Create a Repository

Before creating repositories, read Repositories, Configure a Bucket, and Configure an AI LLM.

UI labels can evolve over time. If a button/label slightly differs in your workspace, follow the same flow and contact us on Discord if needed.

What changed in the UI

The Repositories area is now a top-level section in Cloud and AI Gateway (not only a storage sub-section). It is organized into three categories:

• Overview: global view of repository activity and quick access to repository details.

• Inventory: list of all repositories; this is where you usually create repositories.

• API Keys: centralized list of repository API keys across repositories.

You can create a repository from Overview or Inventory using the Add button.

Repository properties to define at creation time

When you create a repository, focus on these properties:

1. Name

   • Human-readable identifier (for example prod-eu-data, assistant-ai-gateway).

2. API endpoint type

   • Select the protocol your applications will use for this repository:

     • S3, GCS, or Azure Blob for storage resources.

     • OpenAI for AI LLM resources.

3. Initial resources

   • You can attach existing resources during creation, then add more later.

   • Supported resource families include:

     • Cloud Storage buckets/containers/accounts

     • AI LLM configurations

     • Packets (if enabled in your workspace UI)

To avoid collisions and keep the repository virtual namespace coherent, apply these rules during creation:

• S3 & GCS storage resources

  • Bucket names must be unique across providers inside the same repository.

  • You cannot mix an S3 bucket named mybucket with a GCS bucket also named mybucket in one repository.

• Azure Blob storage resources

  • Azure storage account names must not collide with S3/GCS bucket names in the same repository.

  • You cannot combine:

    • an S3 or GCS bucket called mystorage

    • with an Azure container under a storage account also called mystorage in the same repository.

  • You may include multiple containers from the same Azure storage account in one repository.

Do not generate API keys during repository creation. API key generation belongs to repository configuration and is covered in Configure a Repository.

Instructions

1

Open Repositories

Open Cloud and AI Gateway and go to Repositories.

2

Choose where to create

Open either:

• Overview and click Add or (+) button, or

• Inventory and click (+) .

3

Fill repository basics

Complete the form:

• Name

• Optional description/labels (if available in your UI)

4

Attach initial resources

Use Add resource to attach one or more existing resources (Storage, AI LLM) with API endpoint type (S3, GCS, Azure Blob, or OpenAI depending on your use case).

For storage resources, keep a collision-free namespace inside the same repository:

• You cannot attach two resources that create naming conflicts in the exposed virtual namespace.

• Typical collision case: same bucket/account identifier reused across providers in one repository.

Collision reminder:

• S3 and GCS names must stay unique across providers inside the same repository.

• Azure storage account names must not overlap with S3/GCS identifiers in that repository.

5

Save the repository

Click Finish Setup. The repository appears in Inventory and is visible in Overview (depending on the usage).

Continue with configuration

Open your new repository and continue with Configure a Repository to:

• add/remove resources,

• review endpoint and SDK details,

• generate and manage API keys.

Related API references

If you automate repository creation/configuration:

• Repository Management APIs

• Bucket Management APIs

• AI LLM Management APIs