hz/ebiz-dify-ai
1
0
Fork 0
mirror of http://112.124.100.131/huang.ze/ebiz-dify-ai.git synced 2025-12-10 03:16:51 +08:00
Code Issues Packages Projects Releases Wiki Activity

Use python-docx to extract docx files (#2654)

Browse Source
This commit is contained in:
Bowen Liang
2024-03-07 18:24:55 +08:00
committed by GitHub
parent c0b82f8e58
commit b163545771
2 changed files with 11 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
api/core/rag/extractor/word_extractor.py
View File

@@ -10,7 +10,7 @@ from core.rag.models.document import Document
class WordExtractor(BaseExtractor):
"""Load pdf files.
"""Load docx files.
Args:
@@ -46,14 +46,16 @@ class WordExtractor(BaseExtractor):
def extract(self) -> list[Document]:
"""Load given path as single page."""
import docx2txt
from docx import Document as docx_Document
return [
Document(
page_content=docx2txt.process(self.file_path),
metadata={"source": self.file_path},
)
]
document = docx_Document(self.file_path)
doc_texts = [paragraph.text for paragraph in document.paragraphs]
content = '\n'.join(doc_texts)
return [Document(
page_content=content,
metadata={"source": self.file_path},
)]
@staticmethod
def _is_valid_url(url: str) -> bool: