nv-ingest-api 2025.8.18.dev20250818__py3-none-any.whl → 2025.8.20.dev20250820__py3-none-any.whl

nv_ingest_api/internal/extract/pdf/engines/llama.py

@@ -193,7 +193,10 @@ async def async_llama_parse(
         A string of extracted text.
     """
     base_url = "https://api.cloud.llamaindex.ai/api/parsing"
-    headers = {"Authorization": f"Bearer {api_key}"}
+    # Normalize in case api_key contains only whitespace; avoid sending an empty bearer token
+    _token = (api_key or "").strip()
+    _auth_value = f"Bearer {_token}" if _token else "Bearer <no key provided>"
+    headers = {"Authorization": _auth_value}
     mime_type = "application/pdf"
 
     try:

nv_ingest_api/internal/schemas/transform/transform_image_caption_schema.py

@@ -3,13 +3,31 @@
 # SPDX-License-Identifier: Apache-2.0
 
 
-from pydantic import ConfigDict, BaseModel
+from pydantic import ConfigDict, BaseModel, model_validator, field_validator
 
 
 class ImageCaptionExtractionSchema(BaseModel):
-    api_key: str = "api_key"
+    api_key: str = ""
     endpoint_url: str = "https://integrate.api.nvidia.com/v1/chat/completions"
     prompt: str = "Caption the content of this image:"
     model_name: str = "nvidia/llama-3.1-nemotron-nano-vl-8b-v1"
     raise_on_failure: bool = False
     model_config = ConfigDict(extra="forbid")
+
+    @field_validator("api_key", mode="before")
+    @classmethod
+    def _coerce_api_key_none(cls, v):
+        return "" if v is None else v
+
+    @model_validator(mode="before")
+    @classmethod
+    def _coerce_none_to_empty(cls, values):
+        """Allow None for string fields where empty string is acceptable.
+
+        Specifically, convert api_key=None to api_key="" so validation passes
+        when no API key is supplied.
+        """
+        if isinstance(values, dict):
+            if values.get("api_key") is None:
+                values["api_key"] = ""
+        return values

nv_ingest_api/internal/schemas/transform/transform_text_embedding_schema.py

@@ -5,7 +5,7 @@
 
 import logging
 
-from pydantic import ConfigDict, BaseModel, Field
+from pydantic import ConfigDict, BaseModel, Field, model_validator, field_validator
 
 from nv_ingest_api.util.logging.configuration import LogLevel
 
@@ -13,7 +13,7 @@ logger = logging.getLogger(__name__)
 
 
 class TextEmbeddingSchema(BaseModel):
-    api_key: str = Field(default="api_key")
+    api_key: str = Field(default="")
     batch_size: int = Field(default=4)
     embedding_model: str = Field(default="nvidia/llama-3.2-nv-embedqa-1b-v2")
     embedding_nim_endpoint: str = Field(default="http://embedding:8000/v1")
@@ -28,3 +28,16 @@ class TextEmbeddingSchema(BaseModel):
     audio_elements_modality: str = Field(default="text")
 
     model_config = ConfigDict(extra="forbid")
+
+    @field_validator("api_key", mode="before")
+    @classmethod
+    def _coerce_api_key_none(cls, v):
+        return "" if v is None else v
+
+    @model_validator(mode="before")
+    @classmethod
+    def _coerce_none_to_empty(cls, values):
+        """Convert api_key=None to empty string so validation passes when key is omitted."""
+        if isinstance(values, dict) and values.get("api_key") is None:
+            values["api_key"] = ""
+        return values

nv_ingest_api/internal/transform/embed_text.py

@@ -75,8 +75,11 @@ def _make_async_request(
     response = {}
 
     try:
+        # Normalize API key to avoid sending an empty bearer token via SDK internals
+        _token = (api_key or "").strip()
+        _api_key = _token if _token else "<no key provided>"
         client = OpenAI(
-            api_key=api_key,
+            api_key=_api_key,
             base_url=embedding_nim_endpoint,
         )
 

{nv_ingest_api-2025.8.18.dev20250818.dist-info → nv_ingest_api-2025.8.20.dev20250820.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nv-ingest-api
-Version: 2025.8.18.dev20250818
+Version: 2025.8.20.dev20250820
 Summary: Python module with core document ingestion functions.
 Author-email: Jeremy Dyer <jdyer@nvidia.com>
 License:                                  Apache License

{nv_ingest_api-2025.8.18.dev20250818.dist-info → nv_ingest_api-2025.8.20.dev20250820.dist-info}/RECORD

@@ -30,7 +30,7 @@ nv_ingest_api/internal/extract/pdf/__init__.py,sha256=wQSlVx3T14ZgQAt-EPzEczQusX
 nv_ingest_api/internal/extract/pdf/pdf_extractor.py,sha256=CxtWaD6mql9MEqSdk2CfSQ9T-Bn87beBkCOuGGjxGt8,2934
 nv_ingest_api/internal/extract/pdf/engines/__init__.py,sha256=u4GnAZmDKRl0RwYGIRiozIRw70Kybw3A72-lcKFeoTI,582
 nv_ingest_api/internal/extract/pdf/engines/adobe.py,sha256=VT0dEqkU-y2uGkaCqxtKYov_Q8R1028UQVBchgMLca4,17466
-nv_ingest_api/internal/extract/pdf/engines/llama.py,sha256=PpKTqS8jGHBV6mKLGZWwjpfT8ga6Fy8ffrvL-gPAf2c,8182
+nv_ingest_api/internal/extract/pdf/engines/llama.py,sha256=MwzM-n2tu0FHM0wDe_0mONLlzHrPte7EOTuPtzCh7Zs,8384
 nv_ingest_api/internal/extract/pdf/engines/nemoretriever.py,sha256=IVbNcH_phMiRSxnkZ04pGfQrPJ-x1zVR3hXyhxv7juc,22977
 nv_ingest_api/internal/extract/pdf/engines/pdfium.py,sha256=SKmias2iZmAE6Q8WXxmFEjvLOZy-vXRoaRIPpi7Tuhs,22962
 nv_ingest_api/internal/extract/pdf/engines/tika.py,sha256=6GyR2l6EsgNZl9jnYDXLeKNK9Fj2Mw9y2UWDq-eSkOc,3169
@@ -93,16 +93,16 @@ nv_ingest_api/internal/schemas/store/__init__.py,sha256=wQSlVx3T14ZgQAt-EPzEczQu
 nv_ingest_api/internal/schemas/store/store_embedding_schema.py,sha256=tdKeiraim9CDL9htgp4oUSCoPMoO5PrHBnlXqDyCpMw,956
 nv_ingest_api/internal/schemas/store/store_image_schema.py,sha256=p2LGij9i6sG6RYmsfdiQOiWIc2j-POjxYrNuMrp3ELU,1010
 nv_ingest_api/internal/schemas/transform/__init__.py,sha256=wQSlVx3T14ZgQAt-EPzEczQusXVW0W8yynnUaFFGE3s,143
-nv_ingest_api/internal/schemas/transform/transform_image_caption_schema.py,sha256=gRJCfEGrJXErMF_GsZDjyDR8HOrLrUNxz2BVS6LSPY8,542
+nv_ingest_api/internal/schemas/transform/transform_image_caption_schema.py,sha256=O7rOJI9MunXrQVbONtc8mXzZqVLAx5BjqjfhqQOWlQY,1154
 nv_ingest_api/internal/schemas/transform/transform_image_filter_schema.py,sha256=31ThI5fr0yyENeJeE1xMAA-pxk1QVJLwM842zMate_k,429
-nv_ingest_api/internal/schemas/transform/transform_text_embedding_schema.py,sha256=RZCISA8CUqKiY8eJuk4uWxzo4PZ-fuYdzMO7_LYFkoM,1117
+nv_ingest_api/internal/schemas/transform/transform_text_embedding_schema.py,sha256=D6ZFY6m37HqZ9NBGaeqI9VD0z1sWI55V8KTflr8MZ5o,1604
 nv_ingest_api/internal/schemas/transform/transform_text_splitter_schema.py,sha256=D9K8tvu-tkEBQkZo7uuRzgrHdGyM3ZcNycHbHy5HV2E,791
 nv_ingest_api/internal/store/__init__.py,sha256=wQSlVx3T14ZgQAt-EPzEczQusXVW0W8yynnUaFFGE3s,143
 nv_ingest_api/internal/store/embed_text_upload.py,sha256=maxb4FPsBvWgvlrjAPEBlRZEFdJX5NxPG-p8kUbzV7I,9898
 nv_ingest_api/internal/store/image_upload.py,sha256=GNlY4k3pfcHv3lzXxkbmGLeHFsf9PI25bkBn6Xn9h3I,9654
 nv_ingest_api/internal/transform/__init__.py,sha256=wQSlVx3T14ZgQAt-EPzEczQusXVW0W8yynnUaFFGE3s,143
 nv_ingest_api/internal/transform/caption_image.py,sha256=0ILCG2F8ESqKtZiPUM-6F1BHUflFZ76Dzi2GNzkE-lU,8517
-nv_ingest_api/internal/transform/embed_text.py,sha256=AdUXVosBHuZadaFLi9_RVB7vB_hjTziCLUeBZ1oWGZo,20003
+nv_ingest_api/internal/transform/embed_text.py,sha256=LB_2Zvw6plc7uOWT2QN13aDu2qFumXzl_RB3ZcZbLGs,20191
 nv_ingest_api/internal/transform/split_text.py,sha256=LAtInGVuydH43UwjNMQWFVC1A6NdhXP_dZup2xX4qEo,7745
 nv_ingest_api/util/__init__.py,sha256=wQSlVx3T14ZgQAt-EPzEczQusXVW0W8yynnUaFFGE3s,143
 nv_ingest_api/util/control_message/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -161,8 +161,8 @@ nv_ingest_api/util/string_processing/configuration.py,sha256=2HS08msccuPCT0fn_jf
 nv_ingest_api/util/string_processing/yaml.py,sha256=6SW2O6wbXRhGbhETMbtXjYCZn53HeCNOP6a96AaxlHs,1454
 nv_ingest_api/util/system/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nv_ingest_api/util/system/hardware_info.py,sha256=1UFM8XE6M3pgQcpbVsCsqDQ7Dj-zzptL-XRE-DEu9UA,27213
-nv_ingest_api-2025.8.18.dev20250818.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-nv_ingest_api-2025.8.18.dev20250818.dist-info/METADATA,sha256=VL-RWFMM0rRtuBsi3X2soGUsD3gk6Zn64XoeHIAawfE,13947
-nv_ingest_api-2025.8.18.dev20250818.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-nv_ingest_api-2025.8.18.dev20250818.dist-info/top_level.txt,sha256=abjYMlTJGoG5tOdfIB-IWvLyKclw6HLaRSc8MxX4X6I,14
-nv_ingest_api-2025.8.18.dev20250818.dist-info/RECORD,,
+nv_ingest_api-2025.8.20.dev20250820.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+nv_ingest_api-2025.8.20.dev20250820.dist-info/METADATA,sha256=wtjzUuf6l64PjK1i3_XbMB3RsOUhWReCx0hOStoxLT8,13947
+nv_ingest_api-2025.8.20.dev20250820.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+nv_ingest_api-2025.8.20.dev20250820.dist-info/top_level.txt,sha256=abjYMlTJGoG5tOdfIB-IWvLyKclw6HLaRSc8MxX4X6I,14
+nv_ingest_api-2025.8.20.dev20250820.dist-info/RECORD,,