Exciting days to be a part of this wonderful team Pinecone 🎸🤘🚀

Announcing the Pinecone Summit: AI Transformation without Hallucination, a day-long generative AI event of the summer happening on July 13 in SF. summit.pinecone.io

Less is More: Why Use Retrieval Instead of Larger Context Windows pinecone.io/blog/why-use-r…

👍 Cool that GPT 4 and Claude have 32K-100K+ context windows, but it's not as useful as it seems... 🤦🏽‍♂️ Researchers from Stanford University tested LLM accuracy with different context sizes, great summary on Pinecone here: pinecone.io/blog/why-use-r… #NLProc #ArtificialIntelligence

🧠 Discover the power of retrieval-based models in conversational AI! Learn why retrieval beats larger context in this fascinating Pinecone blog. Learn more: hubs.ly/Q01ZCjG80

Introducing Canopy, an open-source #RAG framework to build AI assistants in under an hour. Free storage in Pinecone for up to 100K embeddings, or ~15M words / 30K pages. Supports GPT4-Turbo, with other models coming soon (including open-source). hubs.ly/Q028g-RL0

Canopy (v0.3.0) now supports Anyscale Endpoints! Join tomorrow's webinar by Anyscale for a live look into how to leverage these endpoints + Canopy to build a chat assistant fast. hubs.ly/Q02cHZ8T0 Learn more about Canopy's latest release: github.com/pinecone-io/ca….

Introducing Pinecone serverless, a completely reinvented vector database that lets you easily build fast and accurate GenAI applications at up to 50x lower cost. Available today in public preview, free to try with $100 in usage credits. pinecone.io/blog/serverles…

RAG with Pinecone Serverless Congrats to our friends at Pinecone for the recent launch of Pinecone Serverless! This has a few benefits for developers, including usage-base-pricing (>10x lower costs), improved latency, and effortless scaling (no more pods or storage limits).

In case you missed the chatter, Pinecone serverless is out and changing the game yet again. And now my favorite OSS RAG framework #Canopy supports Serverless as well! github.com/pinecone-io/ca… #Pinecone #RAG #GenAI #VectorDBs #Serverless

Can AI agents solve realistic, time-consuming web tasks such as “Which gyms near me have fitness classes on the weekend, before 7AM?" We introduce AssistantBench, a benchmark with 214 such tasks. Our new GPT-4 based agent gets just 25% accuracy! assistantbench.github.io