OpenWebUI/open-webui
1
0
Fork 0
mirror of https://github.com/open-webui/open-webui synced 2025-06-26 18:26:48 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

feat: docling do picture description support

Browse Source
This commit is contained in:
Timothy Jaeryang Baek
2025-05-14 21:26:49 +04:00
parent 6e8481e157
commit de70d0cb64
5 changed files with 70 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
backend/open_webui/retrieval/loaders/main.py
View File

@@ -126,14 +126,12 @@ class TikaLoader:
class DoclingLoader:
def __init__(
self, url, file_path=None, mime_type=None, ocr_engine=None, ocr_lang=None
):
def __init__(self, url, file_path=None, mime_type=None, params=None):
self.url = url.rstrip("/")
self.file_path = file_path
self.mime_type = mime_type
self.ocr_engine = ocr_engine
self.ocr_lang = ocr_lang
self.params = params or {}
def load(self) -> list[Document]:
with open(self.file_path, "rb") as f:
@@ -150,11 +148,19 @@ class DoclingLoader:
"table_mode": "accurate",
}
if self.ocr_engine and self.ocr_lang:
params["ocr_engine"] = self.ocr_engine
params["ocr_lang"] = [
lang.strip() for lang in self.ocr_lang.split(",") if lang.strip()
]
if self.params:
if self.params.get("do_picture_classification"):
params["do_picture_classification"] = self.params.get(
"do_picture_classification"
)
if 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()
]
endpoint = f"{self.url}/v1alpha/convert/file"
r = requests.post(endpoint, files=files, data=params)
@@ -225,8 +231,13 @@ class Loader:
url=self.kwargs.get("DOCLING_SERVER_URL"),
file_path=file_path,
mime_type=file_content_type,
ocr_engine=self.kwargs.get("DOCLING_OCR_ENGINE"),
ocr_lang=self.kwargs.get("DOCLING_OCR_LANG"),
params={
"ocr_engine": self.kwargs.get("DOCLING_OCR_ENGINE"),
"ocr_lang": self.kwargs.get("DOCLING_OCR_LANG"),
"do_picture_classification": self.kwargs.get(
"DOCLING_DO_PICTURE_DESCRIPTION"
),
},
)
elif (
self.engine == "document_intelligence"