fix unstructured api,remove unused parameters (#3056)

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

@@ -26,7 +26,7 @@ class UnstructuredEmailExtractor(BaseExtractor):
 
     def extract(self) -> list[Document]:
         from unstructured.partition.email import partition_email
-        elements = partition_email(filename=self._file_path, api_url=self._api_url)
+        elements = partition_email(filename=self._file_path)
 
         # noinspection PyBroadException
         try:

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

@@ -36,7 +36,7 @@ class UnstructuredMarkdownExtractor(BaseExtractor):
     def extract(self) -> list[Document]:
         from unstructured.partition.md import partition_md
 
-        elements = partition_md(filename=self._file_path, api_url=self._api_url)
+        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 = []

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

@@ -26,7 +26,7 @@ class UnstructuredMsgExtractor(BaseExtractor):
     def extract(self) -> list[Document]:
         from unstructured.partition.msg import partition_msg
 
-        elements = partition_msg(filename=self._file_path, api_url=self._api_url)
+        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 = []

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

@@ -24,9 +24,9 @@ class UnstructuredPPTExtractor(BaseExtractor):
         self._api_url = api_url
 
     def extract(self) -> list[Document]:
-        from unstructured.partition.ppt import partition_ppt
+        from unstructured.partition.api import partition_via_api
 
-        elements = partition_ppt(filename=self._file_path, api_url=self._api_url)
+        elements = partition_via_api(filename=self._file_path, api_url=self._api_url)
         text_by_page = {}
         for element in elements:
             page = element.metadata.page_number

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

@@ -26,7 +26,7 @@ class UnstructuredPPTXExtractor(BaseExtractor):
     def extract(self) -> list[Document]:
         from unstructured.partition.pptx import partition_pptx
 
-        elements = partition_pptx(filename=self._file_path, api_url=self._api_url)
+        elements = partition_pptx(filename=self._file_path)
         text_by_page = {}
         for element in elements:
             page = element.metadata.page_number

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

@@ -26,7 +26,7 @@ class UnstructuredTextExtractor(BaseExtractor):
     def extract(self) -> list[Document]:
         from unstructured.partition.text import partition_text
 
-        elements = partition_text(filename=self._file_path, api_url=self._api_url)
+        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 = []

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

@@ -26,7 +26,7 @@ class UnstructuredXmlExtractor(BaseExtractor):
     def extract(self) -> list[Document]:
         from unstructured.partition.xml import partition_xml
 
-        elements = partition_xml(filename=self._file_path, xml_keep_tags=True, api_url=self._api_url)
+        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 = []