lila/data-pipeline/promptTemplate.ts

import { readFileSync } from "node:fs";
import path from "node:path";
import type { SupportedLanguageCode, SupportedPos } from "@lila/shared";

export const LANGUAGE_NAMES: Record<SupportedLanguageCode, string> = {
  en: "English",
  it: "Italian",
  de: "German",
  fr: "French",
  es: "Spanish",
};

export type PromptParams = {
  sourceLanguage: SupportedLanguageCode;
  pos: SupportedPos;
  targetLanguages: readonly SupportedLanguageCode[];
  words: readonly string[];
};

export const loadPromptTemplate = (): string =>
  readFileSync(path.join(import.meta.dirname, "prompt"), "utf-8");

export const renderPrompt = (
  template: string,
  params: PromptParams,
): string => {
  const { sourceLanguage, pos, targetLanguages, words } = params;
  if (words.length === 0) {
    throw new Error("renderPrompt: empty word batch");
  }
  if (
    targetLanguages.length === 0 ||
    targetLanguages.includes(sourceLanguage)
  ) {
    throw new Error(
      `renderPrompt: target languages must be non-empty and exclude the source language (got ${targetLanguages.join(", ")})`,
    );
  }

  const rendered = template
    .replaceAll("{{SOURCE_LANGUAGE_NAME}}", LANGUAGE_NAMES[sourceLanguage])
    .replaceAll("{{SOURCE_LANGUAGE_CODE}}", sourceLanguage)
    .replaceAll("{{POS}}", pos)
    .replaceAll("{{TARGET_LANGUAGE_CODES}}", targetLanguages.join(", "))
    .replaceAll(
      "{{TARGET_LANGUAGE_UNION}}",
      targetLanguages.map((code) => `"${code}"`).join(" | "),
    )
    .replaceAll("{{INPUT_WORDS}}", words.join("\n"));

  const leftover = rendered.match(/\{\{[A-Z_]+\}\}/);
  if (leftover) {
    throw new Error(`renderPrompt: unreplaced placeholder ${leftover[0]}`);
  }
  return rendered;
};