unstructured-ingest 0.4.7__tar.gz → 0.5.0__tar.gz

{unstructured_ingest-0.4.7/unstructured_ingest.egg-info → unstructured_ingest-0.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: unstructured-ingest
-Version: 0.4.7
+Version: 0.5.0
 Summary: A library that prepares raw documents for downstream ML tasks.
 Home-page: https://github.com/Unstructured-IO/unstructured-ingest
 Author: Unstructured Technologies
@@ -22,12 +22,12 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: >=3.9.0,<3.14
 Description-Content-Type: text/markdown
 License-File: LICENSE.md
-Requires-Dist: opentelemetry-sdk
-Requires-Dist: click
-Requires-Dist: tqdm
-Requires-Dist: pandas
 Requires-Dist: pydantic>=2.7
+Requires-Dist: pandas
+Requires-Dist: click
 Requires-Dist: dataclasses_json
+Requires-Dist: tqdm
+Requires-Dist: opentelemetry-sdk
 Requires-Dist: python-dateutil
 Provides-Extra: remote
 Requires-Dist: unstructured-client>=0.26.1; extra == "remote"
@@ -66,8 +66,8 @@ Requires-Dist: pyairtable; extra == "airtable"
 Provides-Extra: astradb
 Requires-Dist: astrapy; extra == "astradb"
 Provides-Extra: azure
-Requires-Dist: fsspec; extra == "azure"
 Requires-Dist: adlfs; extra == "azure"
+Requires-Dist: fsspec; extra == "azure"
 Provides-Extra: azure-ai-search
 Requires-Dist: azure-search-documents; extra == "azure-ai-search"
 Provides-Extra: biomed
@@ -81,8 +81,8 @@ Requires-Dist: chromadb; extra == "chroma"
 Provides-Extra: clarifai
 Requires-Dist: clarifai; extra == "clarifai"
 Provides-Extra: confluence
-Requires-Dist: requests; extra == "confluence"
 Requires-Dist: atlassian-python-api; extra == "confluence"
+Requires-Dist: requests; extra == "confluence"
 Provides-Extra: couchbase
 Requires-Dist: couchbase; extra == "couchbase"
 Provides-Extra: delta-table
@@ -99,11 +99,11 @@ Provides-Extra: elasticsearch
 Requires-Dist: elasticsearch[async]; extra == "elasticsearch"
 Provides-Extra: gcs
 Requires-Dist: bs4; extra == "gcs"
-Requires-Dist: gcsfs; extra == "gcs"
 Requires-Dist: fsspec; extra == "gcs"
+Requires-Dist: gcsfs; extra == "gcs"
 Provides-Extra: github
-Requires-Dist: requests; extra == "github"
 Requires-Dist: pygithub>1.58.0; extra == "github"
+Requires-Dist: requests; extra == "github"
 Provides-Extra: gitlab
 Requires-Dist: python-gitlab; extra == "gitlab"
 Provides-Extra: google-drive
@@ -125,22 +125,22 @@ Provides-Extra: mongodb
 Requires-Dist: pymongo; extra == "mongodb"
 Provides-Extra: neo4j
 Requires-Dist: cymple; extra == "neo4j"
-Requires-Dist: neo4j; extra == "neo4j"
 Requires-Dist: networkx; extra == "neo4j"
+Requires-Dist: neo4j; extra == "neo4j"
 Provides-Extra: notion
-Requires-Dist: htmlBuilder; extra == "notion"
-Requires-Dist: backoff; extra == "notion"
 Requires-Dist: notion-client; extra == "notion"
+Requires-Dist: backoff; extra == "notion"
 Requires-Dist: httpx; extra == "notion"
+Requires-Dist: htmlBuilder; extra == "notion"
 Provides-Extra: onedrive
 Requires-Dist: bs4; extra == "onedrive"
-Requires-Dist: Office365-REST-Python-Client; extra == "onedrive"
 Requires-Dist: msal; extra == "onedrive"
+Requires-Dist: Office365-REST-Python-Client; extra == "onedrive"
 Provides-Extra: opensearch
 Requires-Dist: opensearch-py; extra == "opensearch"
 Provides-Extra: outlook
-Requires-Dist: Office365-REST-Python-Client; extra == "outlook"
 Requires-Dist: msal; extra == "outlook"
+Requires-Dist: Office365-REST-Python-Client; extra == "outlook"
 Provides-Extra: pinecone
 Requires-Dist: pinecone-client>=3.7.1; extra == "pinecone"
 Provides-Extra: postgres
@@ -155,8 +155,8 @@ Provides-Extra: s3
 Requires-Dist: s3fs; extra == "s3"
 Requires-Dist: fsspec; extra == "s3"
 Provides-Extra: sharepoint
-Requires-Dist: Office365-REST-Python-Client; extra == "sharepoint"
 Requires-Dist: msal; extra == "sharepoint"
+Requires-Dist: Office365-REST-Python-Client; extra == "sharepoint"
 Provides-Extra: salesforce
 Requires-Dist: simple-salesforce; extra == "salesforce"
 Provides-Extra: sftp
@@ -179,17 +179,17 @@ Provides-Extra: singlestore
 Requires-Dist: singlestoredb; extra == "singlestore"
 Provides-Extra: vectara
 Requires-Dist: aiofiles; extra == "vectara"
-Requires-Dist: requests; extra == "vectara"
 Requires-Dist: httpx; extra == "vectara"
+Requires-Dist: requests; extra == "vectara"
 Provides-Extra: vastdb
+Requires-Dist: ibis; extra == "vastdb"
 Requires-Dist: vastdb; extra == "vastdb"
 Requires-Dist: pyarrow; extra == "vastdb"
-Requires-Dist: ibis; extra == "vastdb"
 Provides-Extra: embed-huggingface
 Requires-Dist: sentence-transformers; extra == "embed-huggingface"
 Provides-Extra: embed-octoai
-Requires-Dist: tiktoken; extra == "embed-octoai"
 Requires-Dist: openai; extra == "embed-octoai"
+Requires-Dist: tiktoken; extra == "embed-octoai"
 Provides-Extra: embed-vertexai
 Requires-Dist: vertexai; extra == "embed-vertexai"
 Provides-Extra: embed-voyageai
@@ -197,11 +197,11 @@ Requires-Dist: voyageai; extra == "embed-voyageai"
 Provides-Extra: embed-mixedbreadai
 Requires-Dist: mixedbread-ai; extra == "embed-mixedbreadai"
 Provides-Extra: openai
-Requires-Dist: tiktoken; extra == "openai"
 Requires-Dist: openai; extra == "openai"
+Requires-Dist: tiktoken; extra == "openai"
 Provides-Extra: bedrock
-Requires-Dist: aioboto3; extra == "bedrock"
 Requires-Dist: boto3; extra == "bedrock"
+Requires-Dist: aioboto3; extra == "bedrock"
 Provides-Extra: togetherai
 Requires-Dist: together; extra == "togetherai"
 

{unstructured_ingest-0.4.7 → unstructured_ingest-0.5.0}/setup.py

@@ -142,7 +142,7 @@ embed_reqs = {
     "embed-voyageai": load_requirements("requirements/embed/voyageai.in"),
     "embed-mixedbreadai": load_requirements("requirements/embed/mixedbreadai.in"),
     "openai": load_requirements("requirements/embed/openai.in"),
-    "bedrock": load_requirements("requirements/embed/aws-bedrock.in"),
+    "bedrock": load_requirements("requirements/embed/bedrock.in"),
     "togetherai": load_requirements("requirements/embed/togetherai.in"),
 }
 

{unstructured_ingest-0.4.7 → unstructured_ingest-0.5.0}/test/integration/connectors/test_onedrive.py

@@ -5,13 +5,25 @@ from pathlib import Path
 import pytest
 from office365.graph_client import GraphClient
 
-from test.integration.connectors.utils.constants import BLOB_STORAGE_TAG, DESTINATION_TAG
+from test.integration.connectors.utils.constants import (
+    BLOB_STORAGE_TAG,
+    DESTINATION_TAG,
+    SOURCE_TAG,
+)
+from test.integration.connectors.utils.validation.source import (
+    SourceValidationConfigs,
+    source_connector_validation,
+)
 from test.integration.utils import requires_env
 from unstructured_ingest.v2.interfaces import FileData, SourceIdentifiers
 from unstructured_ingest.v2.processes.connectors.onedrive import (
     CONNECTOR_TYPE,
     OnedriveAccessConfig,
     OnedriveConnectionConfig,
+    OnedriveDownloader,
+    OnedriveDownloaderConfig,
+    OnedriveIndexer,
+    OnedriveIndexerConfig,
     OnedriveUploader,
     OnedriveUploaderConfig,
 )
@@ -62,9 +74,46 @@ def get_connection_config():
     return connection_config
 
 
+@pytest.mark.asyncio
+@pytest.mark.tags(CONNECTOR_TYPE, SOURCE_TAG, BLOB_STORAGE_TAG)
+@requires_env("MS_CLIENT_CRED", "MS_CLIENT_ID", "MS_TENANT_ID", "MS_USER_PNAME")
+async def test_onedrive_source(temp_dir):
+    connection_config = get_connection_config()
+    index_config = OnedriveIndexerConfig(recursive=True, path="eml")
+
+    download_config = OnedriveDownloaderConfig(download_dir=temp_dir)
+
+    # Instantiate indexer and downloader
+    indexer = OnedriveIndexer(
+        connection_config=connection_config,
+        index_config=index_config,
+    )
+    downloader = OnedriveDownloader(
+        connection_config=connection_config,
+        download_config=download_config,
+    )
+
+    # Run the source connector validation
+    await source_connector_validation(
+        indexer=indexer,
+        downloader=downloader,
+        configs=SourceValidationConfigs(
+            test_id="onedrive",
+            expected_num_files=1,
+            validate_downloaded_files=True,
+            exclude_fields_extend=[
+                "metadata.date_created",
+                "metadata.date_modified",
+                "additional_metadata.LastModified",
+                "additional_metadata.@microsoft.graph.downloadUrl",
+            ],
+        ),
+    )
+
+
 @pytest.mark.tags(CONNECTOR_TYPE, DESTINATION_TAG, BLOB_STORAGE_TAG)
 @requires_env("MS_CLIENT_CRED", "MS_CLIENT_ID", "MS_TENANT_ID", "MS_USER_PNAME")
-def test_onedrive_destination(upload_file: Path, onedrive_test_folder: str):
+def xtest_onedrive_destination(upload_file: Path, onedrive_test_folder: str):
     """
     Integration test for the OneDrive destination connector.
 

unstructured_ingest-0.5.0/test/integration/connectors/test_sharepoint.py

@@ -0,0 +1,71 @@
+import os
+
+import pytest
+
+from test.integration.connectors.utils.constants import BLOB_STORAGE_TAG, SOURCE_TAG
+from test.integration.connectors.utils.validation.source import (
+    SourceValidationConfigs,
+    source_connector_validation,
+)
+from test.integration.utils import requires_env
+from unstructured_ingest.v2.processes.connectors.sharepoint import (
+    CONNECTOR_TYPE,
+    SharepointAccessConfig,
+    SharepointConnectionConfig,
+    SharepointDownloader,
+    SharepointDownloaderConfig,
+    SharepointIndexer,
+    SharepointIndexerConfig,
+)
+
+
+@pytest.mark.asyncio
+@pytest.mark.tags(CONNECTOR_TYPE, SOURCE_TAG, BLOB_STORAGE_TAG)
+@requires_env("SHAREPOINT_CLIENT_ID", "SHAREPOINT_CRED", "MS_TENANT_ID", "MS_USER_PNAME")
+async def test_sharepoint_source(temp_dir):
+    # Retrieve environment variables
+    site = "https://unstructuredio.sharepoint.com/sites/utic-platform-test-source"
+    client_id = os.environ["SHAREPOINT_CLIENT_ID"]
+    client_cred = os.environ["SHAREPOINT_CRED"]
+    user_pname = os.environ["MS_USER_PNAME"]
+    tenant = os.environ["MS_TENANT_ID"]
+
+    # Create connection and indexer configurations
+    access_config = SharepointAccessConfig(client_cred=client_cred)
+    connection_config = SharepointConnectionConfig(
+        client_id=client_id,
+        site=site,
+        tenant=tenant,
+        user_pname=user_pname,
+        access_config=access_config,
+    )
+    index_config = SharepointIndexerConfig(recursive=True)
+
+    download_config = SharepointDownloaderConfig(download_dir=temp_dir)
+
+    # Instantiate indexer and downloader
+    indexer = SharepointIndexer(
+        connection_config=connection_config,
+        index_config=index_config,
+    )
+    downloader = SharepointDownloader(
+        connection_config=connection_config,
+        download_config=download_config,
+    )
+
+    # Run the source connector validation
+    await source_connector_validation(
+        indexer=indexer,
+        downloader=downloader,
+        configs=SourceValidationConfigs(
+            test_id="sharepoint",
+            expected_num_files=4,
+            validate_downloaded_files=True,
+            exclude_fields_extend=[
+                "metadata.date_created",
+                "metadata.date_modified",
+                "additional_metadata.LastModified",
+                "additional_metadata.@microsoft.graph.downloadUrl",
+            ],
+        ),
+    )

{unstructured_ingest-0.4.7 → unstructured_ingest-0.5.0}/test/integration/connectors/utils/validation/source.py

@@ -10,6 +10,13 @@ from pydantic import Field
 from test.integration.connectors.utils.validation.utils import ValidationConfig
 from unstructured_ingest.v2.interfaces import Downloader, FileData, Indexer
 
+NONSTANDARD_METADATA_FIELDS = {
+    "additional_metadata.@microsoft.graph.downloadUrl": [
+        "additional_metadata",
+        "@microsoft.graph.downloadUrl",
+    ]
+}
+
 
 class SourceValidationConfigs(ValidationConfig):
     expected_number_indexed_file_data: Optional[int] = None
@@ -26,7 +33,7 @@ class SourceValidationConfigs(ValidationConfig):
     def get_exclude_fields(self) -> list[str]:
         exclude_fields = self.exclude_fields
         exclude_fields.extend(self.exclude_fields_extend)
-        return exclude_fields
+        return list(set(exclude_fields))
 
     def run_file_data_validation(
         self, predownload_file_data: FileData, postdownload_file_data: FileData
@@ -45,8 +52,13 @@ class SourceValidationConfigs(ValidationConfig):
         exclude_fields = self.get_exclude_fields()
         # Ignore fields that dynamically change every time the tests run
         copied_data = data.copy()
+
         for exclude_field in exclude_fields:
-            exclude_field_vals = exclude_field.split(".")
+            exclude_field_vals = (
+                NONSTANDARD_METADATA_FIELDS[exclude_field]
+                if exclude_field in NONSTANDARD_METADATA_FIELDS
+                else exclude_field.split(".")
+            )
             if len(exclude_field_vals) == 1:
                 current_val = copied_data
                 drop_field = exclude_field_vals[0]
@@ -261,21 +273,38 @@ async def source_connector_validation(
     indexer.precheck()
     download_dir = downloader.download_config.download_dir
     test_output_dir = configs.test_output_dir()
-    for file_data in indexer.run():
-        assert file_data
-        predownload_file_data = file_data.model_copy(deep=True)
-        all_predownload_file_data.append(predownload_file_data)
-        if downloader.is_async():
-            resp = await downloader.run_async(file_data=file_data)
-        else:
-            resp = downloader.run(file_data=file_data)
-        if isinstance(resp, list):
-            for r in resp:
-                postdownload_file_data = r["file_data"].model_copy(deep=True)
+    if indexer.is_async():
+        async for file_data in indexer.run_async():
+            assert file_data
+            predownload_file_data = file_data.model_copy(deep=True)
+            all_predownload_file_data.append(predownload_file_data)
+            if downloader.is_async():
+                resp = await downloader.run_async(file_data=file_data)
+            else:
+                resp = downloader.run(file_data=file_data)
+            if isinstance(resp, list):
+                for r in resp:
+                    postdownload_file_data = r["file_data"].model_copy(deep=True)
+                    all_postdownload_file_data.append(postdownload_file_data)
+            else:
+                postdownload_file_data = resp["file_data"].model_copy(deep=True)
+                all_postdownload_file_data.append(postdownload_file_data)
+    else:
+        for file_data in indexer.run():
+            assert file_data
+            predownload_file_data = file_data.model_copy(deep=True)
+            all_predownload_file_data.append(predownload_file_data)
+            if downloader.is_async():
+                resp = await downloader.run_async(file_data=file_data)
+            else:
+                resp = downloader.run(file_data=file_data)
+            if isinstance(resp, list):
+                for r in resp:
+                    postdownload_file_data = r["file_data"].model_copy(deep=True)
+                    all_postdownload_file_data.append(postdownload_file_data)
+            else:
+                postdownload_file_data = resp["file_data"].model_copy(deep=True)
                 all_postdownload_file_data.append(postdownload_file_data)
-        else:
-            postdownload_file_data = resp["file_data"].model_copy(deep=True)
-            all_postdownload_file_data.append(postdownload_file_data)
     if not overwrite_fixtures:
         print("Running validation")
         run_all_validations(

{unstructured_ingest-0.4.7 → unstructured_ingest-0.5.0}/test/integration/embedders/test_bedrock.py

@@ -31,7 +31,7 @@ def get_aws_credentials() -> dict:
 def test_bedrock_embedder(embedder_file: Path):
     aws_credentials = get_aws_credentials()
     embedder_config = EmbedderConfig(
-        embedding_provider="aws-bedrock",
+        embedding_provider="bedrock",
         embedding_aws_access_key_id=aws_credentials["aws_access_key_id"],
         embedding_aws_secret_access_key=aws_credentials["aws_secret_access_key"],
     )

{unstructured_ingest-0.4.7 → unstructured_ingest-0.5.0}/test/integration/partitioners/test_partitioner.py

@@ -1,4 +1,3 @@
-import json
 import os
 from pathlib import Path
 
@@ -15,6 +14,9 @@ all_partition_files = [path for path in assets_dir.iterdir() if path.is_file()]
 non_image_partition_files = [
     path for path in all_partition_files if path.suffix not in [".jpg", ".png", ".tif"]
 ]
+supported_fast_partition_files = [
+    path for path in non_image_partition_files if path.suffix != ".eml"
+]
 image_partition_files = [
     path for path in all_partition_files if path not in non_image_partition_files
 ]
@@ -33,18 +35,13 @@ async def test_partitioner_api_hi_res(partition_file: Path):
     )
     partitioner = Partitioner(config=partitioner_config)
     results = await partitioner.run_async(filename=partition_file)
-    results_dir = int_test_dir / "results"
-    results_dir.mkdir(exist_ok=True)
-    results_path = results_dir / f"{partition_file.name}.json"
-    with results_path.open("w") as f:
-        json.dump(results, f, indent=2)
     assert results
 
 
 @pytest.mark.parametrize(
     "partition_file",
-    non_image_partition_files,
-    ids=[path.name for path in non_image_partition_files],
+    supported_fast_partition_files,
+    ids=[path.name for path in supported_fast_partition_files],
 )
 @requires_env("UNSTRUCTURED_API_KEY", "UNSTRUCTURED_API_URL")
 @pytest.mark.asyncio
@@ -68,7 +65,11 @@ async def test_partitioner_api_fast_error(partition_file: Path):
     api_key = os.getenv("UNSTRUCTURED_API_KEY")
     api_url = os.getenv("UNSTRUCTURED_API_URL")
     partitioner_config = PartitionerConfig(
-        strategy="fast", partition_by_api=True, api_key=api_key, partition_endpoint=api_url
+        strategy="fast",
+        partition_by_api=True,
+        api_key=api_key,
+        partition_endpoint=api_url,
+        raise_unsupported_filetype=True,
     )
     partitioner = Partitioner(config=partitioner_config)
     with pytest.raises(UserError):

unstructured_ingest-0.5.0/unstructured_ingest/__version__.py

@@ -0,0 +1 @@
+__version__ = "0.5.0"  # pragma: no cover

{unstructured_ingest-0.4.7 → unstructured_ingest-0.5.0}/unstructured_ingest/cli/interfaces.py

@@ -417,7 +417,7 @@ class CliEmbeddingConfig(EmbeddingConfig, CliMixin):
         embed_providers = [
             "openai",
             "huggingface",
-            "aws-bedrock",
+            "bedrock",
             "vertexai",
             "voyageai",
             "octoai",

{unstructured_ingest-0.4.7 → unstructured_ingest-0.5.0}/unstructured_ingest/interfaces.py

@@ -226,7 +226,7 @@ class EmbeddingConfig(BaseConfig):
             )
 
             return OctoAIEmbeddingEncoder(config=OctoAiEmbeddingConfig(**kwargs))
-        elif self.provider == "aws-bedrock":
+        elif self.provider == "bedrock":
             from unstructured_ingest.embed.bedrock import (
                 BedrockEmbeddingConfig,
                 BedrockEmbeddingEncoder,

{unstructured_ingest-0.4.7 → unstructured_ingest-0.5.0}/unstructured_ingest/v2/pipeline/pipeline.py

@@ -268,6 +268,7 @@ class Pipeline:
 
         # Partition content
         elements = self.partitioner_step(downloaded_data)
+        elements = self.clean_results(results=elements)
         # Download data non longer needed, delete if possible
         self.downloader_step.delete_cache()
         elements = self.clean_results(results=elements)

{unstructured_ingest-0.4.7 → unstructured_ingest-0.5.0}/unstructured_ingest/v2/processes/connectors/onedrive.py

@@ -105,6 +105,7 @@ class OnedriveIndexerConfig(IndexerConfig):
 class OnedriveIndexer(Indexer):
     connection_config: OnedriveConnectionConfig
     index_config: OnedriveIndexerConfig
+    connector_type: str = CONNECTOR_TYPE
 
     def precheck(self) -> None:
         try:
@@ -172,7 +173,7 @@ class OnedriveIndexer(Indexer):
         )
         return FileData(
             identifier=drive_item.id,
-            connector_type=CONNECTOR_TYPE,
+            connector_type=self.connector_type,
             source_identifiers=SourceIdentifiers(
                 fullpath=server_path, filename=drive_item.name, rel_path=rel_path
             ),
@@ -201,7 +202,8 @@ class OnedriveIndexer(Indexer):
         token_resp = await asyncio.to_thread(self.connection_config.get_token)
         if "error" in token_resp:
             raise SourceConnectionError(
-                f"[{CONNECTOR_TYPE}]: {token_resp['error']} ({token_resp.get('error_description')})"
+                f"[{self.connector_type}]: {token_resp['error']} "
+                f"({token_resp.get('error_description')})"
             )
 
         client = await asyncio.to_thread(self.connection_config.get_client)
@@ -221,6 +223,7 @@ class OnedriveDownloaderConfig(DownloaderConfig):
 class OnedriveDownloader(Downloader):
     connection_config: OnedriveConnectionConfig
     download_config: OnedriveDownloaderConfig
+    connector_type: str = CONNECTOR_TYPE
 
     @SourceConnectionNetworkError.wrap
     def _fetch_file(self, file_data: FileData) -> DriveItem:
@@ -260,7 +263,9 @@ class OnedriveDownloader(Downloader):
                     file.download_session(f).execute_query()
             return self.generate_download_response(file_data=file_data, download_path=download_path)
         except Exception as e:
-            logger.error(f"[{CONNECTOR_TYPE}] Exception during downloading: {e}", exc_info=True)
+            logger.error(
+                f"[{self.connector_type}] Exception during downloading: {e}", exc_info=True
+            )
             # Re-raise to see full stack trace locally
             raise
 

{unstructured_ingest-0.4.7 → unstructured_ingest-0.5.0}/unstructured_ingest/v2/processes/connectors/sharepoint.py

@@ -56,6 +56,7 @@ class SharepointIndexerConfig(OnedriveIndexerConfig):
 class SharepointIndexer(OnedriveIndexer):
     connection_config: SharepointConnectionConfig
     index_config: SharepointIndexerConfig
+    connector_type: str = CONNECTOR_TYPE
 
     @requires_dependencies(["office365"], extras="sharepoint")
     async def run_async(self, **kwargs: Any) -> AsyncIterator[FileData]:
@@ -64,7 +65,8 @@ class SharepointIndexer(OnedriveIndexer):
         token_resp = await asyncio.to_thread(self.connection_config.get_token)
         if "error" in token_resp:
             raise SourceConnectionError(
-                f"[{CONNECTOR_TYPE}]: {token_resp['error']} ({token_resp.get('error_description')})"
+                f"[{self.connector_type}]: {token_resp['error']} "
+                f"({token_resp.get('error_description')})"
             )
 
         client = await asyncio.to_thread(self.connection_config.get_client)
@@ -90,6 +92,7 @@ class SharepointDownloaderConfig(OnedriveDownloaderConfig):
 class SharepointDownloader(OnedriveDownloader):
     connection_config: SharepointConnectionConfig
     download_config: SharepointDownloaderConfig
+    connector_type: str = CONNECTOR_TYPE
 
     @SourceConnectionNetworkError.wrap
     @requires_dependencies(["office365"], extras="onedrive")

{unstructured_ingest-0.4.7 → unstructured_ingest-0.5.0}/unstructured_ingest/v2/processes/embedder.py

@@ -18,7 +18,7 @@ class EmbedderConfig(BaseModel):
             "openai",
             "azure-openai",
             "huggingface",
-            "aws-bedrock",
+            "bedrock",
             "vertexai",
             "voyageai",
             "octoai",
@@ -162,7 +162,7 @@ class EmbedderConfig(BaseModel):
         if self.embedding_provider == "octoai":
             return self.get_octoai_embedder(embedding_kwargs=kwargs)
 
-        if self.embedding_provider == "aws-bedrock":
+        if self.embedding_provider == "bedrock":
             return self.get_bedrock_embedder()
 
         if self.embedding_provider == "vertexai":

{unstructured_ingest-0.4.7 → unstructured_ingest-0.5.0}/unstructured_ingest/v2/processes/partitioner.py

@@ -1,3 +1,4 @@
+import json
 from abc import ABC
 from dataclasses import dataclass
 from pathlib import Path
@@ -7,6 +8,7 @@ from pydantic import BaseModel, Field, SecretStr
 
 from unstructured_ingest.utils.data_prep import flatten_dict
 from unstructured_ingest.utils.dep_check import requires_dependencies
+from unstructured_ingest.v2.errors import UserError
 from unstructured_ingest.v2.interfaces.process import BaseProcess
 from unstructured_ingest.v2.logger import logger
 from unstructured_ingest.v2.unstructured_api import call_api_async
@@ -73,6 +75,9 @@ class PartitionerConfig(BaseModel):
     hi_res_model_name: Optional[str] = Field(
         default=None, description="Model name for hi-res strategy."
     )
+    raise_unsupported_filetype: bool = Field(
+        default=False, description="Raise an error if the file type is not supported"
+    )
 
     def model_post_init(self, __context: Any) -> None:
         if self.metadata_exclude and self.metadata_include:
@@ -151,13 +156,25 @@ class Partitioner(BaseProcess, ABC):
         class FileDataSourceMetadata(DataSourceMetadata):
             filesize_bytes: Optional[int] = None
 
+        metadata = metadata or {}
         logger.debug(f"using local partition with kwargs: {self.config.to_partition_kwargs()}")
         logger.debug(f"partitioning file {filename} with metadata {metadata}")
-        elements = partition(
-            filename=str(filename.resolve()),
-            data_source_metadata=FileDataSourceMetadata.from_dict(metadata),
-            **self.config.to_partition_kwargs(),
-        )
+        try:
+            elements = partition(
+                filename=str(filename.resolve()),
+                data_source_metadata=FileDataSourceMetadata.from_dict(metadata),
+                **self.config.to_partition_kwargs(),
+            )
+        except ValueError as sdk_error:
+            if (
+                self.is_unstructured_error_unsupported_filetype(sdk_error=sdk_error)
+                and not self.config.raise_unsupported_filetype
+            ):
+                logger.warning(
+                    f"Unsupported file type for strategy {self.config.strategy}: {filename}"
+                )
+                return []
+            raise sdk_error
         return self.postprocess(elements=elements_to_dicts(elements))
 
     @requires_dependencies(dependencies=["unstructured_client"], extras="remote")
@@ -179,10 +196,37 @@ class Partitioner(BaseProcess, ABC):
             element["metadata"]["data_source"] = metadata
         return self.postprocess(elements=elements)
 
+    def is_unstructured_error_unsupported_filetype(self, sdk_error: ValueError) -> bool:
+        error_msg = sdk_error.args[0]
+        return (
+            "Invalid file" in error_msg
+            or "Unstructured schema" in error_msg
+            or "fast strategy is not available for image files" in error_msg
+        )
+
+    def is_client_error_unsupported_filetype(self, error: UserError) -> bool:
+        error_msg = error.args[0]
+        error_dict = json.loads(error_msg)
+        details = error_dict["detail"]
+        return "fast strategy is not available for image files" in details or (
+            "file type" in details.lower() and "is not supported" in details.lower()
+        )
+
     def run(self, filename: Path, metadata: Optional[dict] = None, **kwargs) -> list[dict]:
         return self.partition_locally(filename, metadata=metadata, **kwargs)
 
     async def run_async(
         self, filename: Path, metadata: Optional[dict] = None, **kwargs
     ) -> list[dict]:
-        return await self.partition_via_api(filename, metadata=metadata, **kwargs)
+        try:
+            return await self.partition_via_api(filename, metadata=metadata, **kwargs)
+        except UserError as user_error:
+            if (
+                self.is_client_error_unsupported_filetype(error=user_error)
+                and not self.config.raise_unsupported_filetype
+            ):
+                logger.warning(
+                    f"Unsupported file type for strategy {self.config.strategy}: {filename}"
+                )
+                return []
+            raise user_error