c50106c185
UPLOAD_DIR and DB_PATH were read directly from os.environ, bypassing the Settings dataclass. This caused an inconsistency where overriding Settings had no effect on these values. Now all modules import from infra.settings.settings.
107 lines
3 KiB
Python
107 lines
3 KiB
Python
"""Docling Studio — unified FastAPI backend.
|
|
|
|
Single service providing document management (upload, CRUD), analysis
|
|
orchestration (async Docling processing), and PDF preview — all backed
|
|
by SQLite.
|
|
|
|
Conversion engine is selected via CONVERSION_ENGINE env var:
|
|
- "local" → Docling runs in-process as a Python library (default)
|
|
- "remote" → delegates to a Docling Serve instance via HTTP
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import logging
|
|
from contextlib import asynccontextmanager
|
|
|
|
from fastapi import FastAPI
|
|
from fastapi.middleware.cors import CORSMiddleware
|
|
|
|
from api.analyses import router as analyses_router
|
|
from api.documents import router as documents_router
|
|
from infra.settings import settings
|
|
from persistence.database import init_db
|
|
from services.analysis_service import AnalysisService
|
|
|
|
logging.basicConfig(
|
|
level=logging.INFO,
|
|
format="%(asctime)s [%(levelname)s] %(name)s — %(message)s",
|
|
)
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
def _build_converter():
|
|
"""Build the converter adapter based on configuration."""
|
|
if settings.conversion_engine == "remote":
|
|
from infra.serve_converter import ServeConverter
|
|
|
|
logger.info("Using remote Docling Serve at %s", settings.docling_serve_url)
|
|
return ServeConverter(
|
|
base_url=settings.docling_serve_url,
|
|
api_key=settings.docling_serve_api_key,
|
|
)
|
|
else:
|
|
from infra.local_converter import LocalConverter
|
|
|
|
logger.info("Using local Docling converter")
|
|
return LocalConverter()
|
|
|
|
|
|
def _build_chunker():
|
|
"""Build the chunker adapter — only available in local mode."""
|
|
if settings.conversion_engine == "local":
|
|
from infra.local_chunker import LocalChunker
|
|
|
|
return LocalChunker()
|
|
return None
|
|
|
|
|
|
def _build_analysis_service() -> AnalysisService:
|
|
converter = _build_converter()
|
|
chunker = _build_chunker()
|
|
return AnalysisService(
|
|
converter=converter,
|
|
chunker=chunker,
|
|
conversion_timeout=settings.conversion_timeout,
|
|
)
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# FastAPI app
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
@asynccontextmanager
|
|
async def lifespan(app: FastAPI):
|
|
await init_db()
|
|
app.state.analysis_service = _build_analysis_service()
|
|
logger.info("Docling Studio backend ready (engine=%s)", settings.conversion_engine)
|
|
yield
|
|
|
|
|
|
app = FastAPI(
|
|
title="Docling Studio",
|
|
description="Document analysis studio powered by Docling",
|
|
lifespan=lifespan,
|
|
)
|
|
|
|
app.add_middleware(
|
|
CORSMiddleware,
|
|
allow_origins=settings.cors_origins,
|
|
allow_credentials=True,
|
|
allow_methods=["GET", "POST", "DELETE", "OPTIONS"],
|
|
allow_headers=["Content-Type", "Authorization"],
|
|
)
|
|
|
|
app.include_router(documents_router)
|
|
app.include_router(analyses_router)
|
|
|
|
|
|
@app.get("/api/health")
|
|
def health():
|
|
"""Health check endpoint."""
|
|
return {
|
|
"status": "ok",
|
|
"version": settings.app_version,
|
|
"engine": settings.conversion_engine,
|
|
}
|