llm.generateTextStreamed(options)

Note:

The content in this help topic pertains to SuiteScript 2.1.

Method Description	Returns the streamed response from the LLM for a given prompt. This method is similar to llm.generateText(options) but returns the LLM response as a stream. After calling this method, you can access the partial response (using the StreamedResponse.text property of the returned llm.StreamedResponse object) before the entire response has been generated. You can also use an iterator to examine each token returned by the LLM, as the following example shows: var response = llm.generateTextStreamed("Write a 500 word pitch for a TV show about bears"); var iter = response.iterator(); iter.each(function(token){ log.debug("token.value: " + token.value); log.debug("response.text: " + response.text); return true; }) In this example, token.value contains the values of each token returned by the LLM, and response.text contains the partial response up to and including that token. For more information about iterators in SuiteScript, see Iterator. This method consumes AI Units. For more information, see NetSuite AI Units and NetSuite Features and AI Units FAQ.
Returns	llm.StreamedResponse
Aliases	llm.chatStreamed(options) Note: These aliases use the same parameters and can throw the same errors as the llm.generateTextStreamed(options) method.
Supported Script Types	Server scripts For more information, see SuiteScript 2.1 Script Types.
Governance	100
Module	N/llm Module
Since	2025.1

Parameters

Parameter	Type	Required / Optional	Description	Since
options.prompt	string	required if options.toolResults is not specified	Prompt for the LLM. If you specify a set of tool results using the options.toolResults parameter, any prompt you provide is ignored. The LLM uses only the specified tool results to generate a follow-up response based on those results.	2025.1
options.chatHistory	llm.ChatMessage[]	optional	Chat history to be taken into consideration.	2025.1
options.documents	llm.Document[]	optional	A list of documents to provide additional context for the LLM to generate the response. This parameter is supported only for Cohere models.	2025.1
options.image	file.File	optional	An image to query. You can send an image (as a file.File object) to the LLM and ask questions about the image. For example, you can ask for the following: Advanced image captions Detailed description of an image Information about charts and graphs in an image Note: Image processing is available only when using the Cohere Command A Vision model (cohere.command-a-vision). For more information about creating and loading files, see N/file Module.	2026.1
options.modelFamily	enum	optional	Specifies the LLM to use. Use llm.ModelFamily to set the value. If not specified, the Cohere Command A model (cohere.command-a-03-2025) is used.	2025.1
options.modelParameters	Object	optional	Parameters of the model. For more information about the model parameters, refer to Offered Pretrained Foundational Models in Generative AI in the Oracle Cloud Infrastructure Documentation.	2025.1
options.modelParameters.frequencyPenalty	number	optional	A penalty that's assigned to a token when that token appears frequently. The higher the value, the stronger a penalty is applied to previously present tokens, proportional to how many times they have already appeared in the prompt or prior generation. See Model Parameter Values by LLM for valid values.	2025.1
options.modelParameters.maxTokens	number	optional	The maximum number of tokens the LLM is allowed to generate. The average number of tokens per word is 3. See Model Parameter Values by LLM for valid values.	2025.1
options.modelParameters.presencePenalty	number	optional	A penalty that's assigned to each token when it appears in the output to encourage generating outputs with tokens that haven't been used. Similar to frequencyPenalty, except that this penalty is applied equally to all tokens that have already appeared, regardless of their exact frequencies. See Model Parameter Values by LLM for valid values.	2025.1
options.modelParameters.temperature	number	optional	Defines a range of randomness for the response. A lower temperature will lean toward the highest probability tokens and expected answers, and a higher temperature will deviate toward random and unconventional responses. A lower value works best for responses that must be more factual or accurate, and a higher value works best for getting more creative responses. See Model Parameter Values by LLM for valid values.	2025.1
options.modelParameters.topK	number	optional	Determines how many tokens are considered for generation at each step. See Model Parameter Values by LLM for valid values.	2025.1
options.modelParameters.topP	number	optional	Sets the probability, which ensures that only the most likely tokens with total probability mass of p are considered for generation at each step. If both topK and topP are set, topP acts after topK. See Model Parameter Values by LLM for valid values.	2025.1
options.ociConfig	Object	optional	Important: This object is no longer supported. Any values specified in this object are ignored.	2025.1
options.preamble	string	optional	Preamble override for the LLM. A preamble is the Initial context or guiding message for an LLM. For more details about using a preamble, refer to Offered Pretrained Foundational Models in Generative AI in the Oracle Cloud Infrastructure Documentation.	2025.1
options.safetyMode	string	optional	Specifies the safety mode to use. This parameter is supported for Cohere models only. Use values from the llm.SafetyMode enum to set the value of this parameter. If not specified, the llm.SafetyMode.STRICT mode is used by default.	2025.1
options.timeout	number	optional	Timeout in milliseconds, defaults to 30,000.	2025.1
options.toolResults	llm.ToolResult[]	optional	The tool results to use to generate a follow-up response. When you call llm.generateTextStreamed(options) and provide a set of tools using the options.tools parameter, the LLM can return a set of tool call requests in its response (in the StreamedResponse.toolCalls property). After your script calls the requested tools and creates tool results (as llm.ToolResult objects), you can provide these results to this method. The LLM uses the results to augment its original response. When you specify a value for this parameter, any prompt you provide using the options.prompt parameter is ignored. The LLM uses only the specified tool results to generate a follow-up response based on those results.	2025.2
options.tools	llm.Tool[]	optional	The tools that are available for the LLM to request.	2025.2

Errors

Error Code	Thrown If
SSS_MISSING_REQD_ARGUMENT	The options.prompt parameter is missing.
MUTUALLY_EXCLUSIVE_ARGUMENTS	Both options.modelParameters.presencePenalty and options.modelParameters.frequencyPenalty parameters are used when options.modelFamily is set to COHERE_COMMAND. You can use a value greater than zero for one or the other, but not both. The options.responseFormat parameter is used with any of the options.documents, options.tools, or options.toolResults parameters.
UNRECOGNIZED_MODEL_PARAMETERS	One or more unrecognized model parameters have been used.
INVALID_MODEL_FAMILY_VALUE	The options.modelFamily parameter was not set to a valid options. (For example, there may have been a typo in the value or in the enum.)
MODEL_1_DOES_NOT_ACCEPT_PREAMBLE	The options.preamble parameter was provided but the model does not support a preamble.
MODEL_1_DOES_NOT_ACCEPT_DOCUMENTS	The options.documents parameter was provided but the model does not support retrieval-augmented generation (RAG).
MODEL_1_DOES_NOT_ACCEPT_IMAGE	The options.image parameter was provided but the model does not support image processing.
MODEL_1_DOES_NOT_ACCEPT_SAFETY_MODE	The options.safetyMode parameter was provided but the model does not support safety mode.
DOCUMENT_IDS_MUST_BE_UNIQUE	Documents provided using the options.documents parameter have duplicate IDs.
INAPPROPRIATE_CONTENT_DETECTED	The response from the LLM included sensitive or inappropriate content that is restricted by the specified safety mode.
INVALID_SAFETY_MODE	The options.safetyMode parameter was not set to a valid option from the llm.SafetyMode enum.
INVALID_MAX_TOKENS_VALUE	The options.modelParameters.maxTokens parameter value is incorrect for the model. See Model Parameter Values by LLM for valid values.
INVALID_TEMPERATURE_VALUE	The options.modelParameters.temperature parameter value is incorrect for the model. See Model Parameter Values by LLM for valid values.
INVALID_TOP_K_VALUE	The options.modelParameters.topK parameter value is incorrect for the model. See Model Parameter Values by LLM for valid values.
INVALID_TOP_P_VALUE	The options.modelParameters.topP parameter value is incorrect for the model. See Model Parameter Values by LLM for valid values.
INVALID_FREQUENCY_PENALTY_VALUE	The options.modelParameters.frequencyPenalty parameter value is incorrect for the model. See Model Parameter Values by LLM for valid values.
INVALID_PRESENCE_PENALTY_VALUE	The options.modelParameters.presencePenalty parameter value is incorrect for the model. See Model Parameter Values by LLM for valid values.
MAXIMUM_PARALLEL_REQUESTS_LIMIT_EXCEEDED	The number of parallel requests to the LLM is greater than 5.

Syntax

Important:

The following code sample shows the syntax for this member. It isn't a functional example. For a complete script example, see N/llm Module Script Samples.

            // Add additional code
...

const response = llm.generateTextStreamed({
   // preamble is optional for Cohere models
   preamble: "You are a successful salesperson. Answer in an enthusiastic, professional tone.", 
   prompt: "Hello World!",
   documents: [doc1, doc2], // create documents using llm.createDocument(options)
   modelFamily: llm.ModelFamily.COHERE_COMMAND, // uses COHERE_COMMAND when modelFamily is omitted
   modelParameters: {
      maxTokens: 1000,
      temperature: 0.2,
      topK: 3,
      topP: 0.7,
      frequencyPenalty: 0.4,
      presencePenalty: 0
   }
});

var iter = response.iterator();
iter.each(function(token){
    log.debug("token.value: " + token.value);
    log.debug("response.text: " + response.text);
    return true;
})

...
// Add additional code 

          

Related Topics

• Model Parameter Values by LLM
• N/llm Module
• SuiteScript 2.1 Modules
• SuiteScript 2.1

General Notices