容错显示
This commit is contained in:
1 parent
836dd73446
commit
5be5531722
17 files changed
+433
-76
No files matched your search
+8
-7
@@ -10,11 +10,8 @@ def get_search_provider(ai_writing_config: dict) -> BaseSearchProvider:
|
||||
config.yaml 中配置:
|
||||
ai_writing:
|
||||
search_provider: internet # internet(默认,DDG) / intranet / tavily / demo
|
||||
intranet_search_url: http://...
|
||||
intranet_search_api_key: ""
|
||||
intranet_field_map:
|
||||
content: "abstract"
|
||||
source: "system_name"
|
||||
intranet_search_url: http://10.106.57.180:7863/knowledge_base/search_docs_es
|
||||
intranet_knowledge_base: samples
|
||||
ddg_region: "cn-zh" # DuckDuckGo 区域,默认 cn-zh
|
||||
|
||||
internet 模式:DuckDuckGo 为主搜索(免 API Key),失败时 fallback 到 demo 演示素材。
|
||||
@@ -25,8 +22,7 @@ def get_search_provider(ai_writing_config: dict) -> BaseSearchProvider:
|
||||
if provider == "intranet":
|
||||
return IntranetSearchProvider(
|
||||
base_url=cfg.get("intranet_search_url", ""),
|
||||
api_key=cfg.get("intranet_search_api_key", ""),
|
||||
field_map=cfg.get("intranet_field_map", {}),
|
||||
knowledge_base_name=cfg.get("intranet_knowledge_base", "samples"),
|
||||
)
|
||||
if provider == "tavily":
|
||||
return _FallbackSearchProvider(InternetSearchProvider(), DemoSearchProvider())
|
||||
@@ -45,6 +41,11 @@ class _FallbackSearchProvider(BaseSearchProvider):
|
||||
self._primary = primary
|
||||
self._fallback = fallback
|
||||
|
||||
@property
|
||||
def errors(self) -> list[str]:
|
||||
"""聚合主/兜底 provider 的检索异常,供 researcher 节点取用。"""
|
||||
return list(getattr(self._primary, "errors", [])) + list(getattr(self._fallback, "errors", []))
|
||||
|
||||
async def search(self, query: str, max_results: int = 5, **kwargs):
|
||||
results = await self._primary.search(query, max_results=max_results, **kwargs)
|
||||
if not results:
|
||||
|
||||
+5
@@ -16,6 +16,8 @@ class DuckDuckGoSearchProvider(BaseSearchProvider):
|
||||
def __init__(self, region: str = "cn-zh", max_timeout: int = 30):
|
||||
self.region = region
|
||||
self.max_timeout = max_timeout
|
||||
# 收集本次运行的检索异常,供 researcher 节点取出并提示用户
|
||||
self.errors: list[str] = []
|
||||
|
||||
async def search(
|
||||
self,
|
||||
@@ -31,6 +33,7 @@ class DuckDuckGoSearchProvider(BaseSearchProvider):
|
||||
return results
|
||||
except Exception as e:
|
||||
logger.warning("DuckDuckGo search failed for query=%r: %s", query, e)
|
||||
self.errors.append(f"{type(e).__name__}: {e}")
|
||||
return []
|
||||
|
||||
def _sync_search(self, query: str, max_results: int) -> List[SearchResult]:
|
||||
@@ -38,6 +41,7 @@ class DuckDuckGoSearchProvider(BaseSearchProvider):
|
||||
from ddgs import DDGS
|
||||
except ImportError:
|
||||
logger.error("ddgs not installed. Run: uv add ddgs")
|
||||
self.errors.append("ImportError: ddgs 未安装")
|
||||
return []
|
||||
|
||||
ddgs = DDGS(timeout=self.max_timeout)
|
||||
@@ -51,6 +55,7 @@ class DuckDuckGoSearchProvider(BaseSearchProvider):
|
||||
items = list(raw) if raw else []
|
||||
except Exception as e:
|
||||
logger.warning("DDGS.text failed: %s", e)
|
||||
self.errors.append(f"{type(e).__name__}: {e}")
|
||||
return []
|
||||
|
||||
results = []
|
||||
|
||||
+69
-43
@@ -1,57 +1,83 @@
|
||||
"""内网知识库搜索适配器 —— 对接 ES 检索接口 search_docs_es。"""
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
from typing import List
|
||||
|
||||
from .base import BaseSearchProvider, SearchResult
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# 内网知识库默认检索接口与知识库名(可经 config.yaml 的 ai_writing 段覆盖)
|
||||
_DEFAULT_ENDPOINT = "http://10.106.57.180:7863/knowledge_base/search_docs_es"
|
||||
_DEFAULT_KB = "samples"
|
||||
|
||||
|
||||
class IntranetSearchProvider(BaseSearchProvider):
|
||||
"""内网搜索接口适配器。
|
||||
"""内网知识库搜索接口适配器。
|
||||
|
||||
内网系统需提供 HTTP 接口,推荐格式:
|
||||
POST /api/search
|
||||
请求体:{"query": "...", "page_size": 5}
|
||||
响应体:{"total": 100, "results": [...]}
|
||||
|
||||
对接步骤:
|
||||
1. 取消下方注释代码,调整字段映射
|
||||
2. 在 config.yaml 的 intranet_field_map 中配置字段映射
|
||||
3. 将 search_provider 改为 intranet
|
||||
接口:POST {endpoint}
|
||||
请求体:{"query": "...", "knowledge_base_name": "samples", "ts": "yes"}
|
||||
响应体:[{"page_content": "...", "metadata": {m_title, content, recUuid, m_publish, source1}}]
|
||||
"""
|
||||
|
||||
def __init__(self, base_url: str, api_key: str = "", timeout: int = 10, field_map: dict = None):
|
||||
self.base_url = base_url
|
||||
self.api_key = api_key
|
||||
def __init__(
|
||||
self,
|
||||
base_url: str = "",
|
||||
knowledge_base_name: str = _DEFAULT_KB,
|
||||
timeout: int = 15,
|
||||
**_ignored,
|
||||
):
|
||||
self.endpoint = base_url or _DEFAULT_ENDPOINT
|
||||
self.knowledge_base_name = knowledge_base_name or _DEFAULT_KB
|
||||
self.timeout = timeout
|
||||
self.field_map = field_map or {}
|
||||
|
||||
def _map(self, item: dict, field: str) -> str:
|
||||
key = self.field_map.get(field, field)
|
||||
return str(item.get(key, item.get(field, "")))
|
||||
# 收集本次运行的检索异常,供 researcher 节点取出并提示用户(ES 波动等)
|
||||
self.errors: list[str] = []
|
||||
|
||||
async def search(self, query: str, max_results: int = 5, **kwargs) -> List[SearchResult]:
|
||||
# ── 对接内网时,取消以下注释 ──────────────────────────────────────
|
||||
# import httpx
|
||||
# headers = {"Authorization": f"Bearer {self.api_key}"} if self.api_key else {}
|
||||
# async with httpx.AsyncClient(timeout=self.timeout) as client:
|
||||
# resp = await client.post(
|
||||
# f"{self.base_url}/api/search",
|
||||
# json={"query": query, "page_size": max_results},
|
||||
# headers=headers,
|
||||
# )
|
||||
# resp.raise_for_status()
|
||||
# items = resp.json().get("results", [])
|
||||
# return [
|
||||
# SearchResult(
|
||||
# title=self._map(it, "title"),
|
||||
# content=self._map(it, "content")[:500],
|
||||
# source=self._map(it, "source"),
|
||||
# published_at=self._map(it, "published_at"),
|
||||
# relevance_score=float(it.get(self.field_map.get("relevance_score", "relevance_score"), 0)),
|
||||
# recUuid=self._map(it, "recUuid"),
|
||||
# source_type="intranet",
|
||||
# )
|
||||
# for it in items
|
||||
# ]
|
||||
return []
|
||||
import httpx
|
||||
|
||||
payload = {
|
||||
"query": query,
|
||||
"knowledge_base_name": self.knowledge_base_name,
|
||||
"ts": "yes",
|
||||
}
|
||||
try:
|
||||
async with httpx.AsyncClient(timeout=self.timeout) as client:
|
||||
resp = await client.post(self.endpoint, json=payload)
|
||||
resp.raise_for_status()
|
||||
data = resp.json()
|
||||
except Exception as e:
|
||||
logger.warning("intranet search failed for query=%r: %s", query, e)
|
||||
self.errors.append(f"{type(e).__name__}: {e}")
|
||||
return []
|
||||
|
||||
# 接口直接返回数组;兼容个别情况下包了一层 data/results 的情况
|
||||
if isinstance(data, dict):
|
||||
items = data.get("data") or data.get("results") or []
|
||||
else:
|
||||
items = data or []
|
||||
|
||||
results: List[SearchResult] = []
|
||||
for i, item in enumerate(items[:max_results]):
|
||||
md = (item or {}).get("metadata") or {}
|
||||
content = md.get("content") or (item or {}).get("page_content") or ""
|
||||
results.append(SearchResult(
|
||||
title=str(md.get("m_title") or "").strip() or "(无标题)",
|
||||
content=str(content)[:500],
|
||||
source=str(md.get("source1") or "").strip() or "内网知识库",
|
||||
published_at=str(md.get("m_publish") or "").strip(),
|
||||
url="", # 内网素材的原文地址由前端依据 recUuid 拼接
|
||||
# 接口未返回相关度分值,按 ES 返回顺序赋递减分以保留排序
|
||||
relevance_score=max(0.5, 0.95 - i * 0.03),
|
||||
source_type="intranet",
|
||||
recUuid=str(md.get("recUuid") or "").strip(),
|
||||
))
|
||||
return results
|
||||
|
||||
async def health_check(self) -> bool:
|
||||
return False
|
||||
try:
|
||||
await self.search("测试", max_results=1)
|
||||
return True
|
||||
except Exception:
|
||||
return False
|
||||
Reference in new issue
Block a user