estel/dify
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

remove unstructured pdf extract (#9794)

Browse Source
This commit is contained in:
Jyong
2024-10-24 18:13:05 +08:00
committed by GitHub
parent d018b32d0b
commit 5f11fe521d
1 changed files with 1 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
api/core/rag/extractor/extract_processor.py
View File

@@ -21,7 +21,6 @@ from core.rag.extractor.unstructured.unstructured_eml_extractor import Unstructu
from core.rag.extractor.unstructured.unstructured_epub_extractor import UnstructuredEpubExtractor from core.rag.extractor.unstructured.unstructured_epub_extractor import UnstructuredEpubExtractor
from core.rag.extractor.unstructured.unstructured_markdown_extractor import UnstructuredMarkdownExtractor from core.rag.extractor.unstructured.unstructured_markdown_extractor import UnstructuredMarkdownExtractor
from core.rag.extractor.unstructured.unstructured_msg_extractor import UnstructuredMsgExtractor from core.rag.extractor.unstructured.unstructured_msg_extractor import UnstructuredMsgExtractor
from core.rag.extractor.unstructured.unstructured_pdf_extractor import UnstructuredPDFExtractor
from core.rag.extractor.unstructured.unstructured_ppt_extractor import UnstructuredPPTExtractor from core.rag.extractor.unstructured.unstructured_ppt_extractor import UnstructuredPPTExtractor
from core.rag.extractor.unstructured.unstructured_pptx_extractor import UnstructuredPPTXExtractor from core.rag.extractor.unstructured.unstructured_pptx_extractor import UnstructuredPPTXExtractor
from core.rag.extractor.unstructured.unstructured_text_extractor import UnstructuredTextExtractor from core.rag.extractor.unstructured.unstructured_text_extractor import UnstructuredTextExtractor
@@ -103,7 +102,7 @@ class ExtractProcessor:
if file_extension in {".xlsx", ".xls"}: if file_extension in {".xlsx", ".xls"}:
extractor = ExcelExtractor(file_path) extractor = ExcelExtractor(file_path)
elif file_extension == ".pdf": elif file_extension == ".pdf":
extractor = UnstructuredPDFExtractor(file_path, unstructured_api_url, unstructured_api_key) extractor = PdfExtractor(file_path)
elif file_extension in {".md", ".markdown"}: elif file_extension in {".md", ".markdown"}:
extractor = ( extractor = (
UnstructuredMarkdownExtractor(file_path, unstructured_api_url, unstructured_api_key) UnstructuredMarkdownExtractor(file_path, unstructured_api_url, unstructured_api_key)