curl --request GET \
--url https://api.example.com/chunking/status{
"status": "<string>",
"result": {
"stored": true
},
"error": "<string>"
}Check the status of a document chunking job
curl --request GET \
--url https://api.example.com/chunking/status{
"status": "<string>",
"result": {
"stored": true
},
"error": "<string>"
}job_id returned from the /chunking endpoint to track the progress of your document processing.
/chunking endpoint."queued" - Job is waiting to be processed"started" - Job is currently processing"chunked" - Job completed successfully"failed" - Job encountered an errornull - Job ID not found"chunked". Contains processing results and metadata.Show result properties
curl -X GET "http://localhost:8000/chunking/status?job_id=a3f7b9c1-4e5d-6789-0abc-def123456789"
{
"status": "queued"
}
{
"status": "started"
}
{
"status": "chunked",
"result": {
"stored": true,
"chunks_created": 42,
"collection_name": "edu_mate_a1b2c3d4e5f67890abcdef1234567890"
}
}
{
"status": "failed",
"error": "PDFSyntaxError: Invalid PDF file format"
}
{
"status": null
}
POST /chunkingjob_id in responseGET /chunking/status?job_id=<job_id> every 2-5 seconds"chunked", proceed with using the collection_name for queries"failed", handle the error appropriately