Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Showing content from http://reference.wolfram.com/language/ref/LLMExampleFunction.html below:

LLMExampleFunction—Wolfram Language Documentation

We deliver solutions for the AI era—combining symbolic computation, data-driven insights and deep technology expertise.

• Data & Computational Intelligence
• Model-Based Design
• Algorithm Development
• Wolfram|Alpha for Business
• Blockchain Technology
• Education Technology
• Quantum Computation

WolframConsulting.com

• See Also
  • LLMFunction
  • LLMPrompt
  • LLMTool
  • Service Connections
  • OpenAI
  • Anthropic
  • GoogleGemini
  • AlephAlpha
  • Cohere
  • DeepSeek
  • Groq
  • MistralAI
  • TogetherAI
• Related Guides
  • Free-Form & External Input
  • Text Manipulation
  • Setting Up Input Interpreters
  • String Manipulation
  • Working with Templates
  • Converting between Expressions & Strings
  • Linguistic Data
  • LLM-Related Functionality
  • Text Normalization
  • Text Analysis
  • Text Generation

LLMExampleFunction[prompting,form]

includes the interpreter form to apply to the response.

• An LLMExampleFunction can be used to generate text using a large language model (LLM) with a prompt dynamically generated from a list of examples.
• LLMExampleFunction requires external service authentication, billing and internet connectivity.
• LLMExampleFunction returns an LLMFunction.
• LLMExampleFunction supports all options of LLMFunction:
• LLMEvaluator can be set to an LLMConfiguration object or an association with any of the following keys:
• "MaxTokens" maximum amount of tokens to generate "Model" base model "PromptDelimiter" string to insert between prompts "Prompts" initial prompts "StopTokens" tokens on which to stop generation "Temperature" sampling temperature "ToolMethod" method to use for tool calling "Tools" list of LLMTool objects to make available "TopProbabilities" sampling classes cutoff "TotalProbabilityCutoff" sampling probability cutoff (nucleus sampling)
• Valid forms of "Model" include:
• name named model {service,name} named model from service <|"Service"service,"Name"name,"Task"task|> fully specified model
• The generated text is sampled from a distribution. Details of the sampling can be specified using the following properties of LLMEvaluator:
• "Temperature"t Automatic sample using a positive temperature t "TopProbabilities"k Automatic sample only among the k highest-probability classes "TotalProbabilityCutoff"p Automatic sample among the most probable choices with an accumulated probability of at least p (nucleus sampling)
• Possible values for Authentication are:
• Automatic choose the authentication scheme automatically Environment check for a key in the environment variables SystemCredential check for a key in the system keychain ServiceObject[…] inherit the authentication from a service object assoc provide an explicit key and user ID
• With AuthenticationAutomatic, the function checks the variable ToUpperCase[service]<>"_API_KEY" in Environment and SystemCredential; otherwise, it uses ServiceConnect[service].
• LLMExampleFunction uses machine learning. Its methods, training sets and biases included therein may change and yield varied results in different versions of the Wolfram Language.

Create an LLMFunction from a small training set:

Evaluate the function on an input:

Clarify the task and process the output string using an interpreter type:

Evaluate the function on an input:

Specify examples as a list of rules:

Evaluate the function on an input:

Prepend a prompt to clarify the task:

Evaluate the function on an input:

Specify an interpreter type to process the output:

Evaluate the function on an input:

Some language models are more verbose than others:

They may also provide answers in an arbitrary programming language:

RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4