fix docker issue

This commit is contained in:
EduBrain Dev
2026-04-14 17:25:06 +08:00
parent 4c6a20e5fc
commit c5f96056fa
9 changed files with 170 additions and 537 deletions

View File

@@ -107,7 +107,7 @@ bot_manager = BotManager()
async def lifespan(_app: FastAPI) -> AsyncGenerator[None, None]:
"""
应用生命周期管理:
- 启动时:初始化数据目录、验证数据库连接、预热嵌入服务、初始化 BM25 索引
- 启动时:初始化数据目录、验证数据库连接、预热嵌入服务
- 关闭时:释放数据库连接
"""
_logger = logging.getLogger(__name__)
@@ -126,53 +126,6 @@ async def lifespan(_app: FastAPI) -> AsyncGenerator[None, None]:
except Exception as exc:
_logger.warning("嵌入服务预热失败(将在首次使用时重试): %s", exc)
# ── 初始化 BM25 索引 ──
try:
from app.services.search_engine import BM25Index
import app.api.v1.images as images_module
_images_bm25 = BM25Index()
# 加载数据库中已有的 OCR 记录到索引
from app.database import async_session_factory
from app.models.base import OCRImage
from sqlalchemy import select
async with async_session_factory() as session:
result = await session.execute(
select(OCRImage).where(OCRImage.status == "completed")
)
records = result.scalars().all()
for record in records:
if record.ocr_text:
index_text = record.ocr_text
if record.tags:
try:
tags = json.loads(record.tags)
if tags:
index_text += "\n" + " ".join(tags)
except Exception:
pass
if record.story_summary:
index_text += "\n" + record.story_summary
_images_bm25.add_document(
doc_id=record.id,
text=index_text,
metadata={
"file_path": record.file_path,
"tags": json.loads(record.tags) if record.tags else [],
"story_summary": record.story_summary or "",
"confidence": record.confidence,
"provider": record.provider,
"created_at": str(record.created_at),
},
)
images_module.bm25_index = _images_bm25
_logger.info("BM25 索引加载完成: %d 条记录", _images_bm25.size)
except Exception as exc:
_logger.warning("BM25 索引初始化失败: %s", exc)
yield
# ── 关闭 ──