Get Document - v2 (Legacy)

Retrieve a single document by ID using the v2 compatibility shape.

collection_namestringRequired

document_idstringRequired

include_bboxbooleanOptionalDefaults to false

When true, include normalized element layout (bounding boxes) for the document under bounding_boxes. Omitted by default to keep the response lean.

Successful Response

chunk_countinteger

chunkslist of objects

collection_namestring

document_idstring

metadataobject

regionslist of objects or null

1	import requests
2	import json
3
4	BASE_URL = "https://api.runcaptain.com"
5	API_KEY = "your_api_key"
6	COLLECTION_NAME = "my_documents"
7	DOCUMENT_ID = "doc_abc123"
8
9	response = requests.get(
10	f"{BASE_URL}/v2/collections/{COLLECTION_NAME}/documents/{DOCUMENT_ID}",
11	headers={"Authorization": f"Bearer {API_KEY}"},
12	timeout=30.0,
13	)
14
15	print(json.dumps(response.json(), indent=2))

1	{
2	"chunk_count": 1,
3	"chunks": [
4	{
5	"chunk_id": "chk_abc123_003",
6	"content": "The contract shall commence on the Effective Date...",
7	"chunk_index": 3
8	}
9	],
10	"collection_name": "my_documents",
11	"document_id": "doc_abc123",
12	"metadata": {
13	"filename": "contract.pdf"
14	}
15	}