LLMでTOONを使う — 構造を失わずにトークンコストを削減

[
  { "id": 1, "username": "alice_dev", "email": "[email protected]", "plan": "pro", "active": true },
  { "id": 2, "username": "bob_writer", "email": "[email protected]", "plan": "free", "active": true },
  { "id": 3, "username": "carol_ops", "email": "[email protected]", "plan": "pro", "active": false },
  { "id": 4, "username": "dan_qa", "email": "[email protected]", "plan": "team", "active": true },
  { "id": 5, "username": "eve_design", "email": "[email protected]", "plan": "pro", "active": true },
  { "id": 6, "username": "frank_sec", "email": "[email protected]", "plan": "team", "active": true },
  { "id": 7, "username": "grace_ml", "email": "[email protected]", "plan": "pro", "active": false },
  { "id": 8, "username": "henry_be", "email": "[email protected]", "plan": "free", "active": true },
  { "id": 9, "username": "iris_fe", "email": "[email protected]", "plan": "pro", "active": true },
  { "id": 10, "username": "jack_devrel", "email": "[email protected]", "plan": "team", "active": true }
]

users[10]{id,username,email,plan,active}:
  1,alice_dev,[email protected],pro,true
  2,bob_writer,[email protected],free,true
  3,carol_ops,[email protected],pro,false
  4,dan_qa,[email protected],team,true
  5,eve_design,[email protected],pro,true
  6,frank_sec,[email protected],team,true
  7,grace_ml,[email protected],pro,false
  8,henry_be,[email protected],free,true
  9,iris_fe,[email protected],pro,true
  10,jack_devrel,[email protected],team,true

npm install @toon-format/toon

import { encode, decode } from '@toon-format/toon';

// Convert a JS array/object to TOON before sending to an LLM
const users = [
  { id: 1, username: 'alice_dev', email: '[email protected]', plan: 'pro', active: true },
  { id: 2, username: 'bob_writer', email: '[email protected]', plan: 'free', active: true },
  // ... more rows
];

const toonData = encode(users, { indent: 2 });
console.log(toonData);
// users[2]{id,username,email,plan,active}:
//   1,alice_dev,[email protected],pro,true
//   2,bob_writer,[email protected],free,true

import { encode, decode } from '@toon-format/toon';
import OpenAI from 'openai';

const openai = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });

async function analyseUsers(users) {
  // Step 1: encode data to TOON
  const toonData = encode(users, { indent: 2 });

  // Step 2: build the prompt
  const systemPrompt = [
    'You analyse user datasets. Data is provided in TOON (Token-Optimised Object Notation).',
    'TOON tabular format: name[count]{col1,col2,...}: followed by comma-separated rows, one per line.',
    'Respond with plain prose unless asked to return data, in which case use TOON format.'
  ].join('\n');

  const userPrompt = `Here is the user dataset:\n\n${toonData}\n\nWhich plan has the most active users?`;

  // Step 3: call the API
  const response = await openai.chat.completions.create({
    model: 'gpt-4o',
    messages: [
      { role: 'system', content: systemPrompt },
      { role: 'user', content: userPrompt }
    ]
  });

  return response.choices[0].message.content;
}

// Step 4 (optional): if the model returns TOON, decode it back
const rawResponse = await analyseUsers(myUserArray);
try {
  const structured = decode(rawResponse);
  console.log('Structured result:', structured);
} catch {
  console.log('Prose response:', rawResponse);
}

Data is provided in TOON (Token-Optimised Object Notation).
TOON syntax:
- Objects: {key:value,key2:value2} — keys are never quoted
- Arrays: [val1,val2,val3]
- Tabular: name[rowCount]{col1,col2,...}:
    rowval1,rowval2,...
    rowval1,rowval2,...
Parse each row by matching values to the column headers in order.
Strings containing commas are double-quoted.