unstructured-ingest 0.0.5__tar.gz → 0.0.6__tar.gz

{unstructured-ingest-0.0.5/unstructured_ingest.egg-info → unstructured-ingest-0.0.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: unstructured-ingest
-Version: 0.0.5
+Version: 0.0.6
 Summary: A library that prepares raw documents for downstream ML tasks.
 Home-page: https://github.com/Unstructured-IO/unstructured-ingest
 Author: Unstructured Technologies

unstructured-ingest-0.0.6/unstructured_ingest/__version__.py

@@ -0,0 +1 @@
+__version__ = "0.0.6"  # pragma: no cover

{unstructured-ingest-0.0.5 → unstructured-ingest-0.0.6}/unstructured_ingest/v2/processes/chunker.py

@@ -112,6 +112,7 @@ class Chunker(BaseProcess, ABC):
     @requires_dependencies(dependencies=["unstructured_client"], extras="remote")
     async def run_async(self, elements_filepath: Path, **kwargs: Any) -> list[dict]:
         from unstructured_client import UnstructuredClient
+        from unstructured_client.models.operations import PartitionRequest
         from unstructured_client.models.shared import Files, PartitionParameters
 
         client = UnstructuredClient(
@@ -137,7 +138,8 @@ class Chunker(BaseProcess, ABC):
             )
             filtered_partition_request["files"] = files
             partition_params = PartitionParameters(**filtered_partition_request)
-        resp = client.general.partition(partition_params)
+            partition_request_obj = PartitionRequest(partition_params)
+        resp = client.general.partition(partition_request_obj)
         elements = resp.elements or []
         elements = assign_and_map_hash_ids(elements=elements)
         return elements

{unstructured-ingest-0.0.5 → unstructured-ingest-0.0.6}/unstructured_ingest/v2/processes/partitioner.py

@@ -13,6 +13,7 @@ from unstructured_ingest.v2.logger import logger
 
 if TYPE_CHECKING:
     from unstructured_client import UnstructuredClient
+    from unstructured_client.models.operations import PartitionRequest
     from unstructured_client.models.shared import PartitionParameters
 
 
@@ -153,7 +154,7 @@ class Partitioner(BaseProcess, ABC):
         )
         return self.postprocess(elements=elements_to_dicts(elements))
 
-    async def call_api(self, client: "UnstructuredClient", request: "PartitionParameters"):
+    async def call_api(self, client: "UnstructuredClient", request: "PartitionRequest"):
         # TODO when client supports async, run without using run_in_executor
         # isolate the IO heavy call
         loop = asyncio.get_event_loop()
@@ -189,6 +190,7 @@ class Partitioner(BaseProcess, ABC):
         self, filename: Path, metadata: Optional[dict] = None, **kwargs
     ) -> list[dict]:
         from unstructured_client import UnstructuredClient
+        from unstructured_client.models.operations import PartitionRequest
 
         logger.debug(f"partitioning file {filename} with metadata: {metadata}")
         client = UnstructuredClient(
@@ -196,7 +198,8 @@ class Partitioner(BaseProcess, ABC):
             api_key_auth=self.config.api_key.get_secret_value(),
         )
         partition_params = self.create_partition_parameters(filename=filename)
-        resp = await self.call_api(client=client, request=partition_params)
+        partition_request = PartitionRequest(partition_params)
+        resp = await self.call_api(client=client, request=partition_request)
         elements = resp.elements or []
         # Append the data source metadata the auto partition does for you
         for element in elements:

{unstructured-ingest-0.0.5 → unstructured-ingest-0.0.6/unstructured_ingest.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: unstructured-ingest
-Version: 0.0.5
+Version: 0.0.6
 Summary: A library that prepares raw documents for downstream ML tasks.
 Home-page: https://github.com/Unstructured-IO/unstructured-ingest
 Author: Unstructured Technologies