Skip to content

Add more docling options #9

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

Open
tim-roethig wants to merge 1 commit into
base: dev
Choose a base branch
from
Open

Add more docling options #9

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
18 changes: 18 additions & 0 deletions backend/open_webui/config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2107,6 +2107,24 @@ class BannerModel(BaseModel):
os.getenv("DOCLING_OCR_LANG", "eng,fra,deu,spa"),
)

DOCLING_FORCE_OCR = PersistentConfig(
"DOCLING_FORCE_OCR",
"rag.docling_force_ocr",
os.getenv("DOCLING_FORCE_OCR", "False").lower() == "true",
)

DOCLING_IMAGE_EXPORT_MODE = PersistentConfig(
"DOCLING_IMAGE_EXPORT_MODE",
"rag.docling_image_export_mode",
os.getenv("DOCLING_IMAGE_EXPORT_MODE", "placeholder"),
)

DOCLING_TABLE_MODE = PersistentConfig(
"DOCLING_TABLE_MODE",
"rag.docling_table_mode",
os.getenv("DOCLING_TABLE_MODE", "accurate"),
)

DOCLING_DO_PICTURE_DESCRIPTION = PersistentConfig(
"DOCLING_DO_PICTURE_DESCRIPTION",
"rag.docling_do_picture_description",
Expand Down
6 changes: 5 additions & 1 deletion backend/open_webui/retrieval/loaders/main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -147,7 +147,11 @@ def load(self) -> list[Document]:
)
}

params = {"image_export_mode": "placeholder", "table_mode": "accurate"}
params = {
"image_export_mode": self.params.get("image_export_mode", "placeholder"),
"table_mode": self.params.get("table_mode", "accurate"),
"force_ocr": str(self.params.get("force_ocr", False)).lower(),
}

if self.params:
if self.params.get("do_picture_description"):
Expand Down
27 changes: 27 additions & 0 deletions backend/open_webui/routers/retrieval.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -415,6 +415,9 @@ async def get_rag_config(request: Request, user=Depends(get_admin_user)):
"DOCLING_SERVER_URL": request.app.state.config.DOCLING_SERVER_URL,
"DOCLING_OCR_ENGINE": request.app.state.config.DOCLING_OCR_ENGINE,
"DOCLING_OCR_LANG": request.app.state.config.DOCLING_OCR_LANG,
"DOCLING_FORCE_OCR": request.app.state.config.DOCLING_FORCE_OCR,
"DOCLING_IMAGE_EXPORT_MODE": request.app.state.config.DOCLING_IMAGE_EXPORT_MODE,
"DOCLING_TABLE_MODE": request.app.state.config.DOCLING_TABLE_MODE,
"DOCLING_DO_PICTURE_DESCRIPTION": request.app.state.config.DOCLING_DO_PICTURE_DESCRIPTION,
"DOCLING_PICTURE_DESCRIPTION_MODE": request.app.state.config.DOCLING_PICTURE_DESCRIPTION_MODE,
"DOCLING_PICTURE_DESCRIPTION_LOCAL": request.app.state.config.DOCLING_PICTURE_DESCRIPTION_LOCAL,
Expand Down Expand Up @@ -581,6 +584,9 @@ class ConfigForm(BaseModel):
DOCLING_SERVER_URL: Optional[str] = None
DOCLING_OCR_ENGINE: Optional[str] = None
DOCLING_OCR_LANG: Optional[str] = None
DOCLING_FORCE_OCR: Optional[bool] = None
DOCLING_IMAGE_EXPORT_MODE: Optional[str] = None
DOCLING_TABLE_MODE: Optional[str] = None
DOCLING_DO_PICTURE_DESCRIPTION: Optional[bool] = None
DOCLING_PICTURE_DESCRIPTION_MODE: Optional[str] = None
DOCLING_PICTURE_DESCRIPTION_LOCAL: Optional[dict] = None
Expand Down Expand Up @@ -753,6 +759,21 @@ async def update_rag_config(
if form_data.DOCLING_OCR_LANG is not None
else request.app.state.config.DOCLING_OCR_LANG
)
request.app.state.config.DOCLING_FORCE_OCR = (
form_data.DOCLING_FORCE_OCR
if form_data.DOCLING_FORCE_OCR is not None
else request.app.state.config.DOCLING_FORCE_OCR
)
request.app.state.config.DOCLING_IMAGE_EXPORT_MODE = (
form_data.DOCLING_IMAGE_EXPORT_MODE
if form_data.DOCLING_IMAGE_EXPORT_MODE is not None
else request.app.state.config.DOCLING_IMAGE_EXPORT_MODE
)
request.app.state.config.DOCLING_TABLE_MODE = (
form_data.DOCLING_TABLE_MODE
if form_data.DOCLING_TABLE_MODE is not None
else request.app.state.config.DOCLING_TABLE_MODE
)

request.app.state.config.DOCLING_DO_PICTURE_DESCRIPTION = (
form_data.DOCLING_DO_PICTURE_DESCRIPTION
Expand Down Expand Up @@ -1020,6 +1041,9 @@ async def update_rag_config(
"DOCLING_SERVER_URL": request.app.state.config.DOCLING_SERVER_URL,
"DOCLING_OCR_ENGINE": request.app.state.config.DOCLING_OCR_ENGINE,
"DOCLING_OCR_LANG": request.app.state.config.DOCLING_OCR_LANG,
"DOCLING_FORCE_OCR": request.app.state.config.DOCLING_FORCE_OCR,
"DOCLING_IMAGE_EXPORT_MODE": request.app.state.config.DOCLING_IMAGE_EXPORT_MODE,
"DOCLING_TABLE_MODE": request.app.state.config.DOCLING_TABLE_MODE,
"DOCLING_DO_PICTURE_DESCRIPTION": request.app.state.config.DOCLING_DO_PICTURE_DESCRIPTION,
"DOCLING_PICTURE_DESCRIPTION_MODE": request.app.state.config.DOCLING_PICTURE_DESCRIPTION_MODE,
"DOCLING_PICTURE_DESCRIPTION_LOCAL": request.app.state.config.DOCLING_PICTURE_DESCRIPTION_LOCAL,
Expand Down Expand Up @@ -1421,6 +1445,9 @@ def process_file(
DOCLING_PARAMS={
"ocr_engine": request.app.state.config.DOCLING_OCR_ENGINE,
"ocr_lang": request.app.state.config.DOCLING_OCR_LANG,
"force_ocr": request.app.state.config.DOCLING_FORCE_OCR,
"image_export_mode": request.app.state.config.DOCLING_IMAGE_EXPORT_MODE,
"table_mode": request.app.state.config.DOCLING_TABLE_MODE,
"do_picture_description": request.app.state.config.DOCLING_DO_PICTURE_DESCRIPTION,
"picture_description_mode": request.app.state.config.DOCLING_PICTURE_DESCRIPTION_MODE,
"picture_description_local": request.app.state.config.DOCLING_PICTURE_DESCRIPTION_LOCAL,
Expand Down