> ## Documentation Index
> Fetch the complete documentation index at: https://docs.n3wth.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Knowledge Graph Tools

> Enhanced-mode tools for extracting entities from text, building a knowledge graph from stored memories, and finding relationship paths.

These three tools appear only when `INTELLIGENCE_MODE=enhanced` (the default). They add entity extraction and graph traversal on top of the memory store. Basic mode does not register them.

<Note>
  If these tools are missing from your client, confirm you have not set `INTELLIGENCE_MODE=basic` and check stderr for embedding model download errors. See [Troubleshooting](/r3/troubleshooting).
</Note>

## extract\_entities

Extract named entities and relationships from text using NLP. Identifies people, organizations, technologies, and projects.

<ResponseField name="text" type="string" required>
  Input text to analyze. Longer text yields more entities.
</ResponseField>

**Returns:** `{people[], organizations[], technologies[], projects[], relationships[], keywords[]}`.

## get\_knowledge\_graph

Build a knowledge graph from stored memories. Returns entities as nodes and relationships as edges.

<ResponseField name="entity_type" type="string">
  Filter nodes by type: `people`, `organizations`, `technologies`, or `projects`. Omit for all types.
</ResponseField>

<ResponseField name="entity_name" type="string">
  Filter nodes containing this name (case-insensitive substring match). Omit for all entities.
</ResponseField>

<ResponseField name="relationship_type" type="string">
  Filter edges by relationship: `WORKS_FOR`, `USES`, `BUILT_WITH`, `KNOWS`, etc. Omit for all relationships.
</ResponseField>

<ResponseField name="limit" type="number">
  Maximum nodes to return. Range: 1-100. Default: 20.
</ResponseField>

**Returns:** `{nodes[], edges[]}` where nodes have `{id, type, name, memories[]}` and edges have `{from, to, type, confidence}`.

## find\_connections

Discover relationship paths between entities in the knowledge graph. Uses BFS traversal to find how entities connect.

<ResponseField name="from_entity" type="string" required>
  Starting entity name for path search. Must match an entity in the knowledge graph exactly.
</ResponseField>

<ResponseField name="to_entity" type="string">
  Target entity name. If omitted, returns all reachable entities up to `max_depth`.
</ResponseField>

<ResponseField name="max_depth" type="number">
  Maximum relationship hops to traverse. Range: 1-5. Default: 2.
</ResponseField>

**Returns:** `{from, to, max_depth, paths_found, paths[]}` where each path is an array of `{from, to, type}` edges.

## Related

<Columns cols={2}>
  <Card title="Memory Tools" href="/r3/memory-tools">
    Store the memories the graph is built from.
  </Card>

  <Card title="Configuration" href="/r3/configuration">
    Switch between enhanced and basic intelligence modes.
  </Card>
</Columns>