Editing Beginner’s Guide to JanitorAi


== JanitorAI Beginner's Guide ==
'''JanitorAI''' is a customizable AI chatbot platform that enables users to create, share, and interact with large language model (LLM)-based characters. It supports integration with various AI models and APIs, making it popular among communities interested in interactive storytelling, roleplaying, and conversational AI.

This guide provides an overview of JanitorAI's basic concepts, terminology, and features intended for new users.

=== Overview ===
JanitorAI allows users to:

* Create and share AI-powered chatbots ("bots")
* Customize bot behavior through prompts and settings
* Connect to third-party AI models via API keys (e.g., OpenAI, Claude, DeepSeek)
* Style their profiles and bots using CSS and markdown-like syntax

Users interact with bots through text, and bot responses are generated using external LLMs (Large Language Models), which interpret user input and return appropriate responses.

=== Key Concepts and Terms ===

==== Large Language Model (LLM) ====
A '''Large Language Model''' is an artificial intelligence system trained on vast amounts of text data to understand and generate human-like language. Popular LLMs used on JanitorAI include:

* '''OpenAI's GPT-4 and GPT-3.5'''
* '''Anthropic’s Claude'''
* '''Google Gemini'''
* '''DeepSeek and Mixtral''' (open-source alternatives)

LLMs are not hosted by JanitorAI. Instead, the platform allows users to connect to these models via third-party APIs or proxies.

==== Tokens ====
A '''token''' is a unit of text processed by an LLM. Tokens typically represent short word fragments, whole words, or punctuation. For example:

* "Chatbot" = 1 token
* "I love AI!" = 4 tokens

LLMs have a '''context window''' that limits how many tokens they can process at once. For instance:

* GPT-3.5 has a context window of ~4,096 tokens
* GPT-4-Turbo can handle up to ~128,000 tokens

If a conversation exceeds the token limit, older messages may be truncated, which can lead to the bot "forgetting" earlier context.

==== Context ====
'''Context''' refers to the visible and hidden chat history the model uses to generate replies. Maintaining relevant context is essential for coherent, ongoing conversations. Some bots and models support "long-term memory," but most rely on short-term context stored during a session.

==== Prompting ====
'''Prompting''' is the method of instructing an LLM by crafting the initial input text. On JanitorAI, prompts can define a bot’s:

* Personality and backstory
* Response style
* Dialogue restrictions or behaviors

Effective prompts use a combination of descriptive language and formatting. Some creators use formatting tokens like `{{char}}` and `{{user}}` to reference the bot and user, respectively.

==== API Key ====
An '''API key''' is a string of characters used to authenticate and connect to external AI services. JanitorAI does not provide its own LLMs; instead, users must supply their own API keys from services such as:

* [https://platform.openai.com OpenAI]
* [https://console.anthropic.com Anthropic Claude]
* [https://openrouter.ai OpenRouter]
* [https://deepseek.com DeepSeek]

Using unofficial or proxy-based APIs may allow access to free models, though reliability and legality can vary.

==== Proxy ====
A '''proxy''' is a service that forwards requests between JanitorAI and an LLM API. Some proxies allow users to avoid rate limits, reduce costs, or use models unavailable via official APIs.

Proxies are community-run and should be used with caution, especially when transmitting sensitive information.

=== Getting Started ===

# Create a JanitorAI account at [https://janitorai.com janitorai.com]
# Choose or create a bot
# Configure the bot's prompt, persona, and greeting
# Connect an API key or proxy to enable AI responses
# Begin chatting and refine the bot as needed

=== Safety and Moderation ===
JanitorAI has a content policy that restricts certain types of content and image usage. Bots must comply with platform terms of service, and public bot cards are reviewed to ensure they meet visual and content standards.

Users can block unwanted messages or bots, report violations, and manage chat memory settings for privacy.

=== Related Topics ===

* [[Chatbot]]
* [[Prompt engineering]]
* [[Natural language processing]]
* [[OpenAI]]
* [[Large language model]]
* [[Tokenization (NLP)]]

== Disclaimer ==
Rephrased and edited with ChatGPT for better readability, formatting and more elaborations.