Generative AI (GenAI): Difference between revisions
Jump to navigation
Jump to search
Created page with "Large Language Models (LLM) are used to generate Chat Messages used in Chat Channels." |
No edit summary |
||
| (39 intermediate revisions by 2 users not shown) | |||
| Line 1: | Line 1: | ||
Large Language Models (LLM) | Generative AI [[Neural Network]] models are used in multiple ways in the {{software}} by [[AI Agent]]s. | ||
===Large Language Models=== | |||
List of open weight Large Language Models (LLM){{ref|LLM}} models available to Chat Agents. | |||
* '''Gemma4 (Speed)''': Gemma4 model{{ref|Gemma4}} optimized for fast reactions. | |||
* '''Qwen3.8 (Quality)''': Qwen3.8 model{{ref|Qwen3.8}} optimized for quality needed for coding, creating [[TQL]] queries and calling session endpoints. | |||
===Vision Models=== | |||
These models help the LLM's to identify features in images from the interface or e.g. Overlay exports. | |||
===Diffusion Models=== | |||
These models can create new or edit existing images that can be used in Design Agents. | |||
===Embeddings=== | |||
Embedding model used for AI assisted data search. | |||
{{article end | |||
|notes= | |||
* All models run Tygron [[Cloud Computing]] servers, with no links to external hosting and follow strict [[AI Rules]]. | |||
|seealso=*[[Chat Channel]] | |||
*[[AI Agent]] | |||
|references= | |||
<references> | |||
{{ref|LLM | |||
|name=LLM | |||
|author= | |||
|page= | |||
|source= | |||
|link=https://en.wikipedia.org/wiki/Large_language_model | |||
|lastvisit=2026-06-29 | |||
}} | |||
{{ref|Gemma4 | |||
|name=Gemma4 | |||
|author= | |||
|page= | |||
|source= | |||
|link=https://deepmind.google/models/gemma/gemma-4/ | |||
|lastvisit=2026-06-29 | |||
}} | |||
{{ref|Qwen3.8 | |||
|name=Qwen3.8 | |||
|author= | |||
|page= | |||
|source= | |||
|link=https://qwen.ai/ | |||
|lastvisit=2026-09-03 | |||
}} | |||
</references> | |||
|howtos=*[[How to change the LLM of a Chat Channel]] | |||
|api=* [[Api session event editor chat set neural network]] | |||
}} | |||
{{Editor community nav}} | |||
Latest revision as of 13:29, 7 October 2026
Generative AI Neural Network models are used in multiple ways in the Tygron Platform by AI Agents.
Large Language Models
List of open weight Large Language Models (LLM)[1] models available to Chat Agents.
- Gemma4 (Speed): Gemma4 model[2] optimized for fast reactions.
- Qwen3.8 (Quality): Qwen3.8 model[3] optimized for quality needed for coding, creating TQL queries and calling session endpoints.
Vision Models
These models help the LLM's to identify features in images from the interface or e.g. Overlay exports.
Diffusion Models
These models can create new or edit existing images that can be used in Design Agents.
Embeddings
Embedding model used for AI assisted data search.
Notes
- All models run Tygron Cloud Computing servers, with no links to external hosting and follow strict AI Rules.
How-to's
See also
API Endpoints
References
- ↑ LLM ∙ Found at: https://en.wikipedia.org/wiki/Large_language_model ∙ (last visited: 2026-06-29)
- ↑ Gemma4 ∙ Found at: https://deepmind.google/models/gemma/gemma-4/ ∙ (last visited: 2026-06-29)
- ↑ Qwen3.8 ∙ Found at: https://qwen.ai/ ∙ (last visited: 2026-09-03)