List document chunks

GET

Retrieves the text chunks that were generated from a document during ingestion. Chunks represent semantic sections of the document and are used for retrieval and analysis.

Users can only access chunks from documents they own or have access to through collections. Vector embeddings are only included if specifically requested.

Results are returned in chunk sequence order, representing their position in the original document.

Path parameters

idstringRequired

The ID of the document to retrieve chunks for.

Query parameters

offsetintegerOptional

Specifies the number of objects to skip. Defaults to 0.

limitintegerOptional

Specifies a limit on the number of objects to return, ranging between 1 and 100. Defaults to 100.

include_vectorsbooleanOptional

Whether to include vector embeddings in the response.

Response

Successful Response

resultslist of objects

total_entriesinteger

Errors

Built with

1	from r2r import R2RClient
2
3	client = R2RClient("http://localhost:7272")
4	# when using auth, do client.login(...)
5
6	response = client.documents.list_chunks(
7	id="32b6a70f-a995-5c51-85d2-834f06283a1e"
8	)

1	{
2	"results": [
3	{
4	"id": "id",
5	"document_id": "document_id",
6	"owner_id": "owner_id",
7	"collection_ids": [
8	"collection_ids"
9	],
10	"text": "text",
11	"metadata": {
12	"key": "value"
13	},
14	"vector": [
15	1.1
16	]
17	}
18	],
19	"total_entries": 1
20	}