View a markdown version of this page

AWS::BedrockAgentCore::GatewayTarget InferenceOperationConfiguration - Amazon CloudFormation
SyntaxProperties
Services or capabilities described in Amazon Web Services documentation might vary by Region. To see the differences applicable to the China Regions, see Getting Started with Amazon Web Services in China (PDF).

This is the new Amazon CloudFormation Template Reference Guide. Please update your bookmarks and links. For help getting started with CloudFormation, see the Amazon CloudFormation User Guide.

AWS::BedrockAgentCore::GatewayTarget InferenceOperationConfiguration

The configuration for a specific inference operation, including its request path and the models that the operation supports.

Syntax

To declare this entity in your Amazon CloudFormation template, use the following syntax:

JSON

{
  "Models" : [ ModelEntry, ... ],
  "Path" : String,
  "ProviderPath" : String
}

YAML

  Models: 
    - ModelEntry
  Path: String
  ProviderPath: String

Properties

Models

The list of models supported for this operation.

Required: No

Type: Array of ModelEntry

Minimum: 1

Maximum: 100

Update requires: No interruption

Path

The request path for this operation (for example, /v1/messages or /v1/responses).

Required: Yes

Type: String

Pattern: ^/[a-zA-Z0-9\-\._/]+$

Minimum: 1

Maximum: 256

Update requires: No interruption

ProviderPath

The provider path to forward requests to, if it differs from the request path. For example, /anthropic/v1/messages when the provider expects a different path than the client-facing /v1/messages.

Required: No

Type: String

Pattern: ^/[a-zA-Z0-9\-\._/]+$

Minimum: 1

Maximum: 256

Update requires: No interruption