Get sections

Answers one section of one of the caller's org files: its own text, its subsections, the sections it links to or shares entities with — in this file or another — and the entities it names.

GET /v1/knowledge/files/{id}/sections/{section}

Knowledge → · All API references → · Get started →

Address	`https://api.hanzo.ai/v1/knowledge/files/{id}/sections/{section}`
Method	`GET`
Operation	`get_knowledge_files_by_id_sections_by_section`
Auth	`Authorization: Bearer $HANZO_API_KEY`

Answers one section of one of the caller's org files: its own text, its subsections, the sections it links to or shares entities with — in this file or another — and the entities it names. Open the document itself with section 0.

Request

2 fields.

Field	In	Type	Required	Description
`id`	path	string	yes	ID is the file's id.
`section`	path	string	yes	Section is the section's number in the file's table of contents.

Response

Status	Body	Meaning
`200`	knowledge.sectionOut	ok
`default`	problem-details	refused

200 body — 38 fields.

Field	In	Type	Always	Description
`children`	body	knowledge.tocEntry[]	—	Children are its subsections, to open next.
`children[].id`	body	integer (int64)	—	ID is the section's number; 0 is the document itself.
`children[].level`	body	integer (int64)	—	Level is its depth: 0 for the document, 1 for a top-level heading.
`children[].parent`	body	integer (int64)	—	Parent is the id of the section it sits in; -1 for the document.
`children[].size`	body	integer (int64)	—	Size is how many bytes of the document it spans, subsections included.
`children[].summary`	body	string	—	Summary is a one-line account of what it covers.
`children[].synthetic`	body	boolean	—	Synthetic is true for a section the index cut out of a long run of text the document gave no structure to.
`children[].title`	body	string	—	Title is its heading.
`entities`	body	knowledge.fileEntity[]	—	Entities are the entities it names.
`entities[].files`	body	integer (int64)	—	Files is how many other files of the org name it too.
`entities[].kind`	body	string	—	Kind is person, org, product, place or term.
`entities[].name`	body	string	—	Name is the entity as the text names it.
`entities[].sections`	body	integer (int64)	—	Sections is how many of the file's sections name it.
`file`	body	knowledge.fileBrief	—
`file.bucket`	body	string	—	Bucket and Key are where its bytes are: GET /v1/s3/buckets/{bucket}/objects/{key} answers a signed download URL.
`file.id`	body	string	—	ID is the file's id.
`file.key`	body	string	—	Key is the object's key in Bucket.
`file.name`	body	string	—	Name is the file's name.
`file.type`	body	string	—	Type is the file's media type.
`links`	body	knowledge.sectionLink[]	—	Links are the sections the graph reaches from it, strongest first.
`links[].file`	body	knowledge.fileBrief	—
`links[].file.bucket`	body	string	—	Bucket and Key are where its bytes are: GET /v1/s3/buckets/{bucket}/objects/{key} answers a signed download URL.
`links[].file.id`	body	string	—	ID is the file's id.
`links[].file.key`	body	string	—	Key is the object's key in Bucket.
`links[].file.name`	body	string	—	Name is the file's name.
`links[].file.type`	body	string	—	Type is the file's media type.
`links[].kind`	body	string	—	Kind is href, xref, cites, or entity (the two sections name the same entities).
`links[].label`	body	string	—	Label is the link's text, or the entities the two share.
`links[].section`	body	knowledge.sectionBrief	—
`links[].section.id`	body	integer (int64)	—	ID is the section's number in its file's table of contents; 0 is the document itself.
`links[].section.path`	body	string	—	Path is the section's place in its document: the titles from the document's own down to it, joined by " › ".
`links[].section.title`	body	string	—	Title is the section's heading.
`section`	body	knowledge.sectionBrief	—
`section.id`	body	integer (int64)	—	ID is the section's number in its file's table of contents; 0 is the document itself.
`section.path`	body	string	—	Path is the section's place in its document: the titles from the document's own down to it, joined by " › ".
`section.title`	body	string	—	Title is the section's heading.
`summary`	body	string	—	Summary is its one-line account.
`text`	body	string	—	Text is its own text — up to its first subsection — at most 64 KB.

Failure carries the platform error shape — see Errors.

Examples

CLI

SDK

HTTP

MCP

hanzo has no subcommand for this operation — the CLI serves only what cloud's live route table confirms. Use HTTP or an SDK.

.ts

.py

.go

.rs

.java

import { Configuration, KnowledgeApi } from 'hanzoai';

const api = new KnowledgeApi(new Configuration({ accessToken: process.env.HANZO_API_KEY }));
const { data } = await api.getKnowledgeFilesByIdSectionsBySection({ id: 'id', section: 'section' });

from hanzoai.cloud import ApiClient, Configuration
from hanzoai.cloud.api import KnowledgeApi

client = ApiClient(Configuration(access_token=os.environ["HANZO_API_KEY"]))
result = KnowledgeApi(client).get_knowledge_files_by_id_sections_by_section(id='id', section='section')

cfg := hanzoai.NewConfiguration()
cfg.AddDefaultHeader("Authorization", "Bearer "+os.Getenv("HANZO_API_KEY"))
client := hanzoai.NewAPIClient(cfg)

resp, _, err := client.KnowledgeAPI.GetKnowledgeFilesByIdSectionsBySection(context.Background()).Execute()
if err != nil {
	return err
}

use hanzo_client::apis::{configuration::Configuration, knowledge_api};

let mut cfg = Configuration::new();
cfg.bearer_access_token = std::env::var("HANZO_API_KEY").ok();

let result = knowledge_api::get_knowledge_files_by_id_sections_by_section(&cfg, Default::default()).await?;

import ai.hanzo.cloud.ApiClient;
import ai.hanzo.cloud.api.KnowledgeApi;

ApiClient client = new ApiClient();
client.setBearerToken(System.getenv("HANZO_API_KEY"));

var result = new KnowledgeApi(client).getKnowledgeFilesByIdSectionsBySection();

curl https://api.hanzo.ai/v1/knowledge/files/<id>/sections/<section> \
  -H "Authorization: Bearer $HANZO_API_KEY"

MCP reaches knowledge through the knowledge tool, which names its 9 operations with its own verbs — this one among them, under a name only MCP declares. describe explains any of them:

curl -X POST https://api.hanzo.ai/v1/mcp \
  -H "Content-Type: application/json" \
  -d '{
       "jsonrpc": "2.0",
       "id": 1,
       "method": "tools/call",
       "params": {
         "name": "describe",
         "arguments": {
           "op": "list_knowledge_connectors"
         }
       }
     }'

Knowledge API · All Hanzo APIs · Interactive reference

Was this page useful?

PreviousList graph — GET /v1/knowledge/files/{id}/graph NextList toc