All demosCatalog Studio

Catalog Studio

Messy product copy. Clean catalog fields.

Performance & cost

This session

Ready to run

Delivery time · median: —
Live model compute: —
Live input tokens: 0
Est. cost · USD: $0.00

Use my key for every request

Bypass examples to measure live inference. Uses your quota.

Measurement details · 0 successful requests

Successful requests: 0

Model compute is the average per measured request. Delivery time is the median browser time for successful requests, including queue, network, and retries. Cached delivery speed is not inference speed. Model compute can exceed browser time when one request processes many inputs.

Tokens come from response headers. Inference costs use $0.04 per million input tokens, before plan credits. The estimate includes live and recorded tokens at the same rate; cached examples are not charged again. Missing usage is unavailable or a partial total (≥). Demo resets keep these totals; reload to start a new session.

Try it

Structure the catalog, then inspect a listing.

Build with the SDKTypeScript · Python · dm1

One request from this demo. Copy it into your app.

Uses your MS_API_KEY and quota. Keep the key on your server.

API request

Install · set your key

npm install @cloudraker/milliseconds
export MS_API_KEY="your-api-key"

example.ts

import { DecisionMachine } from "@cloudraker/milliseconds";

// Run on your server; reads MS_API_KEY from the environment.
const dm = new DecisionMachine();

const { result, usage } = await dm.classify(
  [
    "Northline cotton T-shirt. Color: forest green. Size: medium.",
    "Oak & Field side table. Material: solid oak. Dimensions: 45 x 40 x 55 cm.",
    "Soundmere wireless headphones. Brand: Soundmere. Connectivity: Bluetooth 5.3. Color: black.",
    "Soft everyday shirt in blue."
  ],
  {
    "apparel": "Clothing, shirts, tops and wearable garments",
    "furniture": "Home furniture, tables, chairs, shelves",
    "audio": "Audio electronics, headphones, speakers, microphones",
    "other": "Unrelated text, services, or products outside clothing, furniture and audio electronics"
  }
).withUsage();

console.log(result);
console.log({ inputTokens: usage.inputTokens, modelMs: usage.inferenceMs });

example.ts

import { DecisionMachine } from "@cloudraker/milliseconds";

// Run on your server; reads MS_API_KEY from the environment.
const dm = new DecisionMachine();

const { result, usage } = await dm.extract(
  [
    "Northline cotton T-shirt. Color: forest green. Size: medium.",
    "Oak & Field side table. Material: solid oak. Dimensions: 45 x 40 x 55 cm.",
    "Soundmere wireless headphones. Brand: Soundmere. Connectivity: Bluetooth 5.3. Color: black.",
    "Soft everyday shirt in blue."
  ],
  {
    "type": "object",
    "properties": {
      "brand": {
        "type": "string",
        "description": "explicit product brand name, not the seller or model"
      },
      "material": {
        "type": "string",
        "description": "explicit physical material the product is made of"
      },
      "size": {
        "type": "string",
        "description": "explicit clothing size"
      },
      "dimensions": {
        "type": "string",
        "description": "explicit physical product dimensions including units"
      },
      "color": {
        "type": "string",
        "description": "explicit product color"
      },
      "connectivity": {
        "type": "string",
        "description": "explicit audio connection type such as Bluetooth, USB or wired"
      }
    }
  }
).withUsage();

console.log(result);
console.log({ inputTokens: usage.inputTokens, modelMs: usage.inferenceMs });

Install · set your key

pip install cloudraker-milliseconds
export MS_API_KEY="your-api-key"

example.py

from milliseconds import DecisionMachine

# Reads MS_API_KEY from the environment.
dm = DecisionMachine()

result = dm.classify(
    [
      "Northline cotton T-shirt. Color: forest green. Size: medium.",
      "Oak & Field side table. Material: solid oak. Dimensions: 45 x 40 x 55 cm.",
      "Soundmere wireless headphones. Brand: Soundmere. Connectivity: Bluetooth 5.3. Color: black.",
      "Soft everyday shirt in blue."
    ],
    {
      "apparel": "Clothing, shirts, tops and wearable garments",
      "furniture": "Home furniture, tables, chairs, shelves",
      "audio": "Audio electronics, headphones, speakers, microphones",
      "other": "Unrelated text, services, or products outside clothing, furniture and audio electronics"
    }
)

print(result)

example.py

from milliseconds import DecisionMachine

# Reads MS_API_KEY from the environment.
dm = DecisionMachine()

result = dm.extract(
    [
      "Northline cotton T-shirt. Color: forest green. Size: medium.",
      "Oak & Field side table. Material: solid oak. Dimensions: 45 x 40 x 55 cm.",
      "Soundmere wireless headphones. Brand: Soundmere. Connectivity: Bluetooth 5.3. Color: black.",
      "Soft everyday shirt in blue."
    ],
    {
      "type": "object",
      "properties": {
        "brand": {
          "type": "string",
          "description": "explicit product brand name, not the seller or model"
        },
        "material": {
          "type": "string",
          "description": "explicit physical material the product is made of"
        },
        "size": {
          "type": "string",
          "description": "explicit clothing size"
        },
        "dimensions": {
          "type": "string",
          "description": "explicit physical product dimensions including units"
        },
        "color": {
          "type": "string",
          "description": "explicit product color"
        },
        "connectivity": {
          "type": "string",
          "description": "explicit audio connection type such as Bluetooth, USB or wired"
        }
      }
    }
)

print(result)

Install · set your key

npm install -g @cloudraker/milliseconds
export MS_API_KEY="your-api-key"

Terminal

# Reads MS_API_KEY. JSON on stdin supplies the complete request.
dm1 classify --json --usage <<'DM1_REQUEST'
{
  "texts": [
    "Northline cotton T-shirt. Color: forest green. Size: medium.",
    "Oak & Field side table. Material: solid oak. Dimensions: 45 x 40 x 55 cm.",
    "Soundmere wireless headphones. Brand: Soundmere. Connectivity: Bluetooth 5.3. Color: black.",
    "Soft everyday shirt in blue."
  ],
  "labels": {
    "apparel": "Clothing, shirts, tops and wearable garments",
    "furniture": "Home furniture, tables, chairs, shelves",
    "audio": "Audio electronics, headphones, speakers, microphones",
    "other": "Unrelated text, services, or products outside clothing, furniture and audio electronics"
  }
}
DM1_REQUEST

Terminal

# Reads MS_API_KEY. JSON on stdin supplies the complete request.
dm1 extract --json --usage <<'DM1_REQUEST'
{
  "texts": [
    "Northline cotton T-shirt. Color: forest green. Size: medium.",
    "Oak & Field side table. Material: solid oak. Dimensions: 45 x 40 x 55 cm.",
    "Soundmere wireless headphones. Brand: Soundmere. Connectivity: Bluetooth 5.3. Color: black.",
    "Soft everyday shirt in blue."
  ],
  "schema": {
    "type": "object",
    "properties": {
      "brand": {
        "type": "string",
        "description": "explicit product brand name, not the seller or model"
      },
      "material": {
        "type": "string",
        "description": "explicit physical material the product is made of"
      },
      "size": {
        "type": "string",
        "description": "explicit clothing size"
      },
      "dimensions": {
        "type": "string",
        "description": "explicit physical product dimensions including units"
      },
      "color": {
        "type": "string",
        "description": "explicit product color"
      },
      "connectivity": {
        "type": "string",
        "description": "explicit audio connection type such as Bluetooth, USB or wired"
      }
    }
  }
}
DM1_REQUEST

Under the hood How it works & limitations

API calls/classify/extract

From descriptions to a searchable catalog

Classify assigns a category. Extract reads stated attributes. Code checks category requirements and matches returned wording to the original description. Nothing is published.

Demo scope

Text-only listings in clothing, furniture and audio. A source match locates wording; it does not prove the model assigned it to the right attribute. Drafts need human review. Missing or ambiguous facts remain in the review queue. Unit conversion supports unambiguous dimensions in mm or inches, preserving the original.

See how structured records support the shopper experience in Product Search.