@ancient-wolf-19325 I have flyte deployed on AWS. What S3 buckets do I need?

You need at least one S3 bucket for Flyte metadata and another (optionally) for raw data. The metadata bucket stores workflow/task metadata, while the raw data bucket holds large input/output files. Both buckets must be specified in your Flyte deployment configuration (e.g.,

bucketName

and

rawDataBucketName

in Helm values or config files). These buckets must be accessible by FlyteAdmin, FlytePropeller, and task pods, typically via IAM roles for service accounts. For most deployments, a single bucket can serve both purposes, but separating them is supported and sometimes recommended for data management or security reasons. See configuration examples for details on how to set these values. According to the documentation, you must ensure the buckets are in the same AWS region as your cluster and that the IAM policies allow Flyte components to read/write as needed. For more, see the configuration examples and deployment guides. Would you like more detail on how to configure these buckets or IAM permissions? Sources: - Flyte EKS deployment configuration example - Flyte EKS production deployment example 👍 0 button 👎 0 button 💡 Hint: Mention @runllm in the thread for followups.