v0.8: Serper 集成 + H1 章节标题双行居中 + 反方证据观点化 + 术语核查命令
新增:Google 系检索(SerpAPI → Serper.dev) - scripts/lib/serper_client.py:封装 serper.dev 的 Google Search / Scholar / News / Patents - 专利检索用 site:patents.google.com 技巧,serper.dev 没专用 endpoint 但效果很好 - Scholar 带引用数、年份、期刊信息,便于权威信源识别 - News 支持 time_range(d/w/m/y)时效性过滤 - scripts/lib/search_client.py 扩展为多路由门面: - search() 通用:Exa → Tavily - patents() 专利:Serper(Google Patents)→ 通用搜索 + site: 兜底 - scholar() 论文:Serper Scholar → 通用搜索兜底 - news() 新闻:Serper News → 通用搜索兜底 - 所有 httpx 客户端 trust_env=False,绕过系统 socks5 代理(v0.6 修过的 TLS EOF) - .opencode/skills/search-strategy/SKILL.md §三重写:按查询类型路由,明确何时用哪个 API H1 章节标题:两行居中 + 装饰横线 - 新增 ParagraphStyle: h1-chapter-num / h1-chapter-title - 新增 parse_chapter_title() 支持中文/阿拉伯/混合空格章号: "第一章" / "第 9 章" / "第6章" / "Chapter 1" 全覆盖 - 分隔符支持: em dash — / en dash – / - / : / : - 新增 build_chapter_header():章号小字居中 + 章名大字深蓝居中 + HRFlowable 3cm 装饰线 - 只对正文章节(_title_kind == "chapter")启用;前置件(免责声明/执行摘要/术语表/目录) 仍用单行 h1 样式 反方证据段规范化(用户反馈 v0.7 问题 #5) - skill:evidence-table 新增 §"正文中反方证据段落的写作规范": - 禁止机械标题"反驳证据" / "Counter-Evidence" / "反方观点" - 必须观点化,包含具体判断(如"另一种声音:管线虚胖还是真实进展?") - 用 H2 或 H3,禁止加粗段冒充标题 - 给出段落结构模板(1-2 句过渡 → 列表型反方论点 → 整合判断) - dr-analyst.md Hard Rules #3 改为引用该规范 术语表事实核查前置(新 command /dr-glossary) - 新增 .opencode/commands/dr-glossary.md,支持 --from phase1|phase2|phase4 三个时机 - Phase 1 末 / Phase 2 初:从 framework.md 抽取专有名词种子表,在 dr-analyst 起草前 预先核查公司名/产品名/技术名拼写,避免编造错误(Mabwell → Maywavee 这类) - Phase 4:维持当前用法,对 glossary.json 全量核查 实测:dual-target-rnai-pipeline-2026 重生 PDF 55 页,所有 10 章标题双行居中正确渲染 (第一章/第二章/... 第十章 / 第 6 章 / 第 9 章 多种形式都识别)。
This commit is contained in:
@@ -115,11 +115,20 @@ class TavilyClient:
|
||||
|
||||
|
||||
class SearchClient:
|
||||
"""统一搜索门面:先用 Exa,失败/配额问题降级 Tavily。"""
|
||||
"""统一搜索门面,支持多路由:
|
||||
|
||||
- `search(query)`:通用网页搜索,优先 Exa → 降级 Tavily
|
||||
- `patents(query)`:专利检索,走 Serper(Google Patents);失败则通用搜索补刀
|
||||
- `scholar(query)`:学术论文,走 Serper Scholar;失败则通用搜索补刀
|
||||
- `news(query)`:新闻检索,走 Serper News;失败则通用搜索补刀
|
||||
|
||||
所有客户端都延迟导入 serper_client,避免没装 SERPAPI_KEY 时 import 炸。
|
||||
"""
|
||||
|
||||
def __init__(self) -> None:
|
||||
self._exa: ExaClient | None = None
|
||||
self._tavily: TavilyClient | None = None
|
||||
self._serper = None # 惰性实例化
|
||||
try:
|
||||
self._exa = ExaClient()
|
||||
except SearchError:
|
||||
@@ -133,11 +142,26 @@ class SearchClient:
|
||||
"neither EXA_API_KEY nor TAVILY_API_KEY available"
|
||||
)
|
||||
|
||||
def _get_serper(self):
|
||||
"""惰性创建 SerperClient。没 key 时返回 None。"""
|
||||
if self._serper is False:
|
||||
return None
|
||||
if self._serper is None:
|
||||
try:
|
||||
from scripts.lib.serper_client import SerperClient
|
||||
self._serper = SerperClient()
|
||||
except Exception:
|
||||
self._serper = False
|
||||
return None
|
||||
return self._serper
|
||||
|
||||
def close(self) -> None:
|
||||
if self._exa:
|
||||
self._exa.close()
|
||||
if self._tavily:
|
||||
self._tavily.close()
|
||||
if self._serper and self._serper is not False:
|
||||
self._serper.close()
|
||||
|
||||
def __enter__(self) -> "SearchClient":
|
||||
return self
|
||||
@@ -146,18 +170,12 @@ class SearchClient:
|
||||
self.close()
|
||||
|
||||
def search(self, query: str, *, num_results: int = 5) -> list[SearchHit]:
|
||||
# 优先 Exa
|
||||
"""通用网页搜索。Exa 首选,Tavily 备选。"""
|
||||
if self._exa:
|
||||
try:
|
||||
return self._exa.search(query, num_results=num_results)
|
||||
except SearchError as e:
|
||||
msg = str(e).lower()
|
||||
if "exceed" in msg or "quota" in msg or "429" in msg or "402" in msg:
|
||||
# 降级
|
||||
pass
|
||||
else:
|
||||
# 其它错误继续往下试
|
||||
pass
|
||||
except SearchError:
|
||||
pass
|
||||
if self._tavily:
|
||||
try:
|
||||
return self._tavily.search(query, num_results=num_results)
|
||||
@@ -165,13 +183,80 @@ class SearchClient:
|
||||
pass
|
||||
return []
|
||||
|
||||
def patents(self, query: str, *, num_results: int = 10) -> list[SearchHit]:
|
||||
"""专利检索:Serper 走 Google Patents 最准。降级到通用搜索 + site 限定。"""
|
||||
serper = self._get_serper()
|
||||
if serper:
|
||||
try:
|
||||
hits = serper.patents(query, num_results=num_results)
|
||||
return [SearchHit(h.title, h.url, h.snippet) for h in hits]
|
||||
except Exception:
|
||||
pass
|
||||
# 降级:通用搜索加 site 限定
|
||||
return self.search(f"site:patents.google.com {query}", num_results=num_results)
|
||||
|
||||
def scholar(
|
||||
self,
|
||||
query: str,
|
||||
*,
|
||||
num_results: int = 10,
|
||||
year_low: int | None = None,
|
||||
) -> list[SearchHit]:
|
||||
"""学术论文:Serper Scholar 带引用数。降级到通用搜索。"""
|
||||
serper = self._get_serper()
|
||||
if serper:
|
||||
try:
|
||||
hits = serper.scholar(query, num_results=num_results, year_low=year_low)
|
||||
return [
|
||||
SearchHit(
|
||||
title=h.title,
|
||||
url=h.url,
|
||||
snippet=f"{h.snippet} | {h.source} | 引用 {h.cited_by}" if h.cited_by else h.snippet,
|
||||
)
|
||||
for h in hits
|
||||
]
|
||||
except Exception:
|
||||
pass
|
||||
return self.search(query, num_results=num_results)
|
||||
|
||||
def news(
|
||||
self,
|
||||
query: str,
|
||||
*,
|
||||
num_results: int = 10,
|
||||
time_range: str | None = None,
|
||||
) -> list[SearchHit]:
|
||||
"""新闻检索:Serper News。降级到通用搜索。"""
|
||||
serper = self._get_serper()
|
||||
if serper:
|
||||
try:
|
||||
hits = serper.news(query, num_results=num_results, time_range=time_range)
|
||||
return [
|
||||
SearchHit(
|
||||
title=h.title,
|
||||
url=h.url,
|
||||
snippet=f"{h.snippet} | {h.source} | {h.date}" if h.date else h.snippet,
|
||||
)
|
||||
for h in hits
|
||||
]
|
||||
except Exception:
|
||||
pass
|
||||
return self.search(query, num_results=num_results)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from scripts.lib.zenmux_client import load_secrets
|
||||
load_secrets()
|
||||
with SearchClient() as c:
|
||||
hits = c.search("Mabwell 迈威生物 biopharmaceutical", num_results=3)
|
||||
for i, h in enumerate(hits, 1):
|
||||
print(f"[{i}] {h.title[:80]}")
|
||||
print("--- 通用: Mabwell 迈威生物 ---")
|
||||
for h in c.search("Mabwell 迈威生物 biopharmaceutical", num_results=3):
|
||||
print(f" {h.title[:80]}")
|
||||
print(f" {h.url}")
|
||||
print("\n--- 专利: dual-target siRNA ---")
|
||||
for h in c.patents("dual-target siRNA GalNAc", num_results=3):
|
||||
print(f" {h.title[:80]}")
|
||||
print(f" {h.url}")
|
||||
print("\n--- Scholar: dual-target RNAi 2024 ---")
|
||||
for h in c.scholar("dual-target RNAi drug", num_results=3, year_low=2023):
|
||||
print(f" {h.title[:80]}")
|
||||
print(f" {h.url}")
|
||||
print(f" {h.snippet[:160]}")
|
||||
|
||||
Reference in New Issue
Block a user