hz/ebiz-dify-ai
1
0
Fork 0
mirror of http://112.124.100.131/huang.ze/ebiz-dify-ai.git synced 2025-12-11 11:56:53 +08:00
Code Issues Packages Projects Releases Wiki Activity

Added description for .ppt, specify the reason for unstructured.io (#9452)

Browse Source 
Co-authored-by: crazywoola <427733928@qq.com>
This commit is contained in:
Zixuan Cheng
2024-10-24 07:13:06 -07:00
committed by GitHub
parent e71f494839
commit 88dec6ef2b
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
api/core/rag/extractor/extract_processor.py
View File

@@ -121,6 +121,8 @@ class ExtractProcessor:
extractor = UnstructuredEmailExtractor(file_path, unstructured_api_url, unstructured_api_key) extractor = UnstructuredEmailExtractor(file_path, unstructured_api_url, unstructured_api_key)
elif file_extension == ".ppt": elif file_extension == ".ppt":
extractor = UnstructuredPPTExtractor(file_path, unstructured_api_url, unstructured_api_key) extractor = UnstructuredPPTExtractor(file_path, unstructured_api_url, unstructured_api_key)
# You must first specify the API key
# because unstructured_api_key is necessary to parse .ppt documents
elif file_extension == ".pptx": elif file_extension == ".pptx":
extractor = UnstructuredPPTXExtractor(file_path, unstructured_api_url, unstructured_api_key) extractor = UnstructuredPPTXExtractor(file_path, unstructured_api_url, unstructured_api_key)
elif file_extension == ".xml": elif file_extension == ".xml":