Skip to main content
An assistant answers only from the knowledge attached to it. Content gets there through a source — a website, a sitemap, a GitHub repository, an OpenAPI schema, a public help centre or forum, uploaded files, or answers you write yourself — 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.

​
The building blocks

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.
A source is a standing definition of where content comes from: a website, a sitemap, a GitHub repository, an OpenAPI schema, a public Zendesk help centre, a public Discourse forum, a Confluence Cloud site, a Notion workspace, a set of uploaded files, or a set of answers you write yourself. Syncing it again picks up what changed. A source can be edited, renamed and paused after it is created. See Knowledge sources.
Syncing a source starts an ingestion job that runs in the background. You can follow its progress and cancel it. See Ingestion.
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.

​
Supported content

Confluence, Notion, Jira, Jira Service Management, Zendesk tickets and private GitHub repositories read with a token your organisation saves once as a connection. Every other source takes no credential: help centres and forums are read as a signed-out visitor reads them, so content behind their sign-in cannot be connected. Connectors lists what each source reads and what is not supported. 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

Connect a source

Websites, sitemaps, GitHub, OpenAPI schemas, help centres, forums and custom answers.

Upload files

PDFs, Word documents, Markdown and text.
Last modified on November 7, 2026