Skip to content

/AWS1/CL_BDOINFRNCPVDRTGTCONF

The configuration for a provider-based inference target. This configuration explicitly defines the endpoint, model mapping, and operations used to route requests to a large language model (LLM) provider.

CONSTRUCTOR

IMPORTING

Required arguments:

iv_endpoint TYPE /AWS1/BDOPASSTHROUGHENDPOINT /AWS1/BDOPASSTHROUGHENDPOINT

The HTTPS endpoint of the inference provider that the gateway forwards requests to.

Optional arguments:

io_modelmapping TYPE REF TO /AWS1/CL_BDOMODELMAPPING /AWS1/CL_BDOMODELMAPPING

The configuration that translates client-facing model IDs to the model IDs expected by the provider.

it_operations TYPE /AWS1/CL_BDOINFRNCOPCONF=>TT_INFERENCEOPERATIONCONFS TT_INFERENCEOPERATIONCONFS

A list of per-operation configurations that map request paths to the models supported for each operation.


Queryable Attributes

endpoint

The HTTPS endpoint of the inference provider that the gateway forwards requests to.

Accessible with the following methods

Method Description
GET_ENDPOINT() Getter for ENDPOINT, with configurable default
ASK_ENDPOINT() Getter for ENDPOINT w/ exceptions if field has no value
HAS_ENDPOINT() Determine if ENDPOINT has a value

modelMapping

The configuration that translates client-facing model IDs to the model IDs expected by the provider.

Accessible with the following methods

Method Description
GET_MODELMAPPING() Getter for MODELMAPPING

operations

A list of per-operation configurations that map request paths to the models supported for each operation.

Accessible with the following methods

Method Description
GET_OPERATIONS() Getter for OPERATIONS, with configurable default
ASK_OPERATIONS() Getter for OPERATIONS w/ exceptions if field has no value
HAS_OPERATIONS() Determine if OPERATIONS has a value