Glossary
Study as flashcards →11 terms
- Context window Ch. 1Ch. 4
- The amount of preceding text, measured in tokens, that a language model can consider when generating a response.
- Embedding Ch. 1Ch. 4
- A numerical representation of a token that encodes semantic, syntactic, and contextual relationships as a vector in a high-dimensional space.
- Generative AI Ch. 1
- A branch of artificial intelligence that uses large, pre-trained models to generate human-like output such as text, images, or code.
- Hallucination Ch. 3
- LLM output that appears factually incorrect or irrelevant to a given task.
- Multimodal model Ch. 1
- A model capable of processing multiple data types, such as text, images, sound, and video.
- Retrieval-Augmented Generation (RAG) Ch. 4
- An approach that enhances language-model response generation by retrieving and incorporating relevant information from additional data sources.
- Shadow AI Ch. 5
- Use of AI tools outside an organization's approved integration and deployment approach, creating risks involving information security, data privacy, compliance, regulation, and intellectual property.
- Structured prompt Ch. 2
- A prompt for software testing built from role, context, instruction, input data, constraints, and output-format components.
- Symbolic AI Ch. 1
- A rule-based form of artificial intelligence that represents knowledge using symbols and logical rules.
- Tokenization Ch. 1
- The process in language models of breaking text into smaller units called tokens, which may be characters, sub-words, or words.
- Vector database Ch. 4
- A data store that can hold embeddings and support efficient retrieval of related content through semantic similarity.