Pinecone BYOC is now generally available

Pinecone Bring Your Own Cloud (BYOC) is now generally available on AWS, Google Cloud, and Azure, so you can run Pinecone inside your own cloud account while we still manage it for you.

Agents are most useful when they're grounded in your proprietary knowledge, which is also the data you don't want leaving your security boundary. Making it available to them has meant running retrieval infrastructure in your VPC yourself and keeping accuracy and latency steady across every workload. BYOC takes that work off your plate.

How BYOC works:

• The data plane runs on a cluster in your cloud account, in the region you pick, including regions our standard service doesn't cover. Vectors, documents, metadata, and request payloads stay there.
• We handle upgrades, scaling, maintenance, and monitoring without SSH, VPN, inbound network access, or a standing cross-account IAM role. The cluster pulls operations from us over an outbound connection and runs them locally.
• Customer data never leaves the cluster. The only things that go out are cluster state plus anonymized metrics and traces, and you can send those metrics and traces to your own telemetry endpoint too.
• BYOC uses the same APIs and SDKs as our managed service, so you can pick the deployment model workload by workload.

Toyota Motor North America was one of our first BYOC customers. Their AI apps draw on decades of engineering expertise and R&D knowledge in their documentation, and all of it stays inside Toyota's environment and only reaches models they've vetted. BYOC handles it at Toyota's scale, with the security and governance controls their teams need.

Announcement: https://www.pinecone.io/blog/byoc-generally-available/
Docs: https://docs.pinecone.io/guides/production/bring-your-own-cloud

Happy to answer questions in the comments.