Get Job Status

Prerequisites

Get an API key and a workspace ID, and configure authentication first. See API overview and Authentication.

Endpoint

GET /api/v1/indices/rag/index_job/status Check the execution status of an import job and the processing details of each document. index_id and job_id must be passed together.

When the Knowledge Base has no import job in progress, this endpoint may return SystemError. Call it after submitting an import job.

Request parameters

The following parameters are passed through the query string.

Parameter	Required	Type	Description
`index_id`	Yes	string	Knowledge Base ID, corresponding to the `pipelineId` returned when the Knowledge Base was created.
`job_id`	Yes	string	Import job ID. It is the `ingestionId` field returned by Submit Import Job, and can also be found in the `ingestion_id` field of the document list. `index_id` and `job_id` must be passed together; passing only `index_id` returns SystemError.
`page_number`	No	integer	Page number, starting from 1. Default: 1. Use pagination when the job involves many documents.
`page_size`	No	integer	Number of documents per page. Default: 10.

Request example

curl -G "$BASE_URL/api/v1/indices/rag/index_job/status" \
  -H "Authorization: Bearer $BAILIAN_API_KEY" \
  -d "index_id=your-kb-id" \
  -d "job_id=your-job-id"

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": {
    "id": "your-job-id",
    "ingestion_status": "COMPLETED",
    "ingestion_message": "COMPLETED",
    "total_count": 4,
    "rows": [
      {
        "code": "FINISH",
        "doc_id": "file_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx_xxxxxx",
        "doc_name": "sample_document",
        "doc_type": "pdf",
        "size": 191166,
        "status": "FINISH",
        "message": "索引构建成功",
        "ingestion_id": "your-job-id",
        "dataSync": false,
        "canDelete": true,
        "meta_extract_info": [],
        "gmt_modified": 1782209511000
      }
    ],
    "page_number": 1,
    "page_size": 10,
    "started_at": 1782209506000,
    "ended_at": 1782209512000,
    "created_at": 1782209506000,
    "updated_at": 1782209512000
  },
  "success": true,
  "message": "success",
  "request_id": "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "SUCCESS"
}

Response fields

Field	Type	Description
`code`	string	Response code. `Success` when successful.
`status_code`	integer	HTTP status code.
`request_id`	string	Unique request identifier. Provide this ID when troubleshooting.
`success`	boolean	Whether the request succeeded.
`message`	string	Response message. `success` when successful.
`status`	string	Request status: `SUCCESS` or `FAILED`.
`data`	object	Job status and processing details. See the table below for sub-fields.

data fields

Field	Type	Description
`id`	string	Import job ID.
`ingestion_status`	string	Overall job status: `PENDING` (waiting), `RUNNING` (in progress), `COMPLETED` (completed).
`ingestion_message`	string	Job status description, usually consistent with `ingestion_status`.
`total_count`	integer	Total number of documents involved in the job. May be 0 while the job is in progress.
`rows`	array	Processing details of each document. Same structure as the `rows` of List Documents. See the table below for element fields.
`page_number`	integer	Current page number.
`page_size`	integer	Number of items per page.
`started_at`	integer	Job start time as a Unix timestamp in milliseconds.
`ended_at`	integer	Job end time as a Unix timestamp in milliseconds. `null` while in progress.
`created_at`	integer	Job creation time as a Unix timestamp in milliseconds.
`updated_at`	integer	Last job update time as a Unix timestamp in milliseconds.

rows element fields

Field	Type	Description
`doc_id`	string	Document ID.
`doc_name`	string	Document name.
`doc_type`	string	Document type.
`code`	string	Fine-grained processing status code, for example `FINISH` or `PARSE_FAILED`.
`status`	string	Coarse-grained processing status.
`message`	string	Processing status description, for example `索引构建成功` (index built successfully).
`size`	integer	File size in bytes.
`ingestion_id`	string	ID of the import job the document belongs to.
`connectorId`	string	Associated connector ID. Empty string when no connector is used.
`categoryId`	string	ID of the category the file belongs to.
`categoryName`	string	Name of the category the file belongs to.
`tags`	string	File tags, separated by commas.
`dataSync`	boolean	Whether the file participates in data sync.
`canDelete`	boolean	Whether the file can be deleted.
`source_id`	string	File source identifier.
`gmt_modified`	integer	Last modified time as a Unix timestamp in milliseconds.
`meta_extract_info`	array	Metadata extraction results.

Error codes

HTTP status code	Error code (`code`)	Description
400	`Index.InvalidParameter`	Invalid request parameters: `Required parameter missing or invalid.`
401	`InvalidApiKey`	Invalid or missing API key: `Invalid API-key provided.`

​Prerequisites

​Endpoint

​Request parameters

​Request example

​Response example

​Response fields

​data fields

​rows element fields

​Error codes

Prerequisites

Endpoint

Request parameters

Request example

Response example

Response fields

data fields

rows element fields

Error codes