Personalizing Product Descriptions with Algolia + GPT-5

personalizeCopy.js

import OpenAI from 'openai';

const fetchUserProfile = async (userID, ALGOLIA_APPLICATION_ID, ALGOLIA_API_KEY, ALGOLIA_REGION="eu") => {
  const fallbackUserProfile = {
    userID,
    type: "basic",
    affinities: [],
    lastUpdatedAt: new Date().toISOString(),
  };

  try {
    const response = await fetch(
      `https://ai-personalization.${ALGOLIA_REGION}.algolia.com/2/users/${encodeURIComponent(userID)}`,
      {
        headers: {
          "X-Algolia-Application-Id": ALGOLIA_APPLICATION_ID,
          "X-Algolia-API-Key": ALGOLIA_API_KEY,
        },
      }
    );

    if (!response.ok) {
      console.error(await response.text());
      return fallbackUserProfile;
    }

    return await response.json();
  } catch (error) {
    console.error(error)
    return fallbackUserProfile;
  }
};

const sendToGPT5 = (instructions, input, OPENAI_API_KEY) => // Returns a promise
  (new OpenAI({ apiKey: OPENAI_API_KEY })).responses.create({
    model: "gpt-5-nano",
    reasoning: { effort: "low" },
    instructions,
    input
  });

const convertProfileToMarkdown = ({ userID, affinities }) => [
  `Affinities for user "${userID}":`,
  ...affinities.map(affinity => 
    `- ${affinity.name}: ${affinity.value} (score: ${affinity.score})`
  )
].join("\n");

export const personalizeCopy = async (userID, copy, credentials) => {
  const userProfile = await fetchUserProfile(userID, credentials.ALGOLIA_APPLICATION_ID, credentials.ALGOLIA_API_KEY, credentials.ALGOLIA_REGION);
  if (userProfile.affinities.length == 0) return;

  const markdownProfile = convertProfileToMarkdown(userProfile);

  const instructions = `You're a marketing copywriter personalizing ecommerce copy, such as product descriptions. Given a user's preference profile (facet scores) and a generic piece of copy, rewrite that content to emphasize what the user cares about most. Be subtle but relevant, maintaining the general tone and length of the original. Do not respond with anything other than the rewritten copy.`;
  
  const prompt = [
    markdownProfile,
    "",
    "Original copy:",
    copy,
    "",
    "Rewrite this copy based on the user's preferences."
  ].join("\n");
  
  const response = await sendToGPT5(instructions, prompt, credentials.OPENAI_API_KEY);
  return { markdownProfile, output: response.output_text };
};

The credentials object that gets passed into the personalizeCopy function is this format:

{
  ALGOLIA_APPLICATION_ID: "",
  ALGOLIA_API_KEY: "",
  ALGOLIA_REGION: "us" | "eu",
  OPENAI_API_KEY: ""
}

To run this on the backend, you'll first need to npm install openai. If you're trying to run it from the frontend (which isn't recommended since that involves exposing your OpenAI secret key), you can use link to the OpenAI npm module on jsDelivr: import openai from 'https://cdn.jsdelivr.net/npm/openai@5.12.2/+esm'. You would also need to explicitly authorize dangerous frontend usage - an error message will explain how to do that.