🗽 NYC tech community, come learn how to build agentic AI applications with experts from #AWS, #Cohere, and Pinecone! 🤖 RSVP at: go.aws/4eed3IP Event Details: 📍 Amazon JFK14. 7 W 34th St., New York, NY 10001, USA 📅 Date: Monday, June 30 2:30-6:30 PM

🔥 Agents are so hot right now. This group of experts, including our CTO Ram Sriharsha, will tell you why and a whole lot more. Join him, Jun Qian, Jerry Liu, and Andriy Burkov for this upcoming panel hosted by DataCamp. 📅 June 26 🕕 13:15–14:00 EDT 🔗 Save your spot:

🎉 Massive congratulations to our customer Delphi on this milestone—the first of many! We're proud to power vector retrieval for what is one of today's best examples of knowledgeable AI.

🎙️ If you're new to hybrid retrieval, this short podcast with our principal engineer, Jack Pertschuk, is worth a listen. Jack explains what it is, why it's advantageous to use both dense and sparse, and also provides a TL;DR on the evolution of our vector database.

🤖 Building agentic AI apps? Join Amazon Web Services, @Cohere & @Pinecone in NYC on June 30 for a hands-on session on secure, scalable applications. ✅ Code demos ✅ Real-world use cases ✅ Expert insights ⏰ Space is limited: lu.ma/8rm6zryw?utm_s…

Most vector search is bolted on and breaks at scale. Pinecone is different: ✅ Built just for vector search ✅ Billions of vectors, serverless ✅ Native AWS + Bedrock integration (also Azure and GCP integrations) ✅ Powers RAG, semantic search, agents & recommender engines

From "search and summarize" to "reason and act", retrieval-augmented generation (RAG) is evolving and it's the foundation of practical AI implementations. Here's how we're seeing RAG workloads change in 2025: ▪️ RAG has gone from a simple implementation to one that is much more

⛔️ Want to automatically scan and remove banned content from your Discord server? #PineconeCommunity member Joseph Petty shows you how to use a Discord bot and Pinecone Assistant to moderate a server and assist with questions and content moderation. 🔗 blog.greenflux.us/building-an-ai…

Wanted to build semantic search, retrieval-augmented generation, or agentic RAG apps, but got stuck at chunking? Take a look at our article on chunking strategies to get your bearings! You'll learn why chunking is so important, a bunch of different strategies for chunking, and

Want to help shape Pinecone’s onboarding & index creation? We’re interviewing users seriously exploring or building with Pinecone. Book a slot with our team to share your insights in a 15–30 min interview & get a $50 Amazon gift card! Details below: x.com/JesiraeDong/st…

Our founder and CEO Edo Liberty will be at TechCrunch Disrupt. You won't want to miss this.

🚀 DIME (Dimension Importance Estimation) Originally introduced by Guglielmo Faggioli et al., 2024 to pinpoint which embedding dimensions matter for each query, DIME showed that masking noisy coordinates can lift dense-retrieval quality.

What we're adding at Pinecone: - Formalisation as a denoising step – framing DIME as a light-weight projection into a cleaner sub-space. - Research-grade code & full benchmarks – open-source scripts for PRF-DIME and LLM-DIME on MS MARCO, TREC-DL '19/'20, DL-HD, Robust '04