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

# Knowledge overview

> The context library: how contexts, items, chunks, and embeddings work together to power agent retrieval.

export const RightsCallout = ({right, flags}) => <Info>
    Who sees this: requires {right === "none" ? "no special rights — available to every signed-in user" : `the ${right} right (or super admin)`}.
    {flags && flags !== "none" ? ` Only visible when the server enables ${flags}.` : ""}
  </Info>;

<RightsCallout right="agents (read)" />

<Info>
  The Knowledge area shares the same access gate as the Agents area: "Contexts are defined in your backend." Access requires the `agents (read)` right. A future `knowledge (read)` role key will give finer control once the backend ships that area.
</Info>

## The knowledge mental model

Before diving into the UI, understand the three-level model that drives retrieval:

| Level         | What it is                                                                                                                                                                                                                                |
| ------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Context**   | A named collection of knowledge — for example, "Product manuals" or "Support tickets". An agent can have one or more contexts attached.                                                                                                   |
| **Item**      | A single piece of source material inside a context: a file, a URL, a text paste, or a transcript. Items are the unit you create, update, archive, and delete.                                                                             |
| **Chunk**     | A fragment that an item is automatically split into for embedding. Chunking happens in the Processor stage. You do not manage individual chunks — they are the implementation detail that enables semantic search.                        |
| **Embedding** | A vector representation of a chunk. Embeddings are generated by the Embedder stage and stored in the vector index. When an agent retrieves, it searches over embeddings to find the most relevant chunks, then surfaces the source items. |

The path from raw content to something agents can search: item → processor splits it into chunks → embedder turns chunks into embeddings → agent retrieval queries the embeddings.

## The context library

Open **Knowledge** from the sidebar under the Build group. The page title reads "Knowledge" with the description "Contexts your agents retrieve from."

The library shows every context defined for this deployment.

### Statistics panel (super admin only)

Administrators see a collapsible **Usage** panel above the context list with three stat cards:

* **Items total** — aggregate item count across all contexts.
* **Retrievals (7 days)** — how many times agents queried contexts in the last seven days.
* **Upserts (7 days)** — how many items were created or updated in the last seven days.

Click "View usage" to expand the charts; "Hide usage" to collapse them.

### Searching contexts

Type into "Search contexts" to filter the list by context name in real time.

### Favourites and recently viewed

When no search is active, a **Favourites** section and a **Recently viewed** section appear above the context list.

* **Add to favourites** — click the star on any context row to pin it in the Favourites section. The star fills; click again to unpin.
* **Remove from favourites** — click the filled star on a pinned context.

Favourites are personal — they only affect your view.

### Context rows

Each row shows the context name, an optional icon (customizable by super admins), item count, and a failed-job indicator when there are pipeline errors that need attention. Click a row to open the context workspace.

<Note>
  Contexts are defined in code by your development team. The library page shows contexts that already exist in the backend; you cannot create new contexts from the UI. If you need a new context, see [Defining contexts](/developers/tutorials/defining-contexts) in the Developers section.
</Note>

## Inside a context workspace

Clicking a context opens its workspace with three tabs:

| Tab          | What it shows                                                                                                  |
| ------------ | -------------------------------------------------------------------------------------------------------------- |
| **Items**    | The table of items in this context. See [Items](/building/knowledge/items).                                    |
| **Pipeline** | The Sources → Processor → Embedder stage cards and activity log. See [Pipeline](/building/knowledge/pipeline). |
| **Entities** | Entity types for structured extraction. See [Entities](/building/knowledge/entities).                          |

## Next steps

<Columns cols={2}>
  <Card title="Items" icon="list" href="/building/knowledge/items">
    Create, search, bulk-process, and archive items.
  </Card>

  <Card title="Pipeline" icon="workflow" href="/building/knowledge/pipeline">
    Understand the Sources → Processor → Embedder flow.
  </Card>

  <Card title="Entities" icon="tag" href="/building/knowledge/entities">
    Extract structured entities from context content.
  </Card>

  <Card title="Agent knowledge settings" icon="bot" href="/building/agents/workbench">
    Attach a context to an agent in the Knowledge & memory section.
  </Card>
</Columns>