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

# Data

<Frame>
  <img src="https://mintcdn.com/chatzyai/jXmVKZ3P6KCTbIH5/ai-agents/conversational-ai-agent/data.gif?s=8c9b0776df50e52138de151fec28230e" width="2990" height="1792" data-path="ai-agents/conversational-ai-agent/data.gif" />
</Frame>

Your bot learns from various data sources. The more relevant the data, the better your agent performs.

## **Supported Data Types**

* **Text:** Paste plain text directly into the platform.
* **Files:** Upload documents such as `.pdf`, `.docx`, `.txt`, and `.csv`.
* **Website URLs:** Add a URL and let Chatzy extract useful content.
* **FAQs:** Manually input question-answer pairs for precise responses.
* **Google Drive:** Link a public folder with view-only access.
* **Media:** Upload images, videos, and PDF documents to enrich your AI agent's knowledge.

***

### Website Data Options

When adding **Website URLs** as a data source, Chatzy provides multiple ways to fetch content:

* **Crawl**\
  Automatically scans all pages linked from the given URL (excluding file downloads).\
  Example: entering `https://example.com` will crawl all linked pages under that domain.

* **Sitemap**\
  Provide an XML sitemap URL to fetch structured content from your website.

* **Link**\
  Add a single webpage URL to pull specific content.

* **CSV File**\
  Upload a CSV containing multiple URLs for bulk website training.

***

### Apify Crawler (Optional)

You can enable **Use Apify Crawler** for more advanced and accurate website crawling.

* Consumes **2 credits per webpage crawled**.
* Extracts cleaner, structured content optimized for LLM training.
* Recommended for large or dynamic websites.

Learn more: [Apify Website Content Crawler](https://apify.com/apify/website-content-crawler)

***

> The Website tab gives you the flexibility to crawl entire websites, import sitemaps, train from individual pages, or bulk import URLs using CSV files.

***

### FAQ CSV Import

You can bulk import FAQs using a **CSV file**.

* The **first column** is treated as the **Question**.
* The **second column** is treated as the **Answer**.
* The CSV **must not contain headers**.

This is the fastest way to upload a large FAQ database.

***

### Google Drive Import

Train your AI Agent directly from documents stored in Google Drive.

* Enter the **view-only link** of a Google Drive folder.
* The folder may contain **Google Docs** and **Google Sheets**.
* Ensure the folder is publicly accessible with **Viewer** permission.

All supported files inside the folder will be processed automatically.

***

### Media

You can upload media files to provide additional visual and document context to your AI agent.

#### Supported Files

* **Images:** PNG and JPEG (Maximum **5 MB** per file)
* **Videos:** MP4 (Maximum **16 MB** per file)
* **Documents:** PDF (Maximum **25 MB** per file)

#### Upload Guidelines

* Each uploaded file requires a **description** (maximum **25 words**).
* Maximum **30 media files** can be uploaded.
* Files can be uploaded using drag-and-drop or the file picker.
* Enable **Add Directly to Prompt** if you want media links and descriptions to be included directly in the AI Agent's Base Prompt.

***

## Training Your Data

After adding or updating your knowledge sources:

1. Click **Train** in the top-right corner.
2. Wait for the training process to complete.
3. Once training finishes, your AI agent will immediately begin using the latest knowledge during conversations.

### Auto Data Train

If your knowledge sources are updated frequently, you can enable **Auto Data Train** to retrain your agent automatically without manual intervention.

Available options:

* **Off** – Manual training only.
* **Daily** – Retrains every day.
* **Weekly** – Retrains once every week.
* **Fortnightly** – Retrains once every two weeks.
* **Monthly** – Retrains once every month.

This is especially useful for websites or Google Drive folders whose content changes regularly.

***

### Source Type Summary

| Source Type  | Supported Formats                  |
| ------------ | ---------------------------------- |
| Text         | Manual text input                  |
| File Upload  | PDF, DOCX, TXT, CSV                |
| Website      | Crawl, Sitemap, Link, CSV URLs     |
| FAQ          | Manual Q\&A or CSV Import          |
| Google Drive | Public Google Docs & Sheets        |
| Media        | PNG, JPEG, MP4, PDF (30 files max) |