis and Google Cloud Spanner ⤷ Deliver real-time caching ⤷ Achieve sub-millisecond response times for high-performance apps ⤷ Reduce infrastructure costs by offloading reads from Spanner Read more: https://lnkd.in/gbk8YX6U

Redis Agent Memory Server provides a production-ready solution enabling your AI agents with intelligent memory capabilities like maintaining context across conversations and delivering increasingly personalized responses.  Learn more from Lead Developer Advocate, Ricardo Ferreira, in this guide for deploying Redis Agent Memory Server on Amazon EC2 using Terraform: https://lnkd.in/g9Njare8

We’re packing our bags for AWS re:Invent, and let’s just say we have a few surprises in store. Starting at booth #1520 and the Hallucination Hub after-hours, you’ll want to keep an eye on what’s coming next. We heard there might even be a new version of Redis involved. 👀 Stay tuned—it’s going to be a real-time kind of week from Dec 1-5: https://lnkd.in/gbyuNsDr

Mom Creators Corner is back! SF - Production Agents - Hack is here. ⚡🤖 The Production Agents – Hack Kickoff starts November 21st. Join us to build the next generation of intelligent, self-improving AI agents—and shape the future. Join innovators from Amazon Web Services (AWS), Skyflow, Postman, Parallel Web Systems , Forethought, Finster AI , Senso, Sanity, TRM Labs, Coder, Cleric, Anthropic, Redis, Lightpanda, Lightning AI. We advance the frontier of how AI agents learn, adapt, and build. 📅 Friday, November 21 📍 AWS Start up Loft, San Francisco 🏆 Over $50k in prizes! 👉 Register here: https://luma.com/ai-hack Hosted by: Murtaza M. , Giovanni Amenta, Alessandro Amenta , Jacopo P., Simon Tiu , Saroop Bharwani

We worked with our friends over at DeepLearning.AI to bring you "Semantic Caching for AI Agents," a 75-minute course lead by Tyler Hutcherson and Iliya Zhechev that teaches you how to build a semantic cache using Redis to make AI systems faster and more cost effective. Using seven different video lessons and four code examples, you’ll learn to: ➡️ Build your first semantic cache from scratch – Build a working cache to see how each component works, then implement it using Redis’ open source tools. ➡️ Measure cache effectiveness with key metrics – Track cache hit rate, precision, recall, and latency to understand your cache’s real impact. ➡️ Enhance cache accuracy with advanced techniques – Use threshold tuning, cross-encoders, LLM validation, and fuzzy matching to make your cache more effective. ➡️ Build a fast AI agent with semantic caching – Integrate semantic caching into an AI agent that reuses results, skips redundant work, and gets faster over time. Start building today: https://lnkd.in/gxGSKuwj

Chatbots are reshaping customer experience and productivity across industries, but many teams hit roadblocks with latency, memory, and cost. That’s where we come in. Redis is the AI infrastructure layer behind some of the fastest, most intelligent chatbots used today, powering RAG, semantic caching, and long-term memory. Here’s how we’re helping companies deliver real-time, intelligent chatbot experiences that scale smarter and cost less: https://lnkd.in/g6Ax57Ex