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
"""PDF/图片的启动上限、内嵌精确集合与共享模型配置。"""
from __future__ import annotations
from collections.abc import Collection
from typing import TYPE_CHECKING
from ..types import TIERS, TIERS_BY_SERVER_TIER, DeploymentTier, Tier, validate_tier
if TYPE_CHECKING:
from ..config import VlmConfig
def normalize_server_tiers(tiers: Collection[Tier]) -> tuple[Tier, ...]:
"""校验非空显式集合,去重并按公共档位顺序稳定输出。"""
if not isinstance(tiers, Collection) or isinstance(tiers, (str, bytes)) or not tiers:
raise ValueError("Server tiers must be a non-empty collection of flash, basic, standard, advanced")
if any(not isinstance(tier, str) for tier in tiers):
raise ValueError("Server tiers must contain tier names")
selected = {validate_tier(tier) for tier in tiers}
return tuple(tier for tier in TIERS if tier in selected)
def parse_server_tier(value: str) -> tuple[Tier, ...] | None:
"""解析单档上限或 auto;上限包含自身及全部较低 PDF/图片档位。"""
if value.strip().lower() == "auto":
return None
return TIERS_BY_SERVER_TIER[validate_tier(value)]
def resolve_server_tiers(tiers: Collection[Tier] | None, *, vlm_config: VlmConfig | None = None) -> tuple[Tier, ...]:
"""显式列表跳过推荐与启动校准;自动模式按硬件初选并完成适用的 OCR 选型。"""
if tiers is None:
from ..model.runtime.tier_recommendation import recommend_tiers
recommended = normalize_server_tiers(recommend_tiers(vlm_config=vlm_config).pdf_image_tiers)
tiers = TIERS_BY_SERVER_TIER[recommended[-1]]
return normalize_server_tiers(tiers)
def model_tier_for_server_tiers(tiers: Collection[Tier]) -> DeploymentTier | None:
"""合并共享模型需求;advanced 复用 Standard 配置但不增加发布档位。"""
if "standard" in tiers or "advanced" in tiers:
return "standard"
if "basic" in tiers:
return "basic"
return None
__all__ = ["model_tier_for_server_tiers", "normalize_server_tiers", "parse_server_tier", "resolve_server_tiers"]