Pinecone

Build Production-Ready ETL Pipelines for RAG in 10 Minutes with Unstructured!   Join us next Wednesday, December 18th for a hands-on technical webinar with Unstructured’s engineers, showing you how to leverage Platform with Ragas to quickly build pipelines and evaluate accuracy using the latest Llama 3.2. We will transform data in an Amazon Web Services (AWS) S3 bucket to a Pinecone vector database using no code!   Sign up today at https://lnkd.in/gCRtmz6e

Join us Tuesday, December 17, for an introductory workshop on Cascading Retrieval — an enhanced retrieval path that seamlessly combines dense, sparse, and reranking for unparalleled precision, performance, and ease of use. Gareth Jones and Antonio Mallia will guide you through this approach, share key insights from our benchmarks, and conclude with a live demo. Sign up now! https://lnkd.in/gRBT9i-V

Pinecone powerhouse 🏳️🌈 Corbett Waddingham engages the crowd in SF last night at GitHub for "SF Awesome AI Dev Tools", with talks from Comet, Pinecone, and Komodo AI Cory is a powerhouse expert on all that Pinecone has to offer, and appears at our events all across the country. If he comes through your town, don't miss the opportunity to learn about what you can do with Pinecone

What a week indeed! Thanks for the detailed recap, Ari

🚀 Launch Week Day 5: Introducing Pinecone Local We’re wrapping up Launch Week with a new feature designed to accelerate your prototyping and development workflows with Pinecone. Introducing Pinecone Local — a self-hosted, in-memory emulator of the vector database, now available in public preview for all users! Here’s how Pinecone Local makes your life easier: ✅ Spin up and tear down indexes in memory for quick tests and iteration ✅ Use any supported SDK to interact with the Pinecone API — no API key required ✅ Run large-scale tests on your own data without incurring usage costs ✅ Develop your app locally — no internet connection needed Check out our announcement to learn more and try it out today! https://lnkd.in/ePyU3v_e

The Pinecone team enjoyed a packed booth at AWS re:Invent. Connecting to our community -- brainstorming in 1:1s with team members, guiding awareness, and showcasing ways Pinecone helps build better is what we came for. Between our recent events and Launch Week, inspiration and energy are at an all-time high

AI isn't the future, it's making money today: "There's lot of hype, and talk, and thoughts in terms of what AI could do or could be. "But I think in reality, we don't talk a lot about the reality of today -- how people are making money in AI. How people are generating productivity and efficiency. "And actually putting more structure around that conversation... disseminating more information to [over 5,000 of our customers] in terms of how they can build is sort of a big focus" -- Lauren Nemeth, Pinecone COO at a16z Tech Week https://lnkd.in/ggmfk5t9

A developer in our community has released a good RAG tutorial using Pinecone w/ ChatGPT and Make! Always inspiring to see our platform drive creativity. Check it out and see what you can build! https://lnkd.in/gqq8ezdu #developerLove #community #pinecone

🔐 Launch Week Day 4: Enhanced Security and Access Controls Today, we're raising the bar for enterprise-grade security and controls to give you even more confidence when powering mission-critical applications in production. Here’s what’s new: ✅ CMEK: Gain full control of your data encryption and enhance tenant isolation. ✅ Granular RBAC: Assign API key roles for more robust and flexible access management. ✅ Audit Logs: Monitor control plane activities with logs stored securely in Amazon S3 endpoints. ✅ AWS PrivateLink: Now GA for serverless indexes, providing secure, private connectivity for your workloads. Learn more about CMEK and API key roles in our technical deep dive, shared below in the comments.

"What are AI assistants? How can they help me? And how can I put AI in production?" Great to share a stage with Christoffer Noring and Liam Hampton (both from Microsoft) at Microsoft Reactor London, ably MC'd by John Kinson for an audience of brilliant professionals specializing in Legal AI. Topics include LLMs, tool calling, assistants, and how developers can deploy their apps.