> ## Documentation Index
> Fetch the complete documentation index at: https://sitegpt.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Data Sources Overview

> Train your SiteGPT chatbot with content from various data sources

# Data Sources

SiteGPT supports training your chatbot from multiple data sources beyond just websites. This allows you to create a comprehensive AI assistant that can answer questions based on your entire knowledge base.

## Available Data Sources

<CardGroup cols={2}>
  <Card title="Website" icon="globe" href="/setup/training-your-chatbot">
    Crawl your website automatically via sitemap or page-by-page
  </Card>

  <Card title="Google Drive" icon="google-drive" href="/data-sources/google-drive">
    Import documents, sheets, and presentations from Google Drive
  </Card>

  <Card title="Notion" icon="file-lines" href="/data-sources/notion">
    Connect your Notion workspace and import pages
  </Card>

  <Card title="YouTube" icon="youtube" href="/data-sources/youtube">
    Train on video transcripts from YouTube channels or playlists
  </Card>

  <Card title="Dropbox" icon="dropbox" href="/data-sources/dropbox">
    Import files and documents from Dropbox
  </Card>

  <Card title="OneDrive" icon="microsoft" href="/data-sources/onedrive">
    Connect Microsoft OneDrive to import documents
  </Card>

  <Card title="Box" icon="box" href="/data-sources/box">
    Connect Box cloud storage
  </Card>

  <Card title="GitHub" icon="github" href="/data-sources/github">
    Import Markdown docs, READMEs, and files from GitHub repositories
  </Card>
</CardGroup>

## How Data Source Training Works

1. **Connect** - Authenticate with your data source (OAuth for most services)
2. **Select** - Choose which files, folders, or pages to import
3. **Train** - SiteGPT processes the content and trains your chatbot
4. **Sync** - Enable auto-sync to keep content updated (where supported)

## Supported File Types

When importing from cloud storage services like Google Drive, Dropbox, OneDrive, or Box, SiteGPT can process:

| File Type     | Extensions                    |
| ------------- | ----------------------------- |
| Documents     | .pdf, .doc, .docx, .txt, .rtf |
| Spreadsheets  | .xls, .xlsx, .csv             |
| Presentations | .ppt, .pptx                   |
| Web           | .html, .htm                   |

## Best Practices

<AccordionGroup>
  <Accordion title="Organize your content before importing">
    Create dedicated folders for chatbot training content. This makes it easier to manage what gets imported and keeps your chatbot focused.
  </Accordion>

  <Accordion title="Use multiple sources for comprehensive coverage">
    Customers using 3+ data sources see **40% fewer "I don't know" responses**. Combine your website with internal docs and FAQs.
  </Accordion>

  <Accordion title="Keep content up to date">
    Enable auto-sync where available, or set reminders to retrain monthly. Outdated content leads to incorrect answers.
  </Accordion>

  <Accordion title="Review what you're importing">
    Only import content you want the chatbot to reference. Exclude internal-only documents, draft content, or sensitive information.
  </Accordion>
</AccordionGroup>

## Adding a Data Source

1. Navigate to your chatbot's **Training** tab
2. Click **Add Data Source**
3. Select your preferred data source type
4. Follow the authentication prompts
5. Select the content to import
6. Click **Start Training**

<Note>
  Training time depends on the amount of content. A typical import of 50-100 documents takes 2-5 minutes.
</Note>

## Need Help?

If you encounter issues connecting a data source, check the specific integration guide for troubleshooting steps, or contact our support team.