jandres/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-02-24 09:55:09 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

fix(workflow): fix document extractor typing and factory construction

Browse Source
This commit is contained in:
-LAN-
2026-02-16 19:33:30 +08:00
parent eca97b9083
commit cf9216f3ad
2 changed files with 10 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
api/core/app/workflow/node_factory.py
View File

@@ -1,5 +1,5 @@
from collections.abc import Callable, Sequence
from typing import TYPE_CHECKING, Any, cast, final
from typing import TYPE_CHECKING, Any, final
from typing_extensions import override
@@ -160,8 +160,7 @@ class DifyNodeFactory(NodeFactory):
)
if node_type == NodeType.DOCUMENT_EXTRACTOR:
document_extractor_class = cast(type[DocumentExtractorNode], node_class)
return document_extractor_class(
return DocumentExtractorNode(
**common_kwargs,
unstructured_api_config=self._document_extractor_unstructured_api_config,
)

12
api/core/workflow/nodes/document_extractor/node.py
View File

@@ -353,6 +353,7 @@ def _extract_text_from_doc(file_content: bytes, *, unstructured_api_config: Unst
if not unstructured_api_config.api_url:
raise TextExtractionError("Unstructured API URL is not configured for DOC file processing.")
api_key = unstructured_api_config.api_key or ""
try:
with tempfile.NamedTemporaryFile(suffix=".doc", delete=False) as temp_file:
@@ -363,7 +364,7 @@ def _extract_text_from_doc(file_content: bytes, *, unstructured_api_config: Unst
file=file,
metadata_filename=temp_file.name,
api_url=unstructured_api_config.api_url,
api_key=unstructured_api_config.api_key,
api_key=api_key,
)
os.unlink(temp_file.name)
return "\n".join([getattr(element, "text", "") for element in elements])
@@ -561,6 +562,7 @@ def _extract_text_from_excel(file_content: bytes) -> str:
def _extract_text_from_ppt(file_content: bytes, *, unstructured_api_config: UnstructuredApiConfig) -> str:
from unstructured.partition.api import partition_via_api
from unstructured.partition.ppt import partition_ppt
api_key = unstructured_api_config.api_key or ""
try:
if unstructured_api_config.api_url:
@@ -572,7 +574,7 @@ def _extract_text_from_ppt(file_content: bytes, *, unstructured_api_config: Unst
file=file,
metadata_filename=temp_file.name,
api_url=unstructured_api_config.api_url,
api_key=unstructured_api_config.api_key,
api_key=api_key,
)
os.unlink(temp_file.name)
else:
@@ -587,6 +589,7 @@ def _extract_text_from_ppt(file_content: bytes, *, unstructured_api_config: Unst
def _extract_text_from_pptx(file_content: bytes, *, unstructured_api_config: UnstructuredApiConfig) -> str:
from unstructured.partition.api import partition_via_api
from unstructured.partition.pptx import partition_pptx
api_key = unstructured_api_config.api_key or ""
try:
if unstructured_api_config.api_url:
@@ -598,7 +601,7 @@ def _extract_text_from_pptx(file_content: bytes, *, unstructured_api_config: Uns
file=file,
metadata_filename=temp_file.name,
api_url=unstructured_api_config.api_url,
api_key=unstructured_api_config.api_key,
api_key=api_key,
)
os.unlink(temp_file.name)
else:
@@ -612,6 +615,7 @@ def _extract_text_from_pptx(file_content: bytes, *, unstructured_api_config: Uns
def _extract_text_from_epub(file_content: bytes, *, unstructured_api_config: UnstructuredApiConfig) -> str:
from unstructured.partition.api import partition_via_api
from unstructured.partition.epub import partition_epub
api_key = unstructured_api_config.api_key or ""
try:
if unstructured_api_config.api_url:
@@ -623,7 +627,7 @@ def _extract_text_from_epub(file_content: bytes, *, unstructured_api_config: Uns
file=file,
metadata_filename=temp_file.name,
api_url=unstructured_api_config.api_url,
api_key=unstructured_api_config.api_key,
api_key=api_key,
)
os.unlink(temp_file.name)
else: