Pinecone

Keyword search has leveled up 🎚️ In our recent post, we: ✔️ Trace how sparse retrieval evolved from brittle lexical matching to modern, high-performance models ✔️ Unpack the design decisions behind pinecone-sparse-english-v0 ✔️ Show you how to plug it into your app in just a few lines of code 💡 You’ll walk away knowing why this model works—and how to use it. Read on --> https://lnkd.in/gsEnXuVe

Pinecone released a new sparse index and model capability, and I got to write an article about it! Take a look, it's a great primer on how keyword search and various sparse models work. I also took great care in creating instructive diagrams for each sparse model discussed, so it's great for visual learners too! https://lnkd.in/gqETMQqH

🎤 That’s a wrap, London! Our AI Agents in Action meetup with Pinecone went beyond expectations - 100+ people showed up. Huge thanks to everyone who joined us and made it such a memorable night. This is what a strong AI community looks like curious, collaborative, and ready to build. We heard from Perry Krug on how vector databases make AI smarter, and Stanko Kuveljić showed real-world use cases of AI agents across industries. We’d say “stay tuned” like we always do, but another meetup is coming in Novi Sad in just 15 days! And no, this isn’t an April Fools’ joke - we’re really doing it again! 🎭 #ai #londontech #pinecone #aiinnovation #community

"The Power of the Humble Embedding" On the latest episode of the Stack Overflow Podcast, Ryan Donovan chats with Edo Liberty, founder and CEO of Pinecone, about building vector databases, the power of embeddings, the evolution of RAG, and fine-tuning AI models. Don't miss this conversation!

Building a RAG pipeline? You shouldn't need a myriad of tools to work. Join us for today's session where we'll dive into the essentials of Retrieval-Augmented Generation (RAG) pipelines. Whether you're curious about optimizing document search or looking to build more intelligent retrieval systems, this webinar will guide you through every step using Appsmith and Pinecone. "Building a RAG Pipeline with Appsmith & Pinecone" Date: March 27 Time: 1:00 PM PST Location: Virtual RSVP - https://lnkd.in/eeUAvWgX

Tomorrow in Washington (state!) - Don't miss Pinecone's workshop at the Seattle Startup Summit Get into the action with AI Dev Tools galore, and visit the Pinecone booth for neat swag!

Sparse retrieval is gaining traction—but what does that actually mean? 🤔 In this deep dive, we: ✔️ Break down the key definitions ✔️ Explore architecture & performance tradeoffs ✔️ Walk through a real-world example: “Why did the price of X stock go up today?” 👀 We’ve also included a hands-on notebook so you can explore for yourself. Check it out:

How it started → How it’s going: Pinecone at NVIDIA #GTC25 From kicking off the day to peak momentum! Live AI demos, partner stations, executive meetings, and nonstop conversations. Our team has been connecting with AI engineers and leaders from around the world all week. Thanks to everyone who's stopped by 🚀

Want to learn how to build recommendation systems, but don't know where to start? Learn how to create and train embeddings for high-performance recommendation systems from Arjun Patel - Developer Advocate at Pinecone and Blaž Stojanovič - ML Engineer at Kumo on March 27th, 10:00am PT / 1pm ET Register for the webinar here: https://lnkd.in/gb4Ee_fb

🌑 Launch Week Day 5: Dark Mode The moment you've all been waiting for... Dark mode is now live across our website, docs, and console. You’re welcome.😎 P.S. That's a wrap on Launch Week! Check out everything we launched in our recap: https://lnkd.in/gZfWmD_Q