T4: AnySearch 联网检索接入 (anysearch_client trust_env直连 NO_PROXY, kb_router use_web RRF融合, chat_context 自动注入联网上下文, admin 支持 anysearch 服务类型, 新增 POST /api/knowledge/web-search 端点)

backend/python/app/anysearch_client.py

@@ -0,0 +1,118 @@
+"""
+AnySearch 联网检索客户端
+======================
+调用 AnySearch 网页/领域搜索 API (https://api.anysearch.com/v1/search)，
+为 AI 聊天注入实时联网检索结果，亦可被后端端点 / Agent 工具复用。
+
+约束：平台容器存在智能路由代理，对外部 API 偶发重置；本客户端使用
+trust_env=False 直连 (等价于 NO_PROXY=api.anysearch.com)，规避代理重置。
+失败一律返回空/降级结果，保证聊天链路不中断。
+"""
+import logging
+from typing import List, Dict, Optional
+
+logger = logging.getLogger("aiflow.anysearch")
+
+DEFAULT_API_URL = "https://api.anysearch.com/v1/search"
+DEFAULT_ZONE = "cn"
+REQUEST_TIMEOUT = 8.0
+
+
+async def anysearch_search(
+    api_key: str,
+    api_url: str = DEFAULT_API_URL,
+    query: str = "",
+    top_k: int = 5,
+    zone: str = DEFAULT_ZONE,
+    freshness: Optional[str] = None,
+    timeout: float = REQUEST_TIMEOUT,
+) -> List[Dict]:
+    """调用 AnySearch 搜索，返回结构化结果列表。
+
+    每个结果:
+        {
+            "content": snippet 摘要文本,
+            "score": 0.9..0.5 递减,
+            "source": "web_anysearch",
+            "metadata": {"url", "title", "source_domain", "zone"}
+        }
+    失败时返回 [] (不抛异常)。
+    """
+    if not api_key:
+        return []
+    try:
+        import httpx
+    except ImportError:
+        logger.warning("httpx not available for AnySearch")
+        return []
+
+    payload = {
+        "query": query,
+        "zone": zone,
+        "top_k": max(1, min(int(top_k), 20)),
+    }
+    if freshness:
+        payload["freshness"] = freshness
+
+    headers = {
+        "Content-Type": "application/json",
+        "Authorization": f"Bearer {api_key}",
+    }
+    try:
+        # trust_env=False -> 忽略容器内 HTTP(S)_PROXY，直连 api.anysearch.com
+        async with httpx.AsyncClient(trust_env=False, timeout=timeout) as client:
+            resp = await client.post(api_url, json=payload, headers=headers)
+        if resp.status_code != 200:
+            logger.warning(f"AnySearch HTTP {resp.status_code}: {resp.text[:200]}")
+            return []
+        data = resp.json()
+        if data.get("code") != 0:
+            logger.warning(f"AnySearch biz error: {data.get('message')}")
+            return []
+        results = (data.get("data") or {}).get("results") or []
+        hits = []
+        for idx, r in enumerate(results[:top_k]):
+            title = r.get("title", "") or ""
+            url = r.get("url", "") or ""
+            snippet = r.get("snippet") or r.get("content") or ""
+            if not snippet and not title:
+                continue
+            try:
+                from urllib.parse import urlparse
+                domain = urlparse(url).netloc
+            except Exception:
+                domain = ""
+            hits.append({
+                "content": snippet,
+                "score": max(0.4, 0.9 - idx * 0.08),
+                "source": "web_anysearch",
+                "metadata": {
+                    "url": url,
+                    "title": title,
+                    "source_domain": domain,
+                    "zone": zone,
+                },
+            })
+        return hits
+    except Exception as e:
+        logger.warning(f"AnySearch search failed: {e}")
+        return []
+
+
+async def anysearch_health(api_key: str, api_url: str = DEFAULT_API_URL, timeout: float = REQUEST_TIMEOUT) -> Dict:
+    """连通性探测：返回 {"status": "connected"/"disconnected", "detail": ...}。"""
+    if not api_key:
+        return {"status": "disconnected", "detail": "未配置 API Key", "connected": False, "usable": False}
+    try:
+        import httpx
+        async with httpx.AsyncClient(trust_env=False, timeout=timeout) as client:
+            resp = await client.post(
+                api_url,
+                json={"query": "ping", "zone": DEFAULT_ZONE, "top_k": 1},
+                headers={"Content-Type": "application/json", "Authorization": f"Bearer {api_key}"},
+            )
+        if resp.status_code == 200:
+            return {"status": "connected", "detail": "AnySearch 连接正常", "connected": True, "usable": True}
+        return {"status": "error", "detail": f"HTTP {resp.status_code}", "connected": False, "usable": False}
+    except Exception as e:
+        return {"status": "error", "detail": str(e)[:200], "connected": False, "usable": False}

backend/python/app/api/admin/knowledge_admin.py

@@ -32,7 +32,7 @@ logger = logging.getLogger("aiflow")
 
 class ExternalServiceConfig(BaseModel):
     name: str = Field(min_length=1, max_length=200)
-    service_type: str = Field(..., description="dify")
+    service_type: str = Field(..., description="dify / anysearch")
     api_url: str = Field(min_length=1, max_length=500)
     api_key: Optional[str] = None
     config: Optional[Dict[str, Any]] = None
@@ -738,12 +738,15 @@ def _get_external_services_table(db: Session):
             return []
 
 
-def _check_service_connection(service_type: str, api_url: str, api_key: str) -> dict:
-    """测试外部知识库服务连接状态（当前仅支持 Dify）"""
+async def _check_service_connection(service_type: str, api_url: str, api_key: str) -> dict:
+    """测试外部知识库服务连接状态（支持 Dify / AnySearch）"""
     try:
         if service_type == "dify":
             from ...dify_kb import dify_test
             return dify_test(api_url, api_key)
+        if service_type == "anysearch":
+            from ...anysearch_client import anysearch_health
+            return await anysearch_health(api_key or "", api_url or "https://api.anysearch.com/v1/search")
         else:
             # 未知类型（如历史遗留的 fastgpt/ragflow），按通用方式探测可达性
             headers = {}
@@ -781,6 +784,7 @@ async def list_external_services(
             "items": services,
             "supported_types": [
                 {"type": "dify", "name": "Dify", "description": "LLM 应用开发平台，内置知识库管理（RAG）"},
+                {"type": "anysearch", "name": "AnySearch 联网检索", "description": "实时联网网页/领域搜索，为 AI 聊天注入最新网络信息"},
             ]
         }
     }
@@ -794,12 +798,12 @@ async def create_external_service(
 ):
     """创建新的外部知识库服务连接配置"""
     # 验证服务类型（当前仅支持 Dify）
-    valid_types = ["dify"]
+    valid_types = ["dify", "anysearch"]
     if req.service_type not in valid_types:
         raise HTTPException(status_code=400, detail=f"不支持的服务类型: {req.service_type}")
 
     # 检查连接
-    conn_result = _check_service_connection(req.service_type, req.api_url, req.api_key or "")
+    conn_result = await _check_service_connection(req.service_type, req.api_url, req.api_key or "")
 
     service_id = str(uuid.uuid4())
     config_json = json.dumps(req.config or {}, ensure_ascii=False)
@@ -916,7 +920,7 @@ async def update_external_service(
     new_key = req.api_key or row[4]
     if req.api_url or req.api_key:
         service_type = row[2]
-        conn_result = _check_service_connection(service_type, new_url, new_key)
+        conn_result = await _check_service_connection(service_type, new_url, new_key)
         updates["status"] = conn_result.get("status", "disconnected")
 
     updates["updated_at"] = "NOW()"
@@ -999,7 +1003,7 @@ async def check_external_service_status(
     if not row:
         raise HTTPException(status_code=404, detail="外部知识库服务不存在")
 
-    conn_result = _check_service_connection(row[0], row[1], row[2])
+    conn_result = await _check_service_connection(row[0], row[1], row[2])
 
     # 更新状态
     try:

backend/python/app/api/knowledge.py

@@ -1483,6 +1483,46 @@ async def tree_search_endpoint(
     }
 
 
+class WebSearchRequest(BaseModel):
+    query: str = Field(min_length=1, max_length=500)
+    top_k: int = 5
+
+
+@router.post("/web-search", summary="AnySearch 联网检索")
+async def web_search_endpoint(
+    req: WebSearchRequest,
+    db: Session = Depends(get_db),
+    current_user: User = Depends(get_current_user),
+):
+    """联网检索（AnySearch）：返回实时网页结果，供前端 / 智能体引用。"""
+    try:
+        from sqlalchemy import text
+        import json as _json
+        from ..anysearch_client import anysearch_search
+        row = db.execute(text(
+            "SELECT api_key, api_url, config FROM external_kb_services "
+            "WHERE service_type='anysearch' AND is_enabled=1 LIMIT 1"
+        )).fetchone()
+        if not row:
+            return {"code": 0, "data": {"results": [], "enabled": False, "message": "未配置 AnySearch 联网检索服务"}}
+        api_key = row[0] or ""
+        api_url = row[1] or "https://api.anysearch.com/v1/search"
+        cfg = row[2]
+        if isinstance(cfg, str):
+            try:
+                cfg = _json.loads(cfg)
+            except Exception:
+                cfg = {}
+        cfg = cfg or {}
+        zone = cfg.get("zone", "cn")
+        freshness = cfg.get("freshness")
+        hits = await anysearch_search(api_key, api_url, req.query, top_k=req.top_k, zone=zone, freshness=freshness)
+        return {"code": 0, "data": {"results": hits, "enabled": True}}
+    except Exception as e:
+        logger.warning(f"web-search endpoint failed: {e}")
+        return {"code": 1, "message": str(e), "data": {"results": []}}
+
+
 def generate_document_excerpt(doc, query: str) -> str:
     """根据文档类型生成模拟的原文摘录"""
     excerpts = {

backend/python/app/kb_router.py

@@ -63,6 +63,44 @@ async def _search_external(service: Dict, query: str, top_k: int = 5) -> List[Di
         logger.warning(f"Unknown external KB type: {service_type}")
         return []
 
+async def _get_web_services(db_session, enabled_only: bool = True) -> List[Dict]:
+    """获取已启用的 AnySearch 联网检索服务配置。"""
+    from sqlalchemy import text
+    try:
+        query = "SELECT * FROM external_kb_services WHERE service_type='anysearch'"
+        if enabled_only:
+            query += " AND is_enabled = 1"
+        query += " ORDER BY created_at DESC"
+        result = db_session.execute(text(query))
+        columns = result.keys()
+        return [dict(zip(columns, row)) for row in result.fetchall()]
+    except Exception as e:
+        logger.error(f"Failed to get AnySearch services: {e}")
+        return []
+
+
+async def _search_anysearch(service: Dict, query: str, top_k: int = 5) -> List[Dict]:
+    """调用 AnySearch 联网检索（走 app.anysearch_client）。"""
+    try:
+        from app.anysearch_client import anysearch_search
+        api_key = service.get("api_key", "")
+        api_url = service.get("api_url") or "https://api.anysearch.com/v1/search"
+        cfg = service.get("config")
+        if isinstance(cfg, str):
+            try:
+                import json
+                cfg = json.loads(cfg)
+            except Exception:
+                cfg = None
+        cfg = cfg or {}
+        zone = cfg.get("zone", "cn")
+        freshness = cfg.get("freshness")
+        k = int(cfg.get("top_k", top_k))
+        return await anysearch_search(api_key, api_url, query, top_k=k, zone=zone, freshness=freshness)
+    except Exception as e:
+        logger.error(f"AnySearch search error: {e}")
+        return []
+
 
 async def kb_router_search(
     query: str,
@@ -74,6 +112,7 @@ async def kb_router_search(
     use_vector: bool = True,
     use_external: bool = True,
     use_tree: bool = True,
+    use_web: bool = False,
 ) -> List[Dict]:
     """
     知识库路由层 — 混合检索
@@ -83,6 +122,7 @@ async def kb_router_search(
     2. 向量语义检索 (PostgreSQL+pgvector, 新增)
     3. 结构化分片段检索 (TreeSearch, 新增: 知识库目录树 + chunk 级精准命中)
     4. 外部KB检索 (Dify, 按配置)
+    5. 联网检索 (AnySearch, 可选 use_web)
 
     融合方式: Reciprocal Rank Fusion (RRF)
 
@@ -95,6 +135,7 @@ async def kb_router_search(
         use_vector: 是否使用向量检索
         use_external: 是否使用外部KB检索
         use_tree: 是否使用 TreeSearch 结构化分片段检索
+        use_web: 是否使用 AnySearch 联网检索
 
     Returns:
         融合后的检索结果列表
@@ -170,6 +211,23 @@ async def kb_router_search(
                         "metadata": item.get("metadata", {}),
                     })
 
+    # 4. 联网检索 (AnySearch, 可选)
+    if use_web and db_session is not None:
+        try:
+            web_services = await _get_web_services(db_session)
+            for svc in web_services:
+                web_hits = await _search_anysearch(svc, query, top_k)
+                for rank, item in enumerate(web_hits):
+                    all_results.append({
+                        "content": item.get("content", ""),
+                        "score": item.get("score", 0.6),
+                        "source": item.get("source", "web_anysearch"),
+                        "rank": rank + 1,
+                        "metadata": item.get("metadata", {}),
+                    })
+        except Exception as e:
+            logger.warning(f"AnySearch web search failed: {e}")
+
     if not all_results:
         return []