fix: disable ssl verification for intranet ai writing search
This commit is contained in:
董宏凯 committed
1 parent
8fbfd35296
commit
4bfaeb728b
6 files changed
+117
-18
No files matched your search
+13
-7
@@ -27,13 +27,15 @@ from types import SimpleNamespace
|
||||
|
||||
from langchain_core.runnables import RunnableConfig
|
||||
|
||||
from ..search import get_search_provider, SearchResult
|
||||
from ..prompts.researcher_prompts import (
|
||||
EXTRACT_KEYWORDS_SYSTEM,
|
||||
EXTRACT_KEYWORDS_USER,
|
||||
RANK_MATERIALS_SYSTEM,
|
||||
RANK_MATERIALS_USER,
|
||||
)
|
||||
from ..search import SearchResult, get_search_provider
|
||||
from ..search.skill_search import SkillPicker
|
||||
from ..state import AIWritingState, Material, MaterialPackage
|
||||
from ..prompts.researcher_prompts import (
|
||||
EXTRACT_KEYWORDS_SYSTEM, EXTRACT_KEYWORDS_USER,
|
||||
RANK_MATERIALS_SYSTEM, RANK_MATERIALS_USER,
|
||||
)
|
||||
from ._agent_runner import (
|
||||
KEYWORDS_READY_MARKER,
|
||||
MATERIALS_RANKED_MARKER,
|
||||
@@ -620,6 +622,7 @@ async def researcher_node(state: AIWritingState, config: RunnableConfig) -> dict
|
||||
# 内网慢检索超时可在 config.yaml 的 ai_writing.intranet_search_timeout 调大，
|
||||
# 默认 600s，且最低 300s。
|
||||
timeout=_intranet_timeout_seconds(ai_writing_config),
|
||||
verify_ssl=ai_writing_config.get("intranet_verify_ssl", False),
|
||||
)
|
||||
endpoint_label = intranet_url or getattr(provider, "endpoint", "内置默认内网端点")
|
||||
intranet_debug = {
|
||||
@@ -628,6 +631,7 @@ async def researcher_node(state: AIWritingState, config: RunnableConfig) -> dict
|
||||
"endpoint": endpoint_label,
|
||||
"knowledge_base": ai_writing_config.get("intranet_knowledge_base", "samples"),
|
||||
"timeout": _intranet_timeout_seconds(ai_writing_config),
|
||||
"verify_ssl": getattr(provider, "verify_ssl", False),
|
||||
"status": "running",
|
||||
"queries": [],
|
||||
"calls": [],
|
||||
@@ -780,7 +784,7 @@ async def researcher_node(state: AIWritingState, config: RunnableConfig) -> dict
|
||||
timeout=_SKILL_SEARCH_TIMEOUT_SECONDS,
|
||||
)
|
||||
return (results or []), ""
|
||||
except asyncio.TimeoutError:
|
||||
except TimeoutError:
|
||||
msg = f"检索超时（>{_SKILL_SEARCH_TIMEOUT_SECONDS}s）"
|
||||
logger.warning("skill[%s] search timed out after %ss", skill_name, _SKILL_SEARCH_TIMEOUT_SECONDS)
|
||||
search_errors.append(f"skill[{skill_name}]: {msg}")
|
||||
@@ -923,13 +927,14 @@ async def researcher_node(state: AIWritingState, config: RunnableConfig) -> dict
|
||||
intranet_url = (ai_writing_config.get("intranet_search_url") or "").strip()
|
||||
# 诊断开关：开启后即使技能成功也照样跑完内网并记录完整结果（用于验证内网接口是否真能通）。
|
||||
intranet_debug_force = bool(ai_writing_config.get("intranet_search_debug", False))
|
||||
intranet_task: "asyncio.Task | None" = None
|
||||
intranet_task: asyncio.Task | None = None
|
||||
intranet_holder: dict = {}
|
||||
intranet_debug = {
|
||||
"configured": bool(intranet_url),
|
||||
"endpoint": intranet_url or "(未配置 ai_writing.intranet_search_url)",
|
||||
"knowledge_base": ai_writing_config.get("intranet_knowledge_base", "samples"),
|
||||
"timeout": _intranet_timeout_seconds(ai_writing_config),
|
||||
"verify_ssl": bool(ai_writing_config.get("intranet_verify_ssl", False)),
|
||||
"debug_force": intranet_debug_force,
|
||||
"status": "pending" if intranet_url else "not_configured",
|
||||
"queries": [], # 每个检索词：{query, count, error?}
|
||||
@@ -952,6 +957,7 @@ async def researcher_node(state: AIWritingState, config: RunnableConfig) -> dict
|
||||
# 兜底接口超时可在 config.yaml 的 ai_writing.intranet_search_timeout 调大，
|
||||
# 默认 600s（10 分钟），且最低 300s。
|
||||
timeout=_intranet_timeout_seconds(ai_writing_config),
|
||||
verify_ssl=ai_writing_config.get("intranet_verify_ssl", False),
|
||||
)
|
||||
intranet_holder["provider"] = intranet
|
||||
fb_keywords = keywords[:keyword_count] or [intent]
|
||||
|
||||
+4
-2
@@ -1,8 +1,8 @@
|
||||
from .base import BaseSearchProvider, SearchResult
|
||||
from .internet_search import InternetSearchProvider
|
||||
from .intranet_stub import IntranetSearchProvider, normalize_intranet_timeout
|
||||
from .demo_search import DemoSearchProvider
|
||||
from .duckduckgo_search import DuckDuckGoSearchProvider
|
||||
from .internet_search import InternetSearchProvider
|
||||
from .intranet_stub import IntranetSearchProvider, normalize_intranet_timeout, normalize_intranet_verify_ssl
|
||||
from .skill_search import SkillSearchProvider
|
||||
|
||||
|
||||
@@ -14,6 +14,7 @@ def get_search_provider(ai_writing_config: dict) -> BaseSearchProvider:
|
||||
intranet_search_url: http://10.106.57.180:7863/knowledge_base/search_docs_es
|
||||
intranet_knowledge_base: samples
|
||||
intranet_search_timeout: 300 # 内网检索超时秒数，最少 300 秒
|
||||
intranet_verify_ssl: false # 内网 HTTPS 自签名证书场景默认关闭证书校验
|
||||
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。
|
||||
@@ -26,6 +27,7 @@ def get_search_provider(ai_writing_config: dict) -> BaseSearchProvider:
|
||||
base_url=cfg.get("intranet_search_url", ""),
|
||||
knowledge_base_name=cfg.get("intranet_knowledge_base", "samples"),
|
||||
timeout=normalize_intranet_timeout(cfg.get("intranet_search_timeout")),
|
||||
verify_ssl=normalize_intranet_verify_ssl(cfg.get("intranet_verify_ssl")),
|
||||
)
|
||||
if provider == "tavily":
|
||||
return _FallbackSearchProvider(InternetSearchProvider(), DemoSearchProvider())
|
||||
|
||||
+29
-7
@@ -3,7 +3,6 @@ from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import time
|
||||
from typing import List
|
||||
|
||||
from .base import BaseSearchProvider, SearchResult, simplify_query
|
||||
|
||||
@@ -15,6 +14,8 @@ _DEFAULT_KB = "samples"
|
||||
# 内网检索最少等待 5 分钟；该接口经常慢返回，低于这个值会造成素材收集误判为空。
|
||||
_MIN_TIMEOUT_SECONDS = 300
|
||||
_DEFAULT_TIMEOUT_SECONDS = 600
|
||||
# 内网 HTTPS 检索服务常使用自签名/内部 CA 证书，默认跳过证书校验避免 SSL 证书链错误。
|
||||
_DEFAULT_VERIFY_SSL = False
|
||||
# 单条原始响应体最大保留长度，避免把超大响应整段灌进前端时间线
|
||||
_RAW_SNIPPET_LIMIT = 2000
|
||||
|
||||
@@ -28,6 +29,23 @@ def normalize_intranet_timeout(timeout: object, default: int = _DEFAULT_TIMEOUT_
|
||||
return max(value, _MIN_TIMEOUT_SECONDS)
|
||||
|
||||
|
||||
def normalize_intranet_verify_ssl(value: object, default: bool = _DEFAULT_VERIFY_SSL) -> bool:
|
||||
"""返回内网检索是否校验 SSL 证书，兼容 config.yaml 里的 bool / 字符串写法。"""
|
||||
if isinstance(value, bool):
|
||||
return value
|
||||
if value is None:
|
||||
return default
|
||||
if isinstance(value, (int, float)):
|
||||
return bool(value)
|
||||
if isinstance(value, str):
|
||||
normalized = value.strip().lower()
|
||||
if normalized in {"1", "true", "yes", "on"}:
|
||||
return True
|
||||
if normalized in {"0", "false", "no", "off"}:
|
||||
return False
|
||||
return default
|
||||
|
||||
|
||||
def _pick(d: dict, keys: tuple) -> str:
|
||||
"""从结果项里按候选字段名取第一个非空值（两套接口字段名不同，做并集兼容）。"""
|
||||
for k in keys:
|
||||
@@ -62,12 +80,14 @@ class IntranetSearchProvider(BaseSearchProvider):
|
||||
base_url: str = "",
|
||||
knowledge_base_name: str = _DEFAULT_KB,
|
||||
timeout: int = _DEFAULT_TIMEOUT_SECONDS,
|
||||
verify_ssl: bool = _DEFAULT_VERIFY_SSL,
|
||||
**_ignored,
|
||||
):
|
||||
self.endpoint = base_url or _DEFAULT_ENDPOINT
|
||||
self.knowledge_base_name = knowledge_base_name or _DEFAULT_KB
|
||||
# 内网 ES 接口很慢，兜底检索超时默认 10 分钟，且无论配置如何至少 5 分钟。
|
||||
self.timeout = normalize_intranet_timeout(timeout)
|
||||
self.verify_ssl = normalize_intranet_verify_ssl(verify_ssl)
|
||||
# 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] = []
|
||||
# 解析失败时收集的原始响应体，供前端「错误返回结果」折叠展示
|
||||
@@ -82,7 +102,7 @@ class IntranetSearchProvider(BaseSearchProvider):
|
||||
if snippet:
|
||||
self.raw_responses.append(snippet)
|
||||
|
||||
async def search(self, query: str, max_results: int = 5, **kwargs) -> List[SearchResult]:
|
||||
async def search(self, query: str, max_results: int = 5, **kwargs) -> list[SearchResult]:
|
||||
results = await self._search_once(query, max_results)
|
||||
# 0 结果兜底：复合检索词常检不出（如「特朗普竞选」），换成更核心的检索词重试一次
|
||||
# （「特朗普竞选」→「特朗普」）。仅在首检为空、且能简化出不同的词时才重试。
|
||||
@@ -93,7 +113,7 @@ class IntranetSearchProvider(BaseSearchProvider):
|
||||
results = await self._search_once(simpler, max_results)
|
||||
return results
|
||||
|
||||
async def _search_once(self, query: str, max_results: int = 5) -> List[SearchResult]:
|
||||
async def _search_once(self, query: str, max_results: int = 5) -> list[SearchResult]:
|
||||
import httpx
|
||||
|
||||
payload = {
|
||||
@@ -112,12 +132,13 @@ class IntranetSearchProvider(BaseSearchProvider):
|
||||
"status": "pending",
|
||||
"ok": False,
|
||||
"count": 0,
|
||||
"verify_ssl": self.verify_ssl,
|
||||
}
|
||||
# 排查用：每次真实调用都打一行请求明细（端点 / 知识库 / 检索词 / 超时），
|
||||
# 内网复现时直接看后端日志即可知道"到底请求了哪个地址、用什么参数"。
|
||||
logger.info(
|
||||
"[intranet-search] POST endpoint=%s kb=%s timeout=%ss query=%r",
|
||||
self.endpoint, self.knowledge_base_name, self.timeout, query,
|
||||
"[intranet-search] POST endpoint=%s kb=%s timeout=%ss verify_ssl=%s query=%r",
|
||||
self.endpoint, self.knowledge_base_name, self.timeout, self.verify_ssl, query,
|
||||
)
|
||||
try:
|
||||
# trust_env=False：**关键**。内网 ES 是内网地址，但本部署的模型走公网，
|
||||
@@ -125,7 +146,8 @@ class IntranetSearchProvider(BaseSearchProvider):
|
||||
# 会把这个内网请求也套用公网代理 → 代理到不了内网 IP → 连接被重置/空回复，
|
||||
# 表现为「接口异常」。强制忽略代理 env、直连内网（与 multi_agent.py 的回环
|
||||
# 调用同款修法）。
|
||||
async with httpx.AsyncClient(timeout=self.timeout, trust_env=False) as client:
|
||||
# verify=False：内网 HTTPS 常见自签名/内部 CA 证书；这里仅跳过本内网检索端点的证书校验。
|
||||
async with httpx.AsyncClient(timeout=self.timeout, trust_env=False, verify=self.verify_ssl) as client:
|
||||
resp = await client.post(self.endpoint, json=payload)
|
||||
call["http_status"] = getattr(resp, "status_code", None)
|
||||
resp.raise_for_status()
|
||||
@@ -210,7 +232,7 @@ class IntranetSearchProvider(BaseSearchProvider):
|
||||
"[intranet-search] OK endpoint=%s query=%r http_status=%s raw_items=%s",
|
||||
self.endpoint, query, call.get("http_status"), len(items) if isinstance(items, list) else 0,
|
||||
)
|
||||
results: List[SearchResult] = []
|
||||
results: list[SearchResult] = []
|
||||
for i, item in enumerate(items[:max_results]):
|
||||
if not isinstance(item, dict):
|
||||
continue
|
||||
|
||||
Reference in new issue
Block a user