Large Language Model (LLM) APIs allow developers to build apps that can understand and generate text. We can use OpenAI's APIs to build a chatbot that can understand a shopper's question and respond with product recommendations.
You can fork this Gadget project and try it out yourself.
You will still need to set up the Shopify Connection and theme app extension after forking. Read on to learn how to connect Gadget to a Shopify store!
Step 1: Create a Gadget app and connect to Shopify
To learn how to create a Shopify connection, follow the Shopify quickstart guide. Note that you may also use the assistant to create a new Shopify connection.
For this tutorial, we will need the read_products scope and the product and productMedia models.
Now you can install your app on a store from the Partners dashboard. Do not sync data yet! You're going to add some code to generate vector embeddings for your products before the sync is run.
Step 2: Set up OpenAI connection
Now that you are connected to Shopify, you can also set up the OpenAI connection that will be used to fetch embeddings for product descriptions. Gadget provides OpenAI credits for testing while building your app, so you don't need a personal OpenAI API key to get started.
Click on Settings in the nav bar
Click on Plugins
Click on the OpenAI connection
Select the Use Gadget's API keys option in the modal that appears OR enter your own OpenAI API key
Click Add connection at the bottom of the page
Your OpenAI connection is now ready to be used!
Step 3: Add data models for chat responses
Now we need a new data model to capture the chat responses from OpenAI, and the products recommended to shoppers. We need to use a has many through relationship to relate the chat response to the recommended products.
Click + next to the api/models folder and add a new chatLog model
Add the following fields to chatlog:
Field name
Field type
response
string
products
has many through
Now you need to define the products relationship.
Set the sibling to shopifyProduct and the joinModel to recommendedProduct, this will create a new recommendedProduct model
Name the field in recommendedProduct that relates to the chatLog model, chatLog
Name the field in recommendedProduct that relates to the shopifyProduct model, product
Name the field in the shopifyProduct model that relates to the recommendedProduct model, chatRecommendations
Step 4: Add vector field to shopifyProduct model
Before you add code to create the embeddings from product descriptions, you need a place to store the generated embeddings. You can add a vector field to the shopifyProduct model to store the embeddings.
The vector field types store a vector, or array, of floats. It is useful for storing vector embeddings and will allow you to perform vector operations like cosine similarity, which helps you find the most similar products to a given chat message.
To add a vector field to the shopifyProduct model:
Go to api/models/shopifyProduct/schema and add the following field:
Field name
Field type
descriptionEmbedding
vector
Now you are set up to store embeddings for products! The next step is adding code to generate these embeddings.
Step 5: Write code effect to create vector embedding
Now you can add some code to create vector embeddings for all products in your store. You will want to run this code when Shopify fires a products/create or products/update webhook. To do this, you will create a code effect that runs when a Shopify Product is created or updated.
Go to the api/models/shopifyProduct/actions folder and add a new createEmbedding.js action
Paste the following code into api/models/shopifyProduct/actions/createEmbedding.js:
import { applyParams, save, ActionOptions } from "gadget-server";
import { preventCrossShopDataAccess } from "gadget-server/shopify";
export const run: ActionRun = async ({
params,
record,
logger,
api,
connections,
}) => {
applyParams(params, record);
await preventCrossShopDataAccess(params, record);
await save(record);
};
export const onSuccess: ActionOnSuccess = async ({
params,
record,
logger,
api,
connections,
}) => {
try {
// get an embedding for the product title + description using the OpenAI connection
const response = await connections.openai.embeddings.create({
input: `${record.title}: ${record.body}`,
model: "text-embedding-ada-002",
});
const embedding = response.data[0].embedding;
// write to the Gadget Logs
logger.info({ id: record.id }, "got product embedding");
// use the internal API to store vector embedding in Gadget database, on shopifyProduct model
await api.internal.shopifyProduct.update(record.id, {
shopifyProduct: { descriptionEmbedding: embedding },
});
} catch (error) {
logger.error({ error }, "error creating embedding");
}
};
export const options: ActionOptions = {
actionType: "update",
triggers: {
api: true,
},
};
import { applyParams, save, ActionOptions } from "gadget-server";
import { preventCrossShopDataAccess } from "gadget-server/shopify";
export const run: ActionRun = async ({
params,
record,
logger,
api,
connections,
}) => {
applyParams(params, record);
await preventCrossShopDataAccess(params, record);
await save(record);
};
export const onSuccess: ActionOnSuccess = async ({
params,
record,
logger,
api,
connections,
}) => {
try {
// get an embedding for the product title + description using the OpenAI connection
const response = await connections.openai.embeddings.create({
input: `${record.title}: ${record.body}`,
model: "text-embedding-ada-002",
});
const embedding = response.data[0].embedding;
// write to the Gadget Logs
logger.info({ id: record.id }, "got product embedding");
// use the internal API to store vector embedding in Gadget database, on shopifyProduct model
await api.internal.shopifyProduct.update(record.id, {
shopifyProduct: { descriptionEmbedding: embedding },
});
} catch (error) {
logger.error({ error }, "error creating embedding");
}
};
export const options: ActionOptions = {
actionType: "update",
triggers: {
api: true,
},
};
In this snippet:
the OpenAI connection is accessed through connections.openai and the embeddings.create() API is called
the internal API is used in the onSuccess function to update the shopifyProduct model and set the descriptionEmbedding field
The internal API needs to be used because the shopifyProduct model does not have a Gadget API trigger on this action by default. You can read more about the internal API in the Gadget docs.
Now enqueue this action from your api/models/shopifyProduct/actions/create.js and api/models/shopifyProduct/actions/update.js actions:
Open api/models/shopifyProduct/actions/create.js and paste the following code:
api/models/shopifyProduct/actions/create.js
JavaScript
import {
applyParams,
preventCrossShopDataAccess,
save,
ActionOptions,
} from "gadget-server";
export const run: ActionRun = async ({ params, record }) => {
applyParams(params, record);
await preventCrossShopDataAccess(params, record);
await save(record);
};
export const onSuccess: ActionOnSuccess = async ({ record, api }) => {
// only run if the product does not have an embedding, or if the title or body have changed
if (!record.descriptionEmbedding && record.body && record.title) {
await api.enqueue(api.shopifyProduct.createEmbedding, { id: record.id });
}
};
export const options: ActionOptions = {
actionType: "create",
};
import {
applyParams,
preventCrossShopDataAccess,
save,
ActionOptions,
} from "gadget-server";
export const run: ActionRun = async ({ params, record }) => {
applyParams(params, record);
await preventCrossShopDataAccess(params, record);
await save(record);
};
export const onSuccess: ActionOnSuccess = async ({ record, api }) => {
// only run if the product does not have an embedding, or if the title or body have changed
if (!record.descriptionEmbedding && record.body && record.title) {
await api.enqueue(api.shopifyProduct.createEmbedding, { id: record.id });
}
};
export const options: ActionOptions = {
actionType: "create",
};
Open api/models/shopifyProduct/actions/update.js and paste the following code:
Gadget's background actions are used so you can manage OpenAI's rate limits using the built-in concurrency
control and retries!
Now vector embeddings will be generated when a new product is created, or an existing product is updated.
Generate embeddings for existing products
Now that the code is in place to generate vector embeddings for products, you can sync existing Shopify products into your Gadget app's database. To do this:
Click on Settings in the nav bar
Click on the Plugins page
Select the Shopify connection
Click on Installs for the connected Development app
Click on the Sync button for the store you want to sync products from
Product and product media data will be synced from Shopify to your Gadget app's database. The code effect you added will run for each product and generate a vector embedding for the product. You can see these vector embeddings by going to the Data page for the shopifyProduct model. The vector embeddings will be stored in the descriptionEmbedding field.
Step 6: Add /chat HTTP route
We will use an HTTP route to handle incoming chat messages from the storefront. The route will take a message from the shopper, use cosine similarity to determine what products to recommend, and stream a response from OpenAI back to the client.
Hover over the api folder and right-click on it to create a folder named routes
Click + next to api/routes create a new file
Name the file POST-chat.js
Your app now has a new HTTP route that will be triggered when a POST request is made to /chat. You can add code to this file to handle incoming chat messages.
Paste the following code in api/routes/POST-chat.js:
api/routes/POST-chat.js
JavaScript
import { RouteContext, RouteHandler } from "gadget-server";
import { openAIResponseStream } from "gadget-server/ai";
const route: RouteHandler<{
Body: { message: string };
}> = async ({ request, reply, api, logger, connections }) => {
// get input from shopper
const { message } = request.body;
// embed the incoming message from the user
const embeddingResponse = await connections.openai.embeddings.create({
input: message,
model: "text-embedding-ada-002",
});
// find similar product descriptions
const products = await api.shopifyProduct.findMany({
sort: {
descriptionEmbedding: {
cosineSimilarityTo: embeddingResponse.data[0].embedding,
},
},
first: 2,
filter: {
status: {
equals: "active",
},
},
select: {
id: true,
title: true,
body: true,
handle: true,
shop: {
domain: true,
},
featuredMedia: {
file: {
image: true,
},
},
},
});
// capture products in Gadget's Logs
logger.info(
{ products, message: request.body.message },
"found products most similar to user input"
);
const prompt = `You are a helpful shopping assistant trying to match customers with the right product. You will be given a question from a customer and some JSON objects with the id, title, handle, and description (body) of products available for sale that roughly match the customer's question, as well as the store domain. Respond in HTML markup, with an anchor tag at the end with images that link to the product pages and <br /> tags between your text response and product recommendations. The anchor should be of the format: <a href={"https://" + {domain} + "/products/" + {handle}} target="_blank">{title}<img style={border: "1px black solid"} width="200px" src={product.featuredMedia.file.image.url} /></a> but with the domain, handle, and title replaced with passed-in variables. If you have recommended products, end your response with "Click on a product to learn more!" If you are unsure or if the question seems unrelated to shopping, say "Sorry, I don't know how to help with that", and include some suggestions for better questions to ask. Here are the json products you can use to generate a response: ${JSON.stringify(
products
)}`;
// send prompt and similar products to OpenAI to generate a response
// using GPT-4 Turbo model
const chatResponse = await connections.openai.chat.completions.create({
model: "gpt-4-1106-preview",
messages: [
{
role: "system",
content: prompt,
},
{ role: "user", content: message },
],
stream: true,
});
// function fired after the steam is finished
const onComplete = (content: string) => {
// store the response from OpenAI, and the products that were recommended
const recommendedProducts = products.map((product) => ({
create: {
product: {
_link: product.id,
},
},
}));
void api.chatLog.create({
response: content,
recommendedProducts,
});
};
await reply.send(openAIResponseStream(chatResponse, { onComplete }));
};
export default route;
import { RouteContext, RouteHandler } from "gadget-server";
import { openAIResponseStream } from "gadget-server/ai";
const route: RouteHandler<{
Body: { message: string };
}> = async ({ request, reply, api, logger, connections }) => {
// get input from shopper
const { message } = request.body;
// embed the incoming message from the user
const embeddingResponse = await connections.openai.embeddings.create({
input: message,
model: "text-embedding-ada-002",
});
// find similar product descriptions
const products = await api.shopifyProduct.findMany({
sort: {
descriptionEmbedding: {
cosineSimilarityTo: embeddingResponse.data[0].embedding,
},
},
first: 2,
filter: {
status: {
equals: "active",
},
},
select: {
id: true,
title: true,
body: true,
handle: true,
shop: {
domain: true,
},
featuredMedia: {
file: {
image: true,
},
},
},
});
// capture products in Gadget's Logs
logger.info(
{ products, message: request.body.message },
"found products most similar to user input"
);
const prompt = `You are a helpful shopping assistant trying to match customers with the right product. You will be given a question from a customer and some JSON objects with the id, title, handle, and description (body) of products available for sale that roughly match the customer's question, as well as the store domain. Respond in HTML markup, with an anchor tag at the end with images that link to the product pages and <br /> tags between your text response and product recommendations. The anchor should be of the format: <a href={"https://" + {domain} + "/products/" + {handle}} target="_blank">{title}<img style={border: "1px black solid"} width="200px" src={product.featuredMedia.file.image.url} /></a> but with the domain, handle, and title replaced with passed-in variables. If you have recommended products, end your response with "Click on a product to learn more!" If you are unsure or if the question seems unrelated to shopping, say "Sorry, I don't know how to help with that", and include some suggestions for better questions to ask. Here are the json products you can use to generate a response: ${JSON.stringify(
products
)}`;
// send prompt and similar products to OpenAI to generate a response
// using GPT-4 Turbo model
const chatResponse = await connections.openai.chat.completions.create({
model: "gpt-4-1106-preview",
messages: [
{
role: "system",
content: prompt,
},
{ role: "user", content: message },
],
stream: true,
});
// function fired after the steam is finished
const onComplete = (content: string) => {
// store the response from OpenAI, and the products that were recommended
const recommendedProducts = products.map((product) => ({
create: {
product: {
_link: product.id,
},
},
}));
void api.chatLog.create({
response: content,
recommendedProducts,
});
};
await reply.send(openAIResponseStream(chatResponse, { onComplete }));
};
export default route;
This code will:
create a vector embedding from the shopper's message using the OpenAI connection using connections.openai.embeddings.create()
use cosine similarity to find the 2 most similar products to the shopper's message using the Gadget API:
cosine similarity in api/routes/POST-chat.js
JavaScript
const products = await api.shopifyProduct.findMany({
sort: {
descriptionEmbedding: {
// cosine similarity to the embedding of the shopper's message
cosineSimilarityTo: embeddingResponse.data[0].embedding,
},
},
first: 2,
select: {
// ...
},
});
const products = await api.shopifyProduct.findMany({
sort: {
descriptionEmbedding: {
// cosine similarity to the embedding of the shopper's message
cosineSimilarityTo: embeddingResponse.data[0].embedding,
},
},
first: 2,
select: {
// ...
},
});
use the OpenAI chat API to generate a response using the gpt-4-1106-preview model
Once the plugin is installed, you can add it to your app's configuration:
Add a new file in the api/routes folder called +scope.js
Paste the following code into api/routes/+scope.js:
api/routes/+scope.js
JavaScript
import { Server } from "gadget-server";
import cors from "@fastify/cors";
/**
* Route plugin for *
*
* @param { Server } server - server instance to customize, with customizations scoped to descendant paths
*
* @see {@link https://www.fastify.dev/docs/latest/Reference/Server}
*/
export default async function (server: Server) {
await server.register(cors, {
// allow requests from any domain
origin: true,
});
}
import { Server } from "gadget-server";
import cors from "@fastify/cors";
/**
* Route plugin for *
*
* @param { Server } server - server instance to customize, with customizations scoped to descendant paths
*
* @see {@link https://www.fastify.dev/docs/latest/Reference/Server}
*/
export default async function (server: Server) {
await server.register(cors, {
// allow requests from any domain
origin: true,
});
}
This will allow requests from ANY domain! For your actual, production app, you probably want to set the origin option to a specific domain - the domain of your store. Read more about CORS in Gadget in our documentation.
Your route is now complete! Now all that is needed is a frontend app that allows shoppers to ask a question and displays the response along with product recommendations.
Step 7: Use Shopify theme app extension to embed chatbot
We make use of an app embed block for our storefront chatbot theme extension. This means that our extension works with any Shopify theme, both vintage and Online Store 2.0 themes.
Update the direct script tag in extensions/theme-extension/blocks/chatbot.liquid to include your app's script tag URL
Direct script tag
The script tag URL can be found in the Installing section of your app's API Reference. Your script tag needs --development added to your app-specific subdomain when working on your Development environment:
Run shopify app dev to start your app and connect to your existing Partners app and development store
You should now be set up and ready to add the chatbot theme app extension to the storefront theme.
Navigate to your storefront theme editor and click on App embeds in the left sidebar
Enable your app - the chatbot should appear in your storefront preview
Click Save in the top right corner of the page
Theme extension overview
Theme extensions allow you to create custom blocks that merchants can place in the storefront theme editor. You can read more about theme
extensions in the Shopify docs. This chatbot extension is an app embed block, so it works with both vintage and Online Store 2.0 themes.
In this theme there are 3 main files:
blocks/chatbot.liquid - the main file that renders the chatbot
assets/chatbot.js - handles the chatbot logic and calls your Gadget app's API
assets/chatbot.css - the CSS file that styles the chatbot
Your chatbot should now be available in your storefront - try it out!
Next steps
You now have a chatbot that can respond to shopper questions with product recommendations! You can continue to build on this app by:
customizing the embedded React frontend, found in the frontend folder, to give merchants installation instructions
editing the prompt in api/routes/POST-chat.js to customize the chatbot's response
change the look, feel, and merchant customization options for the chatbot by editing the theme extension files
maintain full chat context by passing messages back and forth between the client and server
also maintain chat context between browser sessions and/or windows by storing the full chat context in the database
Have questions about the tutorial? Join Gadget's developer Discord to ask Gadget employees and join the Gadget developer community!
