List Chunks

Prerequisites

Configure the endpoint and authentication first. See API overview and Authentication.

Endpoint

POST /api/v1/indices/rag/index/chunklist Paginate through the chunks in a specified knowledge base. In the response, data.nodes is the chunk array and data.total is the total chunk count.

docId filters chunks by document. Required for document-search and audio/video-search knowledge bases; not needed for data-query or image-QA knowledge bases.

Request body

Field	Required	Type	Description
`indexId`	Yes	string	Knowledge base ID, the `data.id` returned by the createIndex API.
`pageNum`	No	integer	Page number, starting from 1. Default: 1.
`pageSize`	No	integer	Number of chunks returned per page. Default: 20. Maximum: 100.
`docId`	No	string	Filter by document ID, returning only the chunks under that document. Document IDs can be obtained from the List Documents API.

Request example

curl -X POST "$BASE_URL/api/v1/indices/rag/index/chunklist" \
  -H "Authorization: Bearer $BAILIAN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "indexId": "your_index_id",
    "pageNum": 1,
    "pageSize": 10
  }'

BASE_URL is https://{workspace_id}.cn-beijing.maas.aliyuncs.com ({workspace_id} is the workspace ID), and BAILIAN_API_KEY is your Alibaba Cloud Model Studio API key.

Response example

Returns 200 on success.

{
  "code": "Success",
  "status_code": 200,
  "data": {
    "total": 106,
    "nodes": [
      {
        "score": 0.0,
        "text": "这是切片的文本内容示例...",
        "metadata": {
          "_id": "llm-xxxxxxxxxxxx_your_kb_id_file_xxxxxxxx_0_0",
          "doc_id": "file_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx_xxxxxx",
          "doc_name": "sample_document",
          "title": "产品概述",
          "content": "这是切片的文本内容示例...",
          "hier_title": "产品概述|功能介绍",
          "doc_url": "https://oss-example.aliyuncs.com/...",
          "file_path": "https://oss-example.aliyuncs.com/.../docJson/sample.json",
          "image_url": [],
          "_chunk_id": 0,
          "_block_id": 0,
          "pipeline_id": "your_kb_id",
          "workspace_id": "llm-xxxxxxxxxxxx",
          "_chunk_status": 0,
          "_chunk_status_message": "成功",
          "is_displayed_chunk_content": true
        }
      }
    ],
    "isDowngrade": false
  },
  "success": true,
  "message": "success",
  "request_id": "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "SUCCESS"
}

Response fields

Field	Type	Description
`code`	string	Response code. `Success` on success.
`status_code`	integer	HTTP status code.
`data`	object	Business data. Sub-fields: `total` (integer, total chunk count), `nodes` (array<object>, chunk node list. Element fields: `score` (number, relevance score, usually 0 for list queries), `text` (string, chunk text content), `metadata` (object, chunk metadata. Sub-fields: `_id` (string, globally unique chunk identifier), `doc_id` (string, ID of the document the chunk belongs to), `doc_name` (string, name of the document), `title` (string, chunk title), `hier_title` (string, hierarchical title — the title path separated by \|), `content` (string, chunk content), `doc_url` (string, original document access URL), `file_path` (string, OSS path of the chunk parsing output), `image_url` (array<string>, image URLs associated with the chunk), `_chunk_id` (integer, chunk sequence number within the document), `_block_id` (integer, block sequence number), `pipeline_id` (string, ID of the knowledge base), `workspace_id` (string, ID of the workspace), `_chunk_status` (integer, chunk processing status code; 0 indicates success), `_chunk_status_message` (string, chunk processing status description), `is_displayed_chunk_content` (boolean, whether the chunk participates in knowledge base retrieval), `nid` (string, unique chunk number in the knowledge base), `source` (integer, chunk source type))), `isDowngrade` (boolean, whether retrieval downgrade occurred).
`success`	boolean	Whether the request succeeded.
`message`	string	Response message.
`request_id`	string	Unique request identifier. Provide this ID when troubleshooting.
`status`	string	Request status. `SUCCESS` on success.

​Prerequisites

​Endpoint

​Request body

​Request example

​Response example

​Response fields

Prerequisites

Endpoint

Request body

Request example

Response example

Response fields