Use LLM

Supported in: Batch

Call an LLM with a configurable prompt.

Expression categories: String

Declared arguments

Model - The LLM model to use.
Model
Prompt - The user prompt to pass to an LLM model.
List<Expression<AnyType>>
optional Output mode - Choose to output as a simple output where the output is the type of the output type parameter and errors are returned as null, or output a struct with the output the output type and error as fields.
Enum<Simple, With errors>
optional Output type - The output type LLM responses should adhere to.
Type<Array<AnyType> | Boolean | Date | Decimal | Double | Float | Integer | Long | Short | String | Struct | Timestamp>
optional System prompt - The system prompt to pass to an LLM model.
Literal<String>

Argument values:

Model:
gpt4ChatModel(
temperature: 0.0,
)
Prompt: prompt
Output mode: null
Output type: null
System prompt: In the context of a food delivery app, your job is to rate reviews given in the following user promp...

prompt	Output
The food was great!	5

Argument values:

Model:
gpt4ChatModel(
temperature: 0.0,
)
Prompt: [prompt, mediaRef]
Output mode: null
Output type: null
System prompt: You are a highly advanced AI designed to assist healthcare professionals by interpreting medical ima...

prompt	mediaRef	Output
Patient: John Doe, Age: 45, Symptoms: Persistent cough, shortness of breath, and chest pain. Please analyze the attached chest X-ray for any signs of pneumonia or other abnormalities.	{"mimeType":"image/jpeg","reference":{"type":"mediaSetViewItem","mediaSetViewItem":{"mediaSetRid":"r...	Diagnostic Report: Patient: John Doe Age: 45 Symptoms: Persistent cough, shortness of b...

Argument values:

prompt	Output
null	null

Description: Only MediaSet Reference, without a prompt, should have a null output. Argument values:

mediaRef	Output
{"mimeType":"image/jpeg","reference":{"type":"mediaSetViewItem","mediaSetViewItem":{"mediaSetRid":"r...	null

Description: Empty input string should have a null output. Argument values:

prompt	Output
empty string	null

Description: Input prompt surpassing model limits should have a null output. Argument values:

prompt	Output
What is the capital of France?	{ error: null, ok: Paris, }
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a ...	{ error: Context limit exceeded., ok: null, }

Description: Input prompt surpassing model limits should have a null output. Argument values:

prompt	Output
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a ...	null