How to poll status and export results

live-status reports one overall job_state plus a state per language in translations. Export is per language: call it once for each target language, only after that language’s own state is Completed.

Endpoint	Purpose
`GET /translate/document/jobs/{job_id}/live-status`	Overall progress + per-language state. Poll every 10-15 seconds.
`POST /translate/document/jobs/{job_id}/export?lang={code}&format={fmt}`	Enqueue an async export for one target language. Returns `202 Accepted` with `export_state=Pending`.
`GET /translate/document/jobs/{job_id}/export/status`	Poll export status until `export_state` is `Completed`, then download from `download_url`.

live-status response shapes differ by file type, but the poll/export logic below works for both:

Upload type	Progress tracking
PDF	Per page (`page_metrics`)
Word, spreadsheet, presentation	Per segment (`translation_metrics`)

job_state, translations[].state, and translations[].target_language_code are present in both shapes. See Overview for full field lists.

Check each language’s own state, not only top-level job_state.

A job can stay Running or PartiallyCompleted while some languages in translations[] are already Completed and ready to export. Gate your export loop on translations[].state, not job_state alone.

Example

Replace YOUR_SARVAM_API_KEY with your key from Key Management. This example assumes you already created a job, uploaded the file, and called start — see the Overview quickstart.

1 import os
2 import time
3 
4 from sarvamai import SarvamAI
5 
6 client = SarvamAI(api_subscription_key=os.environ["SARVAM_API_KEY"])
7 job_id = "550e8400-e29b-41d4-a716-446655440000"
8 TERMINAL = {"Completed", "PartiallyCompleted", "Failed"}
9 
10 
11 def poll_job(job_id):
12     while True:
13         status = client.document_translation.get_live_status(job_id=job_id)
14         print(f"job_state={status.job_state} progress={status.progress}%")
15         if status.job_state in TERMINAL:
16             return status
17         time.sleep(12)
18 
19 
20 def export_completed(job_id, translations):
21     urls = {}
22     for t in translations:
23         if t.state != "Completed":
24             continue
25         export = client.document_translation.trigger_export(
26             job_id=job_id,
27             lang=t.target_language_code,
28             format="pdf",
29         )
30         while True:
31             status = client.document_translation.get_export_status(
32                 job_id=job_id,
33                 export_id=export.export_id,
34             )
35             if status.export_state == "Completed":
36                 urls[t.target_language_code] = status.download_url
37                 break
38             if status.export_state == "Failed":
39                 print(f"Export failed for {t.target_language_code}")
40                 break
41             time.sleep(5)
42     return urls
43 
44 
45 final = poll_job(job_id)
46 downloads = export_completed(job_id, final.translations or [])
47 print("Downloads:", downloads)

The sample above covers polling through export. See the Overview for the complete five-step flow including create, upload, and start.