jyapayne/dify
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

add doc support in knowledge base for unstructured (#17352)

Browse source
This commit is contained in:
Jyong 2025-04-02 21:35:01 +08:00 • committed by GitHub
commit 6104b91d3f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 9 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

12
api/core/rag/extractor/unstructured/unstructured_doc_extractor.py
View file

@ -10,14 +10,11 @@ logger = logging.getLogger(__name__)
class UnstructuredWordExtractor(BaseExtractor):
"""Loader that uses unstructured to load word documents."""
def __init__(
self,
file_path: str,
api_url: 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
self._api_key = api_key
def extract(self) -> list[Document]:
from unstructured.__version__ import __version__ as __unstructured_version__
@ -41,9 +38,10 @@ class UnstructuredWordExtractor(BaseExtractor):
)
if is_doc:
from unstructured.partition.doc import partition_doc
from unstructured.partition.api import partition_via_api
elements = partition_via_api(filename=self._file_path, api_url=self._api_url, api_key=self._api_key)
elements = partition_doc(filename=self._file_path)
else:
from unstructured.partition.docx import partition_docx