OpenWebUI/open-webui-custom
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refac/breaking: docling params

Browse Source
This commit is contained in:
Timothy Jaeryang Baek
2025-11-24 16:01:13 -05:00
parent b875a438f0
commit 9c19d0abd4
5 changed files with 40 additions and 461 deletions
Download Patch File Download Diff File Expand all files Collapse all files

88
backend/open_webui/config.py
View File

@@ -2538,6 +2538,12 @@ DOCLING_SERVER_URL = PersistentConfig(
os.getenv("DOCLING_SERVER_URL", "http://docling:5001"),
)
DOCLING_API_KEY = PersistentConfig(
"DOCLING_API_KEY",
"rag.docling_api_key",
os.getenv("DOCLING_API_KEY", ""),
)
docling_params = os.getenv("DOCLING_PARAMS", "")
try:
docling_params = json.loads(docling_params)
@@ -2550,88 +2556,6 @@ DOCLING_PARAMS = PersistentConfig(
docling_params,
)
DOCLING_DO_OCR = PersistentConfig(
"DOCLING_DO_OCR",
"rag.docling_do_ocr",
os.getenv("DOCLING_DO_OCR", "True").lower() == "true",
)
DOCLING_FORCE_OCR = PersistentConfig(
"DOCLING_FORCE_OCR",
"rag.docling_force_ocr",
os.getenv("DOCLING_FORCE_OCR", "False").lower() == "true",
)
DOCLING_OCR_ENGINE = PersistentConfig(
"DOCLING_OCR_ENGINE",
"rag.docling_ocr_engine",
os.getenv("DOCLING_OCR_ENGINE", "tesseract"),
)
DOCLING_OCR_LANG = PersistentConfig(
"DOCLING_OCR_LANG",
"rag.docling_ocr_lang",
os.getenv("DOCLING_OCR_LANG", "eng,fra,deu,spa"),
)
DOCLING_PDF_BACKEND = PersistentConfig(
"DOCLING_PDF_BACKEND",
"rag.docling_pdf_backend",
os.getenv("DOCLING_PDF_BACKEND", "dlparse_v4"),
)
DOCLING_TABLE_MODE = PersistentConfig(
"DOCLING_TABLE_MODE",
"rag.docling_table_mode",
os.getenv("DOCLING_TABLE_MODE", "accurate"),
)
DOCLING_PIPELINE = PersistentConfig(
"DOCLING_PIPELINE",
"rag.docling_pipeline",
os.getenv("DOCLING_PIPELINE", "standard"),
)
DOCLING_DO_PICTURE_DESCRIPTION = PersistentConfig(
"DOCLING_DO_PICTURE_DESCRIPTION",
"rag.docling_do_picture_description",
os.getenv("DOCLING_DO_PICTURE_DESCRIPTION", "False").lower() == "true",
)
DOCLING_PICTURE_DESCRIPTION_MODE = PersistentConfig(
"DOCLING_PICTURE_DESCRIPTION_MODE",
"rag.docling_picture_description_mode",
os.getenv("DOCLING_PICTURE_DESCRIPTION_MODE", ""),
)
docling_picture_description_local = os.getenv("DOCLING_PICTURE_DESCRIPTION_LOCAL", "")
try:
docling_picture_description_local = json.loads(docling_picture_description_local)
except json.JSONDecodeError:
docling_picture_description_local = {}
DOCLING_PICTURE_DESCRIPTION_LOCAL = PersistentConfig(
"DOCLING_PICTURE_DESCRIPTION_LOCAL",
"rag.docling_picture_description_local",
docling_picture_description_local,
)
docling_picture_description_api = os.getenv("DOCLING_PICTURE_DESCRIPTION_API", "")
try:
docling_picture_description_api = json.loads(docling_picture_description_api)
except json.JSONDecodeError:
docling_picture_description_api = {}
DOCLING_PICTURE_DESCRIPTION_API = PersistentConfig(
"DOCLING_PICTURE_DESCRIPTION_API",
"rag.docling_picture_description_api",
docling_picture_description_api,
)
DOCUMENT_INTELLIGENCE_ENDPOINT = PersistentConfig(
"DOCUMENT_INTELLIGENCE_ENDPOINT",
"rag.document_intelligence_endpoint",

24
backend/open_webui/main.py
View File

@@ -268,18 +268,8 @@ from open_webui.config import (
EXTERNAL_DOCUMENT_LOADER_API_KEY,
TIKA_SERVER_URL,
DOCLING_SERVER_URL,
DOCLING_API_KEY,
DOCLING_PARAMS,
DOCLING_DO_OCR,
DOCLING_FORCE_OCR,
DOCLING_OCR_ENGINE,
DOCLING_OCR_LANG,
DOCLING_PDF_BACKEND,
DOCLING_TABLE_MODE,
DOCLING_PIPELINE,
DOCLING_DO_PICTURE_DESCRIPTION,
DOCLING_PICTURE_DESCRIPTION_MODE,
DOCLING_PICTURE_DESCRIPTION_LOCAL,
DOCLING_PICTURE_DESCRIPTION_API,
DOCUMENT_INTELLIGENCE_ENDPOINT,
DOCUMENT_INTELLIGENCE_KEY,
MISTRAL_OCR_API_BASE_URL,
@@ -874,18 +864,8 @@ app.state.config.EXTERNAL_DOCUMENT_LOADER_URL = EXTERNAL_DOCUMENT_LOADER_URL
app.state.config.EXTERNAL_DOCUMENT_LOADER_API_KEY = EXTERNAL_DOCUMENT_LOADER_API_KEY
app.state.config.TIKA_SERVER_URL = TIKA_SERVER_URL
app.state.config.DOCLING_SERVER_URL = DOCLING_SERVER_URL
app.state.config.DOCLING_API_KEY = DOCLING_API_KEY
app.state.config.DOCLING_PARAMS = DOCLING_PARAMS
app.state.config.DOCLING_DO_OCR = DOCLING_DO_OCR
app.state.config.DOCLING_FORCE_OCR = DOCLING_FORCE_OCR
app.state.config.DOCLING_OCR_ENGINE = DOCLING_OCR_ENGINE
app.state.config.DOCLING_OCR_LANG = DOCLING_OCR_LANG
app.state.config.DOCLING_PDF_BACKEND = DOCLING_PDF_BACKEND
app.state.config.DOCLING_TABLE_MODE = DOCLING_TABLE_MODE
app.state.config.DOCLING_PIPELINE = DOCLING_PIPELINE
app.state.config.DOCLING_DO_PICTURE_DESCRIPTION = DOCLING_DO_PICTURE_DESCRIPTION
app.state.config.DOCLING_PICTURE_DESCRIPTION_MODE = DOCLING_PICTURE_DESCRIPTION_MODE
app.state.config.DOCLING_PICTURE_DESCRIPTION_LOCAL = DOCLING_PICTURE_DESCRIPTION_LOCAL
app.state.config.DOCLING_PICTURE_DESCRIPTION_API = DOCLING_PICTURE_DESCRIPTION_API
app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT = DOCUMENT_INTELLIGENCE_ENDPOINT
app.state.config.DOCUMENT_INTELLIGENCE_KEY = DOCUMENT_INTELLIGENCE_KEY
app.state.config.MISTRAL_OCR_API_BASE_URL = MISTRAL_OCR_API_BASE_URL

72
backend/open_webui/retrieval/loaders/main.py
View File

@@ -132,8 +132,9 @@ class TikaLoader:
class DoclingLoader:
def __init__(self, url, file_path=None, mime_type=None, params=None):
def __init__(self, url, api_key=None, file_path=None, mime_type=None, params=None):
self.url = url.rstrip("/")
self.api_key = api_key
self.file_path = file_path
self.mime_type = mime_type
@@ -141,6 +142,10 @@ class DoclingLoader:
def load(self) -> list[Document]:
with open(self.file_path, "rb") as f:
headers = {}
if self.api_key:
headers["Authorization"] = f"Bearer {self.api_key}"
files = {
"files": (
self.file_path,
@@ -149,60 +154,15 @@ class DoclingLoader:
)
}
params = {"image_export_mode": "placeholder"}
if self.params:
if self.params.get("do_picture_description"):
params["do_picture_description"] = self.params.get(
"do_picture_description"
)
picture_description_mode = self.params.get(
"picture_description_mode", ""
).lower()
if picture_description_mode == "local" and self.params.get(
"picture_description_local", {}
):
params["picture_description_local"] = json.dumps(
self.params.get("picture_description_local", {})
)
elif picture_description_mode == "api" and self.params.get(
"picture_description_api", {}
):
params["picture_description_api"] = json.dumps(
self.params.get("picture_description_api", {})
)
params["do_ocr"] = self.params.get("do_ocr")
params["force_ocr"] = self.params.get("force_ocr")
if (
self.params.get("do_ocr")
and self.params.get("ocr_engine")
and self.params.get("ocr_lang")
):
params["ocr_engine"] = self.params.get("ocr_engine")
params["ocr_lang"] = [
lang.strip()
for lang in self.params.get("ocr_lang").split(",")
if lang.strip()
]
if self.params.get("pdf_backend"):
params["pdf_backend"] = self.params.get("pdf_backend")
if self.params.get("table_mode"):
params["table_mode"] = self.params.get("table_mode")
if self.params.get("pipeline"):
params["pipeline"] = self.params.get("pipeline")
endpoint = f"{self.url}/v1/convert/file"
r = requests.post(endpoint, files=files, data=params)
r = requests.post(
f"{self.url}/v1/convert/file",
files=files,
data={
"image_export_mode": "placeholder",
**self.params,
},
headers=headers,
)
if r.ok:
result = r.json()
document_data = result.get("document", {})
@@ -211,7 +171,6 @@ class DoclingLoader:
metadata = {"Content-Type": self.mime_type} if self.mime_type else {}
log.debug("Docling extracted text: %s", text)
return [Document(page_content=text, metadata=metadata)]
else:
error_msg = f"Error calling Docling API: {r.reason}"
@@ -340,6 +299,7 @@ class Loader:
loader = DoclingLoader(
url=self.kwargs.get("DOCLING_SERVER_URL"),
api_key=self.kwargs.get("DOCLING_API_KEY", None),
file_path=file_path,
mime_type=file_content_type,
params=params,

114
backend/open_webui/routers/retrieval.py
View File

@@ -453,18 +453,8 @@ async def get_rag_config(request: Request, user=Depends(get_admin_user)):
"EXTERNAL_DOCUMENT_LOADER_API_KEY": request.app.state.config.EXTERNAL_DOCUMENT_LOADER_API_KEY,
"TIKA_SERVER_URL": request.app.state.config.TIKA_SERVER_URL,
"DOCLING_SERVER_URL": request.app.state.config.DOCLING_SERVER_URL,
"DOCLING_API_KEY": request.app.state.config.DOCLING_API_KEY,
"DOCLING_PARAMS": request.app.state.config.DOCLING_PARAMS,
"DOCLING_DO_OCR": request.app.state.config.DOCLING_DO_OCR,
"DOCLING_FORCE_OCR": request.app.state.config.DOCLING_FORCE_OCR,
"DOCLING_OCR_ENGINE": request.app.state.config.DOCLING_OCR_ENGINE,
"DOCLING_OCR_LANG": request.app.state.config.DOCLING_OCR_LANG,
"DOCLING_PDF_BACKEND": request.app.state.config.DOCLING_PDF_BACKEND,
"DOCLING_TABLE_MODE": request.app.state.config.DOCLING_TABLE_MODE,
"DOCLING_PIPELINE": request.app.state.config.DOCLING_PIPELINE,
"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,
"DOCLING_PICTURE_DESCRIPTION_API": request.app.state.config.DOCLING_PICTURE_DESCRIPTION_API,
"DOCUMENT_INTELLIGENCE_ENDPOINT": request.app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT,
"DOCUMENT_INTELLIGENCE_KEY": request.app.state.config.DOCUMENT_INTELLIGENCE_KEY,
"MISTRAL_OCR_API_BASE_URL": request.app.state.config.MISTRAL_OCR_API_BASE_URL,
@@ -642,18 +632,8 @@ class ConfigForm(BaseModel):
TIKA_SERVER_URL: Optional[str] = None
DOCLING_SERVER_URL: Optional[str] = None
DOCLING_API_KEY: Optional[str] = None
DOCLING_PARAMS: Optional[dict] = None
DOCLING_DO_OCR: Optional[bool] = None
DOCLING_FORCE_OCR: Optional[bool] = None
DOCLING_OCR_ENGINE: Optional[str] = None
DOCLING_OCR_LANG: Optional[str] = None
DOCLING_PDF_BACKEND: Optional[str] = None
DOCLING_TABLE_MODE: Optional[str] = None
DOCLING_PIPELINE: Optional[str] = None
DOCLING_DO_PICTURE_DESCRIPTION: Optional[bool] = None
DOCLING_PICTURE_DESCRIPTION_MODE: Optional[str] = None
DOCLING_PICTURE_DESCRIPTION_LOCAL: Optional[dict] = None
DOCLING_PICTURE_DESCRIPTION_API: Optional[dict] = None
DOCUMENT_INTELLIGENCE_ENDPOINT: Optional[str] = None
DOCUMENT_INTELLIGENCE_KEY: Optional[str] = None
MISTRAL_OCR_API_BASE_URL: Optional[str] = None
@@ -831,68 +811,16 @@ async def update_rag_config(
if form_data.DOCLING_SERVER_URL is not None
else request.app.state.config.DOCLING_SERVER_URL
)
request.app.state.config.DOCLING_API_KEY = (
form_data.DOCLING_API_KEY
if form_data.DOCLING_API_KEY is not None
else request.app.state.config.DOCLING_API_KEY
)
request.app.state.config.DOCLING_PARAMS = (
form_data.DOCLING_PARAMS
if form_data.DOCLING_PARAMS is not None
else request.app.state.config.DOCLING_PARAMS
)
request.app.state.config.DOCLING_DO_OCR = (
form_data.DOCLING_DO_OCR
if form_data.DOCLING_DO_OCR is not None
else request.app.state.config.DOCLING_DO_OCR
)
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_OCR_ENGINE = (
form_data.DOCLING_OCR_ENGINE
if form_data.DOCLING_OCR_ENGINE is not None
else request.app.state.config.DOCLING_OCR_ENGINE
)
request.app.state.config.DOCLING_OCR_LANG = (
form_data.DOCLING_OCR_LANG
if form_data.DOCLING_OCR_LANG is not None
else request.app.state.config.DOCLING_OCR_LANG
)
request.app.state.config.DOCLING_PDF_BACKEND = (
form_data.DOCLING_PDF_BACKEND
if form_data.DOCLING_PDF_BACKEND is not None
else request.app.state.config.DOCLING_PDF_BACKEND
)
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_PIPELINE = (
form_data.DOCLING_PIPELINE
if form_data.DOCLING_PIPELINE is not None
else request.app.state.config.DOCLING_PIPELINE
)
request.app.state.config.DOCLING_DO_PICTURE_DESCRIPTION = (
form_data.DOCLING_DO_PICTURE_DESCRIPTION
if form_data.DOCLING_DO_PICTURE_DESCRIPTION is not None
else request.app.state.config.DOCLING_DO_PICTURE_DESCRIPTION
)
request.app.state.config.DOCLING_PICTURE_DESCRIPTION_MODE = (
form_data.DOCLING_PICTURE_DESCRIPTION_MODE
if form_data.DOCLING_PICTURE_DESCRIPTION_MODE is not None
else request.app.state.config.DOCLING_PICTURE_DESCRIPTION_MODE
)
request.app.state.config.DOCLING_PICTURE_DESCRIPTION_LOCAL = (
form_data.DOCLING_PICTURE_DESCRIPTION_LOCAL
if form_data.DOCLING_PICTURE_DESCRIPTION_LOCAL is not None
else request.app.state.config.DOCLING_PICTURE_DESCRIPTION_LOCAL
)
request.app.state.config.DOCLING_PICTURE_DESCRIPTION_API = (
form_data.DOCLING_PICTURE_DESCRIPTION_API
if form_data.DOCLING_PICTURE_DESCRIPTION_API is not None
else request.app.state.config.DOCLING_PICTURE_DESCRIPTION_API
)
request.app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT = (
form_data.DOCUMENT_INTELLIGENCE_ENDPOINT
if form_data.DOCUMENT_INTELLIGENCE_ENDPOINT is not None
@@ -1189,18 +1117,8 @@ async def update_rag_config(
"EXTERNAL_DOCUMENT_LOADER_API_KEY": request.app.state.config.EXTERNAL_DOCUMENT_LOADER_API_KEY,
"TIKA_SERVER_URL": request.app.state.config.TIKA_SERVER_URL,
"DOCLING_SERVER_URL": request.app.state.config.DOCLING_SERVER_URL,
"DOCLING_API_KEY": request.app.state.config.DOCLING_API_KEY,
"DOCLING_PARAMS": request.app.state.config.DOCLING_PARAMS,
"DOCLING_DO_OCR": request.app.state.config.DOCLING_DO_OCR,
"DOCLING_FORCE_OCR": request.app.state.config.DOCLING_FORCE_OCR,
"DOCLING_OCR_ENGINE": request.app.state.config.DOCLING_OCR_ENGINE,
"DOCLING_OCR_LANG": request.app.state.config.DOCLING_OCR_LANG,
"DOCLING_PDF_BACKEND": request.app.state.config.DOCLING_PDF_BACKEND,
"DOCLING_TABLE_MODE": request.app.state.config.DOCLING_TABLE_MODE,
"DOCLING_PIPELINE": request.app.state.config.DOCLING_PIPELINE,
"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,
"DOCLING_PICTURE_DESCRIPTION_API": request.app.state.config.DOCLING_PICTURE_DESCRIPTION_API,
"DOCUMENT_INTELLIGENCE_ENDPOINT": request.app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT,
"DOCUMENT_INTELLIGENCE_KEY": request.app.state.config.DOCUMENT_INTELLIGENCE_KEY,
"MISTRAL_OCR_API_BASE_URL": request.app.state.config.MISTRAL_OCR_API_BASE_URL,
@@ -1607,20 +1525,8 @@ def process_file(
EXTERNAL_DOCUMENT_LOADER_API_KEY=request.app.state.config.EXTERNAL_DOCUMENT_LOADER_API_KEY,
TIKA_SERVER_URL=request.app.state.config.TIKA_SERVER_URL,
DOCLING_SERVER_URL=request.app.state.config.DOCLING_SERVER_URL,
DOCLING_PARAMS={
"do_ocr": request.app.state.config.DOCLING_DO_OCR,
"force_ocr": request.app.state.config.DOCLING_FORCE_OCR,
"ocr_engine": request.app.state.config.DOCLING_OCR_ENGINE,
"ocr_lang": request.app.state.config.DOCLING_OCR_LANG,
"pdf_backend": request.app.state.config.DOCLING_PDF_BACKEND,
"table_mode": request.app.state.config.DOCLING_TABLE_MODE,
"pipeline": request.app.state.config.DOCLING_PIPELINE,
"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,
"picture_description_api": request.app.state.config.DOCLING_PICTURE_DESCRIPTION_API,
**request.app.state.config.DOCLING_PARAMS,
},
DOCLING_API_KEY=request.app.state.config.DOCLING_API_KEY,
DOCLING_PARAMS=request.app.state.config.DOCLING_PARAMS,
PDF_EXTRACT_IMAGES=request.app.state.config.PDF_EXTRACT_IMAGES,
DOCUMENT_INTELLIGENCE_ENDPOINT=request.app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT,
DOCUMENT_INTELLIGENCE_KEY=request.app.state.config.DOCUMENT_INTELLIGENCE_KEY,