Consumption of GenAI models Using Orchestration - A Beginner's Guide

[schiwekM]

Tutorials: https://developers.sap.com/tutorials/ai-core-orchestration-consumption.html

I think the JS Sample in step 4 last code block is wrong.

Currently it writes:

const orchestrationClient = new OrchestrationClient(
          {
            llm: {
              model_name: model,
              model_params: { 
                max_tokens: 1000, 
                temperature: 0.6, 
              }, 
            },
            template: templatingConfig
          },
          { resourceGroup: RESOURCE_GROUP }
        );

but according to https://sap.github.io/ai-sdk/docs/js/orchestration/chat-completion it should be:

const orchestrationClient = new OrchestrationClient(
          {
            llm: {
              model_name: model,
              model_params: { 
                max_tokens: 1000, 
                temperature: 0.6, 
              }, 
            },
            templating: templatingConfig
          },
          { resourceGroup: RESOURCE_GROUP }
        );

Thanks for fixing & BR,
Marten

[I321506]

@schiwekM Thank you for pointing this out. Will fix this ASAP.