• What’s new in two. Everything new with Redis in two minutes.
• Sign up for the public preview of Redis Data Integration (RDI) in Redis Cloud.
• We compare the networking differences between Amazon ElastiCache and Redis Cloud. Read more here.
• Our complete guide to vector search.
• Build AI agents in minutes with our AI agent builder.

If you saw our re:Invent booth, you already know. We were front and center in the expo hall and had our biggest week yet: nearly 10,000 conversations, 500+ demos, and 10 booth talks, with eight partner and customer teams joining us live.

Here’s what we brought to the floor:

• Hallucination Hub
  A hands-on take on the problem everyone’s dealing with: LLM hallucinations.
• Flight Club customer lounge
  A dedicated spot to meet with customers, partners, and teams building with Redis every day.
• New demos, live
  Redis Cloud in action across vectors, RAG, agent memory, and data integration—live builds, real workloads.
• Sky on-stage
  A real-world session on how Sky uses Redis Cloud to stream live events to 23 million people. See how Sky made it happen, here.

Semantic caching isn’t just a cost play. It’s how you keep LLM apps fast, consistent, and stable under load.

But high hit rates don’t happen by accident. Our new guide walks you through the levers that actually move performance: cleaning semantic noise, tuning embedding models and similarity thresholds, adding reranking, using metadata filters, setting smarter TTL/eviction policies, pre-warming key entries, and monitoring for drift.

Manvinder Singh, our VP of AI Product Management breaks down 10 practical techniques to optimize your semantic cache, with detailed examples and guidance you can apply using Redis LangCache.