Skip to content

feat(document_extractor): integrate unstructured API for PPTX extraction #10180

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Nov 1, 2024
Merged

feat(document_extractor): integrate unstructured API for PPTX extraction #10180

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
32d828d
feat(document_extractor): integrate unstructured API for PPTX extraction
laipz8200 Nov 1, 2024
c23528c
fix(document_extractor): streamline PPTX text extraction logic
laipz8200 Nov 1, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 10 additions & 1 deletion api/core/workflow/nodes/document_extractor/node.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,12 +6,14 @@
import pandas as pd
import pypdfium2
import yaml
from unstructured.partition.api import partition_via_api
from unstructured.partition.email import partition_email
from unstructured.partition.epub import partition_epub
from unstructured.partition.msg import partition_msg
from unstructured.partition.ppt import partition_ppt
from unstructured.partition.pptx import partition_pptx

from configs import dify_config
from core.file import File, FileTransferMethod, file_manager
from core.helper import ssrf_proxy
from core.variables import ArrayFileSegment
Expand Down Expand Up @@ -263,7 +265,14 @@ def _extract_text_from_ppt(file_content: bytes) -> str:
def _extract_text_from_pptx(file_content: bytes) -> str:
try:
with io.BytesIO(file_content) as file:
elements = partition_pptx(file=file)
if dify_config.UNSTRUCTURED_API_URL and dify_config.UNSTRUCTURED_API_KEY:
elements = partition_via_api(
file=file,
api_url=dify_config.UNSTRUCTURED_API_URL,
api_key=dify_config.UNSTRUCTURED_API_KEY,
)
else:
elements = partition_pptx(file=file)
return "\n".join([getattr(element, "text", "") for element in elements])
except Exception as e:
raise TextExtractionError(f"Failed to extract text from PPTX: {str(e)}") from e
Expand Down