feat: use MINERU_PARAMS json field for mineru settings

This commit is contained in:
palazski
2025-10-15 22:59:59 +03:00
parent 40e9d9c330
commit 288b323df8
6 changed files with 77 additions and 213 deletions
+1 -6
View File
@@ -382,12 +382,7 @@ class Loader:
api_mode=self.kwargs.get("MINERU_API_MODE", "local"),
api_url=self.kwargs.get("MINERU_API_URL", "http://localhost:8000"),
api_key=self.kwargs.get("MINERU_API_KEY", ""),
enable_ocr=self.kwargs.get("MINERU_ENABLE_OCR", False),
enable_formula=self.kwargs.get("MINERU_ENABLE_FORMULA", True),
enable_table=self.kwargs.get("MINERU_ENABLE_TABLE", True),
language=self.kwargs.get("MINERU_LANGUAGE", "en"),
model_version=self.kwargs.get("MINERU_MODEL_VERSION", "pipeline"),
page_ranges=self.kwargs.get("MINERU_PAGE_RANGES", ""),
params=self.kwargs.get("MINERU_PARAMS", {}),
)
elif (
self.engine == "mistral_ocr"
+10 -12
View File
@@ -25,23 +25,21 @@ class MinerULoader:
api_mode: str = "local",
api_url: str = "http://localhost:8000",
api_key: str = "",
enable_ocr: bool = False,
enable_formula: bool = True,
enable_table: bool = True,
language: str = "en",
model_version: str = "pipeline",
page_ranges: str = "",
params: dict = None,
):
self.file_path = file_path
self.api_mode = api_mode.lower()
self.api_url = api_url.rstrip("/")
self.api_key = api_key
self.enable_ocr = enable_ocr
self.enable_formula = enable_formula
self.enable_table = enable_table
self.language = language
self.model_version = model_version
self.page_ranges = page_ranges
# Parse params dict with defaults
params = params or {}
self.enable_ocr = params.get("enable_ocr", False)
self.enable_formula = params.get("enable_formula", True)
self.enable_table = params.get("enable_table", True)
self.language = params.get("language", "en")
self.model_version = params.get("model_version", "pipeline")
self.page_ranges = params.get("page_ranges", "")
# Validate API mode
if self.api_mode not in ["local", "cloud"]: