RetroSearch Browse

The Wolfram Language includes a variety of capabilities for making use of large-language models (LLMs). Chat Notebooks provide interactive chat-based access, including the ability to offer natural-language-based assistance in using the Wolfram Language. The Wolfram Language also includes powerful functions for calling LLM functionality programmatically and for allowing LLMs to access Wolfram Language tools. The Wolfram Prompt Repository provides a curated collection of prompts for delivering a range of LLM-based capabilities.

Chat Notebooks

File ▶ New ▶ Chat Notebook

— insert a new chat input cell

— start a new chat block

Chat Notebook Shortcuts

@name — represent a persona prompt in a chat

!fun — represent a function prompt in a chat

#name — represent a prompt modifier in a chat

| — separate prompt arguments in a chat input

> — use the remaining chat input content as an argument

^ — use the preceding cell in a chat notebook as an argument

^^ — use all preceding content in a chat block as an argument

Symbolic Chat

ChatObject — create and represent an ongoing chat conversation

ChatEvaluate — add chat interactions and continue a conversation

ChatSubmit — asynchronous chat interactions

Programmatic Access to LLM Functionality

LLMFunction — a templated function to be evaluated by an LLM

LLMResourceFunction — use a prewritten template (from Prompt Repository, URL, etc.)

LLMExampleFunction — construct a template from examples

Raw Content Generation

LLMSynthesize — synthesize text from a prompt using an LLM

LLMSynthesizeSubmit — asynchronous text generation

Prompt Construction

LLMPromptGenerator — add context-dependent messages to an LLM prompt

LLMPrompt — retrieve a prewritten prompt

Semantic Search and RAG

SemanticSearch — search in a text corpus by semantic similarity

SemanticSearchIndex ▪ CreateSemanticSearchIndex ▪ UpdateSemanticSearchIndex ▪ SemanticSearchIndices

Calling the Wolfram Language from Within LLMs

LLMTool — symbolic representation of a tool for use by an LLM

LLMToolRequest ▪ LLMToolResponse ▪ GenerateLLMToolResponse

LLM Specification

$LLMEvaluator — default LLM configuration to be used

LLMEvaluator — option to specify LLM configuration to use

LLMConfiguration — symbolic representation of an LLM configuration

Low-Level Infrastructure

ServiceConnect ▪ ServiceExecute ▪ StringTemplate ▪ TemplateObject ▪ ResourceObject ▪ Authentication ▪ SystemCredential ▪ Environment

Chat & Generative Model Services

"OpenAI" — speech, image, text computation with OpenAI

"Anthropic" — chat and other text computation with Anthropic

"GoogleGemini" — chat and other text computation with Google Gemini

"GoogleSpeech" — speech synthesis and recognition using GoogleSpeech

"ElevenLabs" — speech synthesis and recognition using ElevenLabs

"AlephAlpha" ▪ "Cohere" ▪ "DeepSeek" ▪ "Groq" ▪ "MistralAI" ▪ "TogetherAI"

Related Functionality

TextSummarize — automatically produce different types of summarization

ImageSynthesize — generate an image from a textual prompt

SpeechSynthesize — synthesize a speech signal from text

Vector Database Infrastructure

VectorDatabaseSearch — approximate nearest-neighbor search in vector database

CreateVectorDatabase — create a database from a list of vectors

CreateSemanticSearchIndex — create vector database from text

VectorDatabaseObject ▪ AddToVectorDatabase ▪ VectorDatabaseObjects

Related Guides

▪

Machine Learning

▪

Neural Networks

▪

Natural Language Processing

Top

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