> For the complete documentation index, see [llms.txt](https://k-ai.gitbook.io/knowledge-ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://k-ai.gitbook.io/knowledge-ai/sources-and-ingestion/instance-api/semantic-graph.md).

# Semantic Graph

The Semantic Graph endpoints expose the **Neural Semantic Graph** built from indexed documents: nodes, relationships, and exploration primitives. Each semantic node is a triple of `(node_1, node_2, edge)` — an entity-relationship-entity extracted from indexed content.

Authenticated with `instance-id` + `api-key` headers — see [Instance API keys](/knowledge-ai/authentication/api-keys.md).

***

## POST /api/semantic-graph/identify-nodes

Identify all semantic nodes relevant to a natural-language query. The system translates the query, embeds it, finds approximate related nodes (cosine similarity ≥ 0.95), then uses an LLM crew to select the most relevant documents.

If `need_documents` is `true`, partial document content from the matching chunks is included in `documents_contents`. If `false`, `documents_contents` is an empty array and document IDs are available within each semantic node's `documents` field.

{% openapi src="/files/ggZwaT7KDX2BbCKblljY" path="/api/semantic-graph/identify-nodes" method="post" %}
[instance-api.yaml](https://3937809777-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F85gF5n5kGsNQKMPwm2VR%2Fuploads%2Fgit-blob-8f3d896df32794f28ab6f557a94cbd117983f7c2%2Finstance-api.yaml?alt=media)
{% endopenapi %}

{% tabs %}
{% tab title="curl" %}

```bash
curl -X POST https://api.kai-studio.ai/api/semantic-graph/identify-nodes \
  -H "instance-id: <YOUR_INSTANCE_ID>" \
  -H "api-key: <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{"query": "What are the safety requirements?", "need_documents": true}'
```

{% endtab %}

{% tab title="Python" %}

```python
import httpx

response = httpx.post(
    "https://api.kai-studio.ai/api/semantic-graph/identify-nodes",
    headers={
        "instance-id": "<YOUR_INSTANCE_ID>",
        "api-key": "<YOUR_API_KEY>",
    },
    json={"query": "What are the safety requirements?", "need_documents": True},
)
response.raise_for_status()
payload = response.json()["response"]
for node in payload["semantic_nodes"]:
    print(node["node_1"], "->", node["edge"], "->", node["node_2"])
```

{% endtab %}

{% tab title="TypeScript" %}

```ts
const response = await fetch(
  "https://api.kai-studio.ai/api/semantic-graph/identify-nodes",
  {
    method: "POST",
    headers: {
      "instance-id": "<YOUR_INSTANCE_ID>",
      "api-key": "<YOUR_API_KEY>",
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      query: "What are the safety requirements?",
      need_documents: true,
    }),
  },
);
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());
```

{% endtab %}
{% endtabs %}

***

## POST /api/semantic-graph/nodes

List all semantic nodes in the instance with pagination. Each node carries `id`, `node_1`, `node_2`, `edge`, and an `extraproperties` object listing the contributing `documents`, `chunks`, and occurrence `count`.

{% openapi src="/files/ggZwaT7KDX2BbCKblljY" path="/api/semantic-graph/nodes" method="post" %}
[instance-api.yaml](https://3937809777-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F85gF5n5kGsNQKMPwm2VR%2Fuploads%2Fgit-blob-8f3d896df32794f28ab6f557a94cbd117983f7c2%2Finstance-api.yaml?alt=media)
{% endopenapi %}

{% tabs %}
{% tab title="curl" %}

```bash
curl -X POST https://api.kai-studio.ai/api/semantic-graph/nodes \
  -H "instance-id: <YOUR_INSTANCE_ID>" \
  -H "api-key: <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{"offset": 0, "limit": 50}'
```

{% endtab %}

{% tab title="Python" %}

```python
import httpx

response = httpx.post(
    "https://api.kai-studio.ai/api/semantic-graph/nodes",
    headers={
        "instance-id": "<YOUR_INSTANCE_ID>",
        "api-key": "<YOUR_API_KEY>",
    },
    json={"offset": 0, "limit": 50},
)
response.raise_for_status()
print(response.json())
```

{% endtab %}

{% tab title="TypeScript" %}

```ts
const response = await fetch(
  "https://api.kai-studio.ai/api/semantic-graph/nodes",
  {
    method: "POST",
    headers: {
      "instance-id": "<YOUR_INSTANCE_ID>",
      "api-key": "<YOUR_API_KEY>",
      "Content-Type": "application/json",
    },
    body: JSON.stringify({ offset: 0, limit: 50 }),
  },
);
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());
```

{% endtab %}
{% endtabs %}

***

## POST /api/semantic-graph/nodes-by-label

List semantic nodes where either `node_1` or `node_2` matches the given label. The label must not be empty; an empty label returns a 403 error.

{% openapi src="/files/ggZwaT7KDX2BbCKblljY" path="/api/semantic-graph/nodes-by-label" method="post" %}
[instance-api.yaml](https://3937809777-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F85gF5n5kGsNQKMPwm2VR%2Fuploads%2Fgit-blob-8f3d896df32794f28ab6f557a94cbd117983f7c2%2Finstance-api.yaml?alt=media)
{% endopenapi %}

***

## POST /api/semantic-graph/linked-nodes-by-id

Find semantic nodes that share entity labels with the `node_1` or `node_2` of a given semantic node. This enables graph exploration by following connections from a known node. The given node itself is excluded from the results.

{% openapi src="/files/ggZwaT7KDX2BbCKblljY" path="/api/semantic-graph/linked-nodes-by-id" method="post" %}
[instance-api.yaml](https://3937809777-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F85gF5n5kGsNQKMPwm2VR%2Fuploads%2Fgit-blob-8f3d896df32794f28ab6f557a94cbd117983f7c2%2Finstance-api.yaml?alt=media)
{% endopenapi %}


---

# 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, and the optional `goal` query parameter:

```
GET https://k-ai.gitbook.io/knowledge-ai/sources-and-ingestion/instance-api/semantic-graph.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.