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

feat: add PaddleOCR-vl loader support and implement retrieval router infrastructure (#23945)

Browse Source 
Co-authored-by: Tim Baek <tim@openwebui.com>
Co-authored-by: joaoback <156559121+joaoback@users.noreply.github.com>
This commit is contained in:
goodbey857
2026-04-24 15:19:37 +09:00
committed by GitHub
co-authored by Tim Baek joaoback
parent 0e311a95a7
commit 58bc254809
10 changed files with 199 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/open_webui/config.py
+12
View File
@@ -2827,6 +2827,18 @@ MISTRAL_OCR_API_KEY = PersistentConfig(
os.getenv('MISTRAL_OCR_API_KEY', ''),
)
PADDLEOCR_VL_BASE_URL = PersistentConfig(
'PADDLEOCR_VL_BASE_URL',
'rag.paddleocr_vl_base_url',
os.getenv('PADDLEOCR_VL_BASE_URL', 'http://localhost:8080'),
)
PADDLEOCR_VL_TOKEN = PersistentConfig(
'PADDLEOCR_VL_TOKEN',
'rag.paddleocr_vl_token',
os.getenv('PADDLEOCR_VL_TOKEN', ''),
)
BYPASS_EMBEDDING_AND_RETRIEVAL = PersistentConfig(
'BYPASS_EMBEDDING_AND_RETRIEVAL',
'rag.bypass_embedding_and_retrieval',
backend/open_webui/main.py
+4
View File
@@ -303,6 +303,8 @@ from open_webui.config import (
DOCUMENT_INTELLIGENCE_MODEL,
MISTRAL_OCR_API_BASE_URL,
MISTRAL_OCR_API_KEY,
PADDLEOCR_VL_BASE_URL,
PADDLEOCR_VL_TOKEN,
RAG_TEXT_SPLITTER,
ENABLE_MARKDOWN_HEADER_TEXT_SPLITTER,
TIKTOKEN_ENCODING_NAME,
@@ -1023,6 +1025,8 @@ app.state.config.DOCUMENT_INTELLIGENCE_KEY = DOCUMENT_INTELLIGENCE_KEY
app.state.config.DOCUMENT_INTELLIGENCE_MODEL = DOCUMENT_INTELLIGENCE_MODEL
app.state.config.MISTRAL_OCR_API_BASE_URL = MISTRAL_OCR_API_BASE_URL
app.state.config.MISTRAL_OCR_API_KEY = MISTRAL_OCR_API_KEY
app.state.config.PADDLEOCR_VL_BASE_URL = PADDLEOCR_VL_BASE_URL
app.state.config.PADDLEOCR_VL_TOKEN = PADDLEOCR_VL_TOKEN
app.state.config.MINERU_API_MODE = MINERU_API_MODE
app.state.config.MINERU_API_URL = MINERU_API_URL
app.state.config.MINERU_API_KEY = MINERU_API_KEY
backend/open_webui/retrieval/loaders/main.py
+10 -1
View File
@@ -23,7 +23,7 @@ from open_webui.retrieval.loaders.external_document import ExternalDocumentLoade
from open_webui.retrieval.loaders.mistral import MistralLoader
from open_webui.retrieval.loaders.datalab_marker import DatalabMarkerLoader
from open_webui.retrieval.loaders.mineru import MinerULoader
from open_webui.retrieval.loaders.paddleocr_vl import PaddleOCRVLLoader
from open_webui.env import GLOBAL_LOG_LEVEL, REQUESTS_VERIFY
@@ -399,6 +399,15 @@ class Loader:
api_key=self.kwargs.get('MISTRAL_OCR_API_KEY'),
file_path=file_path,
)
elif (
self.engine == 'paddleocr_vl'
and self.kwargs.get('PADDLEOCR_VL_TOKEN') != ''
):
loader = PaddleOCRVLLoader(
api_url=self.kwargs.get('PADDLEOCR_VL_BASE_URL'),
token=self.kwargs.get('PADDLEOCR_VL_TOKEN'),
file_path=file_path,
)
else:
if file_ext == 'pdf':
loader = PyPDFLoader(
backend/open_webui/retrieval/loaders/paddleocr_vl.py
+127
View File
@@ -0,0 +1,127 @@
import base64
import os
import requests
import logging
import sys
from typing import List
from langchain_core.documents import Document
from open_webui.env import GLOBAL_LOG_LEVEL
logging.basicConfig(stream=sys.stdout, level=GLOBAL_LOG_LEVEL)
log = logging.getLogger(__name__)
class PaddleOCRVLLoader:
"""Loader that uses PaddleOCR-vl API to extract text from PDF/images."""
def __init__(
self,
api_url: str,
token: str,
file_path: str,
):
if not api_url or not token:
raise ValueError("PaddleOCR-vl API URL and Token are required.")
if not os.path.exists(file_path):
raise FileNotFoundError(f"File not found at {file_path}")
self.api_url = api_url.rstrip('/')
self.token = token
self.file_path = file_path
self.file_name = os.path.basename(file_path)
def load(self) -> List[Document]:
log.info(f"Processing with PaddleOCR-vl: {self.file_path}")
try:
with open(self.file_path, "rb") as file:
file_bytes = file.read()
file_data = base64.b64encode(file_bytes).decode("ascii")
except Exception as e:
log.error(f"Failed to read file {self.file_path}: {e}")
raise
headers = {
"Authorization": f"token {self.token}",
"Content-Type": "application/json"
}
# Detect fileType based on file extension
ext = self.file_path.lower().split('.')[-1]
image_extensions = ['png', 'jpg', 'jpeg', 'bmp', 'tiff', 'webp']
file_type = 1 if ext in image_extensions else 0
payload = {
"file": file_data,
"fileType": file_type,
"useDocOrientationClassify": False,
"useDocUnwarping": False,
"useChartRecognition": False,
}
try:
response = requests.post(f"{self.api_url}/layout-parsing", json=payload, headers=headers)
response.raise_for_status()
result = response.json().get("result", {})
layout_results = result.get("layoutParsingResults", [])
documents = []
total_pages = len(layout_results)
skipped_pages = 0
for i, res in enumerate(layout_results):
markdown_text = res.get("markdown", {}).get("text", "")
if isinstance(markdown_text, str):
cleaned_content = markdown_text.strip()
else:
cleaned_content = str(markdown_text).strip()
if not cleaned_content:
skipped_pages += 1
continue
documents.append(
Document(
page_content=cleaned_content,
metadata={
"page": i,
"page_label": i + 1,
"total_pages": total_pages,
"file_name": self.file_name,
"processing_engine": "paddleocr-vl"
}
)
)
if skipped_pages > 0:
log.info(f"PaddleOCR-vl: Processed {len(documents)} pages, skipped {skipped_pages} empty pages.")
if not documents:
log.warning("No valid text content found by PaddleOCR-vl.")
return [
Document(
page_content="No valid text content found in document",
metadata={
"error": "no_valid_pages",
"file_name": self.file_name,
"processing_engine": "paddleocr-vl"
}
)
]
return documents
except Exception as e:
log.error(f"Error calling PaddleOCR-vl: {e}")
return [
Document(
page_content=f"Error during OCR processing: {e}",
metadata={
"error": "processing_failed",
"file_name": self.file_name,
"processing_engine": "paddleocr-vl"
}
)
]
backend/open_webui/retrieval/utils.py
+2
View File
@@ -114,6 +114,8 @@ def build_loader_from_config(request):
DOCUMENT_INTELLIGENCE_MODEL=config.DOCUMENT_INTELLIGENCE_MODEL,
MISTRAL_OCR_API_BASE_URL=config.MISTRAL_OCR_API_BASE_URL,
MISTRAL_OCR_API_KEY=config.MISTRAL_OCR_API_KEY,
PADDLEOCR_VL_BASE_URL=config.PADDLEOCR_VL_BASE_URL,
PADDLEOCR_VL_TOKEN=config.PADDLEOCR_VL_TOKEN,
MINERU_API_MODE=config.MINERU_API_MODE,
MINERU_API_URL=config.MINERU_API_URL,
MINERU_API_KEY=config.MINERU_API_KEY,
backend/open_webui/routers/retrieval.py
+16
View File
@@ -480,6 +480,8 @@ async def get_rag_config(request: Request, user=Depends(get_admin_user)):
'DOCUMENT_INTELLIGENCE_MODEL': request.app.state.config.DOCUMENT_INTELLIGENCE_MODEL,
'MISTRAL_OCR_API_BASE_URL': request.app.state.config.MISTRAL_OCR_API_BASE_URL,
'MISTRAL_OCR_API_KEY': request.app.state.config.MISTRAL_OCR_API_KEY,
'PADDLEOCR_VL_BASE_URL': request.app.state.config.PADDLEOCR_VL_BASE_URL,
'PADDLEOCR_VL_TOKEN': request.app.state.config.PADDLEOCR_VL_TOKEN,
# MinerU settings
'MINERU_API_MODE': request.app.state.config.MINERU_API_MODE,
'MINERU_API_URL': request.app.state.config.MINERU_API_URL,
@@ -686,6 +688,8 @@ class ConfigForm(BaseModel):
DOCUMENT_INTELLIGENCE_MODEL: Optional[str] = None
MISTRAL_OCR_API_BASE_URL: Optional[str] = None
MISTRAL_OCR_API_KEY: Optional[str] = None
PADDLEOCR_VL_BASE_URL: Optional[str] = None
PADDLEOCR_VL_TOKEN: Optional[str] = None
# MinerU settings
MINERU_API_MODE: Optional[str] = None
@@ -887,6 +891,16 @@ async def update_rag_config(request: Request, form_data: ConfigForm, user=Depend
if form_data.MISTRAL_OCR_API_KEY is not None
else request.app.state.config.MISTRAL_OCR_API_KEY
)
request.app.state.config.PADDLEOCR_VL_BASE_URL = (
form_data.PADDLEOCR_VL_BASE_URL
if form_data.PADDLEOCR_VL_BASE_URL is not None
else request.app.state.config.PADDLEOCR_VL_BASE_URL
)
request.app.state.config.PADDLEOCR_VL_TOKEN = (
form_data.PADDLEOCR_VL_TOKEN
if form_data.PADDLEOCR_VL_TOKEN is not None
else request.app.state.config.PADDLEOCR_VL_TOKEN
)
# MinerU settings
request.app.state.config.MINERU_API_MODE = (
@@ -1152,6 +1166,8 @@ async def update_rag_config(request: Request, form_data: ConfigForm, user=Depend
'DOCUMENT_INTELLIGENCE_MODEL': request.app.state.config.DOCUMENT_INTELLIGENCE_MODEL,
'MISTRAL_OCR_API_BASE_URL': request.app.state.config.MISTRAL_OCR_API_BASE_URL,
'MISTRAL_OCR_API_KEY': request.app.state.config.MISTRAL_OCR_API_KEY,
'PADDLEOCR_VL_BASE_URL': request.app.state.config.PADDLEOCR_VL_BASE_URL,
'PADDLEOCR_VL_TOKEN': request.app.state.config.PADDLEOCR_VL_TOKEN,
# MinerU settings
'MINERU_API_MODE': request.app.state.config.MINERU_API_MODE,
'MINERU_API_URL': request.app.state.config.MINERU_API_URL,