unstructured-ingest 0.5.15__py3-none-any.whl → 0.5.16__py3-none-any.whl

unstructured_ingest/v2/processes/connectors/zendesk/zendesk.py

@@ -1,22 +1,17 @@
 from __future__ import annotations
 
-import datetime
 import hashlib
 from dataclasses import dataclass
 from pathlib import Path
 from time import time
-from typing import Any, AsyncGenerator, List, Literal
+from typing import Any, AsyncGenerator, Literal, Union
 
 from pydantic import BaseModel, Field, Secret
 
-from unstructured_ingest.utils.data_prep import batch_generator
 from unstructured_ingest.utils.dep_check import requires_dependencies
 from unstructured_ingest.utils.html import HtmlMixin
-from unstructured_ingest.v2.errors import UserAuthError
 from unstructured_ingest.v2.interfaces import (
     AccessConfig,
-    BatchFileData,
-    BatchItem,
     ConnectionConfig,
     Downloader,
     DownloaderConfig,
@@ -36,20 +31,11 @@ CONNECTOR_TYPE = "zendesk"
 
 
 class ZendeskAdditionalMetadata(BaseModel):
-    item_type: str
-    leading_id: str  # is the same as id just being verbose.
-    tail_id: str  # last id in the batch.
+    item_type: Literal["ticket", "article"]
+    content: Union[ZendeskTicket, ZendeskArticle]
 
 
-class ZendeskFileDataSourceMetadata(FileDataSourceMetadata):
-    """
-    inherits metadata object as tickets and articles
-    are treated in single batch, we need to denote indices ticket/article
-    as the source metadata.
-    """
-
-
-class ZendeskBatchFileData(BatchFileData):
+class ZendeskFileData(FileData):
     additional_metadata: ZendeskAdditionalMetadata
 
 
@@ -59,48 +45,21 @@ class ZendeskAccessConfig(AccessConfig):
     )
 
 
-class ZendeskBatchItemTicket(BatchItem):
-    subject: str
-    description: str
-    item_type: str = "tickets"  # placeholder for downloader
-
-
-class ZendeskBatchItemArticle(BatchItem):
-    title: str
-    author_id: str
-    title: str
-    content: str
-
-
 class ZendeskConnectionConfig(ConnectionConfig):
     subdomain: str = Field(description="Subdomain for zendesk site, <sub-domain>.company.com")
     email: str = Field(description="Email for zendesk site registered at the subdomain")
     access_config: Secret[ZendeskAccessConfig]
 
-    async def get_client_async(self) -> ZendeskClient:
-        """Provides an async manager for ZendeskClient."""
-        access_config = self.access_config.get_secret_value()
-
-        client = ZendeskClient(
-            email=self.email, subdomain=self.subdomain, token=access_config.api_token
-        )
-        return client
-
     def get_client(self) -> ZendeskClient:
 
         access_config = self.access_config.get_secret_value()
 
-        client = ZendeskClient(
+        return ZendeskClient(
             email=self.email, subdomain=self.subdomain, token=access_config.api_token
         )
-        return client
 
 
 class ZendeskIndexerConfig(IndexerConfig):
-    batch_size: int = Field(
-        default=2,
-        description="Number of tickets or articles.",
-    )
     item_type: Literal["tickets", "articles", "all"] = Field(
         default="tickets",
         description="Type of item from zendesk to parse, can only be `tickets` or `articles`.",
@@ -115,142 +74,76 @@ class ZendeskIndexer(Indexer):
 
     def precheck(self) -> None:
         """Validates connection to Zendesk API."""
-        try:
-            client = self.connection_config.get_client()
-            if not client.get_users():
-                subdomain_endpoint = f"{self.connection_config.subdomain}.zendesk.com"
-                raise UserAuthError(f"Users do not exist in subdomain {subdomain_endpoint}")
-        except UserAuthError as e:
-            logger.error(f"Source connection error: {e}", exc_info=True)
-            raise
-        except Exception as e:
-            logger.error(f"Failed to validate connection to Zendesk: {e}", exc_info=True)
-            raise UserAuthError(f"Failed to validate connection: {e}")
+        self.connection_config.get_client()
 
     def is_async(self) -> bool:
         return True
 
-    async def _list_articles_async(self) -> List[ZendeskArticle]:
-        client = await self.connection_config.get_client_async()
-        return await client.get_articles_async()
-
-    async def _list_tickets_async(self) -> List[ZendeskTicket]:
-        client = await self.connection_config.get_client_async()
-        return await client.get_tickets_async()
-
     def _generate_fullpath(self, identifier: str) -> Path:
         return Path(hashlib.sha256(identifier.encode("utf-8")).hexdigest()[:16] + ".txt")
 
-    async def handle_articles_async(
-        self, articles: List[ZendeskArticle], batch_size: int
-    ) -> AsyncGenerator[ZendeskBatchFileData, None]:
-        """Parses articles from a list and yields FileData objects asynchronously in batches."""
-        for article_batch in batch_generator(articles, batch_size=batch_size):
-
-            article_batch = sorted(article_batch)
-
-            additional_metadata = ZendeskAdditionalMetadata(
-                item_type="articles",
-                leading_id=str(article_batch[0].id),
-                tail_id=str(article_batch[-1].id),
-            )
-
-            metadata = ZendeskFileDataSourceMetadata(
-                date_processed=str(time()),
-                record_locator={
-                    "id": str(article_batch[0].id),
-                    "item_type": "articles",
-                },
-            )
-
-            batch_items: List[ZendeskBatchItemArticle] = [
-                ZendeskBatchItemArticle(
-                    identifier=str(article.id),
-                    author_id=str(article.author_id),
-                    title=str(article.title),
-                    content=str(article.content),
-                )
-                for article in article_batch
-            ]
-
-            full_path = self._generate_fullpath(str(article_batch[0].id))
-            full_path = Path(str(full_path).replace(".txt", ".html"))
-
-            source_identifiers = SourceIdentifiers(filename=full_path.name, fullpath=str(full_path))
-
-            batched_file_data = ZendeskBatchFileData(
-                identifier=str(article_batch[0].id),
-                connector_type=self.connector_type,
-                metadata=metadata,
-                batch_items=batch_items,
-                additional_metadata=additional_metadata,
-                source_identifiers=source_identifiers,
-            )
-
-            yield batched_file_data
-
-    async def handle_tickets_async(
-        self, tickets: List[ZendeskTicket], batch_size: int
-    ) -> AsyncGenerator[ZendeskBatchFileData, None]:
-        """Parses tickets from a list and yields FileData objects asynchronously in batches."""
-        for ticket_batch in batch_generator(tickets, batch_size=batch_size):
-
-            sorted_batch = sorted(ticket_batch)
-
-            additional_metadata = ZendeskAdditionalMetadata(
-                item_type="tickets",
-                leading_id=str(sorted_batch[0].id),
-                tail_id=str(sorted_batch[-1].id),
-            )
-
-            metadata = ZendeskFileDataSourceMetadata(
-                date_processed=str(time()),
-                record_locator={
-                    "id": str(sorted_batch[0].id),
-                    "item_type": "tickets",
-                },
-            )
-
-            batch_items: List[ZendeskBatchItemTicket] = [
-                ZendeskBatchItemTicket(
+    async def get_tickets(self) -> AsyncGenerator[ZendeskFileData, None]:
+        async with self.connection_config.get_client() as client:
+            async for ticket in client.get_tickets():
+                yield ZendeskFileData(
                     identifier=str(ticket.id),
-                    subject=str(ticket.subject),
-                    description=str(ticket.description),
+                    connector_type=self.connector_type,
+                    source_identifiers=SourceIdentifiers(
+                        filename=f"{ticket.id}.txt", fullpath=f"tickets/{ticket.id}.txt"
+                    ),
+                    additional_metadata=ZendeskAdditionalMetadata(
+                        item_type="ticket", content=ticket
+                    ),
+                    metadata=FileDataSourceMetadata(
+                        url=str(ticket.url) if ticket.url else None,
+                        date_created=ticket.created_at.isoformat() if ticket.created_at else None,
+                        date_modified=ticket.updated_at.isoformat() if ticket.updated_at else None,
+                        date_processed=str(time()),
+                    ),
                 )
-                for ticket in sorted_batch
-            ]
-
-            full_path = self._generate_fullpath(str(sorted_batch[0].id))
-            source_identifiers = SourceIdentifiers(filename=full_path.name, fullpath=str(full_path))
-
-            batched_file_data = ZendeskBatchFileData(
-                connector_type=self.connector_type,
-                metadata=metadata,
-                batch_items=batch_items,
-                additional_metadata=additional_metadata,
-                source_identifiers=source_identifiers,
-            )
 
-            yield batched_file_data
+    async def get_articles(self) -> AsyncGenerator[ZendeskFileData, None]:
+        async with self.connection_config.get_client() as client:
+            async for article in client.get_articles():
+                yield ZendeskFileData(
+                    identifier=str(article.id),
+                    connector_type=self.connector_type,
+                    source_identifiers=SourceIdentifiers(
+                        filename=f"{article.id}.html", fullpath=f"articles/{article.id}.html"
+                    ),
+                    additional_metadata=ZendeskAdditionalMetadata(
+                        item_type="article", content=article
+                    ),
+                    metadata=FileDataSourceMetadata(
+                        url=str(article.url) if article.url else None,
+                        date_created=article.created_at.isoformat() if article.created_at else None,
+                        date_modified=(
+                            article.updated_at.isoformat() if article.updated_at else None
+                        ),
+                        date_processed=str(time()),
+                    ),
+                )
 
-    async def run_async(self, **kwargs: Any) -> AsyncGenerator[FileData, None]:
+    async def run_async(self, **kwargs: Any) -> AsyncGenerator[ZendeskFileData, None]:
         """Determines item type and processes accordingly asynchronously."""
         item_type = self.index_config.item_type
-        batch_size = self.index_config.batch_size
 
         if item_type == "articles":
-            articles = await self._list_articles_async()
-            async for file_data in self.handle_articles_async(
-                articles, batch_size
-            ):  # Using async version
-                yield file_data
+            async for article_file_data in self.get_articles():
+                yield article_file_data
 
         elif item_type == "tickets":
-            tickets = await self._list_tickets_async()
-            async for file_data in self.handle_tickets_async(
-                tickets, batch_size
-            ):  # Using async version
-                yield file_data
+            async for ticket_file_data in self.get_tickets():
+                yield ticket_file_data
+
+        elif item_type == "all":
+            async for article_file_data in self.get_articles():
+                yield article_file_data
+            async for ticket_file_data in self.get_tickets():
+                yield ticket_file_data
+
+        else:
+            raise ValueError(f"Item type {item_type} is not supported by the indexer")
 
 
 class ZendeskDownloaderConfig(DownloaderConfig, HtmlMixin):
@@ -289,130 +182,46 @@ class ZendeskDownloader(Downloader):
             session=session,
         )
 
-    @requires_dependencies(["bs4", "aiofiles"], extras="zendesk")
-    async def handle_articles_async(
-        self, client: ZendeskClient, batch_file_data: ZendeskBatchFileData
-    ):
-        """
-        Processes the article information, downloads the attachments for each article,
-        and updates the content accordingly.
-        """
+    @requires_dependencies(["aiofiles", "bs4"], extras="zendesk")
+    async def download_article(self, article: ZendeskArticle, download_path: Path) -> None:
         import aiofiles
         import bs4
 
-        # Determine the download path
-        download_path = self.get_download_path(batch_file_data)
-
-        if download_path is None:
-            raise ValueError("Download path could not be determined")
-
-        download_path.parent.mkdir(parents=True, exist_ok=True)
-
-        async with aiofiles.open(download_path, "a", encoding="utf8") as f:
-            for article in batch_file_data.batch_items:
-                html_data_str = article.content
-                soup = bs4.BeautifulSoup(html_data_str, "html.parser")
-
-                if self.download_config.extract_images:
-                    # Get article attachments asynchronously
-                    image_data_decoded: List = await client.get_article_attachments_async(
-                        article_id=article.identifier
-                    )
-                    img_tags = soup.find_all("img")
-
-                    # Ensure we don't exceed the available images
-                    for img_tag, img_data in zip(img_tags, image_data_decoded):
-                        img_tag["src"] = img_data.get("encoded_content", "")
-
+        article_html = article.as_html()
+        soup = bs4.BeautifulSoup(article_html, "html.parser")
+        async with aiofiles.open(download_path, "w", encoding="utf8") as f:
             await f.write(soup.prettify())
 
-        return super().generate_download_response(
-            file_data=batch_file_data, download_path=download_path
-        )
-
     @requires_dependencies(["aiofiles"], extras="zendesk")
-    async def handle_tickets_async(
-        self, client: ZendeskClient, batch_file_data: ZendeskBatchFileData
-    ) -> DownloadResponse:
-        """
-        Processes a batch of tickets asynchronously, writing their details and comments to a file.
-        """
+    async def download_ticket(self, ticket: ZendeskTicket, download_path: Path) -> None:
         import aiofiles
 
-        # Determine the download path
-        download_path = self.get_download_path(batch_file_data)
-        if download_path is None:
-            raise ValueError("Download path could not be determined")
-
-        download_path.parent.mkdir(parents=True, exist_ok=True)
-
-        # Process each ticket in the batch
-        async with aiofiles.open(download_path, "a", encoding="utf8") as f:
-            for batch_item in batch_file_data.batch_items:
-                ticket_identifier = batch_item.identifier
-                first_date = None
-                comments: List[dict] = []
-
-                # Fetch comments asynchronously
-                comments_list = await client.get_comments_async(ticket_id=int(ticket_identifier))
-
-                for comment in comments_list:  # Iterate over the resolved list
-                    date_created = (
-                        comment.metadata["created_at"].isoformat()
-                        if isinstance(comment.metadata["created_at"], datetime.datetime)
-                        else str(comment.metadata["created_at"])
-                    )
-
-                    if first_date is None:
-                        first_date = date_created
-
-                    comments.append(
-                        {
-                            "comment_id": comment.id,
-                            "author_id": comment.author_id,
-                            "body": comment.body,
-                            "date_created": date_created,
-                        }
-                    )
-
-                # Write ticket details to file
-                content = (
-                    "\nticket\n"
-                    f"{batch_item.identifier}\n"
-                    f"{batch_file_data.metadata.record_locator.get('subject', '')}\n"
-                    f"{batch_file_data.metadata.record_locator.get('description', '')}\n"
-                    f"{first_date}\n"
-                )
-
-                # Append comments
+        async with aiofiles.open(download_path, "w", encoding="utf8") as f:
+            await f.write(ticket.as_text())
+            async with self.connection_config.get_client() as client:
+                comments = [comment async for comment in client.get_comments(ticket_id=ticket.id)]
                 for comment in comments:
-                    content += (
-                        "comment\n"
-                        f"{comment.get('comment_id', '')}\n"
-                        f"{comment.get('author_id', '')}\n"
-                        f"{comment.get('body', '')}\n"
-                        f"{comment.get('date_created', '')}\n"
-                    )
-
-                await f.write(content)
+                    await f.write(comment.as_text())
 
-        return super().generate_download_response(
-            file_data=batch_file_data, download_path=download_path
-        )
+    async def run_async(self, file_data: FileData, **kwargs: Any) -> DownloadResponse:
 
-    async def run_async(self, file_data: ZendeskBatchFileData, **kwargs: Any) -> DownloadResponse:
+        zendesk_filedata = ZendeskFileData.cast(file_data=file_data)
 
-        zendesk_filedata: FileData = FileData.cast(file_data=file_data)
-
-        client = await self.connection_config.get_client_async()
-        item_type = zendesk_filedata.metadata.record_locator["item_type"]
+        item_type = zendesk_filedata.additional_metadata.item_type
+        download_path = self.get_download_path(file_data=zendesk_filedata)
+        download_path.parent.mkdir(parents=True, exist_ok=True)
 
-        if item_type == "articles":
-            return await self.handle_articles_async(client, file_data)
-        elif item_type == "tickets":
-            return await self.handle_tickets_async(client, file_data)
+        if item_type == "article":
+            article = ZendeskArticle.model_validate(zendesk_filedata.additional_metadata.content)
+            await self.download_article(article=article, download_path=download_path)
+        elif item_type == "ticket":
+            ticket = ZendeskTicket.model_validate(zendesk_filedata.additional_metadata.content)
+            await self.download_ticket(ticket=ticket, download_path=download_path)
         else:
             raise RuntimeError(f"Item type {item_type} cannot be handled by the downloader")
+        return super().generate_download_response(
+            file_data=zendesk_filedata, download_path=download_path
+        )
 
 
 # create entry

{unstructured_ingest-0.5.15.dist-info → unstructured_ingest-0.5.16.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: unstructured-ingest
-Version: 0.5.15
+Version: 0.5.16
 Summary: A library that prepares raw documents for downstream ML tasks.
 Home-page: https://github.com/Unstructured-IO/unstructured-ingest
 Author: Unstructured Technologies
@@ -23,12 +23,12 @@ Requires-Python: >=3.9.0,<3.14
 Description-Content-Type: text/markdown
 License-File: LICENSE.md
 Requires-Dist: pandas
+Requires-Dist: opentelemetry-sdk
 Requires-Dist: tqdm
+Requires-Dist: dataclasses_json
 Requires-Dist: pydantic>=2.7
 Requires-Dist: python-dateutil
 Requires-Dist: click
-Requires-Dist: opentelemetry-sdk
-Requires-Dist: dataclasses_json
 Provides-Extra: remote
 Requires-Dist: unstructured-client>=0.30.0; extra == "remote"
 Provides-Extra: csv
@@ -71,11 +71,11 @@ Requires-Dist: fsspec; extra == "azure"
 Provides-Extra: azure-ai-search
 Requires-Dist: azure-search-documents; extra == "azure-ai-search"
 Provides-Extra: biomed
-Requires-Dist: bs4; extra == "biomed"
 Requires-Dist: requests; extra == "biomed"
+Requires-Dist: bs4; extra == "biomed"
 Provides-Extra: box
-Requires-Dist: fsspec; extra == "box"
 Requires-Dist: boxfs; extra == "box"
+Requires-Dist: fsspec; extra == "box"
 Provides-Extra: chroma
 Requires-Dist: chromadb; extra == "chroma"
 Provides-Extra: clarifai
@@ -91,19 +91,19 @@ Requires-Dist: boto3; extra == "delta-table"
 Provides-Extra: discord
 Requires-Dist: discord.py; extra == "discord"
 Provides-Extra: dropbox
-Requires-Dist: dropboxdrivefs; extra == "dropbox"
 Requires-Dist: fsspec; extra == "dropbox"
+Requires-Dist: dropboxdrivefs; extra == "dropbox"
 Provides-Extra: duckdb
 Requires-Dist: duckdb; extra == "duckdb"
 Provides-Extra: elasticsearch
 Requires-Dist: elasticsearch[async]; extra == "elasticsearch"
 Provides-Extra: gcs
-Requires-Dist: gcsfs; extra == "gcs"
-Requires-Dist: bs4; extra == "gcs"
 Requires-Dist: fsspec; extra == "gcs"
+Requires-Dist: bs4; extra == "gcs"
+Requires-Dist: gcsfs; extra == "gcs"
 Provides-Extra: github
-Requires-Dist: pygithub>1.58.0; extra == "github"
 Requires-Dist: requests; extra == "github"
+Requires-Dist: pygithub>1.58.0; extra == "github"
 Provides-Extra: gitlab
 Requires-Dist: python-gitlab; extra == "gitlab"
 Provides-Extra: google-drive
@@ -124,8 +124,8 @@ Requires-Dist: pymilvus; extra == "milvus"
 Provides-Extra: mongodb
 Requires-Dist: pymongo; extra == "mongodb"
 Provides-Extra: neo4j
-Requires-Dist: cymple; extra == "neo4j"
 Requires-Dist: neo4j-rust-ext; extra == "neo4j"
+Requires-Dist: cymple; extra == "neo4j"
 Requires-Dist: networkx; extra == "neo4j"
 Provides-Extra: notion
 Requires-Dist: httpx; extra == "notion"
@@ -133,14 +133,14 @@ Requires-Dist: htmlBuilder; extra == "notion"
 Requires-Dist: notion-client; extra == "notion"
 Requires-Dist: backoff; extra == "notion"
 Provides-Extra: onedrive
+Requires-Dist: msal; extra == "onedrive"
 Requires-Dist: Office365-REST-Python-Client; extra == "onedrive"
 Requires-Dist: bs4; extra == "onedrive"
-Requires-Dist: msal; 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
@@ -155,13 +155,13 @@ 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
-Requires-Dist: paramiko; extra == "sftp"
 Requires-Dist: fsspec; extra == "sftp"
+Requires-Dist: paramiko; extra == "sftp"
 Provides-Extra: slack
 Requires-Dist: slack_sdk[optional]; extra == "slack"
 Provides-Extra: snowflake
@@ -178,12 +178,12 @@ Requires-Dist: databricks-sql-connector; extra == "databricks-delta-tables"
 Provides-Extra: singlestore
 Requires-Dist: singlestoredb; extra == "singlestore"
 Provides-Extra: vectara
-Requires-Dist: httpx; extra == "vectara"
-Requires-Dist: requests; extra == "vectara"
 Requires-Dist: aiofiles; extra == "vectara"
+Requires-Dist: requests; extra == "vectara"
+Requires-Dist: httpx; extra == "vectara"
 Provides-Extra: vastdb
-Requires-Dist: vastdb; extra == "vastdb"
 Requires-Dist: ibis; extra == "vastdb"
+Requires-Dist: vastdb; extra == "vastdb"
 Requires-Dist: pyarrow; extra == "vastdb"
 Provides-Extra: zendesk
 Requires-Dist: httpx; extra == "zendesk"
@@ -192,8 +192,8 @@ Requires-Dist: aiofiles; extra == "zendesk"
 Provides-Extra: embed-huggingface
 Requires-Dist: sentence-transformers; extra == "embed-huggingface"
 Provides-Extra: embed-octoai
-Requires-Dist: openai; extra == "embed-octoai"
 Requires-Dist: tiktoken; extra == "embed-octoai"
+Requires-Dist: openai; extra == "embed-octoai"
 Provides-Extra: embed-vertexai
 Requires-Dist: vertexai; extra == "embed-vertexai"
 Provides-Extra: embed-voyageai
@@ -201,8 +201,8 @@ Requires-Dist: voyageai; extra == "embed-voyageai"
 Provides-Extra: embed-mixedbreadai
 Requires-Dist: mixedbread-ai; extra == "embed-mixedbreadai"
 Provides-Extra: openai
-Requires-Dist: openai; extra == "openai"
 Requires-Dist: tiktoken; extra == "openai"
+Requires-Dist: openai; extra == "openai"
 Provides-Extra: bedrock
 Requires-Dist: aioboto3; extra == "bedrock"
 Requires-Dist: boto3; extra == "bedrock"

{unstructured_ingest-0.5.15.dist-info → unstructured_ingest-0.5.16.dist-info}/RECORD

@@ -25,7 +25,7 @@ test/integration/connectors/test_redis.py,sha256=1aKwOb-K4zCxZwHmgW_WzGJwqLntbWT
 test/integration/connectors/test_s3.py,sha256=E1dypeag_E3OIfpQWIz3jb7ctRHRD63UtyTrzyvJzpc,7473
 test/integration/connectors/test_sharepoint.py,sha256=weGby5YD6se7R7KLEq96hxUZYPzwoqZqXXTPhtQWZsQ,7646
 test/integration/connectors/test_vectara.py,sha256=4kKOOTGUjeZw2jKRcgVDI7ifbRPRZfjjVO4d_7H5C6I,8710
-test/integration/connectors/test_zendesk.py,sha256=Jc1GcMBnCrpzm6_6tJi-FdYxSs15xnp94a7kVwrObMc,4167
+test/integration/connectors/test_zendesk.py,sha256=nMBVNlEQr1uvmI1fzUC1bmoa2doXnYp5n4bMJS2FN-o,3727
 test/integration/connectors/databricks/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 test/integration/connectors/databricks/test_volumes_native.py,sha256=KqiapQAV0s_Zv0CO8BwYoiCk30dwrSZzuigUWNRIem0,9559
 test/integration/connectors/discord/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -52,7 +52,7 @@ test/integration/connectors/utils/docker_compose.py,sha256=GVTB6Cel05c0VQ2n4AwkQ
 test/integration/connectors/utils/validation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 test/integration/connectors/utils/validation/destination.py,sha256=HUdwpvszGOuGnKZFawGdxRNptbbJDIghyi-roQjhEs4,2697
 test/integration/connectors/utils/validation/equality.py,sha256=R6d_1c-Si5518WJcBcshF_wBRnywnZ0ORQ-NL0xNmGo,2602
-test/integration/connectors/utils/validation/source.py,sha256=xnAZI26ILdeMhgrWAGrU2N2fqK58YNGkfyUhJekZ0Ho,13541
+test/integration/connectors/utils/validation/source.py,sha256=tIZHrLONlU6nfrTesC_tymSxYOkZyIyM4UuTtvqyjr8,13652
 test/integration/connectors/utils/validation/utils.py,sha256=xYYvAbqP6_lZyH09_JjB4w2Sf8aQPvDVT5vZTs05ILs,1428
 test/integration/connectors/weaviate/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 test/integration/connectors/weaviate/conftest.py,sha256=6Q6QdrLJmGHowRFSmoVSzup2EX6qASfS2Z5tqlpTm9M,387
@@ -111,7 +111,7 @@ test/unit/v2/partitioners/test_partitioner.py,sha256=iIYg7IpftV3LusoO4H8tr1IHY1U
 test/unit/v2/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 test/unit/v2/utils/data_generator.py,sha256=UoYVNjG4S4wlaA9gceQ82HIpF9_6I1UTHD1_GrQBHp0,973
 unstructured_ingest/__init__.py,sha256=U4S_2y3zgLZVfMenHRaJFBW8yqh2mUBuI291LGQVOJ8,35
-unstructured_ingest/__version__.py,sha256=noAC1JV7rAfkk9NQctRgYOifiiASnPhPSbtOr9y3Hkk,43
+unstructured_ingest/__version__.py,sha256=EgX3pL6NG5u1RONYNW1ysr-stCliU2U7MUb-vn-absY,43
 unstructured_ingest/error.py,sha256=qDncnJgbf5ils956RcO2CGlAKYDT5OaEM9Clv1JVTNc,1448
 unstructured_ingest/interfaces.py,sha256=7DOnDpGvUNlCoFR7UPRGmOarqH5sFtuUOO5vf8X3oTM,31489
 unstructured_ingest/logger.py,sha256=S5nSqGcABoQyeicgRnBQFjDScCaTvFVivOCvbo-laL0,4479
@@ -411,10 +411,10 @@ unstructured_ingest/v2/pipeline/otel.py,sha256=K3pQvWVgWzyOWMKCBUofsH7wTZPJ0Ysw5
 unstructured_ingest/v2/pipeline/pipeline.py,sha256=m3m9F9wZsCEhsFK_0WZv5_ENl2M42VHBV6Vc39t90v8,16842
 unstructured_ingest/v2/pipeline/steps/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 unstructured_ingest/v2/pipeline/steps/chunk.py,sha256=s2BY2v1cs_ImTsPrg8J-92k-fV73b61nDiSy4p9736k,3223
-unstructured_ingest/v2/pipeline/steps/download.py,sha256=nZ4B0d9p-6TgWqrBoKUQPlr8m6dz1RGNr_3OjUhRpWg,8259
+unstructured_ingest/v2/pipeline/steps/download.py,sha256=umfKzObfbhQe3iFLWlLW3T9zB-Uj1FGOE-OkQ0MkGmY,8260
 unstructured_ingest/v2/pipeline/steps/embed.py,sha256=HPQgEWvVrpThUD1FB9k7XNiARXkd6rb4lnpxTGmEQxI,3201
 unstructured_ingest/v2/pipeline/steps/filter.py,sha256=pju7knTSbB2ll1jC9DPePRDnHlOlvEcU1-sjk6xYGGc,1211
-unstructured_ingest/v2/pipeline/steps/index.py,sha256=m0BbUwe_7s_gFxR9K31IJdAf3_GgKXXajGJec5jcSXA,3557
+unstructured_ingest/v2/pipeline/steps/index.py,sha256=JrPIwMV3S-t2pPwJ00OfOoULgYzvMY1Q-HFgXXpP4H4,3563
 unstructured_ingest/v2/pipeline/steps/partition.py,sha256=yE4HFFyORhnzH25PoJG6MNquMXqpzAznyf9NoZYBV5E,3284
 unstructured_ingest/v2/pipeline/steps/stage.py,sha256=VR8SLUJdVva61aieVKyxUHzupTCQbQeaMA0CKu4Fx7o,2347
 unstructured_ingest/v2/pipeline/steps/uncompress.py,sha256=p2nPFGbcpivPAZO5jDogTfn0iaL5bCFsgBNMejxVbzE,1768
@@ -460,7 +460,7 @@ unstructured_ingest/v2/processes/connectors/databricks/volumes_aws.py,sha256=h6q
 unstructured_ingest/v2/processes/connectors/databricks/volumes_azure.py,sha256=gjICJJwhDHBLt_L-LrMlvJ3DL1DYtwFpyMLb_zYvOIg,3755
 unstructured_ingest/v2/processes/connectors/databricks/volumes_gcp.py,sha256=Uss3XPPaq1AsqJOEy4RJgBJw2-bTjrXH2PgtVNYd2w0,3006
 unstructured_ingest/v2/processes/connectors/databricks/volumes_native.py,sha256=g1qYnIrML4TjN7rmC0MGrD5JzAprb6SymBHlEdOumz0,3113
-unstructured_ingest/v2/processes/connectors/databricks/volumes_table.py,sha256=2KNLwDZJDhsMAUGCzktEIn4Lvb0nxLWabBOPJbgyoEE,5010
+unstructured_ingest/v2/processes/connectors/databricks/volumes_table.py,sha256=FZhjrMYBr_je6mWYp7MUUvyKR9YwGD2HiNljeT7U5ws,5044
 unstructured_ingest/v2/processes/connectors/duckdb/__init__.py,sha256=5sVvJCWhU-YkjHIwk4W6BZCanFYK5W4xTpWtQ8xzeB4,561
 unstructured_ingest/v2/processes/connectors/duckdb/base.py,sha256=IHaY1mWuidt6GDEJhB1c_orwmjeyXuRCVJ88djYDciM,2793
 unstructured_ingest/v2/processes/connectors/duckdb/duckdb.py,sha256=oUHHaLpO2pWW2Lu4Mc-XFjrA0ze97205WQ_xP95ua4M,4296
@@ -573,13 +573,13 @@ unstructured_ingest/v2/processes/connectors/weaviate/embedded.py,sha256=S8Zg8Stu
 unstructured_ingest/v2/processes/connectors/weaviate/local.py,sha256=LuTBKPseVewsz8VqxRPRLfGEm3BeI9nBZxpy7ZU5tOA,2201
 unstructured_ingest/v2/processes/connectors/weaviate/weaviate.py,sha256=UZ_s8dnVNx9BWFG2fPah4VbQbgEDF4nP78bQeU3jg08,12821
 unstructured_ingest/v2/processes/connectors/zendesk/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-unstructured_ingest/v2/processes/connectors/zendesk/client.py,sha256=MNyI6SUuxZHf_6zONoC6jR2f9BvyTYoMyGKDOhl4kgs,7897
-unstructured_ingest/v2/processes/connectors/zendesk/zendesk.py,sha256=vQHZa5YYiDPXXPRAPMnPXhh0QzXeiBVx_YIWskZBQIc,15465
+unstructured_ingest/v2/processes/connectors/zendesk/client.py,sha256=DDAYQB7catKfyGKxB5sfTwbOxrDj_NfWxrN372vA5Gc,11955
+unstructured_ingest/v2/processes/connectors/zendesk/zendesk.py,sha256=R8SXYkRhVUoWEHdGCt2CzcTxxuFundw_0GlGZ34YmbM,8987
 unstructured_ingest/v2/processes/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 unstructured_ingest/v2/processes/utils/blob_storage.py,sha256=EWvK4HRYubr9i1UyMhv5cU9u0UzVkCDC_BIm4Uxab7Y,964
-unstructured_ingest-0.5.15.dist-info/LICENSE.md,sha256=SxkKP_62uIAKb9mb1eH7FH4Kn2aYT09fgjKpJt5PyTk,11360
-unstructured_ingest-0.5.15.dist-info/METADATA,sha256=TimVS8ZngyfFUMhuD317dXl6nlI9acBRC_LxZWZczuU,8465
-unstructured_ingest-0.5.15.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-unstructured_ingest-0.5.15.dist-info/entry_points.txt,sha256=gUAAFnjFPnBgThJSEbw0N5ZjxtaKlT1s9e05_arQrNw,70
-unstructured_ingest-0.5.15.dist-info/top_level.txt,sha256=DMuDMHZRMdeay8v8Kdi855muIv92F0OkutvBCaBEW6M,25
-unstructured_ingest-0.5.15.dist-info/RECORD,,
+unstructured_ingest-0.5.16.dist-info/LICENSE.md,sha256=SxkKP_62uIAKb9mb1eH7FH4Kn2aYT09fgjKpJt5PyTk,11360
+unstructured_ingest-0.5.16.dist-info/METADATA,sha256=Sm1qizGZbPHlXmzpcPhDuIsO-uWO-mrpfQZhovwhTQI,8465
+unstructured_ingest-0.5.16.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+unstructured_ingest-0.5.16.dist-info/entry_points.txt,sha256=gUAAFnjFPnBgThJSEbw0N5ZjxtaKlT1s9e05_arQrNw,70
+unstructured_ingest-0.5.16.dist-info/top_level.txt,sha256=DMuDMHZRMdeay8v8Kdi855muIv92F0OkutvBCaBEW6M,25
+unstructured_ingest-0.5.16.dist-info/RECORD,,