C# Object Generation

Object Generation lets you turn natural language prompts into strongly-typed Unity C# objects by guiding the AI to return JSON that matches your class definition.

It's perfect for generating game data like:

• 📦 Items

• 🎮 Quests

• 🗨️ NPC Dialogue Trees

• 📋 Skill Definitions

• 🧠 AI Configuration Profiles

---

✅ How It Works

1. Define a C# class with special attributes

2. Call .GENObject<T>() with a descriptive prompt

3. AI returns JSON, which is parsed into a T object using JsonConvert

🔒 Schema guidance ensures the AI produces valid JSON matching your structure.

---

🚨 Required Annotations

Provider	Required Attribute
OpenAI	[OpenAIJsonSchemaResponse(...)] (on the class)
Others (e.g. Gemini)	[JsonSchema(...)] (on each property)

These attributes are mandatory. Without them, the task will fail to register the schema.

---

🎮 Example: Generate an RPG Item

using Glitch9.AIDevKit.OpenAI;
using Glitch9.IO.Json.Schema;
using System.Collections.Generic;

[OpenAIJsonSchemaResponse("item_response", Description = "RPG-style inventory item", Strict = true)]
public class GameItem
{
    [JsonSchema("id", Description = "Unique item ID", Required = true)]
    public string Id { get; set; }

    [JsonSchema("name", Description = "Name of the item", Required = true)]
    public string Name { get; set; }

    [JsonSchema("rarity", Description = "Item rarity", Enum = new[] { "Common", "Uncommon", "Rare", "Epic", "Legendary" })]
    public string Rarity { get; set; }

    [JsonSchema("effects", Description = "List of effects applied when used")]
    public List<string> Effects { get; set; }
}

---

✅ Unity Usage

GameItem item = await "Generate a legendary sword with magical effects"
    .GENObject<GameItem>()
    .SetModel(GPTModel.GPT4o)
    .SetTemperature(0.4f)
    .ExecuteAsync();

Debug.Log(item.Name + " - " + item.Rarity); // "Blade of Eternity - Legendary"

---

🧪 Example Output from AI

{
  "id": "legendary_sword_001",
  "name": "Blade of Eternity",
  "rarity": "Legendary",
  "effects": ["+50 Attack", "Fire Enchantment", "Life Steal"]
}

---

🎮 Example: Generate a Simple Quest

[OpenAIJsonSchemaResponse("quest_response", Description = "Basic RPG quest", Strict = true)]
public class Quest
{
    [JsonSchema("title", Description = "Quest name", Required = true)]
    public string Title { get; set; }

    [JsonSchema("description", Description = "What the player must do", Required = true)]
    public string Description { get; set; }

    [JsonSchema("objective", Description = "Main goal of the quest")]
    public string Objective { get; set; }

    [JsonSchema("rewardXP", Description = "XP rewarded upon completion")]
    public int RewardXP { get; set; }
}

Quest quest = await "Create a side quest for a fantasy game where a farmer asks you to find his lost chicken"
    .GENObject<Quest>()
    .SetModel(GPTModel.GPT4o)
    .ExecuteAsync();

---

🧠 Tips for Better Accuracy

✅ Tip	Why it helps
Use Strict = true	Ensures output matches your schema exactly
Provide clear, focused prompts	e.g., "Generate a level 5 healing potion item"
Use [JsonSchema] attributes	Describes intent to both AI and schema validator
Catch errors with try/catch	Handle malformed JSON safely in production

---

🧩 JSON Schema Attributes Cheat Sheet

Attribute	Use
Name	JSON field name
Description	AI guidance
Required	Ensures field presence
Enum	Limits possible values
Minimum, Maximum	For numbers
MinItems, MaxItems	For arrays
AdditionalProperties	Disable extra fields