Heidelberg AI Curriculum

Showing 41–80 of 902 terms in the glossary

Symbols40 terms

@livekit.agents.function_tool Commands Decorator Decorators: A decorator that tells LiveKit to treat the following Python function as a tool the assistant can call when the user asks for it.
5 other definitions
@livekit.agents.function_tool · Commands
A decorator that tells LiveKit to expose a regular Python function as a tool the language model can call.
@livekit.agents.function_tool · Decorator
A decorator that tells LiveKit to expose a regular Python function as a tool the LLM can call.
@livekit.agents.function_tool · Decorators
A decorator that tells LiveKit to treat a regular Python function as a tool the language model can call during a voice chat.
@livekit.agents.function_tool · Decorators
A decorator that tells LiveKit to treat a regular Python function as a tool the LLM can call during conversation.
@livekit.agents.function_tool · Commands
A decorator that tells LiveKit to treat a regular Python function as a callable tool for the assistant.
/ Features Slash commands: Typing a forward slash at the start of your message opens the command menu so you can see and filter all available Claude Code commands.
1 other definition
/ · Features
In GitHub Copilot Chat, typing / opens a list of slash commands — shortcuts for common tasks like /explain (explain selected code) or /tests (generate unit tests) — so you do not need to write a full prompt.
/api/chat Files & config: Ollama's built-in REST API endpoint for sending chat messages and receiving model responses programmatically.
/api/docs Commands: A URL path you open in your browser on a running AnythingLLM instance to see its full interactive API reference, listing every endpoint you can call from code.
/api/v1/chat/completions API Endpoints: The OpenRouter API endpoint you send your message to — it receives your request, routes it to the chosen AI model, and returns the reply.
/Applications Files: The standard folder on a Mac where most apps are stored for easy launching.
/blend Commands: Command used after uploading up to five source pictures to combine their visual ideas into a single new image.
/browser Slash commands: A slash command that tells the agent to open a real web browser and carry out a web-based action you describe.
/bye Slash commands: A slash command you type inside an Ollama chat session to end the conversation and return to your normal terminal prompt (also works as /exit).
/clear Slash commands: Starts a fresh conversation with empty context; the previous conversation stays available via /resume.
/compact Slash commands: Summarises the conversation so far to free up context space; you can optionally tell it what to focus on (e.g. /compact Focus on test output).
1 other definition
/compact · Slash commands
A slash command that summarises the current conversation to reduce context size, useful when a long session is making responses slower or less focused.
/config Slash commands: Opens the Settings panel where you can change your theme, model, output style, and other preferences.
/context Slash commands: Displays a visual breakdown of what is filling your context window and shows optimization suggestions and capacity warnings.
/help Slash commands: Shows a list of available commands and a brief description of each.
/imagine Commands: The core Midjourney command you type to ask the AI to create images from a text description.
/implement Commands: Executes an approved plan — ideally in a fresh session so it follows the plan instead of drifting on old conversation.
/init Slash commands: A slash command that scans your project and automatically generates an AGENTS.md file with a summary of the codebase structure and build instructions.
/loop Slash commands: Runs a prompt repeatedly while the session stays open; omit the interval and Claude self-paces between iterations.
/mcp Slash commands: Manages MCP server connections and OAuth authentication; run with no argument to open the interactive list.
/model Slash commands: Opens a picker to switch the AI model Claude Code uses; the choice is saved as your default for new sessions.
1 other definition
/model · Slash commands
An interactive slash command that lets you switch the AI model Codex is using mid-session without restarting.
/models Slash commands: A slash command that lists all AI models available to you through your configured providers.
/new Slash commands: A slash command that starts a fresh session, clearing the conversation history so you can begin a new task with a clean slate.
/permissions Slash commands: An interactive slash command that sets what Codex is allowed to do without asking first — adjusting the approval threshold for the current session.
/plan Commands: Asks the agent to write an implementation plan (steps, files, and the checks that must pass) without editing any code yet.
/prime Commands: Loads context for a fresh session — the ticket, the file tree, and recent git history — so the agent gets oriented in one step.
/redo Slash commands: A slash command that re-applies a change you previously undid.
/resume Slash commands: Opens a picker to return to a previous conversation by name or ID, restoring the full message history.
/review Commands: A structured code-review pass over the changes, looking for bugs, missing tests and security issues.
/rewind Slash commands: Rolls the conversation and code changes back to an earlier point, or summarizes from a selected message, letting you undo a direction that went wrong.
/schedule Slash commands: A slash command that sets up a task to run automatically at a fixed time or on a repeating schedule, without you having to start it manually.
1 other definition
/schedule · Slash commands
Creates or manages routines that run on Anthropic-managed cloud infrastructure on a schedule, even when your computer is off.
/sessions Slash commands: A slash command that shows your previous conversations so you can switch back to an earlier session and continue where you left off.
/share Slash commands: A slash command that generates a shareable public web link to your current conversation so teammates can review the chat without needing opencode installed.
/skill-name Slash commands: The pattern for invoking any custom skill you have created; replace skill-name with the actual name of your SKILL.md file (e.g. /review-pr).
/skills approve Slash commands: Accept a staged skill so the agent can reuse it.
/skills diff Slash commands: Show exactly what a proposed skill would add or change before you accept it.
/skills pending Slash commands: List skills the agent has staged and is waiting for you to review.
/skills reject Slash commands: Discard a staged skill you do not want.
/thinking Slash commands: A slash command that toggles the display of the model's reasoning blocks, letting you see the thinking the AI showed before answering — it controls visibility only, not whether the model reasons.
/tokens Slash commands: An Aider slash command that reports how many tokens the current chat context is using, so you can see how much of the model's context window is occupied.
/undo Slash commands: An Aider slash command that undoes the last git commit if it was made by Aider, restoring your files to how they were before that change.
1 other definition
/undo · Slash commands
A slash command that removes your last message, the AI's response, and any file changes made during that exchange, letting you rephrase and try again.

#Symbols40 terms

Symbols40 terms