跳到主要内容

The AI Gateway provides a focused set of key features to support gateway operations, traffic control, and service observability.

Gateway Management

Gateway​

Definition: Manage the Kubernetes Gateway resources that serve as the entry point of the AI Gateway.

Key Functions:
  • View and manage Gateways deployed across clusters and namespaces.
  • Configure Listener, TLS, and routing-related settings; review Gateway details for operations/troubleshooting.

Gateway Config​

Definition: Manage templates for common settings applied to Gateway instances, including shared resources, replica counts, and tags. Multiple Gateways can reference the same Config to enforce consistent resource and operational policies.

Key Functions:
  • Create and manage reusable Gateway configuration templates.
  • Define common resource policies (resources), replicas, and tagging standards.
  • Apply consistent settings across multiple Gateways by referencing the same Config.

TLS Secret (Certificates)​

Definition: Manage Kubernetes Secret resources and support registration, rotation, and deletion of certificate/private-key pairs used by Gateway Listeners for HTTPS endpoints.

Key Functions:
  • Create and manage TLS Secrets.
  • Delete unused/expired TLS materials and review TLS Secret details for operations.

Traffic

Backend​

Definition: Manage routing targets for APIs, including external LLM providers (e.g., OpenAI, Anthropic) and in-cluster models/REST services.

Key Functions:
  • Register backends and manage backend connection settings and endpoints.
  • View backend details to validate routing targets and troubleshoot issues.

API​

Definition: Define traffic routing rules (HTTPRoute/API) on the Gateway by bundling hostname, path prefix, match conditions, backend, filters, and policies into a single Gateway exposure unit.

Key Functions:
  • Create APIs and manage API configuration.
  • Review API details for operational control.

Traffic Policies​

Definition: Manage traffic policies applied to Gateways and Route such as authentication, rate limiting, header transformations, and AI prompt guards, following the Kubernetes Gateway API policy attachment model.

Key Functions:
  • Create and manage reusable traffic policies for Gateways.
  • Inspect policy bindings and effective behavior for operations and troubleshooting.

API Keys​

Definition: Manages Kubernetes Secret resources, primarily used to store API keys for public LLM providers and credentials for user authentication.

Key Functions:
  • Create and manage Kubernetes Secret resources.
  • View metadata and references for operations/troubleshooting.

Observability

Topology​

Definition: Visualize the relationship graph among Gateways, APIs, Backends, Policies, and Secrets to view traffic flow, policy attachments, and backend mappings at a glance.

Key Functions:
  • Visualize component relationships and high-level flow
  • Support operational understanding and troubleshooting