LLM/docling-serve
1
0
Fork 0
mirror of https://github.com/docling-project/docling-serve.git synced 2025-11-29 00:23:36 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: expose max wait time in sync endpoints (#164)

Browse Source 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
This commit is contained in:
Michele Dolfi
2025-04-30 12:30:11 +02:00
committed by GitHub
parent 35c2630c61
commit 919cf5c041
3 changed files with 8 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
docling_serve/app.py
View File

@@ -251,7 +251,6 @@ def create_app(): # noqa: C901
async def _wait_task_complete(
orchestrator: BaseAsyncOrchestrator, task_id: str
) -> bool:
MAX_WAIT = 120
start_time = time.monotonic()
while True:
task = await orchestrator.task_status(task_id=task_id)
@@ -259,7 +258,7 @@ def create_app(): # noqa: C901
return True
await asyncio.sleep(5)
elapsed_time = time.monotonic() - start_time
if elapsed_time > MAX_WAIT:
if elapsed_time > docling_serve_settings.max_sync_wait:
return False
#############################
@@ -310,7 +309,8 @@ def create_app(): # noqa: C901
if not success:
# TODO: abort task!
return HTTPException(
status_code=504, detail="Conversion is taking too long."
status_code=504,
detail=f"Conversion is taking too long. The maximum wait time is configure as DOCLING_SERVE_MAX_SYNC_WAIT={docling_serve_settings.max_sync_wait}.",
)
result = await orchestrator.task_result(
@@ -351,7 +351,8 @@ def create_app(): # noqa: C901
if not success:
# TODO: abort task!
return HTTPException(
status_code=504, detail="Conversion is taking too long."
status_code=504,
detail=f"Conversion is taking too long. The maximum wait time is configure as DOCLING_SERVE_MAX_SYNC_WAIT={docling_serve_settings.max_sync_wait}.",
)
result = await orchestrator.task_result(

2
docling_serve/settings.py
View File

@@ -48,6 +48,8 @@ class DoclingServeSettings(BaseSettings):
max_num_pages: int = sys.maxsize
max_file_size: int = sys.maxsize
max_sync_wait: int = 120 # 2 minutes
cors_origins: list[str] = ["*"]
cors_methods: list[str] = ["*"]
cors_headers: list[str] = ["*"]

1
docs/configuration.md
View File

@@ -45,6 +45,7 @@ THe following table describes the options to configure the Docling Serve app.
| | `DOCLING_SERVE_MAX_DOCUMENT_TIMEOUT` | `604800` (7 days) | The maximum time 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_MAX_SYNC_WAIT` | `120` | Max number of seconds a synchronous endpoint is waiting for the task completion. |
| | `DOCLING_SERVE_OPTIONS_CACHE_SIZE` | `2` | How many DocumentConveter objects (including their loaded models) to keep in the cache. |
| | `DOCLING_SERVE_CORS_ORIGINS` | `["*"]` | A list of origins that should be permitted to make cross-origin requests. |
| | `DOCLING_SERVE_CORS_METHODS` | `["*"]` | A list of HTTP methods that should be allowed for cross-origin requests. |