Redis

“Die Hard" is a Christmas movie. We know for sure because LangCache, our fully managed semantic caching service, told us it was true. We even put it on the Nasdaq tower. Check it out yourself. And also check out LangCache for free today: https://lnkd.in/gD2mzvMb

Redis is helping power the next wave of intelligent, collaborative applications on Azure. In this new session with Catherine Wang, Matthew Soucoup, and Microsoft, we explore how Redis enhances agentic applications through: - Semantic cache for faster, more efficient LLM calls - Vector store for high-quality, relevant retrieval - Chat history to keep interactions grounded and contextual - Sessions to orchestrate complex, multi-agent workflows We also highlight the latest .NET Aspire innovations with Redis and the Microsoft Agent Framework, along with practical patterns you can use today to build smarter, more performant cloud-native apps. Watch the video to see how Redis + Azure + .NET Aspire make agentic applications intelligent, scalable, and production-ready: https://lnkd.in/gfJnRmqm

Using Azure Managed Redis with Azure Cosmos DB is a powerful way to cut RU costs and tame p99 latency for read-heavy workloads on Azure.  “Azure Managed Redis & Azure Cosmos DB with Cache-Aside: A Practical Guide” breaks down how to: ⤷ Apply the cache-aside pattern so apps read from Redis first and fall back to Cosmos DB on a miss ⤷ Use Cosmos DB ETags in cache keys and the Change Feed to drive precise, low-friction cache invalidation ⤷ Align TTLs, eviction policies, and failure behavior with your SRE and business requirements ⤷ Combine sub-millisecond Redis reads with Cosmos DB’s global distribution and consistency for predictable performance at scale We also include a code sample wiring up Cosmos DB Change Feed → Azure Functions → Azure Managed Redis to keep hot keys fresh automatically. Read the full blog: https://lnkd.in/gye5wmHG Cc: Jan Kalis, Andrew Liu, James Codella, Ph.D., Philip Laussermair

RedisVL is evolving from a convenience layer into a cross-language framework for building real-time, context-aware AI systems. Momentum is surging: nearly 500k downloads in October and rapid adoption of the LangGraph Checkpointer are making Redis the go-to context engine for AI agents. And with RedisVL 0.11.0, developers get major new capabilities: - Multi-vector queries for richer multimodal search - Enhanced text relevance + index customization - SVS-Vamana: a new high-performance, memory-efficient vector index - Native LangCache integration for faster, cheaper LLM apps RedisVL is becoming the AI-native toolkit teams rely on. Read more: https://lnkd.in/g7ZqQfvt

ICYMI: We’re excited to join Fierce Software’s ecosystem of leading technology partners. We’ll work together to power innovations in the federal sector and work smarter with real-time data. By combining our high-performance real-time data and AI platform with Fierce Software’s deep public sector expertise, we’re empowering teams to deliver faster insights, stronger systems, and better mission outcomes. Read more about our partnership: https://lnkd.in/gdujee83

Intelligent agents live or die by the quality of their context. Redis 8.4 introduces FT.HYBRID, a unified API that fuses full-text, vector, and metadata search into a single ranked result set using in-engine score fusion. This eliminates pre-filters, post-processing, and multi-step pipelines, and enables fast, accurate, context-aware retrieval. Hybrid retrieval matters because research shows it dramatically improves RAG performance—up to 49% fewer retrieval failures, 3–3.5X higher recall, and 11–15% better answer accuracy versus single-mode search. Read more: https://lnkd.in/ghZ75KJ7

Excited to share that our paper “𝘄𝗮𝗟𝗟𝗠𝗮𝗿𝘁𝗖𝗮𝗰𝗵𝗲: 𝘈 𝘋𝘪𝘴𝘵𝘳𝘪𝘣𝘶𝘵𝘦𝘥, 𝘔𝘶𝘭𝘵𝘪-𝘵𝘦𝘯𝘢𝘯𝘵 𝘢𝘯𝘥 𝘌𝘯𝘩𝘢𝘯𝘤𝘦𝘥 𝘚𝘦𝘮𝘢𝘯𝘵𝘪𝘤 𝘊𝘢𝘤𝘩𝘪𝘯𝘨 𝘚𝘺𝘴𝘵𝘦𝘮 𝘧𝘰𝘳 𝘓𝘓𝘔𝘴” has been referenced in the new DeepLearning.AI × Redis course on Semantic Caching for AI Agents. It’s great to see semantic caching gain visibility as a key capability for building scalable AI systems. Even better when our work contributes to the conversation. Appreciation to my co-authors who made this research possible. Grateful to Kunal Banerjee, Anirban Chatterjee for their continued mentorship and support. Special thanks to Tyler Hutcherson for talking about our work in the course.😊 📄 Paper: https://lnkd.in/g5uU2Q2M  🔗 Course link: https://lnkd.in/gfWC9BJG Do check out the course! #IndustryResearch #ArtificialIntelligence #MachineLearning #GenerativeAI #Caching