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

style: change style in DoclingLoader

Browse Source
This commit is contained in:
Fabio Polito 2025-03-05 23:15:55 +00:00
parent 9aa407dbd2
commit 0716f96da8
1 changed files with 9 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
backend/open_webui/retrieval/loaders/main.py
View File

@ -119,14 +119,11 @@ class TikaLoader:
class DoclingLoader: class DoclingLoader:
def __init__(self, url, file_path=None, mime_type=None): def __init__(self, url, file_path=None, mime_type=None):
self.url = url.rstrip("/") # Ensure no trailing slash self.url = url.rstrip("/")
self.file_path = file_path self.file_path = file_path
self.mime_type = mime_type self.mime_type = mime_type
def load(self) -> list[Document]: def load(self) -> list[Document]:
if self.file_path is None:
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 = {
"files": ( "files": (
@ -167,10 +164,10 @@ class DoclingLoader:
} }
endpoint = f"{self.url}/v1alpha/convert/file" endpoint = f"{self.url}/v1alpha/convert/file"
response = requests.post(endpoint, files=files, data=params) r = requests.post(endpoint, files=files, data=params)
if response.ok: if r.ok:
result = response.json() result = r.json()
document_data = result.get("document", {}) document_data = result.get("document", {})
text = document_data.get("md_content", "<No text content found>") text = document_data.get("md_content", "<No text content found>")
@ -180,14 +177,14 @@ class DoclingLoader:
return [Document(page_content=text, metadata=metadata)] return [Document(page_content=text, metadata=metadata)]
else: else:
error_msg = f"Error calling Docling API: {response.status_code}" error_msg = f"Error calling Docling API: {r.reason}"
if response.text: if r.text:
try: try:
error_data = response.json() error_data = r.json()
if "detail" in error_data: if "detail" in error_data:
error_msg += f" - {error_data['detail']}" error_msg += f" - {error_data['detail']}"
except: except Exception:
error_msg += f" - {response.text}" error_msg += f" - {r.text}"
raise Exception(f"Error calling Docling: {error_msg}") raise Exception(f"Error calling Docling: {error_msg}")