Skip to main content

Single file

Use client.jobs.upload() — the standard entry point for uploading and queuing a single document:
The returned Job object can be awaited with job.wait_until_done().

Multiple files

Each file gets its own Job. Files are processed sequentially.

With options


From bytes


From a connector (S3 / GCS / Azure)

If you have a connector configured, process files directly from cloud storage:
See Connectors for setup.

Polling manually

If you need fine-grained control over polling:
Or use job.wait_until_done() — it handles this automatically with configurable timeout and poll interval.