boostrs api

Batch Extract Skills

Submit batches of documents (courses) and have them automatically processed to get the matching skills for each of them.
Each document in the batch will be processed automatically and the corresponding skills will be extracted based on the document's content.
Submit a batch of documents for automated text analysis and skill extraction

Batch details & upload limits

The limits are as follows:
  • max 7,500 characters per content field of a document
  • max 50,000 documents per batch
  • max request size 10 MB
The batch will be rejected if at least one of the limits is exceeded.
The maximum size of a request means the entire JSON content counts against the limit, including the field labels, optional fields, length of field values (ex: external_id, provider etc.).
Examples of batch values 1. Batch of 1,300 documents, with 7,500 characters per document content field value. 2. Batch 2,000 documents with 5,000 characters per document content field value.

Request body (sample)

"name": "",
"category_id": 12345,
"documents": [
"title": "internal name 1",
"content": "",
"language_code": "en",
"provider": "",
"external_id": ""
"title": "doc 2",
"content": "",
"language_code": "fr",
"provider": "",
"external_id": ""

Response fields

Batch ID
The name given to the batch.
Batch status.
'active' - all documents have been processed.
'queued' - documents will start processing based on arrival.
'processing' - some documents have been processed and some documents are being processed right now.
Total number of documents request in the batch.
Number of documents for which the processing is complete.
Number of documents which are queued.