Fix: manual parser with mineru (#11336)

### What problem does this PR solve?

Fix: manual parser with mineru #11320
Fix: missing parameter in mineru #11334
Fix: add outlines parameter for pdf parsers

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
Billy Bao
2025-11-18 15:22:52 +08:00
committed by GitHub
parent 0db00f70b2
commit fea157ba08
5 changed files with 30 additions and 1 deletions

View File

@ -61,7 +61,9 @@ class DoclingParser(RAGFlowPdfParser):
self.page_images: list[Image.Image] = []
self.page_from = 0
self.page_to = 10_000
self.outlines = []
def check_installation(self) -> bool:
if DocumentConverter is None:
self.logger.warning("[Docling] 'docling' is not importable, please: pip install docling")

View File

@ -59,6 +59,7 @@ class MinerUParser(RAGFlowPdfParser):
self.mineru_api = mineru_api.rstrip("/")
self.mineru_server_url = mineru_server_url.rstrip("/")
self.using_api = False
self.outlines = []
self.logger = logging.getLogger(self.__class__.__name__)
def _extract_zip_no_root(self, zip_path, extract_to, root_dir):

View File

@ -47,6 +47,7 @@ class TencentCloudAPIClient:
self.secret_id = secret_id
self.secret_key = secret_key
self.region = region
self.outlines = []
# Create credentials
self.cred = credential.Credential(secret_id, secret_key)