2. Language Model
The Language Model (LLM) is the foundation of the AI Builder. It is the "brain" that drives how the character or agent behaves and performs tasks.
You can select any LLM of your choice from the 20+ available models.
Available Language Models
There are two types of AI Models available in AI builder.
Skillful Models
These models are advanced and capable of using strategies, tools/skills, and memory to perform complex tasks.
Purpose: Ideal for niche tasks or multi-step problem-solving where the model must go beyond basic interactions, such as web scarping or fetching specific data from an API.
Example Use Case: A financial advisor bot connected to real-time stock market data and user financial records to provide personalized investment advice.
Currently available Skillful Models (LLM) :
GPT o3 Mini
GPT-4
GPT-4o
GPT-4o Mini
Gemini-2.5-pro-preview-03-25
Gemini-2.5-pro-exp-03-25
Gemini-2.0-flash-exp
Gemini-2.0-flash
Gemini-1.5-pro
Gemini-1.5-pro-latest
Basic Models
These models are limited to text-based interactions and lack the ability to use external tools or retain memory.
Purpose: Best for simple conversational tasks like FAQs or chats.
Currently available Basic Models (LLM):
GPT o1
Claude 3 Opus
Claude 3 Sonnet
Claude 3 Haiku
Claude 3.5 Sonnet
DeepSeek: R1
Nillion: DeepSeek-R1-Distill-Qwen-14B
Nillion: Llama-3.1-8B-Instruct
NilBot - Finetuned - GPT-4o-mini
Llama 3.3 70B Instruct (Meta)
Llama 3.1 Sonar 70B Online (Perplexity)
Mistral Large
Gemini-1.5-flash-latest
How LLMs Work Within AI Builder?
The LLM processes the character template, including:
Who the character is: Defined in the persona, including backstory and personality.
Context of character: Detailed in the scenario for context-specific actions.
Example dialogues: Provide structure to ensure the character responds consistently.
Note: Basic AI models may evolve in the future to support additional functionalities such as ability to use skills.
Last updated