A practical knowledge base for AI protocols, agents, core concepts, frameworks, and tools.
Learn what API Relay means and how it is used. An API relay is a term many AI tool users have run into recently. It usually refers to a transfer platform that sits between the user and the model's official service: instead of connecting directly to the official interfaces of OpenAI, Anthropic, Google, and others, the user calls the models through a unified address and key provided by the relay.
Learn what API Key means and how it is used. An API key is a string of characters you'll often see when using AI interfaces, plugins, and relays. It looks like a random password, but it's essentially a calling credential the service provider issues to you.
Learn what Agent means and how it is used. In an AI context, an agent usually refers to a system that can not only answer questions but also plan steps toward a goal, call tools, observe results, and keep acting.
Learn what Model Parameters means and how it is used. Model parameters are an unavoidable term when understanding "model size." We often hear that a model has billions, tens of billions, or hundreds of billions of parameters; these parameters aren't rules written in by users, but a large set of numeric values the model learns during training.
Learn what API (Application Programming Interface) means and how it is used. API stands for Application Programming Interface. It's a set of conventions by which software programs request services from one another and exchange data.
Learn what Multimodal AI means and how it is used. In the past, many AI tools handled only text, or only images. What sets multimodal AI apart is that it can understand and generate multiple forms of information at once, such as text, images, audio, and video.
Learn what AI Hallucination (Hallucination) means and how it is used. In an AI context, hallucination refers to a model generating content that looks fluent, confident, and real, but that is actually wrong, fabricated, unsupported, or inconsistent with the given materials.
Learn what ChatGPT Images (ChatGPT Image Features) means and how it is used. ChatGPT Images refers to using image generation, image editing, and image understanding capabilities within ChatGPT. It's more than "having AI draw a picture"—it's a set of multimodal capabilities built around images: you can describe the scene you want in words, or upload an image and ask it to edit, analyze, or extend it.
Learn what Vector Database means and how it is used. A vector database is a term that comes up often in RAG, semantic search, and recommendation systems. Its biggest difference from an ordinary database is this: ordinary databases are good at finding "exact matches," while vector databases are good at finding "similar in meaning."
Learn what Embedding means and how it is used. In an AI context, an embedding refers to converting text, images, audio, or other objects into a set of numbers, so machines can compare how similar they are.
Learn what Context Window means and how it is used. The context window is a crucial term for understanding large language models. It refers to the range of information a model can "see" and reference within one conversation or one request.
Learn what RAG (Retrieval-Augmented Generation) means and how it is used. RAG stands for Retrieval-Augmented Generation. It's a method that has a large language model look things up first and then answer based on the materials.
Showing 12 of 12 entries
Every entry grouped by topic — one click straight to the explanation.
