Visit Pinecone at Microsoft Build and see how we complete the AI toolchain #copilot #microsoft #msbuild
AI Apps: Driving innovation from development to production hubs.ly/Q02y2zyD0

Introducing Private Endpoints for AWS PrivateLink. Connect securely from your VPC to Pinecone without exposing traffic to the public Internet.

hubs.ly/Q02xY0110

If you're in Seattle for Microsoft Build, visit Pinecone at booth FP08 and learn more about our integrations with Azure OpenAI and GitHub CoPilot.

Join us on Wednesday evening with New Relic and Pulumi for an AI Infrastructure Happy Hour
hubs.ly/Q02xMCvX0

You can list all records or just those with a common ID prefix with the Java client (v1.1.0) in addition to our Python client (v3.0.1 and later) and Node.js client (v2.1.0). Learn how this helps you better manage documents for RAG: hubs.ly/Q02xLpHn0

The latest release of the Pinecone Spark Connector (V1.0.0) adds support for serverless indexes. Learn more about the release, and start building today: hubs.ly/Q02xsHVV0

A crucial part of vector databases is the ANN algorithms they use to index data. Read this article to get an overview of the vector indexing landscape and analyses of a few popular algorithms hubs.ly/Q02xk5pq0

Now you can build AI applications with Pinecone in seconds! Try our new sample apps hubs.ly/Q02wQwNK0

Multi-tenancy enables you to share infrastructure and operational overhead across customers, while reducing costs and simplifying system management.

See our updated documentation for how to implement multi-tenancy in Pinecone serverless: hubs.ly/Q02wHyFq0.

'It costs about $200/month total to run and only 20% of my time was building the AI portions' - Hassan of Together AI shares design and tooling choices that made it simple to scale his POC to product-level usage overnight.

Watch the full video: hubs.ly/Q02wBj-c0

The new version of our Python client (v4.0.0) improves your vector upsert throughput 3x.
Check out the release notes for more details: hubs.ly/Q02w0LwH0

[status] Investigating: We are currently investigating the issue. stspg.io/q5gr86hycr8t?u…

This month, we continued expanding our serverless service and improving your experience building with Pinecone. Check out some of our product highlights: hubs.ly/Q02vLmvK0

chunking is a critical part of data prep in RAG (dare I say, the most important part?)

I just added two new code walkthroughs to the Pinecone RAG series:

1. overview of different chunking methods
2. deep dive into semantic chunking

pinecone.io/learn/series/r…

#GenAI

End-to-end RAG tutorial by Santiago with Pinecone + LangChain

New AI + a16z podcast: Pinecone CEO @edoliberty chats with Satish Talluri and Derrick Harris about the opportunities for vector databases and retrieval augmented generation (RAG), and ML in 2024 vs in 2003. a16z.com/podcast/vector…

Pinecone now support HashiCorp Terraform so you can manage your Pinecone resources via infrastructure as code. Learn more and start building today hubs.ly/Q02v6nr10

Adding authentication and authorization to RAG apps is important in many enterprise scenarios - and beyond. Here's an approach to manage authorization at scale, using @Aserto_com, Clerk and @Pinecone.

hubs.ly/Q02t-BNZ0

Join our next RAG Brag episode on May 7th, with Mike Heap & Alex Rainey, founders of My AskAI, as they share how LLM and Pinecone help customer support teams save hours of reading, searching, and waiting with their own AI chatbots > hubs.ly/Q02tT38m0

Attending the #AWSSummit in London today? Pinecone was recently recognized as the top SaaS product on the AWS Marketplace (last month). Visit booth B12 to see how Pinecone serverless on AWS lets you deliver remarkable GenAI applications faster, & at up to 50x lower cost @AWScloud