Quickstart Guide
This is a quickstart guide to get you up and running with the Shopify Embeddings. This guide will walk you through the steps to get your Shopify product data into Pinecone and create embeddings for each product.Authentication
Shopify Product Embeddings
Once you have installed the app we can create embeddings and store your Shopify product data in Pinecone, you can create embeddings for each product. Embeddings are vector representations of your product data. You can use these embeddings to find similar products, recommend products, and more.1
Loop Through Products
Loop Through Shopify Product Data
2
Create Embeddings
Create embeddings for each product returns and store in Pinecone
3
Store Chunks of Product Data
Store the vector representation of the product data in Pinecone and associated metadata with the product data
let page = 1;
// Get Shopify Products
async function getShopifyProducts(nextPageToken, shop, limit, maxPage, shopify_access_token, pinecone_index, pinecone_api_key, pinecone_namespace) {
if (nextPageToken && page <= maxPage) {
const axiosConfig = {
headers: {
'Content-Type': 'application/json',
'X-Shopify-Access-Token': shopify_access_token
},
};
const response = await axios.get(`https://${shop}/admin/api/2021-10/products.json?limit=${limit}&page_info=${nextPageToken}; rel="next"`, axiosConfig);
nextPageToken = response.headers.link?.split(",")?.find((link) => link.includes(`rel="next"`))?.match(/<(.+)>/)?.[1];
const products = response.data.products;
const documents = [];
for (const item of products) {
try {
const id = item.id || null;
const title = item.title || null;
const handle = item.handle || null;
const image = item.image.src || null;
const images_src = item.image.src || null;
const vendor = item.vendor || null;
const product_type = item.product_type || null;
for (const variant of item.variants) {
const sku = variant.sku || null;
const variants_sku = variant.sku || null;
const variants_price = variant.price || null;
const variants_compare_at_price = variant.compare_at_price || null;
const variants_inventory_quantity = variant.inventory_quantity || null;
const option_1 = variant.option1 || null;
const option_2 = variant.option2 || null;
const option_3 = variant.option3 || null;
const shipping_weight = variant.weight || null;
const variant_id = variant.id || null;
let metadata = {
id,
title,
handle,
image,
sku,
variants_sku,
images_src,
variants_price,
variants_compare_at_price,
variants_inventory_quantity,
vendor,
option_1,
option_2,
option_3,
shipping_weight,
product_type,
variant_id
};
const document = {
id: uuid(),
title,
metadata,
};
documents.push(document);
}
} catch (error) {
logger.info(`Error processing item: ${JSON.stringify(item);}`);
logger.info(error);
}
for (let i = 0; i < documents.length; i += DOCUMENT_UPSERT_BATCH_SIZE) {
// Split documents into batches
var batchDocuments = documents.slice(i, i + DOCUMENT_UPSERT_BATCH_SIZE);
logger.info(batchDocuments);
// Convert batchDocuments to string
var batchDocumentString = JSON.stringify(batchDocuments)
// Remove commas from string
logger.info(batchDocumentString);
// Create Embeddings
logger.info('Looping through documents...');
const user_id = "domsteil";
// OpenAI Request Body
var raw = JSON.stringify({ "input": batchDocumentString, "model": "text-embedding-ada-002", "user": user_id });
// OpenAI Request Options
var requestOptions = {
method: 'POST',
headers: {
'Content-Type': 'application/json',
'Authorization': process.env.OPEN_AI
},
body: raw,
redirect: 'follow'
};
// Make Callout to OpenAI to get Embeddings
logger.info('Creating Embedding...');
// Make Callout to OpenAI
let embeddings_response = await fetch("https://api.openai.com/v1/embeddings", requestOptions)
// Create Pinecone Request Body
const vectors_embeddings = await embeddings_response.json();
logger.info(vectors_embeddings);
// Create Pinecone Request Body
var vectors_object = { id: uuid(), values: vectors_embeddings.data[0].embedding, metadata: { "text": batchDocumentString, "user": user_id } };
logger.info(vectors_object);
var raw = JSON.stringify({ "vectors": vectors_object, "namespace": "shopify_product_data" });
var pineconeRequestOptions = {
method: "POST",
headers: {
"Content-Type": "application/json",
"Host": pinecone_index,
"Content-Length": 60,
"Api-Key": pinecone_api_key,
},
body: raw,
redirect: "follow",
};
// Make Callout to Pinecone
// Pinecone Upsert
logger.info('Upserting Pinecone...');
let pinecone_query_response = await fetch(`https://${pinecone_index}/vectors/upsert`, pineconeRequestOptions)
.then(response => response.text())
.then(json => {
logger.info(json);
})
.catch(error => {
logger.error(error);
});
}
}
page += 1;
logger.info(`On page ${page}, processing next page...`);
return getShopifyProducts(nextPageToken, shop, limit, maxPage, shopify_access_token, pinecone_index, pinecone_api_key, pinecone_namespace);