Files
PlantAI-rag-new/paper_writer_service/app/services/paper/search.py
T
admin 91f6a1c242 feat: 新增论文撰写功能 paper-writer(独立 MCP 服务 + BFF 大脑 + 前端三卡)
- paper_writer_service(8097):FastAPI + MCP streamable-http 单端点,9 工具
  (propose_paper_outline/write_paper_section/get_paper_progress/search_refs/
  revise_paper_section/revise_paper/get_paper/complete_paper/cancel_paper),
  SQLite 三表(papers/paper_sections/citations,WAL),GB/T 7714 引用协议
- BFF:services/paper/{mcp_client,agent}.py(裸 JSON-RPC 客户端 + 规则状态机)、
  routers/paper.py、schemas.py 4 个 Paper*Block + ArtifactBlock 加 paper_id/citation_count、
  config.py 开关、main.py 条件注册、docgen.py 抽 insert_artifact 公共 helper
- 前端:intent.js paperIntent 纯函数、Composer docgen 分支 sub-route、sendPaper/轮询、
  PaperBriefCard/PaperOutlineCard/PaperProgressCard、DocPane cite-chip
- deploy/paper_restart.sh + toggle_paper.sh;compile_sdk.sh 白名单追加 paper 文件
- tests/paper 26 条(工具逻辑 + MCP 协议 + BFF 状态机 + 块 schema + 前端 intent 单测)
2026-09-30 22:29:22 +08:00

102 lines
3.6 KiB
Python

"""search.py —— vstore 8094 知识库检索客户端(search_refs 后端)。
- httpx 裸调 GET /api/vstore/search-chunks
- 失败不抛异常:返回 {"ok": False, "error": {...}},工具层降级为空结果
- vstore chunk 条目无 doi/pmid/journal/year(仅 doc_id/doc_name/snippet/score),
故 search_refs 的 meta 为尽力而为(通常为空)→ 引用多为 title kind → 降级格式 + disclaimer
"""
from __future__ import annotations
import asyncio
import os
from typing import Any
import httpx
DEFAULT_VSTORE_BASE_URL = "http://127.0.0.1:8094"
RETRY_BACKOFF = (0.5, 1.0, 2.0)
MAX_RETRIES = 2
DEFAULT_TIMEOUT = 30.0
_client: httpx.AsyncClient | None = None
def _base_url() -> str:
return (os.environ.get("VSTORE_BASE_URL") or DEFAULT_VSTORE_BASE_URL).rstrip("/")
def get_client() -> httpx.AsyncClient:
global _client
if _client is None:
_client = httpx.AsyncClient(
base_url=_base_url(), timeout=httpx.Timeout(DEFAULT_TIMEOUT, connect=5.0)
)
return _client
def set_client(client: httpx.AsyncClient) -> None:
"""注入 client(测试用 MockTransport)。"""
global _client
_client = client
async def close_client() -> None:
global _client
if _client is not None:
await _client.aclose()
_client = None
async def search_chunks(
query: str,
*,
top_k: int = 8,
min_score: float = 0.30,
timeout: float = 12.0,
) -> dict[str, Any]:
"""GET /api/vstore/search-chunks。失败返回 {ok:False, error:{...}}(不抛)。"""
client = get_client()
last_exc: BaseException | None = None
for attempt in range(MAX_RETRIES + 1):
try:
resp = await client.get(
"/api/vstore/search-chunks",
params={"q": query, "top_k": top_k, "min_score": min_score},
timeout=timeout,
)
if resp.status_code < 500:
try:
payload = resp.json()
except ValueError:
return {"ok": False, "error": {"code": "BAD_RESPONSE", "message": "vstore 响应非 JSON"}}
if not isinstance(payload, dict):
return {"ok": False, "error": {"code": "BAD_RESPONSE", "message": "vstore 响应形态异常"}}
return payload
last_exc = RuntimeError(f"vstore {resp.status_code}")
except (httpx.HTTPError, httpx.TimeoutException) as exc:
last_exc = exc
if attempt < MAX_RETRIES:
await asyncio.sleep(RETRY_BACKOFF[min(attempt, len(RETRY_BACKOFF) - 1)])
return {"ok": False, "error": {"code": "UPSTREAM_DOWN", "message": f"vstore 不可达:{last_exc}"}}
async def search_refs(paper_id: str = "", query: str = "", top_k: int = 8) -> dict[str, Any]:
"""search_refs 工具:透传 vstore 检索,映射为 {doc_id,title,snippet,score,meta}。"""
if not query:
return {"ok": False, "code": "BAD_REQUEST", "message": "缺少检索词 query"}
r = await search_chunks(query, top_k=max(1, min(int(top_k), 20)))
if not r.get("ok"):
return {"ok": True, "items": [], "warning": (r.get("error") or {}).get("message", "")}
items: list[dict[str, Any]] = []
for it in r.get("items") or []:
if not isinstance(it, dict):
continue
items.append({
"doc_id": it.get("doc_id") or "",
"title": it.get("doc_name") or it.get("doc_id") or "",
"snippet": it.get("snippet") or "",
"score": it.get("score"),
"meta": {}, # vstore chunk 无 doi/pmid/journal/year,尽力为空
})
return {"ok": True, "items": items}