Pinecone Meetup SF: Taking AI Apps to Production

Taking AI applications from experiment to large-scale production can be complicated. At this meetup we’ll walk you through a reference architecture that makes it easy, complete with a vector database (Pinecone), data processing, data sync, security features, and everything else you’ll need. And since it’s orchestrated with Pulumi, you’ll be able to fork and run this in your own AWS environment even before the reception starts!

Next up, Jay Alammar, Director and Engineering Fellow (NLP) from Cohere, will show you how to build Retrieval Augmented (RAG) applications with Pinecone and Embed v3 (from Cohere)!

We'll have food, drinks, and like-minded folks you can talk to about the roadblocks and solutions you've found along the way.

• 6:00pm Doors open
• 6:30pm-7:30pm Talks
• 7:30 Eat, drink, and chat!