Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Python ai4sciencedocument-analysisdocxextract-datalayout-analysisocrparserpdfpdf-converterpdf-extractor-llmpdf-extractor-pretrainpdf-extractor-ragpdf-parserpptxpythonxlsx
"""启动只调用共同 Tasks 契约的同步包装服务。"""
from __future__ import annotations
from pathlib import Path
import typer
from ...utils.i18n import t
from ...utils.server import run_server
from ..errors import exit_with_message
def file_parse_server_cmd(
api_url: str = typer.Option(..., "--api-url", envvar="MINERU_API_URL", help=t("Upstream Tasks API base URL")),
api_key: str | None = typer.Option(None, "--api-key", envvar="MINERU_API_KEY", help=t("Upstream Bearer API key")),
host: str = typer.Option("127.0.0.1", "--host", help=t("Server host")),
port: int = typer.Option(8003, "--port", min=1, max=65535, help=t("Server port")),
state_dir: Path | None = typer.Option(None, "--state-dir", help=t("File parse recovery state directory")),
retention_seconds: int = typer.Option(
86400, "--retention-seconds", min=0, help=t("Terminal retention seconds (default 86400; 0 disables collection)")
),
) -> None:
"""惰性加载包装应用,不启动本地解析模型或继承调用者的认证头。"""
from filelock import Timeout
from ..file_parse import FileParseSettings, create_app
try:
settings = FileParseSettings(api_url, api_key, state_dir, retention_seconds)
except ValueError as exc:
exit_with_message("invalid_request", str(exc))
try:
run_server(create_app(settings), host=host, port=port)
except Timeout:
exit_with_message("invalid_request", "Another file-parse-server is using this state directory")
__all__ = ["file_parse_server_cmd"]