Heidelberg AI Curriculum

Showing 481–520 of 902 terms in the glossary

Letter J5 terms

job-function plugin How it works: A prepackaged skill set for a role (Finance, Sales, Support, Bio-Research…) that gives Cowork the context and steps for that kind of work.
JSON Data Format General Core: A plain-text format for structured data, made of named fields and their values inside curly brackets. Most APIs send and receive JSON, and both people and programs can read it.
Also known as: JSON file
2 other definitions
JSON · Data Format
A simple text format used to package the transcript of spoken words for sending over the WebSocket.
JSON · General
A text format that represents data as name‑value pairs, used for sending configuration and receiving results.
JSON mode Features: A looser version of structured outputs that guarantees the response will be valid JSON but does not enforce a specific field structure.
JSON schema Data Formats: A structured description of a tool’s input parameters written in JSON format, used by the Realtime API to validate calls.
JSONL Concepts: A plain-text file format where each line is a separate, valid JSON object — used to package many requests into one file for batch processing.

Letter K6 terms

K-AI Features: The built-in KNIME AI assistant that can answer questions about the platform (Q&A mode) or automatically extend your workflow by suggesting and adding nodes (Build mode).
KeyError Concepts: A Python error that occurs when you try to access a dictionary or DataFrame column using a name that does not exist in it.
KNIME Hub Features: The online repository where you can store, share, and download KNIME workflows and components; available as a free Community Hub or an enterprise Business Hub.
Knowledge Concepts: Persistent instructions you write once that Lovable follows across all future conversations, available at both workspace and project level.
Knowledge Base Features Core: A collection of documents an AI tool can search when it answers, such as manuals, policies or past reports. Its answers can only be as current and correct as the documents in it.
1 other definition
Knowledge Base · Features
A repository of documents you upload to Dify so the AI can search and retrieve relevant passages when answering questions, rather than relying only on its training data.
knowledge graph Concepts: An LLM-built map of the entities and relationships across your indexed documents, which Onyx uses to answer questions that span many sources rather than sitting in one file.

Letter L29 terms

Label Interface: A tag applied to an issue that categorises it (e.g., bug, enhancement) for easy filtering.
langchain-community Tools/Modules: A collection of extra tools for LangChain that lets you connect to services like ElevenLabs.
language='en_us' Parameters: A parameter telling the pipeline to use the English (United States) voice model.
latency budget Concepts: The maximum time allowed for a computation or response to meet real‑time requirements.
least privilege Core: Giving each person, account or tool only the access it needs for its task, and nothing more. If something goes wrong, less can be damaged.
Also known as: principle of least privilege, minimal permissions
Let's Encrypt Tools: Free service that provides TLS certificates so your custom domain uses HTTPS.
licence Core: The legal terms that say what you may do with software, a model or content: use it, change it, share it or sell it. Read the licence before you use something at work, especially for commercial use.
Also known as: license, software licence, software license
Live preview Concepts: A real-time view of your running app inside v0's chat, served from the sandbox so what you see matches what your users will experience.
LiveKit Components Framework Platform: A software platform that lets you build real‑time voice applications by handling audio routing and connections for you.
4 other definitions
LiveKit · Components
A Python library that handles real‑time audio routing and lets you connect speech‑to‑text, language models, and text‑to‑speech services.
LiveKit · Framework
A software platform that provides building blocks for real‑time audio and video applications.
LiveKit · Platform
A software platform that handles real‑time audio routing and lets you connect speech‑to‑text, language models, and text‑to‑speech services.
LiveKit · Components
A platform that provides Python classes and tools for building real‑time voice applications.
livekit.agents.Agent Class/Interface Classes Components: The base class you inherit from to create your own voice assistant, providing built‑in hooks for speech‑to‑text, language model, and text‑to‑speech integration.
4 other definitions
livekit.agents.Agent · Components
The base class you inherit from to create your own voice assistant logic.
livekit.agents.Agent · Class/Interface
A base Python class you extend to create a voice AI agent with LiveKit.
livekit.agents.Agent · Classes
A base Python class provided by LiveKit that you extend to create a custom voice AI agent.
livekit.agents.Agent · Components
The base class you inherit from to create your own voice assistant logic.
livekit.cli.run_app(entrypoint) Command Commands: A command‑line call that launches the agent using the method marked with @entrypoint.
4 other definitions
livekit.cli.run_app(entrypoint) · Command
A command‑line function that launches your script by calling the method you marked with @entrypoint.
livekit.cli.run_app(entrypoint) · Commands
A command‑line call that launches your agent script using the function you marked with @entrypoint.
livekit.cli.run_app(entrypoint) · Commands
A command‑line helper that launches your Python script by calling the function you marked with @entrypoint.
livekit.cli.run_app(entrypoint) · Commands
A command‑line call that runs the specified entrypoint method to start the agent.
lk cloud login CLI Commands: A command in the LiveKit CLI that authenticates you with your LiveKit cloud account so you can deploy apps.
lk cloud login / lk app env / lk start / lk agent create Commands: LiveKit CLI commands that log you into the cloud service, upload secret variables, prepare deployment settings, and build & launch a containerized agent.
llama-3.1-8b-instant Models: Meta's smaller Llama 3.1 model with 8 billion parameters, available on Groq for fast, low-cost responses; runs at ~560 tokens per second with a 131,072-token context window.
1 other definition
llama-3.1-8b-instant · Models
A small, fast Llama model on Groq suited to high-volume tasks where speed and a higher request cap matter more than reasoning depth.
llama-3.3-70b-versatile Models: Meta's Llama 3.3 model with 70 billion parameters, available on Groq for general-purpose tasks; runs at ~280 tokens per second and supports a 131,072-token context window.
1 other definition
llama-3.3-70b-versatile · Models
A larger, more capable Llama model on Groq, chosen in the model field when you need stronger reasoning rather than maximum speed.
llama3 Models: Meta's Llama 3 open-weight language model, available through Ollama and described as the most capable openly available LLM at the time of its release.
LLM Concepts Core: An AI model trained on huge amounts of text to predict the next word. That skill lets it answer questions, write, summarise and translate, but it can also produce fluent text that is wrong.
Also known as: large language model, language model
2 other definitions
LLM · Concepts
Large Language Model — the AI text engine (such as GPT-4 or Claude) that reads instructions and generates responses inside a Flowise workflow.
LLM · Concepts
Short for large language model, an AI that generates text based on patterns it learned from lots of data.
LLM Node Features: A workflow node that sends a prompt to a language model — supporting text, images, and documents — and returns the model's output as a variable the rest of the workflow can use.
LLM/VLM Concepts: Large language or vision‑language model used as a service to generate high‑level robot plans.
llmster Commands: The headless (no desktop window) daemon version of LM Studio designed for servers or machines without a screen — it runs as a standalone background service and can still serve models over the API.
LM Studio Concepts: A free desktop app that runs AI models on your own computer and exposes an OpenAI-compatible server.
lms Commands: The command-line tool bundled with LM Studio that lets you start the server, download models, and manage everything from a terminal instead of the desktop app.
lms --version Commands: Prints the installed version number of the lms command-line tool — the actual documented subcommand is lms version, but both forms report the current CLI version.
lms server start Commands: Launches LM Studio's local API server so other programs on your computer (or network) can send it requests and get AI responses back.
lms server status Commands: Prints whether the LM Studio API server is currently running and which port it is listening on.
lms server stop Commands: Gracefully shuts down the running LM Studio API server, terminating any in-progress requests before stopping.
local model Concepts Running locally Core: A model that runs on your own computer or your organisation's server instead of a provider's cloud. Your data stays on the machine, but you need enough memory, and the answers are usually weaker than those of the largest cloud models.
Also known as: self-hosted model, on-device model
2 other definitions
local model · Running locally
A model that runs on your own hardware so nothing leaves your machine; what you can run is limited by your memory.
local model · Concepts
An AI model that runs entirely on your own machine, keeping all conversation data private because nothing is sent to a cloud API.
localhost API & URLs Concepts Core: The name your computer uses for itself. An address such as localhost:3000 opens a service running on your own machine, which other computers can't reach.
Also known as: 127.0.0.1, loopback address
3 other definitions
localhost · Concepts
Your own computer, as an address — localhost:1234 is a server running on this machine, port 1234.
localhost · API & URLs
A special hostname that always means 'this computer' — using it ensures the connection never leaves your machine.
localhost · Concepts
A special hostname that always refers to your own computer, so a service at localhost is only reachable from that same machine.
localhost:1234 API & URLs: The host and port where LM Studio's server listens by default — shorthand for 'your own machine, port 1234'.

JLetter J5 terms

KLetter K6 terms

LLetter L29 terms

Letter J5 terms

Letter K6 terms

Letter L29 terms