fix unstructured setting (#12116)

api/configs/feature/__init__.py

 
     UNSTRUCTURED_API_KEY: Optional[str] = Field(
         description="API key for Unstructured.io service",
-        default=None,
+        default="",
     )
 
     SCARF_NO_ANALYTICS: Optional[str] = Field(

api/core/rag/extractor/extract_processor.py

                 input_file = Path(file_path)
                 file_extension = input_file.suffix.lower()
                 etl_type = dify_config.ETL_TYPE
-                unstructured_api_url = dify_config.UNSTRUCTURED_API_URL
-                unstructured_api_key = dify_config.UNSTRUCTURED_API_KEY
-                assert unstructured_api_url is not None, "unstructured_api_url is required"
-                assert unstructured_api_key is not None, "unstructured_api_key is required"
                 extractor: Optional[BaseExtractor] = None
                 if etl_type == "Unstructured":
+                    unstructured_api_url = dify_config.UNSTRUCTURED_API_URL
+                    unstructured_api_key = dify_config.UNSTRUCTURED_API_KEY or ""
+
                     if file_extension in {".xlsx", ".xls"}:
                         extractor = ExcelExtractor(file_path)
                     elif file_extension == ".pdf":

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

 import base64
 import logging
+from typing import Optional
 
 from bs4 import BeautifulSoup  # type: ignore
 
         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: Optional[str] = None, api_key: str = ""):
         """Initialize with file path."""
         self._file_path = file_path
         self._api_url = api_url

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

         self,
         file_path: str,
         api_url: Optional[str] = None,
-        api_key: Optional[str] = None,
+        api_key: str = "",
     ):
         """Initialize with file path."""
         self._file_path = file_path
         if self._api_url:
             from unstructured.partition.api import partition_via_api
 
-            if self._api_key is None:
-                raise ValueError("api_key is required")
-
             elements = partition_via_api(filename=self._file_path, api_url=self._api_url, api_key=self._api_key)
         else:
             from unstructured.partition.epub import partition_epub

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

 import logging
+from typing import Optional
 
 from core.rag.extractor.extractor_base import BaseExtractor
 from core.rag.models.document import Document
             if the specified encoding fails.
     """
 
-    def __init__(self, file_path: str, api_url: str, api_key: str):
+    def __init__(self, file_path: str, api_url: Optional[str] = None, api_key: str = ""):
         """Initialize with file path."""
         self._file_path = file_path
         self._api_url = api_url

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

 import logging
+from typing import Optional
 
 from core.rag.extractor.extractor_base import BaseExtractor
 from core.rag.models.document import Document
         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: Optional[str] = None, api_key: str = ""):
         """Initialize with file path."""
         self._file_path = file_path
         self._api_url = api_url

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

 import logging
+from typing import Optional
 
 from core.rag.extractor.extractor_base import BaseExtractor
 from core.rag.models.document import Document
         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: Optional[str] = None, 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

 import logging
+from typing import Optional
 
 from core.rag.extractor.extractor_base import BaseExtractor
 from core.rag.models.document import Document
         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: Optional[str] = None, api_key: str = ""):
         """Initialize with file path."""
         self._file_path = file_path
         self._api_url = api_url

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

 import logging
+from typing import Optional
 
 from core.rag.extractor.extractor_base import BaseExtractor
 from core.rag.models.document import Document
         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: Optional[str] = None, api_key: str = ""):
         """Initialize with file path."""
         self._file_path = file_path
         self._api_url = api_url