AIDevKit - AI Suite for Unity
API ReferencesDiscordGlitch9
  • Introduction
    • AI Dev Kit 3.7.0
    • Troubleshooting
    • FAQ
    • Update Logs
  • Provider Setup
    • API Key Setup
    • OpenAI
    • Google Gemini
    • ElevenLabs
    • Ollama
    • OpenRouter
  • Editor Tools
    • Introduction
    • Editor Chat
    • Model Library
    • Voice Library
  • GEN Tasks
    • Overview
    • Prefixes
    • Response
    • Chat
    • Image
    • Video
    • SoundFX
    • Speech
    • Transcript
    • Voice Change
    • Audio Isolation
    • Sequence
  • Advanced API (Pro)
    • Assistants
      • How it works
      • Creating custom functions
      • Creating assistants API
    • Realtime
  • Legacy API
    • OpenAI
      • 💬Chat completions
      • 🖼️Image operations
      • 🗣️Text to speech
      • 🎙️Speech to text
        • Recording real-time in Unity
      • 💾Files
      • 🔎Embeddings
      • 🛡️Moderations
      • ⚙️Fine-tuning
    • Google Gemini
      • 📝System instructions
      • 💬Text generation
      • ⚙️Fine-tuning
      • ▶️Fucntion calling
      • 🔎Embeddings
      • 🛡️Safety
      • 💻Code execution
  • Legacy Documents
    • AI Dev Kit 1.0
      • Preperation
      • Scriptable Toolkits
        • Chat Streamer
        • Image Generator
        • Voice Transcriber
        • Voice Generator
      • Editor Tools
      • Troubleshooting (Legacy)
        • ❗Build Error: The name 'UnityMenu' does not exist in the current context
        • ❗The type or namespace name 'AndroidJavaObject' could not be found
        • ❗The type or namaspace name 'Plastic' does not exist
        • ❗Build Error: The name 'Asset Database' does not exist in the current context
        • ❗'ModelData.Create(Provider, string, UnixTime?, string)': not all code paths return a value
      • Code Generators
        • C# Script Generator
        • Unity Component Generator
    • AI Dev Kit 2.0
      • Event Handlers
      • Editor Chat
      • Editor Vision (TTI, ITI)
      • Editor Speech (TTS)
      • Management Tools
        • Prompt History Viewer
        • AI Model Manager
        • TTS Voice Manager
        • OpenAI File Manager
        • OpenAI Assistant Manager
        • ElevenLabs Voice Library
Powered by GitBook
On this page
  • Accessing Editor ChatGPT
  • Setting Up
  • Generating Text with Editor ChatGPT
  • Managing Sessions
  • Practical Tips
  • Best Practices
  1. Legacy Documents
  2. AI Dev Kit 2.0

Editor Chat

PreviousEvent HandlersNextEditor Vision (TTI, ITI)

Last updated 10 months ago

This feature is only available in the Pro version.

Editor ChatGPT integrates OpenAI's powerful GPT models into the Unity Editor, providing developers with the capability to generate text, code, dialogues, and more, directly within their development environment. This tool is ideal for enhancing narrative-driven games, automating content creation, and enriching the interactive elements of your project.

Accessing Editor ChatGPT

To open EditorChatGPT, navigate to Tools > Glitch9 > OpenAI > EditorChatGPT in the Unity Editor. This will launch the EditorChatGPT window, where you can interact with the tool's features.

Setting Up

Upon opening Editor ChatGPT, you'll be presented with two main layouts: Workspace and Chatbot. Each serves a different purpose, with Workspace providing a more traditional text generation interface and Chatbot offering a conversational interface for generating dialogues.

Choosing a Layout

  • Chatbot Layout: Brings ChatGPT-like conversational capabilities directly into the Unity Editor

  • Workspace Layout: Ideal for generating larger blocks of text or code.

You can switch between layouts using the "Switch Layout" button located at the top of the EditorChatGPT window.

Generating Text with Editor ChatGPT

  1. Selecting the Model: At the bottom of the Editor ChatGPT window, choose the GPT model that best suits your needs (e.g., GPT-3.5 Turbo, GPT-4).

  2. Inputting Your Prompt: In the prompt field, type the text or question you want the AI to generate content for.

  3. Customizing Settings: Adjust settings like Max Tokens, Temperature, and Frequency Penalty to fine-tune the AI's output.

  4. Generating the Response: Click the "Generate" button to receive the AI's response. In the Chatbot layout, you can simply press Enter after typing your prompt.

Managing Sessions

  • Viewing History: EditorChatGPT keeps a record of your sessions, allowing you to review past prompts and responses.

  • Clearing Chat: If you wish to start afresh or clear the clutter, use the "Clear Chat" option to reset the session.

Practical Tips

  • Prompt Engineering: Experiment with different prompts to get the best results from the AI. The way a prompt is phrased can significantly impact the quality and relevance of the output.

  • Iterative Refinement: Don't hesitate to refine your prompts based on the AI's responses. It can lead to more precise and useful outputs.

  • Utilizing the Output: Generated text can be directly implemented into your game scripts, used as placeholders, or serve as inspiration for content creation.

Best Practices

  • Rate Limiting: Be mindful of the API call limits. Plan your usage to avoid hitting the rate limit unexpectedly.

  • Privacy and Sensitivity: When generating content, consider the privacy and sensitivity of the topics. Ensure generated content aligns with your project's guidelines and audience expectations.

  • Creative Exploration: Experiment with different conversational styles and topics to discover new content avenues and dialogue ideas.