feat: export reproducible retrieval history snapshots

This commit is contained in:
2026-10-16 23:08:13 +08:00
parent 5736ad1924
commit f5cddee937
12 changed files with 800 additions and 3 deletions
+23
View File
@@ -1,12 +1,14 @@
from uuid import UUID
from fastapi import APIRouter, Depends, HTTPException, Query
from fastapi.responses import Response
from sqlalchemy import func, select
from sqlalchemy.orm import Session
from app.db.session import get_db
from app.models import RetrievalRun
from app.schemas.catalog import Page
from app.schemas.exports import ExportHistory
from app.schemas.hybrid import (
ChunkKeywordRequest,
ChunkKeywordResponse,
@@ -17,6 +19,7 @@ from app.schemas.retrieval import RetrievalRequest, RetrievalResponse
from app.schemas.vectors import VectorRetrievalResponse
from app.services.auth import require_admin
from app.services.embedding_runtime import get_embedding_provider
from app.services.exports import export_history
from app.services.hybrid import retrieve_chunks, retrieve_hybrid
from app.services.retrieval import retrieve
@@ -25,6 +28,26 @@ router = APIRouter(prefix="/retrieval", tags=["retrieval"])
RunResponse = RetrievalResponse | VectorRetrievalResponse | ChunkKeywordResponse | HybridResponse
@router.post(
"/exports",
response_class=Response,
responses={200: {"content": {"application/x-ndjson": {}}, "description": "JSONL 历史快照"}},
dependencies=[Depends(require_admin)],
)
def download_history(payload: ExportHistory, db: Session = Depends(get_db)):
"""管理员按明确编号导出历史;沿用 Origin/CSRF,失败不返回部分文件。"""
content, export_id, digest = export_history(db, payload)
return Response(
content,
media_type="application/x-ndjson; charset=utf-8",
headers={
"Content-Disposition": f'attachment; filename="nalati-retrieval-{export_id}.jsonl"',
"X-Records-SHA256": digest,
"X-Content-Type-Options": "nosniff",
},
)
@router.post("", response_model=RetrievalResponse)
def keyword_retrieval(payload: RetrievalRequest, db: Session = Depends(get_db)):
"""只检索已核验知识;保存原始检索结果供复核,不调用大模型。"""