> ## Documentation Index
> Fetch the complete documentation index at: https://guide.beenos-solutions.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Add Content Sources to Your Beenos Solutions Knowledge Base

> Upload documents, crawl web URLs, or paste plain text to populate your Beenos Solutions knowledge base with fully indexed, searchable content.

Populating your knowledge base is the first step toward building an AI agent that delivers accurate, source-grounded responses. Beenos Solutions gives you three ways to bring content in — file uploads, web URL crawling, and direct text entry — so you can work with whatever format your content already lives in. Once added, each source is automatically processed and indexed, usually within a couple of minutes.

## Add a New Source

<Tabs>
  <Tab title="Upload a Document">
    Upload local files directly from your computer. Beenos Solutions parses and indexes the full text content of each file you provide.

    <Steps>
      <Step title="Open your knowledge base">
        Navigate to the **Knowledge Base** section from the left sidebar and select the knowledge base you want to add content to. If you haven't created one yet, click **New Knowledge Base** and give it a name.
      </Step>

      <Step title="Click Add Source">
        On the knowledge base detail page, click the **Add Source** button in the top-right corner, then select **Upload a Document** from the dropdown.
      </Step>

      <Step title="Select or drop your file">
        Drag and drop a file onto the upload area, or click **Browse Files** to open your system file picker. You can upload one file at a time. The maximum file size per upload is **50 MB** on the Free plan and **500 MB** on Pro and Enterprise plans.
      </Step>

      <Step title="Confirm and upload">
        Review the detected file name and format, then click **Upload**. Beenos Solutions will begin parsing and indexing the file immediately. The source will appear in your sources list with a **Processing** status badge while indexing is underway.
      </Step>
    </Steps>
  </Tab>

  <Tab title="Add a URL">
    Point Beenos Solutions at a public web page or an entire website section and let the crawler fetch the content for you.

    <Steps>
      <Step title="Open your knowledge base">
        Navigate to **Knowledge Base** in the left sidebar and open the knowledge base you want to update.
      </Step>

      <Step title="Click Add Source">
        Click **Add Source**, then select **Add a URL** from the dropdown menu.
      </Step>

      <Step title="Enter the URL">
        Paste the full URL (including `https://`) into the URL field. Choose your crawl scope:

        * **Single page** — indexes only the exact URL you entered.
        * **Recursive crawl** — follows internal links from the starting URL up to a configurable page depth (1–5 levels). Use this option to index an entire documentation site or blog section.
      </Step>

      <Step title="Set a refresh schedule (optional)">
        If your web content changes regularly, enable **Auto-refresh** and choose a schedule: **Daily**, **Weekly**, or **Monthly**. Beenos Solutions will re-crawl the URL on that cadence and update the index automatically.
      </Step>

      <Step title="Click Add URL">
        Click **Add URL** to start the crawl. The source appears in your list with a **Processing** badge. Crawl time depends on the number of pages discovered.
      </Step>
    </Steps>
  </Tab>

  <Tab title="Paste Text">
    Enter content directly if it doesn't exist as a file or a public URL — useful for internal notes, policies written in a document editor, or short reference snippets.

    <Steps>
      <Step title="Open your knowledge base">
        Go to **Knowledge Base** in the sidebar and select your target knowledge base.
      </Step>

      <Step title="Click Add Source">
        Click **Add Source** and choose **Paste Text** from the dropdown.
      </Step>

      <Step title="Give the source a name">
        Enter a descriptive name in the **Source Name** field (for example, *Refund Policy v2* or *Onboarding FAQ*). This label appears in search results and source attribution shown to your agents.
      </Step>

      <Step title="Enter your content">
        Type or paste your content into the text editor. The editor supports plain text and basic Markdown formatting. There is no hard character limit, but very large pastes may be split into multiple chunks during indexing.
      </Step>

      <Step title="Click Save Source">
        Click **Save Source**. The content is queued for indexing immediately and will be searchable once processing completes.
      </Step>
    </Steps>
  </Tab>
</Tabs>

## Supported Formats

Beenos Solutions can parse the following file types when you upload a document. Unsupported formats are rejected at upload with an error message.

<AccordionGroup>
  <Accordion title="PDF (.pdf)">
    Full text extraction is supported for both native PDFs and scanned PDFs with embedded OCR text. Scanned PDFs without a text layer are not currently supported — convert them using an OCR tool before uploading.
  </Accordion>

  <Accordion title="Word Document (.docx)">
    Content is extracted from the body text, headings, and tables. Comments, tracked changes, and embedded macros are ignored during parsing.
  </Accordion>

  <Accordion title="Plain Text (.txt)">
    Uploaded as-is with no formatting transformation. Encoding must be UTF-8. Files in other encodings should be converted before uploading.
  </Accordion>

  <Accordion title="Markdown (.md, .mdx)">
    Markdown and MDX files are parsed and indexed as plain text. Frontmatter fields (such as `title` and `description`) are extracted and stored as source metadata.
  </Accordion>

  <Accordion title="CSV (.csv)">
    Each row is indexed as a separate chunk. The first row is treated as a header and used to provide column context for each subsequent row. Large CSVs with thousands of rows may take longer to index than other file types.
  </Accordion>
</AccordionGroup>

<Tip>
  Give every source a clear, specific name before saving it. Descriptive names like *Q4 2024 Product Changelog* or *EU Privacy Policy* make it much easier to identify sources in search results, manage them later, and understand which content your agents are drawing from.
</Tip>

<Note>
  Most sources finish indexing within **1–2 minutes** of being added. Large files, deep recursive URL crawls, or CSVs with many rows may take up to **10 minutes**. Your agents cannot query a source until its status badge changes from **Processing** to **Indexed**.
</Note>