fix: Update calls to unstructured-client for forward compatibility (#33)

* fix: Update calls to unstructured-client for forward compatibility

Per the usage example [here](https://docs.unstructured.io/api-reference/api-services/sdk-python#basics), the call to `sdk.general.partition` expects a `shared.PartitionRequest` object. In older versions of the client, this object was not needed, but the call has stayed backwards compatible. The next version of the client (0.26.0) is going to lose support for directly passing `PartitionParameters`.

* Reorder new import

* Add a changelog note

* Adjust order of imports

* Sync the new version

* Add missing import for PartitionRequest

Author: awalker4

CHANGELOG.md

@@ -1,3 +1,11 @@
+## 0.0.6
+
+### Enhancements
+
+### Fixes
+
+* **unstructured-client compatibility fix** Update the calls to `unstructured_client.general.partion` to avoid a breaking change in the newest version.
+
 ## 0.0.5
 
 ### Enhancements

requirements/remote/client.in

@@ -1,3 +1,3 @@
 -r ../common/base.in
 
-unstructured-client
+unstructured-client >= 0.23.0

unstructured_ingest/__version__.py

@@ -1 +1 @@
-__version__ = "0.0.5"  # pragma: no cover
+__version__ = "0.0.6"  # pragma: no cover

unstructured_ingest/v2/processes/chunker.py

@@ -112,6 +112,7 @@ def run(self, elements_filepath: Path, **kwargs: Any) -> list[dict]:
     @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 @@ async def run_async(self, elements_filepath: Path, **kwargs: Any) -> list[dict]:
             )
             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/v2/processes/partitioner.py

@@ -13,6 +13,7 @@
 
 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 FileDataSourceMetadata(DataSourceMetadata):
         )
         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()
@@ -189,14 +190,16 @@ async def partition_via_api(
         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(
             server_url=self.config.partition_endpoint,
             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: