Retrieval Augmented Generation
Retrieval Augmented Generation (RAG) is a technique that retrieves relevant external data and supplies it to a model so its output is grounded in that data. The Gen AI Leader exam covers RAG to improve model output.
All Gen AI Leader Terms
Generative AI
Generative AI is a class of AI that creates new content — text, images, code, audio — from patterns learned during training.
Foundation model
A foundation model is a large model pre-trained on broad data that can be adapted to many downstream tasks.
Large language model
A large language model (LLM) is a foundation model trained on text to understand and generate natural language.
Gemini
Gemini is Google's family of multimodal generative AI models, offered through the Gemini app and across Google Cloud and Workspace.
Vertex AI
Vertex AI is Google Cloud's unified platform for building, tuning, deploying, and managing machine learning and generative AI models.
Token
A token is a chunk of text — roughly a word or word-piece — that a language model processes, and tokens are the unit used to measure context length and cost.
Context window
A context window is the maximum amount of text, measured in tokens, a model can consider at once.
Prompt engineering
Prompt engineering is the practice of designing inputs to guide a model's output, using techniques such as zero-shot, few-shot, and chain-of-thought.
Grounding
Grounding connects a model's responses to authoritative or real-time data sources to improve accuracy and reduce hallucinations.
Retrieval Augmented Generation
Retrieval Augmented Generation (RAG) is a technique that retrieves relevant external data and supplies it to a model so its output is grounded in that data.
Hallucination
A hallucination is a confident but incorrect or fabricated response from a generative model.
Responsible AI
Responsible AI is the practice of developing and using AI in ways that are fair, transparent, private, and safe.
Model tuning
Model tuning customizes a foundation model for a specific task or domain, for example through fine-tuning or adapters.