Chat Channel: Difference between revisions

From Tygron Support wiki
Jump to navigation Jump to search
No edit summary
No edit summary
 
(77 intermediate revisions by 2 users not shown)
Line 1: Line 1:
Chat Channels define the conversation with AI Agents. Each channel can have multiple [[Chat Message]]s.
{{Beta functionality}}


===Attributes===
Chat Channels define the chat interaction with [[AI Agent]]s visible in the [[Chat panel]]. Each channel can have multiple [[Chat Message]]s.
Chat Channel attributes can be used to guide the behavior of the underlying LLM [[Neural Network]].


{{channel attributes|suppresscategory=true|allowselflink=true|
==AI Agents==
{{:temperature (Chat Attribute)}}
{{main|AI Agent}}
{{:top_p (Chat Attribute)}}
The {{software}} has several default [[AI Agent|Chat Agent]]s available. It is also possible to add additional Agents with custom instructions.
{{:top_k (Chat Attribute)}}
 
{{:num_predict (Chat Attribute)}}
===Model===
{{:timout_sec (Chat Attribute)}}
{{main|Generative AI (GenAI)}}
{{:think_mode (Chat Attribute)}}
 
{{:cachable (Chat Attribute)}}
The Large Language Model used by the Agent.
{{:project_info (Chat Attribute)}}
 
}}
===Instructions===
An instruction is a set of prompts, settings, or rules that guides an [[AI Agent]]’s behavior, determines what data it can access, and explains how to respond to inputs.
 
===Tools===
{{main|Agent Tool}}
Tools can help the Agent achieve it's goal.
 
===Skills===
{{main|Skill}}
It is also possible to help the AI with [[Skill]]s. These are "job descriptions" of how to do specific tasks and can increase the scope of the agent's capabilities.


==Attributes==
{{:Agent Attributes}}


{{article end
{{article end
|notes=* To properly use this technology and to protect your data, several measures have been taken. These are described in our [[AI Rules]].
|howtos=*[[How to add a Chat Channel]]
*[[How to duplicate a Chat Channel]]
*[[How to remove a Chat Channel]]
*[[How to set the instructions of a Chat Channel]]
*[[How to change the LLM of a Chat Channel]]
*[[How to configure a Chat Channel]]
*[[How to allow a Chat Channel to edit a project]]
*[[How to toggle the thinking section of a Chat Channel]]
|api=*[[Api session items chatchannels]]
|api=*[[Api session items chatchannels]]
*[[Api session event editor chatchannel]]
*[[Api session event editor chat]]
*[[Api session event editor chat set instructions]]
*[[Api session event editor chat add item channel]]
|seealso=*[[Chat Message]]
*[[Generative AI (GenAI)]]
*[[AI Agent]]
*[[Agent Tool]]
*[[Chat panel]]
*[[Skill]]
}}
}}
{{Editor community nav}}


[[Category:Items]][[Category:Chat]]
[[Category:Items]][[Category:Chat]]

Latest revision as of 11:56, 15 October 2026

This functionality is currently in BETA.
Read more about Beta features.


Chat Channels define the chat interaction with AI Agents visible in the Chat panel. Each channel can have multiple Chat Messages.

AI Agents

Main article: AI Agent

The Tygron Platform has several default Chat Agents available. It is also possible to add additional Agents with custom instructions.

Model

Main article: Generative AI (GenAI)

The Large Language Model used by the Agent.

Instructions

An instruction is a set of prompts, settings, or rules that guides an AI Agent’s behavior, determines what data it can access, and explains how to respond to inputs.

Tools

Main article: Agent Tool

Tools can help the Agent achieve it's goal.

Skills

Main article: Skill

It is also possible to help the AI with Skills. These are "job descriptions" of how to do specific tasks and can increase the scope of the agent's capabilities.

Attributes

Agent attributes can be used to guide the behavior of the underlying AI Agent's Generative AI (GenAI) model.

Attribute Unit Description Default value
TEMPERATURE number Temperature controls the randomness of text that is generated by Agent's GenAI model during inference. A value >1 is more creative, <1 is more strict behavior. 1
THINKING_BUDGET_TOKENS number The maximum number of tokens the Agent's LLM can think before stopping. 1000
TOP_P number Top-P sampling selects a group of Agent GenAI model tokens whose cumulative probability is at least P. 0.95
TOP_K number Top-K sampling limits the Agent's LLM to choosing from the K most likely tokens at each step. 64
MAX_TOKENS number The maximum number of tokens the Agent's LLM can generate before stopping. 5000
TIMEOUT_SEC sec The maximum time allowed for the AI Agent before it is stopped. 600
THINK_MODE boolean With think-mode enabled the Agent's LLM returns both the reasoning and final answer. 1
PROJECT_INFO boolean Whether to include some basic info about the project that is accessible by the AI Agent. 1
CACHEABLE boolean Debug value, when deactivated the Agent Tools can no longer cache wiki pages. 1