AI Chatbot

This plugin adds an AI chatbot trained on your website content to your Remix application built using the OpenAI API. It's a simple component that will be displayed on the bottom right of your website.

This documentation is for the Remix Supabase version. Please make sure you're looking at the right documentation.

Using the Plugin

Installation

To install the plugin, you can use git subtrees from your original repository:

git subtree add --prefix plugins/chatbot git@github.com:makerkit/remix-supabase-saas-kit-plugins.git chatbot --squash

After running this command, you will have the plugin in your repository at plugins/chatbot. Once pulled, you can apply any customization you need.

Using the CLI

If you're using the CLI, you can run the following command to install the plugin:

npx @makerkit/cli plugins install

Follow the instructions to install the plugin.

If the installation fails

Some users are not able to install using the GitHub SSH URL. If you're having issues with that:

1. properly set up SSH access to GitHub with your SSH key
2. use the HTTPS URL instead of the SSH URL

To use the HTTPS URL, you can run the following command:

git subtree add --prefix plugins/chatbot https://github.com/makerkit/remix-supabase-saas-kit-plugins chatbot --squash

Add the plugin as a workspace in your package.json

You can do so by adding the following to your package.json file:

{
  "workspaces": [
    "plugins/chatbot"
  ]
}

Add it next to the other workspaces in your package.json file.

Add the paths alias to the TypeScript configuration

To make sure that the TypeScript compiler can find the plugin, you will need to add the following paths alias to your tsconfig.json file, in addition to the other paths aliases that you may have.

If not yet present, add the following to your tsconfig.json file:

{
  "compilerOptions": {
    "paths": {
      "~/plugins/*": [
        "./plugins/*"
      ]
    }
  }
}

You only need to add this once, even if you have multiple plugins.

Add the plugin path to your Tailwind configuration

You can do so by adding the following to your tailwind.config.js file:

content: ['./app/**/*.{ts,tsx,jsx,js}', './plugins/**/*.{ts,tsx,jsx,js}']

This is only needed the first time you install a plugin.

Add Langchain to the Remix config

To work with Remix, Langchain needs to be bundled with the server code.

You can do so by adding the following to your remix.config.ts file:

serverDependenciesToBundle: [
  /^(@)?contentlayer.*/,
  /@mdx-js.*/,
  /langchain.*/,
]

Installing dependencies

To install the dependencies, you can run the following command:

npm i

NPM will install the dependencies in the plugins/chatbot folder as an NPM workspace.

Configuring the database migration

This plugin needs to store the documents that the AI will be trained on as vectors in the Supabase database. As such, we need to add a migrration to the database.

The migration SQL file is available at plugins/chatbot/migration.sql. You can generate a new mutation using the following command:

supabase migration new chatbot

Make sure you're happy with the default table names before proceeding so that they don't conflict with your existing tables.

Now paste the content of the plugins/chatbot/migration.sql file into the new migration file that was created.

When going to production, you will need to run the migration using the Supabase CLI:

supabase db push

Importing the Plugin

You can import the Chatbot component from the plugin in your root.tsx file if you want it available on all pages:

import ChatBot from '~/plugins/chatbot/components/ChatBot';
 
export default function RootLayout() {
  return (
    <>
      <ChatBot />
      {/* ... */}
    </>
  );
}

Alternatively, you can import the Chatbot component in the layout of the page where you want it to appear. If you only want it available in the website pages, then you will import it in the site layout.

Configuring the plugin

To configure the plugin, add the following environment variables to your .env.local files:

OPENAI_API_KEY=

• OPENAI_API_KEY - Your OpenAI API key. You can get one from your OpenAI dashboard.

When going to production, you will need to add these environment variables from your provider dashboard.

Additionally, we need to pass the fallback URL to the chatbot:

• This is the link the chatbot will display if it can't answer the question. You can use an email such as mailto:youremail@yourstartup.com or a link to the customer service page of your website.

<Chatbot fallbackUrl="mailto:yourapp.com" />

Setting the API Route Handler

Remix Route

Create a route at app/api.chat.ts with the following content:

import type { ActionArgs } from '@remix-run/node';
import handleChatBotRequest from '~/plugins/chatbot/lib/server/route-action.server';
 
export const action = (args: ActionArgs) => {
  return handleChatBotRequest(args.request);
};

Indexing the content's embeddings

By default, the AI will be trained on the content of your website available within your documentation pages at /docs.

In addition, you can provide a list of questions and answers.

To do so, add MDX files at plugins/chatbot/questions/<filename>.mdx file and add content with the following format:

---
question: "<question>"
---
 
<answer>

For example, you can create a file at plugins/chatbot/questions/refund-policy.mdx:

---
question: "What is your refund policy?"
---
 
We offer a 30-day money-back guarantee. If you're not happy with our product,
we will refund you.

To generate the embeddings, you can run the following command:

npx tsx plugins/chatbot/cli.ts generate

Follow the instructions to generate the embeddings.

If you are generating the embeddings for your production environment, you will need to provide the Supabase credentials in the .env file.

Captcha Protection (optional) (WIP)

To protect your chatbot from bots (ha ha!), you can add a captcha challenge using Cloudflare's Turnstile service.

To do so, you will need to pass the site key to the Chatbot component:

<Chatbot siteKey="************8" />

[You can get the site key from your Turnstile dashboard](https://developers. cloudflare.com/turnstile/get-started/).

On the server side, you will need to add the following environment variables: CHATBOT_TURNSTILE_SECRET_KEY.

You can also get the secret key from your Turnstile dashboard. Since this is a secret key - avoid adding it to your repository. Please use the environment variables of your provider to add it to your production environment.

Deduplicating Indexing

To avoid indexing the same content multiple times, the CLI generates a file named plugins/chatbot/indexed-files.json that contains a list of all the pages that have been indexed and the SHA256 hash of their content.

If the content of the file changes, the CLI will re-index the pages.

Keeping the plugin up to date

To keep the plugin up to date, you can use git subtrees again:

git subtree pull --prefix plugins/chatbot git@github.com:makerkit/remix-supabase-saas-kit-plugins.git chatbot --squash

Best Practices

As you may know - the AI is only as good as the data it's trained on. As such, make sure to provide as much content as possible to the AI. I don't mean dozens of pages - but hundreds. Seriously, the more content you provide

• the more useful the AI will be. Without context, hallucinations are bound to happen - and you don't want that.

Provide a fallback email

If the AI can't answer the question, it will display a fallback URL. Make sure to provide a fallback URL that will allow your users to contact you in case the AI can't answer their question.