nv-ingest-api 2025.5.13.dev20250513__tar.gz → 2025.5.14.dev20250514__tar.gz

{nv_ingest_api-2025.5.13.dev20250513/src/nv_ingest_api.egg-info → nv_ingest_api-2025.5.14.dev20250514}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nv-ingest-api
-Version: 2025.5.13.dev20250513
+Version: 2025.5.14.dev20250514
 Summary: Python module with core document ingestion functions.
 Author-email: Jeremy Dyer <jdyer@nvidia.com>
 License:                                  Apache License

{nv_ingest_api-2025.5.13.dev20250513 → nv_ingest_api-2025.5.14.dev20250514}/src/nv_ingest_api/internal/extract/image/chart_extractor.py

@@ -27,7 +27,7 @@ from nv_ingest_api.util.nim import create_inference_client
 PADDLE_MIN_WIDTH = 32
 PADDLE_MIN_HEIGHT = 32
 
-logger = logging.getLogger(f"morpheus.{__name__}")
+logger = logging.getLogger(f"ray.{__name__}")
 
 
 def _filter_valid_chart_images(
@@ -80,7 +80,7 @@ def _run_chart_inference(
             yolox_client.infer,
             data=data_yolox,
             model_name="yolox",
-            stage_name="chart_data_extraction",
+            stage_name="chart_extraction",
             max_batch_size=8,
             trace_info=trace_info,
         )
@@ -88,7 +88,7 @@ def _run_chart_inference(
             paddle_client.infer,
             data=data_paddle,
             model_name="paddle",
-            stage_name="chart_data_extraction",
+            stage_name="chart_extraction",
             max_batch_size=1 if paddle_client.protocol == "grpc" else 2,
             trace_info=trace_info,
         )

{nv_ingest_api-2025.5.13.dev20250513 → nv_ingest_api-2025.5.14.dev20250514}/src/nv_ingest_api/internal/extract/image/image_helpers/common.py

@@ -223,7 +223,7 @@ def extract_page_elements_from_images(
             model_name="yolox",
             max_batch_size=YOLOX_MAX_BATCH_SIZE,
             trace_info=trace_info,
-            stage_name="pdf_content_extractor",
+            stage_name="pdf_extraction",
         )
 
         # Process each result along with its corresponding image.

{nv_ingest_api-2025.5.13.dev20250513 → nv_ingest_api-2025.5.14.dev20250514}/src/nv_ingest_api/internal/extract/image/infographic_extractor.py

@@ -100,7 +100,7 @@ def _update_infographic_metadata(
         paddle_results = paddle_client.infer(
             data=data_paddle,
             model_name="paddle",
-            stage_name="infographic_data_extraction",
+            stage_name="infographic_extraction",
             max_batch_size=1 if paddle_client.protocol == "grpc" else 2,
             trace_info=trace_info,
         )

{nv_ingest_api-2025.5.13.dev20250513 → nv_ingest_api-2025.5.14.dev20250514}/src/nv_ingest_api/internal/extract/image/table_extractor.py

@@ -81,7 +81,7 @@ def _run_inference(
                 yolox_client.infer,
                 data=data_yolox,
                 model_name="yolox",
-                stage_name="table_data_extraction",
+                stage_name="table_extraction",
                 max_batch_size=8,
                 trace_info=trace_info,
             )
@@ -89,7 +89,7 @@ def _run_inference(
             paddle_client.infer,
             data=data_paddle,
             model_name="paddle",
-            stage_name="table_data_extraction",
+            stage_name="table_extraction",
             max_batch_size=1 if paddle_client.protocol == "grpc" else 2,
             trace_info=trace_info,
         )

{nv_ingest_api-2025.5.13.dev20250513 → nv_ingest_api-2025.5.14.dev20250514}/src/nv_ingest_api/internal/extract/pdf/engines/nemoretriever.py

@@ -466,7 +466,7 @@ def _extract_text_and_bounding_boxes(
     inference_results = nemoretriever_parse_client.infer(
         data=data,
         model_name="nemoretriever_parse",
-        stage_name="pdf_content_extractor",
+        stage_name="pdf_extraction",
         max_batch_size=NEMORETRIEVER_PARSE_MAX_BATCH_SIZE,
         execution_trace_log=execution_trace_log,
     )

{nv_ingest_api-2025.5.13.dev20250513 → nv_ingest_api-2025.5.14.dev20250514}/src/nv_ingest_api/internal/extract/pdf/engines/pdfium.py

@@ -105,7 +105,7 @@ def _extract_page_elements_using_image_ensemble(
             model_name="yolox",
             max_batch_size=YOLOX_MAX_BATCH_SIZE,
             trace_info=execution_trace_log,
-            stage_name="pdf_content_extractor",
+            stage_name="pdf_extraction",
         )
 
         # Process results: iterate over each image's inference output.

{nv_ingest_api-2025.5.13.dev20250513 → nv_ingest_api-2025.5.14.dev20250514}/src/nv_ingest_api/util/image_processing/processing.py

@@ -150,7 +150,7 @@ def extract_tables_and_charts_yolox(
             min_score=YOLOX_MIN_SCORE,
             final_thresh=YOLOX_FINAL_SCORE,
             trace_info=trace_info,
-            stage_name="pdf_content_extractor",
+            stage_name="pdf_extraction",
         )
 
         # Process results: iterate over each image's inference output.

{nv_ingest_api-2025.5.13.dev20250513 → nv_ingest_api-2025.5.14.dev20250514}/src/nv_ingest_api/util/pdf/pdfium.py

@@ -119,7 +119,7 @@ def pdfium_try_get_bitmap_as_numpy(image_obj) -> np.ndarray:
     return img_array
 
 
-@traceable_func(trace_name="pdf_content_extractor::pdfium_pages_to_numpy")
+@traceable_func(trace_name="pdf_extraction::pdfium_pages_to_numpy")
 def pdfium_pages_to_numpy(
     pages: List[pdfium.PdfPage],
     render_dpi: int = 300,

{nv_ingest_api-2025.5.13.dev20250513 → nv_ingest_api-2025.5.14.dev20250514/src/nv_ingest_api.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nv-ingest-api
-Version: 2025.5.13.dev20250513
+Version: 2025.5.14.dev20250514
 Summary: Python module with core document ingestion functions.
 Author-email: Jeremy Dyer <jdyer@nvidia.com>
 License:                                  Apache License