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

  • LLM Functionality

Symbols

  • ChatEvaluate
  • ChatObject
  • GenerateLLMToolResponse
  • ImageSynthesize
  • LLMConfiguration
  • LLMEvaluator
  • LLMExampleFunction
  • LLMFunction
  • LLMPrompt
  • LLMResourceFunction
  • LLMSynthesize
  • LLMTool
  • LLMToolRequest
  • LLMToolResponse
  • $LLMEvaluator
[
EXPERIMENTAL
]
LLMConfiguration
​
LLMConfiguration[…]
represents a configuration for an LLM.
​
​
LLMConfiguration[propval]
creates a configuration based on
$LLMEvaluator
with the specified property set to
val
.
​
​
LLMConfiguration[
prop
1

val
1
,
prop
2

val
2
,…]
specifies several properties and values.
​
​
LLMConfiguration[LLMConfiguration[…],propspec]
creates a configuration based on an existing configuration.
​
Details and Options

Examples  
(3)
Basic Examples  
(3)
Create a configuration that includes a prompt:
In[1]:=
config=
LLMConfiguration
"Prompts"
LLMPrompt
["ELI5"]
Out[1]=
LLMConfiguration
model: Automatic

Use the configuration in an LLM evaluation:
In[2]:=
LLMSynthesize
"What is the tallest mountain?",
LLMEvaluator
config
Out[2]=
The tallest mountain is called Mount Everest and it's really, really high! People have to climb for many days to get to the top.
​
Specify multiple properties of a configuration:
In[1]:=
config=
LLMConfiguration
"Prompts"
LLMPrompt
["ELI5"],"Tools"
LLMTool[
]

Out[1]=
LLMConfiguration
model: Automatic

In[2]:=
LLMSynthesize
"Which is bigger, Chicago or Boston? Use the tool to check.",
LLMEvaluator
config
Out[2]=
First, let's use the tool to find out the population of Chicago and Boston. ​Now let's use the tool to find the population of Boston.​So, Chicago has a bigger population than Boston. It has about 2,746,388 people living there, while Boston has about 675,647 people.
​
Modify an existing configuration:
In[1]:=
config1=
LLMConfiguration
"Prompts"
LLMPrompt
["ELI5"]
Out[1]=
LLMConfiguration
model: Automatic

In[2]:=
config2=
LLMConfiguration
config1,"Tools"
LLMTool[
]

Out[2]=
LLMConfiguration
model: Automatic

SeeAlso
LLMSynthesize
 
▪
ChatObject
 
▪
LLMEvaluator
 
▪
$LLMEvaluator
RelatedGuides
▪
LLM Functionality
""

© 2025 Wolfram. All rights reserved.

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