📄️ Agents
There are 3 types of agents that can be created: Chat, Content Creator and Business Analyst
📄️ Prompting
ToothFairyAI Agents interact with users via prompts and instructions to tell the agent what to generate. The prompts are used to guide the agent on what to generate and how to generate it.
📄️ Topics
Topics are required so an AI agent can speak about specific documents and or related information. Topic selections allow for more control with an agent and specifies what its knowledge base consists of. To get you started there are 3 topics already created; PRIVATE, PUBLIC and WEBSITE.
📄️ Functions
Functions allow an AI instance (or agents) to consume data from an API endpoint. Administrators can apply settings to functions which determine how an agent makes requests to an API.
📄️ Domains
Domains allow an AI agent to consume data from a domain (or website).
📄️ Dictionaries
The dictionary helps assist with the translation of words from one language to another. We offer the ability add the source text (with context) and the translation. This will be used if the source is found in the documentation or if it is found in the chat.
📄️ Authorisations
Authorisations are used to authenticate API requests made by the agent. This is an optional setting and is only required if the API requires authentication.
📄️ Connections
Connections are used to authenticate DB requests made by the agent. This is an optional setting and is only required if the DB requires authentication.
📄️ Providers
Providers are used to connect your ToothFairyAI workspace to 3rd party LLM providers.
📄️ Channels
Channels are used to connect your ToothFairyAI workspace to 3rd party communication platforms.
📄️ Environments
Environments are used to store predefined code snippets and docker images for the use of coder agents with code execution
📄️ Intents
Intents are used to identify the user's intention from the text provided. The user can create a new intent by providing a name and a color for the intent. The color will be used to highlight the identified intent in the text.
📄️ NER (Named Entity Recognition)
NER is a useful tool for identifying and extracting key entities from text. These entities can include names of people, organizations, locations, expressions of time, quantities, monetary values, and percentages.