Emil_Shanaty/open-webui-ai4me
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Extend docling configuration options to include:

Browse Source 
* do_ocr
* force_ocr
* pdf_backend
* table_mode
* pipeline

as per https://github.com/docling-project/docling-serve/blob/main/docs/usage.md

See https://github.com/open-webui/open-webui/issues/17148
This commit is contained in:
Antonio Pisano
2025-09-08 18:51:33 +02:00
parent 2407d9b905
commit daa2a036f8
5 changed files with 198 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/open_webui/retrieval/loaders/main.py
+16 -2
View File
@@ -148,7 +148,7 @@ class DoclingLoader:
)
}
params = {"image_export_mode": "placeholder", "table_mode": "accurate"}
params = {"image_export_mode": "placeholder"}
if self.params:
if self.params.get("do_picture_description"):
@@ -174,7 +174,11 @@ class DoclingLoader:
self.params.get("picture_description_api", {})
)
if self.params.get("ocr_engine") and self.params.get("ocr_lang"):
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()
@@ -182,6 +186,16 @@ class DoclingLoader:
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)