Wolfram Language Paclet Repository

Community-contributed installable additions to the Wolfram Language

Primary Navigation

    • Cloud & Deployment
    • Core Language & Structure
    • Data Manipulation & Analysis
    • Engineering Data & Computation
    • External Interfaces & Connections
    • Financial Data & Computation
    • Geographic Data & Computation
    • Geometry
    • Graphs & Networks
    • Higher Mathematical Computation
    • Images
    • Knowledge Representation & Natural Language
    • Machine Learning
    • Notebook Documents & Presentation
    • Scientific and Medical Data & Computation
    • Social, Cultural & Linguistic Data
    • Strings & Text
    • Symbolic & Numeric Computation
    • System Operation & Setup
    • Time-Related Computation
    • User Interface Construction
    • Visualization & Graphics
    • Random Paclet
    • Alphabetical List
  • Using Paclets
    • Get Started
    • Download Definition Notebook
  • Learn More about Wolfram Language

LLMFunctions

Guides

  • LLMFunctions

Symbols

  • ChatEvaluate
  • ChatObject
  • GenerateLLMToolResponse
  • ImageSynthesize
  • LLMConfiguration
  • LLMEvaluator
  • LLMExampleFunction
  • LLMFunction
  • LLMPrompt
  • LLMResourceFunction
  • LLMSynthesize
  • LLMTool
  • LLMToolRequest
  • LLMToolResponse
  • $LLMEvaluator
[
EXPERIMENTAL
]
LLMFunction
​
LLMFunction[prompt]
represents a template for an large language model (LLM) prompt.
​
​
LLMFunction[{
prompt
1
,
prompt
2
,…}]
represents a combination of multiple prompts.
​
​
LLMFunction[prompt,form]
includes the interpreter
form
to apply to the response.
​
​
LLMFunction[…][params]
give the LLM service response for
prompt
applied to parameters
params
.
​
Details

Examples  
(6)
Basic Examples  
(3)
Create a function for getting cooking instructions:
In[1]:=
LLMFunction
["Describe how to cook `1`"]
Out[1]=
LLMFunction
template: Describe how to cook
1
interpreter: String

​
Create a helper tool:
In[1]:=
findbyproperty=
LLMFunction
["What is something that is `1` and `2`"]
Out[1]=
LLMFunction
template: What is something that is
1
and
2
interpreter: String

Use the function:
In[2]:=
findbyproperty["Blue","Round"]
Out[2]=
A blueberry.
​
Create a function that returns a city as an
Entity
:
In[1]:=
cityfinder=
LLMFunction
["Find a city between `1` and `2`","City"]
Out[1]=
LLMFunction
template: Find a city between
1
and
2
interpreter: City

Use the function:
In[2]:=
cityfinder["St. Louis","Chicago"]
Out[2]=
Springfield
Scope  
(2)

Properties & Relations  
(1)

SeeAlso
LLMExampleFunction
 
▪
LLMSynthesize
 
▪
LLMPrompt
 
▪
LLMTool
""

© 2025 Wolfram. All rights reserved.

  • Legal & Privacy Policy
  • Contact Us
  • WolframAlpha.com
  • WolframCloud.com