---
title: "AI Knowledge Base Data Sources | Hostman Docs"
description: "Learn how to manage knowledge base data sources by uploading files or connecting URLs. Explore supported formats, indexing rules, reindexing options, and how to edit or delete sources in AI agents."
---

> For the complete documentation index for AI agents, see [llms.txt](https://hostman.com/llms.txt).

You can manage the data sources used in a knowledge base: upload new files or remove existing ones.

## Data Source Formats

**Supported file formats**: `.csv`, `.doc`, `.docx`, `.htm`, `.html`, `.md`, `.txt`, `.xls`, `.xlsx`, `.xml`, `.pdf`.

**Maximum file size**: 50 MB per file.

-   Only textual data should be used as sources.
-   There are no content or formatting restrictions, except for tables: the first row must contain column headers.
-   Media files (images, video, etc.) will not prevent indexing, but the agent will only work with text.
-   Sources can include URLs (e.g., your own documentation or online catalogs) so the agent can provide relevant links. However, URLs are treated as text—the agent cannot read or analyze the contents of a webpage directly.
-   Specialized parsers are used for each format. For example, when processing HTML pages, scripts (JS), CSS, meta tags, and other technical elements are ignored—only page content is indexed.

## Adding a Data Source

1.  Go to **AI Services** → **Knowledge Bases**.
2.  Click on the knowledge base and open the **Data Sources** tab.
3.  Click **Add source** and choose the method:
    -   **File upload**: 
        -   Select the **Upload File** tab and add 1–100 files.

![Charming Smew 2026 08 19 13 52](https://content.hostman.com/assets/d8462d18-2c4a-403e-8668-a9c932e6a56d.png?width=1579&height=836)

-   -   **Connecting via link**:
        1.  Select the **Connect via link** tab and paste the link into the **Source link** field. You can add multiple URLs at once.
            
            URL sources requirements:
            
            -   The page must be accessible without authentication.
            -   The page must fully load via `curl`, without client-side generation (no SPA).
        2.  (Optional) Enable automatic reindexing and set up its schedule. Reindexing occurs when the ETag header changes. If no ETag is provided, the index updates at each scheduled run.
        3.  Click **Connect**. 

![Charming Smew 2026 08 19 14 00](https://content.hostman.com/assets/ce0208f5-7fec-4427-993c-0a3d75b24ec7.png?width=1582&height=839)

## Managing Data Sources

The **Data Sources** tab displays all added sources:

-   **File icon**: manually uploaded source
-   **Globe icon**: source added via URL

Hovering over a source shows the **Reindex** button, which reloads the content and updates the index:

-   **Files**: reindexes the current version
-   **URLs**: fetches the latest content from the link

![Charming Smew 2026 08 19 14 04 2026 08 19 14 05](https://content.hostman.com/assets/828ab882-fef9-4d13-932c-eb69db92be41.png?width=1578&height=782)

Clicking the three-dot menu next to a source allows you to:

-   Download the file (for manually uploaded sources)
-   Edit the URL or schedule (for linked sources)
-   Delete the source