GPT Crawler

Crawl a site to generate knowledge files to create your own custom GPT

Example

Here is a custom GPT that I quickly made to help answer questions about how to use and integrate Builder.io by simply providing the URL to the Builder docs.

This project crawled the docs and generated the file that I uploaded as the basis for the custom GPT.

Try it out yourself by asking questions about how to integrate Builder.io into a site.

Note that you may need a paid ChatGPT plan to access this feature

Get started

Prerequisites

Be sure you have Node.js >= 16 installed

Clone the repo

git clone https://github.com/builderio/gpt-crawler

Configure the crawler

Open config.ts and edit the url and selectors properties to match your needs.

E.g. to crawl the Builder.io docs to make our custom GPT you can use:

export const config: Config = {
  url: "https://www.builder.io/c/docs/developers",
  match: "https://www.builder.io/c/docs/**",
  selector: `.docs-builder-container`,
  maxPagesToCrawl: 1000,
  outputFileName: "output.json",
};

See the top of the file for the type definition for what you can configure:

type Config = {
  /** URL to start the crawl */
  url: string;
  /** Pattern to match against for links on a page to subsequently crawl */
  match: string;
  /** Selector to grab the inner text from */
  selector: string;
  /** Don't crawl more than this many pages */
  maxPagesToCrawl: number;
  /** File name for the finished data */
  outputFileName: string;
  /** Optional function to run for each page found */
  onVisitPage?: (options: {
    page: Page;
    pushData: (data: any) => Promise<void>;
  }) => Promise<void>;
};