Rating

Rating LOP

The Rating LOP provides a standardized way to rate items within a TouchDesigner project. It can be used manually by developers or programmatically by AI agents like Agent or Gemini Live. Ratings are saved to a JSON file, making it easy to track preferences, evaluate generated content, or collect feedback.

How It Works

The operator takes an “Item to Rate” (a string identifier) and a “Rating” (a float between 0.0 and 1.0). When the “Rate Item” pulse is triggered, it saves the item and its corresponding rating to a specified JSON file. This process can also be automated.

Parameters

Page: Rating

Item to Rate (Item) op('rating').par.Item Str

Default:

"" (Empty String)

Rating (Rating) op('rating').par.Rating Float

Default:

0.0

Auto Rate on Change (Autorate) op('rating').par.Autorate Toggle

Default:

Off

Rate Item (Rateitem) op('rating').par.Rateitem Pulse

Default:

None

File Settings Header

Storage Location (Storagelocation) op('rating').par.Storagelocation Menu

Default:

Project Folder

Rating Folder (Ratingfolder) op('rating').par.Ratingfolder Folder

Default:

"" (Empty String)

Rating File (Ratingfile) op('rating').par.Ratingfile Str

Default:

ratings

Last Rating File (Lastratingfile) op('rating').par.Lastratingfile Str

Default:

"" (Empty String)

Status Header

Last Rated Item (Lastrateditem) op('rating').par.Lastrateditem Str

Default:

"" (Empty String)

Output Display (Outputdisplay) op('rating').par.Outputdisplay Str

Default:

"" (Empty String)

Undo Last Rating (Undolastrating) op('rating').par.Undolastrating Pulse

Default:

None

Page: GetTool

GetTool Settings Header

Enable Tools (Enabletools) op('rating').par.Enabletools Toggle

Default:

On

Tool Configuration Header

Tool Info (Toolinfo) op('rating').par.Toolinfo Str

Default:

"" (Empty String)

Agent Selects Item (Agentselectsitem) op('rating').par.Agentselectsitem Toggle

Default:

Off

Page: About

Bypass (Bypass) op('rating').par.Bypass Toggle

Default:

Off

Show Built-in Parameters (Showbuiltin) op('rating').par.Showbuiltin Toggle

Default:

Off

Agent Tool Integration

🔧 GetTool Enabled 2 tools

This operator exposes 2 tools that allow Agent and Gemini Live LOPs to rate items and retrieve ratings for AI-driven evaluation and quality assessment workflows.

Use the Tool Debugger operator to inspect exact tool definitions, schemas, and parameters.

The most powerful feature of the Rating LOP is its ability to be used as a “Tool” by AI agents. When Enable Tools is on, the Rating LOP exposes its functionality to operators like Agent or Gemini Live, allowing the AI to programmatically rate items based on its own evaluation.

How the GetTool Works

The GetTool method in the Rating LOP dynamically generates two tools for an AI agent:

1. rate_item: This tool allows the agent to assign a rating to an item.
2. get_ratings: This tool lets the agent retrieve a list of all previously rated items.

This is especially useful in generative workflows where an AI creates content (e.g., images, text, or music) and then evaluates its own output.

Usage with Agent and Gemini Live

To let an AI agent use the Rating LOP, you assign it as a tool in the agent’s parameters. This allows the AI to call the rate_item and get_ratings functions programmatically.

1. Select the Agent: Click on the Agent or Gemini Live operator in your network to open its parameters.

2. Navigate to the Tools Page: Go to the Tools page in the parameter window.

3. Enable LOP Tools: Turn the Use LOP Tools toggle On.

4. Assign the Rating LOP: The External Op Tools parameter is a sequence of blocks for adding tools. Find an empty block (e.g., the first one, which has an OP parameter labeled Tool 0 OP).

5. Drag and Drop: Drag your rating LOP from the network editor and drop it directly onto the OP parameter field.

   

   Drag / drop the Rating LOP here!

6. Activate the Tool: Ensure the Mode menu for that tool block is set to enabled.

Once assigned, the agent will have access to the Rating LOP’s functions. You can then instruct it in your prompt to use these tools.

Example Prompt:

“You are an art critic. The user will provide you with an image. Your task is to analyze it and rate it on a scale from 0.0 to 1.0 based on its composition and color harmony. Use the rate_item tool to submit your rating.”

This workflow creates a powerful feedback loop where an AI can generate, evaluate, and record its own performance, enabling more complex and autonomous systems.