fix: DOCLING_SERVE_SYNC_POLL_INTERVAL controls the synchronous polling time (#413)

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

docling_serve/app.py

@@ -341,7 +341,7 @@ def create_app():  # noqa: C901
             task = await orchestrator.task_status(task_id=task_id)
             if task.is_completed():
                 return True
-            await asyncio.sleep(5)
+            await asyncio.sleep(docling_serve_settings.sync_poll_interval)
             elapsed_time = time.monotonic() - start_time
             if elapsed_time > docling_serve_settings.max_sync_wait:
                 return False

docling_serve/settings.py

@@ -57,6 +57,7 @@ class DoclingServeSettings(BaseSettings):
     max_num_pages: int = sys.maxsize
     max_file_size: int = sys.maxsize
 
+    sync_poll_interval: int = 2  # seconds
     max_sync_wait: int = 120  # 2 minutes
 
     cors_origins: list[str] = ["*"]

docs/configuration.md

@@ -47,6 +47,7 @@ THe following table describes the options to configure the Docling Serve app.
 |  | `DOCLING_NUM_THREADS` | `4` | Number of concurrent threads for processing a document. |
 |  | `DOCLING_SERVE_MAX_NUM_PAGES` |  | The maximum number of pages for a document to be processed. |
 |  | `DOCLING_SERVE_MAX_FILE_SIZE` |  | The maximum file size for a document to be processed. |
+|  | `DOCLING_SERVE_SYNC_POLL_INTERVAL` | `2` | Number of seconds to sleep between polling the task status in the sync endpoints. |
 |  | `DOCLING_SERVE_MAX_SYNC_WAIT` | `120` | Max number of seconds a synchronous endpoint is waiting for the task completion. |
 |  | `DOCLING_SERVE_LOAD_MODELS_AT_BOOT` | `True` | If enabled, the models for the default options will be loaded at boot. |
 |  | `DOCLING_SERVE_OPTIONS_CACHE_SIZE` | `2` | How many DocumentConveter objects (including their loaded models) to keep in the cache. |