1. SuiteCloud Platform
  2. SuiteScript
  3. SuiteScript 2.x
  4. SuiteScript 2.x Generative AI APIs

SuiteScript 2.x Generative AI APIs

Note:

The content in this help topic pertains to SuiteScript 2.1.

SuiteScript Generative AI APIs (N/llm Module) enable you to work with generative artificial intelligence (AI) in NetSuite using SuiteScript. You can use these APIs to send requests to large language models (LLMs) and to receive responses from them. NetSuite accesses LLMs through an integration with the Oracle Cloud Infrastructure (OCI) Generative AI service.

NetSuite provides generative AI capability in the user interface in two ways:

Important:

SuiteScript Generative AI APIs (N/llm module) are available only for accounts located in certain regions. For a list of these regions, see Generative AI Availability in NetSuite.

How the SuiteScript Generative AI APIs Work

  1. A NetSuite developer uses the N/llm module in their SuiteScript code to send a request to the LLM.

  2. NetSuite accepts the prompt and any optional parameters included in the request and passes them to the OCI Generative AI Service.

  3. OCI Generative AI service processes the request. OCI Generative AI service uses the LLM specified in your code. If you do not specify the LLM in your code, it uses the Cohere Command R LLM. The data never leaves Oracle, nor is it used by third parties for model training.

    Note:

    When you use the N/llm module, your data may be processed globally according to the Oracle Services Privacy Policy.

  4. OCI Generative AI Service sends the LLM response back to NetSuite.

  5. NetSuite processes the response and returns it to the SuiteScript code.

  6. The SuiteScript code uses the response per the rest of the script.

                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   

Supported LLMs

The generateText methods have a modelFamily parameter that you can use to specify the LLM used, and a modelParameters object that enables you to send supported parameters to the LLM with your prompt. Model parameters are those supported by the Cohere Command R model (cohere.command-r-08-2024), Cohere Command R+model (cohere.command-r-plus-08-2024), or the Meta Llama 3.2 model (meta.llama-3.2-90b-vision-instruct) available through the OCI Generative AI service. If your code does not specify the model to use (through the modelFamily parameter), the Cohere Command R model is used. For more information, refer to the Chat Model Parameters topic in the Oracle Cloud Infrastructure Documentation.

The evaluateText methods take an existing prompt, along with values for any variables that the prompt uses, and send it to the LLM. You can use Prompt Studio to specify the model family that each prompt uses.

Usage Modes

There are three usage modes for using the N/llm module. The following table describes the usage modes in more detail.

Usage Mode

Description

When to Use This Mode

Free

Free, limited usage through NetSuite.

When using the free limited-use mode, each successful response to NetSuite from the OCI Generative AI service counts as one use. When the capacity is used completely, the LLM module returns an error for subsequent calls until the next month.

  • Testing the capability

  • Known, low quantity needed

On Demand

Unlimited, paid usage through your company’s own Oracle Cloud account. When using the unlimited-use model through your company’s own Oracle Cloud account, your company pays for on demand inferencing in the Oracle Generative AI service. To learn if this is the right choice for your company, refer to Paying for On Demand Inferencing in the Oracle Cloud Infrastructure Documentation.

This mode requires that you complete the setup described in Using Your Own OCI Configuration for SuiteScript Generative AI APIs. You must provide your OCI credentials either in your SuiteScript code (using the ociConfig object) or on the Settings subtab of the AI Preferences page.

  • Known medium quantity needed

  • Unknown quantity needed

  • Use cases that would fail if you ran out of capacity

  • You are developing a SuiteApp

  • You prefer pay-as-you-go service

Dedicated AI Cluster

Unlimited, paid usage through your company’s own Oracle Cloud account. When using the unlimited-use model through your company’s own Oracle Cloud account, your company pays for dedicated AI clusters in the Oracle Generative AI service. To learn if this is the right choice for your company, refer to Paying for Dedicated AI Clusters in the Oracle Cloud Infrastructure Documentation.

This mode requires that you complete the setup described in Using Your Own OCI Configuration for SuiteScript Generative AI APIs. You must provide your OCI credentials either in your SuiteScript code (using the ociConfig object, including the ociConfig.endpointId value) or on the Settings subtab of the AI Preferences page.

  • Known high quantity needed

  • Unknown quantity needed

  • Use cases that would fail if you ran out of capacity

  • You are developing a SuiteApp

  • Your use case requires a dedicated AI cluster

SuiteScript API Governance Limits for N/llm

The N/llm module is subject to SuiteScript API governance limits. The governance limits are included in individual method topics. For more information, see SuiteScript Governance and Limits and SuiteScript 2.x API Governance.

Related Topics

General Notices