> For the complete documentation index, see [llms.txt](https://api.docs.blockbrain.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://api.docs.blockbrain.ai/concepts/knowledge-base.md).

# Document Databases

**Document Databases** store and serve the source materials that knowledge workflows rely on: files, email contents, and structured documents. In this stack, documents are linked to conversations (data rooms) and Insights via short-lived references, enabling retrieval, processing, and indexing while preserving provenance and access controls.

#### When to use a Document Database

* **You need durable storage** for artifacts used by Knowledge Bots and Insights.´
* **You require provenance** linking documents to the conversations and notes that cited them.
* **You plan to index content** for search/RAG, analytics, or compliance review.
* **You integrate enterprise sources** (e.g., SharePoint, email) and need a unified handling model.

### Typical lifecycle

1. A conversation or connector ingests a file/email into the document store.
2. The system generates a short-lived `ref` for safe access.
3. Tools process the document (text extraction, splitting, metadata enrichment, embeddings).
4. Insights cite the document via provenance links and store `ref` values for follow-up processing.
5. Indexers ingest normalized content and metadata into search/RAG systems.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://api.docs.blockbrain.ai/concepts/knowledge-base.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.