Skip to main content
POST
/
api
/
kb
/
ingest
/
jobs
Create Ingest Job
curl --request POST \
  --url https://api.example.com/api/kb/ingest/jobs \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form file='@example-file' \
  --form 'collection=<string>' \
  --form chunk_size=1 \
  --form chunk_overlap=1 \
  --form 'separators=<string>' \
  --form embedding_model_id=text-embedding-v4 \
  --form embedding_batch_size=1 \
  --form max_retries=1 \
  --form retry_delay=1
{
  "id": "<string>",
  "user_id": 123,
  "job_type": "<string>",
  "queue": "<string>",
  "status": "<string>",
  "attempts": 123,
  "max_attempts": 123,
  "progress": {},
  "result": {},
  "error_message": "<string>",
  "celery_task_id": "<string>",
  "started_at": "2023-11-07T05:31:56Z",
  "finished_at": "2023-11-07T05:31:56Z",
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z"
}

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

multipart/form-data
file
file
required
collection
string
parse_method
enum<string> | null

Available parsing methods

Available options:
default,
pypdf,
pdfplumber,
unstructured,
pymupdf,
deepdoc
chunk_strategy
enum<string> | null

Available chunk strategies

Available options:
recursive,
fixed_size,
markdown
chunk_size
integer | null
Required range: x > 0
chunk_overlap
integer | null
Required range: x >= 0
separators
string | null
embedding_model_id
string
default:text-embedding-v4
embedding_batch_size
integer | null
Required range: x > 0
max_retries
integer | null
Required range: x >= 0
retry_delay
number | null
Required range: x >= 0

Response

Successful Response

id
string
required
user_id
integer
required
job_type
string
required
queue
string
required
status
string
required
attempts
integer
required
max_attempts
integer
required
progress
Progress · object
result
Result · object
error_message
string | null
celery_task_id
string | null
started_at
string<date-time> | null
finished_at
string<date-time> | null
created_at
string<date-time> | null
updated_at
string<date-time> | null