Concept graph
Generative AI and LLM glossary
Clear AI definitions with practical context, examples, and links to related models, tools, and concepts.
Models
Speech-to-speech
Speech-to-speech, or full-duplex voice, takes spoken audio and returns spoken audio in one live session instead of chaining STT, an LLM, and TTS.
Models
Speech-to-text
Speech-to-text, or ASR, converts audio into text, optionally with timestamps, speakers, and punctuation.
Data Sampling
stratified-sampling
A sampling method that ensures representation from different subgroups in a dataset.
Development
Structured Outputs
Structured Outputs constrain model responses to match a developer-supplied schema, typically for reliable JSON or function-call arguments.
Machine Learning
Supervised Learning
A type of machine learning where the model learns from labeled data.
Machine Learning
Support Vector Machine (SVM)
A supervised learning model used for classification and regression tasks.
Machine Learning
support-vector-regression
An extension of support vector machines that predicts continuous values instead of categories.
Artificial Intelligence
swarm intelligence
Swarm intelligence is the collective behavior of decentralized systems typically seen in nature.
Data Science
synthetic-data-generation
The process of creating artificial data that mimics real-world data for training machine learning models.
Product
System prompt
A system prompt is trusted developer instruction that sets role, tools, and policy before the user message.
NLP
task-oriented-dialogue-systems
Systems designed to manage specific tasks through natural language conversation.
Inference
Temperature
Temperature scales how randomly a model samples the next token: lower is more deterministic, higher explores more.
Deep Learning
temporal-convolutional-network
A type of neural network designed for sequence modeling using convolutional layers.
Models
Text-to-image
Text-to-image models generate pictures from a text prompt, sometimes with negative prompts, seeds, and reference images.
Models
Text-to-video
Text-to-video models generate moving clips from text, and sometimes from images, keyframes, or prior video.
Data Analysis
Time Series Analysis
A method used to analyze time-ordered data points to extract meaningful statistics and characteristics.
Data Analysis
Time Series Forecasting
The process of predicting future values based on previously observed values in a time-ordered series.
Models
Time-series foundation model
A time-series foundation model is pretrained on many series so it can forecast new series with little or no task-specific training.
Inference
Token
A token is the subword or symbol unit a model reads and writes; context limits, pricing, and latency are counted in tokens.
Natural Language Processing
Tokenization
The process of converting text into smaller pieces, called tokens.
Agents
Tool calling
Tool calling lets a model request that the application run a defined function, API, or built-in tool, then return the result to the model.
Inference
Top-k
Top-k sampling restricts next-token choice to the k highest-probability tokens before sampling.
Inference
Top-p
Top-p, or nucleus sampling, draws the next token from the smallest set of tokens whose cumulative probability exceeds p.
Control Systems
Transfer Function
A mathematical representation of the relationship between input and output of a system.