Glossary

Definitions of terms used in the curriculum.

Showing 681–720 of 902 terms in the glossary

Letter P18 terms

Project

  • Concepts
A folder (or set of folders) you open in Antigravity that defines the workspace boundary — the files, tools, and permissions the agent is allowed to use.

Also known as: project

3 other definitions

Project · Concepts

A named workspace in claude.ai that holds its own documents and instructions so every chat inside it starts with shared context without re-pasting.

project · Concepts

A logical container in Hetzner Cloud used to group servers, networks and other resources together.

Project · Concepts

A single app you are building inside Lovable, with its own code, chat history, integrations, and settings.

Projects

  • Features
A workspace inside ChatGPT that groups related chats, uploaded files, and shared context under one goal, useful for ongoing work that spans multiple sessions.

prompt

  • Concepts
  • Interface
  • Parameters
  • Core
The instruction or question you give an AI model. A good prompt says what you want, gives the material to work on and describes what the answer should look like.

Also known as: Prompt, prompts

5 other definitions

prompt · Interface

A text description you write that tells the AI what to create or do.

prompt · Concepts

The message or question you type into ChatGPT — it is the instruction that tells the AI what you want it to do.

prompt · Parameters

A short text description you write to tell the AI what image, video or edit you want.

prompt · Concepts

The message or question you type to Gemini to tell it what you want it to do.

Prompt · Concepts

A plain-English instruction you type to tell Lovable what to create, change, fix, or explain in your app.

prompt caching

  • Features
A feature that reuses the processed results of repeated prompt prefixes — like a shared system prompt — so subsequent calls with the same opening are faster.

prompt injection

  • Core
Planted instructions inside a document, web page or email that try to make an AI tool do something you didn't ask for, such as leak data. Treat any text the AI reads as untrusted, and limit what the tool is allowed to do.

Also known as: indirect prompt injection

Prompt queue

  • Concepts
A queue of pending prompts you can reorder, edit, copy, or remove before Lovable processes them.

prompt_cache_key

  • Features
An optional routing hint you attach to a request so that related requests (such as turns in the same conversation) are directed to the same cache, reducing latency.

Pronunciation fixes

  • Tips
Adding spaces, hyphens, or phonetic spellings to your script so Cartesia says a word correctly.

provider

  • Concepts
  • Core
The company or service that runs an AI model and sells access to it, for example through a chat app or an API. The provider's terms decide what happens to the data you send.

Also known as: model provider, AI provider

1 other definition

provider · Concepts

A company that supplies the AI model opencode talks to (for example Anthropic, OpenAI, or Google); you configure your API key for each provider you want to use.

provider: custom

  • Files & config
A config setting that points Hermes at any OpenAI-compatible server — used for local models.
1 other definition

provider: custom · Files & config

A setting in the Hermes Agent config.yaml that tells Hermes to call a custom OpenAI-compatible endpoint directly, such as your local Ollama server, using the base_url you specify.

PRP

  • Concepts
Product Requirements Prompt — a comprehensive, validation-gated blueprint the agent generates from a request and then executes.

pseudonymisation

  • Core
Replacing names and other direct identifiers with codes, while a separate key can still link them back. Pseudonymised data still counts as personal data under the GDPR.

Also known as: pseudonymised data, pseudonymization, pseudonymised

Publish

  • Features
The action that deploys a snapshot of your project to a live URL so others can visit and use your app.

pull request

  • Change control
  • Core
A request to merge the changes from one branch into another, usually the main branch. Others can review the changes, comment and approve before anything is merged.

Also known as: pull requests, PR, merge request

1 other definition

pull request · Change control

A forge record that compares a proposed branch with a target branch and collects discussion, checks, and a merge decision.

Used in Gitea, Review and branch protection

Pull request (PR)

  • Commands
  • Concepts
A request to merge changes from one branch into another, showing a side‑by‑side diff for review.

Also known as: pull request (PR)

1 other definition

pull request (PR) · Commands

A request on GitHub to review and possibly merge changes from one branch into another.

push

  • Commands
  • Core
Sending your local commits to the shared copy of a repository on a server, so others can see them.

Also known as: git push

1 other definition

push · Commands

Sending your committed changes from your computer up to the GitHub repository.

pytest tests/ -q

  • Commands
Runs the automated test suite in the tests/ folder using pytest, with -q (quiet) flag to show only failures rather than every test name.

Python

  • Core
A popular programming language that is easy to read and widely used for data analysis, science and AI. Many AI tools and scripts need Python installed on your computer.

Letter Q5 terms

Quadrant client wrapper

  • Concepts
A small Python class that simplifies creating collections, adding (upserting) vectors with IDs and payloads, and performing similarity searches using the Quadrant service.

quantization

  • Size & speed
  • Core
Storing a model's numbers with less precision, for example 4 bits instead of 16, so it needs less memory and runs on smaller machines. The cost is a small loss in answer quality.

Also known as: quantisation, quantized model

1 other definition

quantization · Size & speed

Shrinking a model by storing its weights at lower precision (e.g. 4-bit instead of 16-bit) so it fits a smaller machine, at a small quality cost.

Quick Create

  • Tools
A shortcut that produces a simple video from a brief text prompt without opening the full editor.

Quick Search

  • Features
The default, faster search mode suited for simple factual questions where a brief answer with a few sources is enough.

qwen2.5

  • Models
Alibaba's Qwen 2.5 open-weight language model series, available through Ollama and well-regarded for coding and mathematics tasks.

Letter R17 terms

RAG

  • Concepts
  • Core
Retrieval-augmented generation: the app first finds relevant passages in your documents, then gives them to the model together with your question. The answer can then quote your sources instead of relying on what the model remembers.
3 other definitions

RAG · Concepts

Retrieval-Augmented Generation — a pattern where your application fetches relevant documents from a database and adds them to the prompt so the model can answer questions about your own data.

RAG · Concepts

Retrieval-Augmented Generation — a technique where the AI looks up relevant passages from your knowledge base and uses them to write a more accurate, grounded answer.

RAG · Concepts

Retrieval-Augmented Generation — a technique where the AI fetches relevant passages from your own documents before answering, so responses are grounded in your data rather than general training.

RAM

  • Hardware
Volatile memory that holds data while the microcontroller runs, cleared when power is lost.

rate limit

  • Core
A cap on how many requests or tokens you may send in a given time. When you hit it, the service slows you down or refuses requests until the limit resets.

Also known as: rate limits, usage limit

ReAct

  • Concepts
An agent strategy available in Dify that guides the model through explicit Thought → Action → Observation cycles, useful for models that lack native function-calling support.

React Server Components

  • Concepts
A Next.js feature where parts of your page are rendered on the server before being sent to the browser, improving load speed and search-engine visibility; v0 uses Next.js, which enables these by default.

README

  • Core
The introductory file at the top of a project that explains what it does and how to install and use it. Read it before you install anything.

Also known as: README file, README.md

reasoning model

  • How models are built
  • Core
A model that works through a problem in hidden intermediate steps before it answers. It is slower and uses more tokens, but it does better on maths, code and multi-step tasks.

Also known as: thinking model

1 other definition

reasoning model · How models are built

A model trained to "think" through steps before it answers, trading speed for accuracy on hard problems.

reasoning tokens

  • Concepts
Internal thinking text the model generates before its final answer; depending on the reasoning_format setting they may appear in the response or be hidden, but they always count toward your token usage.

reasoning_effort

  • Features
An API parameter that tells the model how much thinking to perform before answering — options are low, medium, or high, trading speed for thoroughness.

Red

  • Process
The label for an example that the current prompt gets wrong.

red‑green‑refactor cycle

  • Process
A three‑step process where you first find a failing example (red), make the smallest change to fix it (green), then tidy up the prompt without breaking any tests (refactor).

Refactor

  • Process
A step where you simplify or reorganise the prompt while keeping all examples passing.

reference image field

  • Interface
The place in the Sora interface where you upload a photo to guide the AI’s visual output.
4 other definitions

reference image field · Interface

A place in the video generation interface where you upload a photo to guide the AI’s visual output.

reference image field · Interface

A place in the video generation interface where you upload a photo to guide the AI’s visual output.

reference image field · Interface

The place in the video generation interface where you upload a photo to guide the AI’s visual output.

reference image field · Interface

The place in the video generation interface where you upload a photo to guide the AI’s visual output.

Reference Image Integration

  • Features
Uploading a photo alongside your text prompt so the AI can copy exact visual details from that image into the generated video.
1 other definition

Reference Image Integration · Features

Uploading a photo alongside your prompt so Sora can use its visual details for more accurate video generation.

regression run

  • Process
Re‑executing all examples after a change to ensure previously passing cases are still correct.

Relaxed Mode

  • Modes
A setting that removes fast‑hour limits by queuing jobs when GPU demand is low, allowing unlimited video generation with longer wait times.

relay server

  • Components
A small backend service that forwards audio data between your web app and OpenAI’s Realtime API over WebSocket.
1 other definition

relay server · Components

A small backend program that forwards WebSocket messages between your front‑end app and an external API like OpenAI’s Realtime service.