chore(api/core): apply ruff reformatting (#7624)

api/core/rag/extractor/unstructured/unstructured_doc_extractor.py

@@ -8,13 +8,12 @@ logger = logging.getLogger(__name__)
 
 
 class UnstructuredWordExtractor(BaseExtractor):
-    """Loader that uses unstructured to load word documents.
-    """
+    """Loader that uses unstructured to load word documents."""
 
     def __init__(
-            self,
-            file_path: str,
-            api_url: str,
+        self,
+        file_path: str,
+        api_url: str,
     ):
         """Initialize with file path."""
         self._file_path = file_path
@@ -24,9 +23,7 @@ class UnstructuredWordExtractor(BaseExtractor):
         from unstructured.__version__ import __version__ as __unstructured_version__
         from unstructured.file_utils.filetype import FileType, detect_filetype
 
-        unstructured_version = tuple(
-            int(x) for x in __unstructured_version__.split(".")
-        )
+        unstructured_version = tuple(int(x) for x in __unstructured_version__.split("."))
         # check the file extension
         try:
             import magic  # noqa: F401
@@ -53,6 +50,7 @@ class UnstructuredWordExtractor(BaseExtractor):
             elements = partition_docx(filename=self._file_path)
 
         from unstructured.chunking.title import chunk_by_title
+
         chunks = chunk_by_title(elements, max_characters=2000, combine_text_under_n_chars=2000)
         documents = []
         for chunk in chunks:

api/core/rag/extractor/unstructured/unstructured_eml_extractor.py

@@ -26,6 +26,7 @@ class UnstructuredEmailExtractor(BaseExtractor):
 
     def extract(self) -> list[Document]:
         from unstructured.partition.email import partition_email
+
         elements = partition_email(filename=self._file_path)
 
         # noinspection PyBroadException
@@ -34,15 +35,16 @@ class UnstructuredEmailExtractor(BaseExtractor):
                 element_text = element.text.strip()
 
                 padding_needed = 4 - len(element_text) % 4
-                element_text += '=' * padding_needed
+                element_text += "=" * padding_needed
 
                 element_decode = base64.b64decode(element_text)
-                soup = BeautifulSoup(element_decode.decode('utf-8'), 'html.parser')
+                soup = BeautifulSoup(element_decode.decode("utf-8"), "html.parser")
                 element.text = soup.get_text()
         except Exception:
             pass
 
         from unstructured.chunking.title import chunk_by_title
+
         chunks = chunk_by_title(elements, max_characters=2000, combine_text_under_n_chars=2000)
         documents = []
         for chunk in chunks:

api/core/rag/extractor/unstructured/unstructured_epub_extractor.py

@@ -28,6 +28,7 @@ class UnstructuredEpubExtractor(BaseExtractor):
 
         elements = partition_epub(filename=self._file_path, xml_keep_tags=True)
         from unstructured.chunking.title import chunk_by_title
+
         chunks = chunk_by_title(elements, max_characters=2000, combine_text_under_n_chars=2000)
         documents = []
         for chunk in chunks:

api/core/rag/extractor/unstructured/unstructured_markdown_extractor.py

@@ -38,6 +38,7 @@ class UnstructuredMarkdownExtractor(BaseExtractor):
 
         elements = partition_md(filename=self._file_path)
         from unstructured.chunking.title import chunk_by_title
+
         chunks = chunk_by_title(elements, max_characters=2000, combine_text_under_n_chars=2000)
         documents = []
         for chunk in chunks:

api/core/rag/extractor/unstructured/unstructured_msg_extractor.py

@@ -14,11 +14,7 @@ class UnstructuredMsgExtractor(BaseExtractor):
         file_path: Path to the file to load.
     """
 
-    def __init__(
-        self,
-        file_path: str,
-        api_url: str
-    ):
+    def __init__(self, file_path: str, api_url: str):
         """Initialize with file path."""
         self._file_path = file_path
         self._api_url = api_url
@@ -28,6 +24,7 @@ class UnstructuredMsgExtractor(BaseExtractor):
 
         elements = partition_msg(filename=self._file_path)
         from unstructured.chunking.title import chunk_by_title
+
         chunks = chunk_by_title(elements, max_characters=2000, combine_text_under_n_chars=2000)
         documents = []
         for chunk in chunks:

api/core/rag/extractor/unstructured/unstructured_ppt_extractor.py

@@ -14,12 +14,7 @@ class UnstructuredPPTExtractor(BaseExtractor):
         file_path: Path to the file to load.
     """
 
-    def __init__(
-            self,
-            file_path: str,
-            api_url: str,
-            api_key: str
-    ):
+    def __init__(self, file_path: str, api_url: str, api_key: str):
         """Initialize with file path."""
         self._file_path = file_path
         self._api_url = api_url

api/core/rag/extractor/unstructured/unstructured_pptx_extractor.py

@@ -14,11 +14,7 @@ class UnstructuredPPTXExtractor(BaseExtractor):
         file_path: Path to the file to load.
     """
 
-    def __init__(
-            self,
-            file_path: str,
-            api_url: str
-    ):
+    def __init__(self, file_path: str, api_url: str):
         """Initialize with file path."""
         self._file_path = file_path
         self._api_url = api_url

api/core/rag/extractor/unstructured/unstructured_text_extractor.py

@@ -14,11 +14,7 @@ class UnstructuredTextExtractor(BaseExtractor):
         file_path: Path to the file to load.
     """
 
-    def __init__(
-        self,
-        file_path: str,
-        api_url: str
-    ):
+    def __init__(self, file_path: str, api_url: str):
         """Initialize with file path."""
         self._file_path = file_path
         self._api_url = api_url
@@ -28,6 +24,7 @@ class UnstructuredTextExtractor(BaseExtractor):
 
         elements = partition_text(filename=self._file_path)
         from unstructured.chunking.title import chunk_by_title
+
         chunks = chunk_by_title(elements, max_characters=2000, combine_text_under_n_chars=2000)
         documents = []
         for chunk in chunks:

api/core/rag/extractor/unstructured/unstructured_xml_extractor.py

@@ -14,11 +14,7 @@ class UnstructuredXmlExtractor(BaseExtractor):
         file_path: Path to the file to load.
     """
 
-    def __init__(
-        self,
-        file_path: str,
-        api_url: str
-    ):
+    def __init__(self, file_path: str, api_url: str):
         """Initialize with file path."""
         self._file_path = file_path
         self._api_url = api_url
@@ -28,6 +24,7 @@ class UnstructuredXmlExtractor(BaseExtractor):
 
         elements = partition_xml(filename=self._file_path, xml_keep_tags=True)
         from unstructured.chunking.title import chunk_by_title
+
         chunks = chunk_by_title(elements, max_characters=2000, combine_text_under_n_chars=2000)
         documents = []
         for chunk in chunks: