feat: add mineru as document parser support with both local and managed api

This commit is contained in:
palazski
2025-10-13 21:09:52 +03:00
parent 46ae3f4f5d
commit 40e9d9c330
6 changed files with 866 additions and 0 deletions
+55
View File
@@ -2291,6 +2291,61 @@ DATALAB_MARKER_OUTPUT_FORMAT = PersistentConfig(
os.environ.get("DATALAB_MARKER_OUTPUT_FORMAT", "markdown"),
)
# MinerU Configuration
MINERU_API_MODE = PersistentConfig(
"MINERU_API_MODE",
"rag.mineru_api_mode",
os.environ.get("MINERU_API_MODE", "local"), # "local" or "cloud"
)
MINERU_API_URL = PersistentConfig(
"MINERU_API_URL",
"rag.mineru_api_url",
os.environ.get("MINERU_API_URL", "http://localhost:8000"),
)
MINERU_API_KEY = PersistentConfig(
"MINERU_API_KEY",
"rag.mineru_api_key",
os.environ.get("MINERU_API_KEY", ""),
)
MINERU_ENABLE_OCR = PersistentConfig(
"MINERU_ENABLE_OCR",
"rag.mineru_enable_ocr",
os.environ.get("MINERU_ENABLE_OCR", "false").lower() == "true",
)
MINERU_ENABLE_FORMULA = PersistentConfig(
"MINERU_ENABLE_FORMULA",
"rag.mineru_enable_formula",
os.environ.get("MINERU_ENABLE_FORMULA", "true").lower() == "true",
)
MINERU_ENABLE_TABLE = PersistentConfig(
"MINERU_ENABLE_TABLE",
"rag.mineru_enable_table",
os.environ.get("MINERU_ENABLE_TABLE", "true").lower() == "true",
)
MINERU_LANGUAGE = PersistentConfig(
"MINERU_LANGUAGE",
"rag.mineru_language",
os.environ.get("MINERU_LANGUAGE", "en"),
)
MINERU_MODEL_VERSION = PersistentConfig(
"MINERU_MODEL_VERSION",
"rag.mineru_model_version",
os.environ.get("MINERU_MODEL_VERSION", "pipeline"), # "pipeline" or "vlm"
)
MINERU_PAGE_RANGES = PersistentConfig(
"MINERU_PAGE_RANGES",
"rag.mineru_page_ranges",
os.environ.get("MINERU_PAGE_RANGES", ""),
)
EXTERNAL_DOCUMENT_LOADER_URL = PersistentConfig(
"EXTERNAL_DOCUMENT_LOADER_URL",
"rag.external_document_loader_url",