AI Terminology
Navigator Terminology
Use Cases & AI Architectures
Element Library
How to Deploy a Solution
How to create a local expert LLM
LLM Dataset Generator
LLM Trainer
LLM Chat
Document QnA
How to create a computer vision model
Building a Dataset: Image Classifier
Building a Dataset: Object Detector
Prototyping & Hardening for Production
How to implement your AI model
Templates: Document QnA
Templates: LLM Dataset Generation
Templates: Train an LLM
Templates: Custom LLM Chatbot
Templates: Local Expert
Supported LLM Base Models

Table of Contents

LLM Chat

You have generated your LLM Dataset and you have trained your LLM Model. Now we can use our LLM Chat and interact with the trained expert.

  1. Start by creating a new Canvas and drag the LLM Chat element onto the Canvas.
  2. Open the LLM Chat Element setting and and make the following adjustments:
  • Select a Trained Artifact from the drop down. This is where the models you’ve trained with the LLM Trainer are stored. If you don’t have a trained artifact, you will chat with the pre-trained base model.
  • Base Model Architecture: This is the core model you’ll be fine tuning. Select any model from the dropdown.
  • Model System Prompt: This default prompts your model to act as an assistant. You can leave this setting alone, or play with it to change how the model responds.
    For example: ask the model to talk like a Pirate or Rock Star, speak in a casual tone, or speak in like a poet. If you have brand voice guidelines, this is the place to add them.
    ‍
  • Max token: 256 is recommended for testing
  • ‍Model Storage Path: Using the “Select Directory” button, choose the folder where you want to save the base model for the chat.
  • ‍Model Adapter Folder Path: A backup to the built in model artifact registry. If you have a model that is not in your registry, you can plug it in here.
  • ‍Max Tokens: A setting limiting the number of tokens from the LLMs output. By default this is loaded from the Trained Artifact.
  • ‍Temperature: A balance between predictability and creativity. Lower settings prioritize learned patterns, giving more deterministic outputs. Higher temperatures encourage creativity and diversity.

‍