Websites

Raag can ingest data directly from a website either by providing a single URL or a whole website to our crawler.

If you're using the crawler mode, then we'll take care of everything for you.

Crawl website

import * as Ragg from '@ragg/node-sdk'

const ragg = Ragg.init(<API_KEY>)

const result = await ragg.websites.crawlWebsite({
    workspaceId: string,
    url: 'https://google.com',
});

console.log(result.urls)
// ["https://google.com", "https://google.com/something"]

Add web pages

import * as Ragg from '@ragg/node-sdk'

const ragg = Ragg.init(<API_KEY>)

const dataSource = await ragg.websites.addWebPages({
    workspaceId: string,
    urls: string[],
    syncIntervalHours: 2,
});

List all datasource

const ragg = Ragg.init(<API_KEY>)

const dataSource = await ragg.dataSource.list({
    workspaceId: string,
});