merge feat/plugins

api/core/rag/extractor/excel_extractor.py

@@ -4,7 +4,7 @@ import os
 from typing import Optional, cast
 
 import pandas as pd
-from openpyxl import load_workbook
+from openpyxl import load_workbook  # type: ignore
 
 from core.rag.extractor.extractor_base import BaseExtractor
 from core.rag.models.document import Document

api/core/rag/extractor/extract_processor.py

@@ -24,7 +24,6 @@ from core.rag.extractor.unstructured.unstructured_markdown_extractor import Unst
 from core.rag.extractor.unstructured.unstructured_msg_extractor import UnstructuredMsgExtractor
 from core.rag.extractor.unstructured.unstructured_ppt_extractor import UnstructuredPPTExtractor
 from core.rag.extractor.unstructured.unstructured_pptx_extractor import UnstructuredPPTXExtractor
-from core.rag.extractor.unstructured.unstructured_text_extractor import UnstructuredTextExtractor
 from core.rag.extractor.unstructured.unstructured_xml_extractor import UnstructuredXmlExtractor
 from core.rag.extractor.word_extractor import WordExtractor
 from core.rag.models.document import Document
@@ -103,12 +102,11 @@ class ExtractProcessor:
                 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":
@@ -141,11 +139,7 @@ class ExtractProcessor:
                         extractor = UnstructuredEpubExtractor(file_path, unstructured_api_url, unstructured_api_key)
                     else:
                         # txt
-                        extractor = (
-                            UnstructuredTextExtractor(file_path, unstructured_api_url)
-                            if is_automatic
-                            else TextExtractor(file_path, autodetect_encoding=True)
-                        )
+                        extractor = TextExtractor(file_path, autodetect_encoding=True)
                 else:
                     if file_extension in {".xlsx", ".xls"}:
                         extractor = ExcelExtractor(file_path)

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

@@ -1,5 +1,6 @@
 import base64
 import logging
+from typing import Optional
 
 from bs4 import BeautifulSoup  # type: ignore
 
@@ -15,7 +16,7 @@ class UnstructuredEmailExtractor(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: 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

@@ -19,7 +19,7 @@ class UnstructuredEpubExtractor(BaseExtractor):
         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
@@ -30,9 +30,6 @@ class UnstructuredEpubExtractor(BaseExtractor):
         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

@@ -1,4 +1,5 @@
 import logging
+from typing import Optional
 
 from core.rag.extractor.extractor_base import BaseExtractor
 from core.rag.models.document import Document
@@ -24,7 +25,7 @@ class UnstructuredMarkdownExtractor(BaseExtractor):
             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

@@ -1,4 +1,5 @@
 import logging
+from typing import Optional
 
 from core.rag.extractor.extractor_base import BaseExtractor
 from core.rag.models.document import Document
@@ -14,7 +15,7 @@ class UnstructuredMsgExtractor(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: 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

@@ -1,4 +1,5 @@
 import logging
+from typing import Optional
 
 from core.rag.extractor.extractor_base import BaseExtractor
 from core.rag.models.document import Document
@@ -14,7 +15,7 @@ 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: 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

@@ -1,4 +1,5 @@
 import logging
+from typing import Optional
 
 from core.rag.extractor.extractor_base import BaseExtractor
 from core.rag.models.document import Document
@@ -14,7 +15,7 @@ class UnstructuredPPTXExtractor(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: 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

@@ -1,4 +1,5 @@
 import logging
+from typing import Optional
 
 from core.rag.extractor.extractor_base import BaseExtractor
 from core.rag.models.document import Document
@@ -14,7 +15,7 @@ class UnstructuredXmlExtractor(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: Optional[str] = None, api_key: str = ""):
         """Initialize with file path."""
         self._file_path = file_path
         self._api_url = api_url

api/core/rag/extractor/word_extractor.py

@@ -267,8 +267,10 @@ class WordExtractor(BaseExtractor):
                 if isinstance(element.tag, str) and element.tag.endswith("p"):  # paragraph
                     para = paragraphs.pop(0)
                     parsed_paragraph = parse_paragraph(para)
-                    if parsed_paragraph:
+                    if parsed_paragraph.strip():
                         content.append(parsed_paragraph)
+                    else:
+                        content.append("\n")
                 elif isinstance(element.tag, str) and element.tag.endswith("tbl"):  # table
                     table = tables.pop(0)
                     content.append(self._table_to_markdown(table, image_map))