Generative AI Applications and MCP Documentation

These flashcards cover essential vocabulary and concepts related to generative AI applications and the Model Context Protocol (MCP) based on the lecture notes.

Generative AI Applications

Applications that use AI to generate content or provide specific functionalities that leverage AI capabilities.

Foundation Models

Models broadly trained on massive datasets without task-specific optimization.

Retrieval-Augmented Generation (RAG)

A method used for providing domain-specific information to a model through prompts.

Model Context Protocol (MCP)

A protocol designed to enable standardized communication between AI models and external tools.

Long Conversation Memory

A system that stores contextual information over time in conversational AI.

Dimensionality of Text Embeddings

The measure of the number of features in text embeddings, e.g. 1536 for the text-embedding-ada-002 model.

Logic, Calculation, and Search

Abilities that large language models (LLMs) lack but basic computer programs can manage easily.

Agents

Objects that consume input and output helpful information in the context of Large Language Models (LLMs).

LangChain

A framework built around large language models (LLMs) that facilitates their use in various applications.

Transfer Learning

A concept allowing reuse of the same core components of pretrained transformer models for different tasks.