nv-ingest-client 2025.10.9.dev20251009__tar.gz → 2025.10.11.dev20251011__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Potentially problematic release.
This version of nv-ingest-client might be problematic. Click here for more details.
- {nv_ingest_client-2025.10.9.dev20251009/src/nv_ingest_client.egg-info → nv_ingest_client-2025.10.11.dev20251011}/PKG-INFO +1 -1
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/client/client.py +20 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/client/interface.py +19 -6
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011/src/nv_ingest_client.egg-info}/PKG-INFO +1 -1
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/LICENSE +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/MANIFEST.in +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/README.md +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/pyproject.toml +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/setup.cfg +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/__init__.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/cli/__init__.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/cli/util/__init__.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/cli/util/click.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/cli/util/processing.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/cli/util/system.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/client/__init__.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/client/ingest_job_handler.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/client/util/processing.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/nv_ingest_cli.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/primitives/__init__.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/primitives/jobs/__init__.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/primitives/jobs/job_spec.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/primitives/jobs/job_state.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/primitives/tasks/__init__.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/primitives/tasks/audio_extraction.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/primitives/tasks/caption.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/primitives/tasks/chart_extraction.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/primitives/tasks/dedup.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/primitives/tasks/embed.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/primitives/tasks/extract.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/primitives/tasks/filter.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/primitives/tasks/infographic_extraction.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/primitives/tasks/split.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/primitives/tasks/store.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/primitives/tasks/table_extraction.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/primitives/tasks/task_base.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/primitives/tasks/task_factory.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/primitives/tasks/udf.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/primitives/tasks/vdb_upload.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/util/__init__.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/util/dataset.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/util/document_analysis.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/util/file_processing/__init__.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/util/file_processing/extract.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/util/image_disk_utils.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/util/milvus.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/util/process_json_files.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/util/processing.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/util/system.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/util/transport.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/util/util.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/util/vdb/__init__.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/util/vdb/adt_vdb.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/util/vdb/milvus.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/util/vdb/opensearch.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client/util/zipkin.py +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client.egg-info/SOURCES.txt +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client.egg-info/dependency_links.txt +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client.egg-info/entry_points.txt +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client.egg-info/requires.txt +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/nv_ingest_client.egg-info/top_level.txt +0 -0
- {nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/version.py +0 -0
|
@@ -239,6 +239,9 @@ class _ConcurrentProcessor:
|
|
|
239
239
|
|
|
240
240
|
is_failed, description = check_ingest_result(result_data)
|
|
241
241
|
|
|
242
|
+
if trace_id:
|
|
243
|
+
self.client.register_parent_trace_id(trace_id)
|
|
244
|
+
|
|
242
245
|
if is_failed:
|
|
243
246
|
failed_job_spec = self.client._job_index_to_job_spec.get(job_index)
|
|
244
247
|
self.failures.append((f"{job_index}:{failed_job_spec.source_id}", description))
|
|
@@ -722,6 +725,7 @@ class NvIngestClient:
|
|
|
722
725
|
except ValueError:
|
|
723
726
|
self._telemetry_max_calls = 10000
|
|
724
727
|
self._telemetry = {}
|
|
728
|
+
self._completed_parent_trace_ids: List[str] = [] # 1054
|
|
725
729
|
self.reset_telemetry()
|
|
726
730
|
|
|
727
731
|
def __str__(self) -> str:
|
|
@@ -1794,3 +1798,19 @@ class NvIngestClient:
|
|
|
1794
1798
|
job_ids.append(job_id)
|
|
1795
1799
|
|
|
1796
1800
|
return job_ids
|
|
1801
|
+
|
|
1802
|
+
def register_parent_trace_id(self, trace_id: Optional[str]) -> None:
|
|
1803
|
+
"""Record a parent trace identifier once its aggregation completed."""
|
|
1804
|
+
|
|
1805
|
+
if not trace_id:
|
|
1806
|
+
return
|
|
1807
|
+
|
|
1808
|
+
if trace_id not in self._completed_parent_trace_ids:
|
|
1809
|
+
self._completed_parent_trace_ids.append(trace_id)
|
|
1810
|
+
|
|
1811
|
+
def consume_completed_parent_trace_ids(self) -> List[str]:
|
|
1812
|
+
"""Return and clear the set of completed parent trace identifiers."""
|
|
1813
|
+
|
|
1814
|
+
trace_ids = list(self._completed_parent_trace_ids)
|
|
1815
|
+
self._completed_parent_trace_ids.clear()
|
|
1816
|
+
return trace_ids
|
|
@@ -426,20 +426,25 @@ class Ingestor:
|
|
|
426
426
|
'concurrency_limit', 'timeout', 'max_job_retries', 'retry_delay',
|
|
427
427
|
'data_only', 'return_full_response', 'verbose'. Unrecognized keys are passed
|
|
428
428
|
through to process_jobs_concurrently.
|
|
429
|
+
Optional flags include `include_parent_trace_ids=True` to also return
|
|
430
|
+
parent job trace identifiers gathered during ingestion.
|
|
429
431
|
|
|
430
432
|
Returns
|
|
431
433
|
-------
|
|
432
|
-
results : list
|
|
433
|
-
|
|
434
|
-
|
|
435
|
-
- If `return_full_response=True`: List of full response envelopes (each dict
|
|
436
|
-
contains keys like 'data', 'trace', 'annotations').
|
|
434
|
+
results : list of dict
|
|
435
|
+
List of successful job results when `return_failures` is False.
|
|
436
|
+
|
|
437
437
|
results, failures : tuple (list of dict, list of tuple of str)
|
|
438
438
|
Tuple containing successful results and failure information when `return_failures` is True.
|
|
439
|
+
|
|
440
|
+
If `include_parent_trace_ids=True` is provided via kwargs, an additional
|
|
441
|
+
list of parent trace IDs is appended to the return value.
|
|
439
442
|
"""
|
|
440
443
|
if save_to_disk and (not self._output_config):
|
|
441
444
|
self.save_to_disk()
|
|
442
445
|
|
|
446
|
+
include_parent_trace_ids = bool(kwargs.pop("include_parent_trace_ids", False))
|
|
447
|
+
|
|
443
448
|
self._prepare_ingest_run()
|
|
444
449
|
|
|
445
450
|
# Add jobs locally first
|
|
@@ -641,7 +646,15 @@ class Ingestor:
|
|
|
641
646
|
except Exception:
|
|
642
647
|
pass
|
|
643
648
|
|
|
644
|
-
|
|
649
|
+
parent_trace_ids = self._client.consume_completed_parent_trace_ids() if include_parent_trace_ids else []
|
|
650
|
+
|
|
651
|
+
if return_failures and include_parent_trace_ids:
|
|
652
|
+
return results, failures, parent_trace_ids
|
|
653
|
+
if return_failures:
|
|
654
|
+
return results, failures
|
|
655
|
+
if include_parent_trace_ids:
|
|
656
|
+
return results, parent_trace_ids
|
|
657
|
+
return results
|
|
645
658
|
|
|
646
659
|
def ingest_async(self, **kwargs: Any) -> Future:
|
|
647
660
|
"""
|
|
File without changes
|
{nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/MANIFEST.in
RENAMED
|
File without changes
|
{nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/README.md
RENAMED
|
File without changes
|
{nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/pyproject.toml
RENAMED
|
File without changes
|
{nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/setup.cfg
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{nv_ingest_client-2025.10.9.dev20251009 → nv_ingest_client-2025.10.11.dev20251011}/src/version.py
RENAMED
|
File without changes
|