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

# Documents & ingestion

> Upload files, ingest URLs, and crawl websites — then let AutoSage make them searchable.

Documents are the corpus your assistant answers from. Add content to a knowledge base and AutoSage processes it in the background, turning it into grounded, citable passages. Everything below happens from the dashboard — no code required.

## What you can add

<CardGroup cols={2}>
  <Card title="Files" icon="file-arrow-up">
    PDFs (including scanned PDFs and images, read with OCR), audio files (transcribed to text), and structured documents such as Word files and spreadsheets.
  </Card>

  <Card title="A single URL" icon="link">
    Point AutoSage at one web page and it scrapes the page to clean text.
  </Card>

  <Card title="A website" icon="globe">
    Discover the pages on a site and pick which ones to ingest. A crawl covers up to about 25 pages.
  </Card>
</CardGroup>

<Info>
  Upload is automatic. As soon as you provide a file, the dashboard begins ingesting it — there is no separate "start" step.
</Info>

## How ingestion works

Once content arrives, AutoSage processes it in the background so it becomes searchable and citable:

<Steps>
  <Step title="Parse">
    The raw file, page, or recording is read into text — including OCR for scanned PDFs and images, and transcription for audio.
  </Step>

  <Step title="Summarize">
    AutoSage generates a summary that helps the assistant reason about the document as a whole.
  </Step>

  <Step title="Chunk">
    The text is split into passages sized for accurate retrieval.
  </Step>

  <Step title="Embed & index">
    Each passage is embedded and added to the knowledge base's private vector store, ready to be retrieved and cited.
  </Step>
</Steps>

## Document status

Every document moves through a clear lifecycle you can watch in the dashboard:

| Status         | What it means                                                       |
| -------------- | ------------------------------------------------------------------- |
| Pending upload | The document is being received.                                     |
| Queued         | Received and waiting for background processing to begin.            |
| Processing     | Being parsed, summarized, chunked, and indexed.                     |
| Processed      | Ready — the document is now searchable and can be cited in answers. |
| Failed         | Processing could not complete. Reprocess the document or remove it. |

<Tip>
  Wait until a document reads **Processed** before expecting answers to include it. Until then, its content is still being made searchable.
</Tip>

## Reprocess and delete

<AccordionGroup>
  <Accordion title="Reprocess a document" icon="rotate">
    Run a document through processing again — useful after a failed attempt, or when you want it re-indexed. The document returns to the processing states and becomes **Processed** when it finishes.
  </Accordion>

  <Accordion title="Delete a document" icon="trash">
    Removing a document takes it out of search immediately and cleans up its stored content and index entries. Deleting is safe and does not affect other documents in the knowledge base.
  </Accordion>
</AccordionGroup>

## Keeping your quota tidy

Documents count toward your tenant's **max documents** and **max storage** quotas from the moment they are added — including documents that are still pending or that ended in a failed state.

<Tip>
  If an upload fails, delete it once you have retried. Clearing out pending and failed documents you no longer need keeps room in your quota for the content you actually want searchable.
</Tip>

<Warning>
  When a new document would push the tenant past its **max documents** or **max storage** quota, the upload is refused with a clear message. Remove content you no longer need, or raise the tenant's quota, then add the document again.
</Warning>

## Next steps

<CardGroup cols={2}>
  <Card title="Shape the answers" icon="pen-nib" href="/knowledge-bases/prompts">
    Set a persona and instructions so answers sound the way you want.
  </Card>

  <Card title="Build an agent" icon="robot" href="/agents/overview">
    Turn your knowledge base into a deployable, schedulable agent.
  </Card>
</CardGroup>