OpenWebUI/open-webui
1
0
Fork 0
mirror of https://github.com/open-webui/open-webui synced 2025-05-21 21:46:22 +00:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity

fix: fix DoclingLoader input params

Browse Source
This commit is contained in:
Fabio Polito 2025-03-05 17:53:45 +00:00
parent 2419ef06a0
commit a44b35e99e
1 changed files with 37 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
backend/open_webui/retrieval/loaders/main.py
View File

@ -126,10 +126,29 @@ class DoclingLoader:
raise ValueError("File path is required for DoclingLoader") raise ValueError("File path is required for DoclingLoader")
with open(self.file_path, "rb") as f: with open(self.file_path, "rb") as f:
files = {"files": (self.file_path, f, self.mime_type or "application/octet-stream")} files = {
"files": (
self.file_path,
f,
self.mime_type or "application/octet-stream",
)
}
params = { params = {
"from_formats": ["docx", "pptx", "html", "xml_pubmed", "image", "pdf", "asciidoc", "md", "xlsx", "xml_uspto", "json_docling"], "from_formats": [
"docx",
"pptx",
"html",
"image",
"pdf",
"asciidoc",
"md",
"csv",
"xlsx",
"xml_uspto",
"xml_jats",
"json_docling",
],
"to_formats": ["md"], "to_formats": ["md"],
"image_export_mode": "placeholder", "image_export_mode": "placeholder",
"do_ocr": True, "do_ocr": True,
@ -137,7 +156,7 @@ class DoclingLoader:
"ocr_engine": "easyocr", "ocr_engine": "easyocr",
"ocr_lang": None, "ocr_lang": None,
"pdf_backend": "dlparse_v2", "pdf_backend": "dlparse_v2",
"table_mode": "fast", "table_mode": "accurate",
"abort_on_error": False, "abort_on_error": False,
"return_as_file": False, "return_as_file": False,
"do_table_structure": True, "do_table_structure": True,