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

# How your content becomes answerable

> Collections, sources, ingestion jobs and documents: the four pieces that turn a website, a repository or an uploaded file into passages an assistant can cite.

An assistant answers only from the knowledge attached to it. Content gets there through a **source** — a website, a sitemap, a GitHub repository or uploaded files — which is synced into a **collection**. Syncing runs an **ingestion job** in the background: MITHUNAI fetches the content, extracts its text, splits it into **passages** and indexes them. A collection is what one or more assistants answer from, and a passage is what a citation points at.

```mermaid theme={"theme":{"light":"github-light","dark":"github-dark"}}
flowchart LR
    S[Source<br/>website, sitemap,<br/>GitHub, files] -->|sync| J[Ingestion job]
    J --> E[Extract text] --> C[Split into passages] --> V[Embed and index]
    V --> K[(Collection)]
    K --> A[Assistant]
```

## The building blocks

<AccordionGroup>
  <Accordion title="Collection" icon="database">
    A **collection** is a corpus: the set of content one or more assistants answer from. Every source ingests into a collection.

    A collection's **embedding model** is fixed when the collection is created and never changes, because passages embedded by different models cannot be compared. To move to a different embedding model, create a new collection and ingest your sources into it.

    Collections can be renamed, archived and restored. An archived collection keeps serving answers but accepts no new ingestion. Collections cannot be deleted.
  </Accordion>

  <Accordion title="Source" icon="plug">
    A **source** is a standing definition of where content comes from: a website, a sitemap, a GitHub repository or a set of uploaded files. Syncing it again picks up what changed. See [Knowledge sources](/knowledge/sources).
  </Accordion>

  <Accordion title="Ingestion job" icon="loader">
    Syncing a source starts an **ingestion job** that runs in the background. You can follow its progress and cancel it. See [Ingestion](/knowledge/ingestion).
  </Accordion>

  <Accordion title="Document and passage" icon="file-text">
    A **document** is one ingested item, such as a page or a file. Documents are split into **passages**, and passages are what retrieval searches and what citations point at, so a citation lands on the paragraph that supports a claim rather than on a 40-page manual.
  </Accordion>
</AccordionGroup>

## Supported content

| Source          | What it ingests                                                          |
| --------------- | ------------------------------------------------------------------------ |
| **Website**     | Pages reached by following links from a start URL, within bounds you set |
| **Sitemap**     | Exactly the URLs a `sitemap.xml` lists                                   |
| **GitHub**      | Files from a repository branch, filtered by path                         |
| **File upload** | PDF, Word (`.docx`), Markdown and plain-text files                       |

MITHUNAI extracts text from HTML, Markdown, plain text, reStructuredText, source code, PDF and Word documents. Content it cannot extract is skipped rather than ingested badly.

## Your content is treated as untrusted input

Anyone who can edit your documentation can put text into your corpus. For a public site or repository, that can include anyone whose pull request you merge. MITHUNAI therefore:

* **Bounds every fetch**, so a runaway or hostile source cannot consume unbounded resources.
* **Restricts where crawls can go**, so a link or redirect cannot reach internal infrastructure.
* **Detects and redacts secrets** in extracted content, so a credential committed to a repository is removed before an assistant can repeat it.
* **Separates content from instructions** when answering, so text such as "ignore your instructions" is treated as content.

These measures reduce prompt-injection risk; no system that feeds untrusted text to a model can eliminate it. Review what you connect as part of your security perimeter.

## Next

<Columns cols={2}>
  <Card title="Connect a source" icon="plug" href="/knowledge/sources">
    Websites, sitemaps and GitHub repositories.
  </Card>

  <Card title="Upload files" icon="upload" href="/knowledge/file-uploads">
    PDFs, Word documents, Markdown and text.
  </Card>
</Columns>