> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.cloudraker.com/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.cloudraker.com/_mcp/server.

# Search and the knowledge graph

After a space's files finish processing, two tabs let you work with their content. **Search** finds passages. **Graph** shows the entities and relationships extracted from your documents. In both, click a result to open its exact source.

## Grounding — click a result, see the source

Every result in Search and the Graph is **grounded**. Click a result to open the cited value **in its original source**. Extracted values in the Data tab and in action results are grounded the same way, when the action had grounding enabled. Grounding is off by default. See [Extract data](/workspace/actions/extract-data).

* For a **PDF**, the viewer opens the cited page and highlights the bounding box of the citation.
* For **audio**, the player moves to the mention's timecode. The transcript scrolls to it.

Every extracted value, search hit, and graph entity points back to its source. You can verify each value before you approve it.

## Search

The **Search** tab runs semantic and keyword search across the space's documents and transcripts. Type into **Search this space's documents…** to begin. The empty state reads **Search this space** — "Find passages across this space's documents and transcripts."

Results are **grouped by file**, each with a type icon and filename. Every hit shows:

* A **location badge** — **p. N** for documents, or **Speaker N · m:ss–m:ss** for audio.
* A snippet with the matching words highlighted.

Click **Show N more** to expand a file's remaining hits. Click a hit to open it in its source, as described in the grounding section above. If nothing matches, you see "No results" — "Try different words or a broader query."

## Graph — the knowledge graph

The **Graph** tab shows a knowledge graph that the platform builds from the space's processed documents. An overlay panel titled **Space graph** shows a count line ("`{entities}` entities, `{relations}` relations"), a **Refetch** button, and an entity **search box**.

The graph is empty until files finish processing. Until then, you see **No entities yet**, "Processed files will appear here after ontology extraction finishes." After that, the canvas shows entities as nodes and relationships as edges. Zoom and fit controls are available.

* **Click an entity** to open a detail rail. The rail shows its name, a **type badge**, an optional key, and its **mentions**. Each mention shows the source file name and a location badge (page or timecode). Click a mention to open it in its source.
* **Click an edge** to see the relation, its source → target, and the source file. Click through to the source.

The space's **space type** configures the graph's shape, under its Ontology tab. This includes the extraction guidance, the entity types, and whether the model gets the current date. See [Space types](/workspace/spaces/space-types).