feat: 知识库朴素语义搜索（输入→检索→结果列表）

backend/app/api/knowledge.py

@@ -1,8 +1,9 @@
 """
-知识库 API — 上传 / 列表 / 删除 / 来源筛选
+知识库 API — 上传 / 列表 / 删除 / 来源筛选 / 语义搜索
 """
 
 from typing import Optional
+from pydantic import BaseModel
 
 from fastapi import APIRouter, Depends, HTTPException, UploadFile, File, Query, status
 from sqlmodel import Session
@@ -104,3 +105,28 @@ def get_grouped_knowledge_items(
     """
     svc = KnowledgeService()
     return svc.get_grouped_items()
+
+
+class SearchRequest(BaseModel):
+    query: str
+    top_k: int = 5
+
+
+@router.post("/search")
+def search_knowledge(
+    body: SearchRequest,
+    session: Session = Depends(get_session),
+    current_user: User = Depends(require_role(UserRole.zhipianren, UserRole.zebian, UserRole.biandao)),
+):
+    """
+    语义检索：输入一段文字，返回最相关的知识库条目及相似度。
+    查询向量用 type="query"（区分于存入时的 type="db"）。
+    三角色均可读。
+    """
+    svc = KnowledgeService()
+    results = svc.search_similar(query_text=body.query, top_k=body.top_k)
+    return {
+        "results": results,
+        "query": body.query,
+        "count": len(results),
+    }

backend/app/services/knowledge_service.py

@@ -232,7 +232,10 @@ class KnowledgeService:
     def search_similar(self, query_text: str, top_k: int = 5) -> list[dict]:
         """
         语义检索：查询句转为向量，用 SQL 余弦距离（<=>）在数据库层检索
-        返回 top_k 条相似笔记，含相似度分数
+        返回 top_k 条相似笔记，含相似度分数 + 原文片段（SQL 端截断前 200 字）。
+
+        注意：当前取前 200 字是已知妥协（整篇向量检索无法定位中段命中点），
+        Phase 4a 做切块检索（chunk）时可优化为取最相关片段。
         """
         query_vector = self.embedder.embed_single(query_text, embed_type="query")
         vec_str = "[" + ",".join(str(v) for v in query_vector) + "]"
@@ -243,6 +246,9 @@ class KnowledgeService:
                     ki.id,
                     ki.title,
                     ki.source_type,
+                    ki.author,
+                    ki.tags,
+                    SUBSTRING(ki.content_md, 1, 200) AS snippet,
                     1 - (ke.embedding <=> '{vec_str}'::vector) AS similarity
                 FROM knowledge_embeddings ke
                 JOIN knowledge_items ki ON ke.knowledge_id = ki.id
@@ -252,10 +258,20 @@ class KnowledgeService:
             """
             stmt = text(sql)
             rows = session.execute(stmt).all()
-            return [
-                {"id": r.id, "title": r.title, "source_type": r.source_type, "similarity": round(r.similarity, 4)}
-                for r in rows
-            ]
+            results = []
+            for r in rows:
+                tags = r.tags or {}
+                source_detail = tags.get("source_detail") if isinstance(tags, dict) else None
+                results.append({
+                    "id": r.id,
+                    "title": r.title,
+                    "source_type": r.source_type,
+                    "author": r.author,
+                    "source_detail": source_detail,
+                    "snippet": r.snippet,
+                    "similarity": round(r.similarity, 4),
+                })
+            return results
 
     def get_item_count(self) -> int:
         with Session(engine) as session: