feat: 新增多格式文件上传入库与认证体系

- 新增 JWT 认证模块，支持登录/注册/用户管理
- 新增文件上传接口，支持 .txt/.md/.html/.pdf/.docx 等格式解析入库
- 新增检索结果 AI 总结功能
- 新增文本去重缓存机制
- 新增全局认证夹具简化测试
- 新增配置项与环境变量支持
- 完善文档与测试覆盖

app/core/retriever.py

@@ -15,11 +15,12 @@ from qdrant_client import models
 
 from app.config import settings
 from app.core.embeddings import EmbeddingService, create_embedding_service
-from app.core.query_parser import QueryParser
+from app.core.query_parser import QueryParser, RouteDecision
 from app.core.ranker import finalize, rrf_fuse
+from app.core.result_summarizer import ResultSummarizer
 from app.core.sparse import SparseEncoder
 from app.models.knowledge import load_taxonomy
-from app.models.search import SearchHit, SearchRequest, SearchResponse
+from app.models.search import ExtractedInfo, SearchHit, SearchRequest, SearchResponse
 from app.services.ollama import OllamaClient
 from app.services.qdrant import (
     COLLECTION_CHUNKS,
@@ -47,6 +48,7 @@ class Retriever:
         query_parser: QueryParser | None = None,
         embedding: EmbeddingService | None = None,
         sparse_encoder: SparseEncoder | None = None,
+        result_summarizer: ResultSummarizer | None = None,
     ) -> None:
         self.qdrant = qdrant or QdrantService()
         self.query_parser = query_parser or QueryParser(
@@ -55,6 +57,7 @@ class Retriever:
         )
         self.embedding = embedding or create_embedding_service()
         self.sparse_encoder = sparse_encoder or SparseEncoder()
+        self.result_summarizer = result_summarizer or ResultSummarizer()
 
     async def search(self, request: SearchRequest) -> SearchResponse:
         """分层检索主流程"""
@@ -74,12 +77,8 @@ class Retriever:
             # L1 无候选文档 → 全库 chunk 兜底
             chunk_hits = await self._search_collection(COLLECTION_CHUNKS, dense, sparse, settings.retrieval_top_k, None)
             logger.info("L1 无命中，全库 chunk 兜底", hits=len(chunk_hits))
-            return SearchResponse(
-                query=request.query,
-                hits=self._to_hits(finalize(chunk_hits, self._final_k(request))),
-                routed_categories=route.filter_categories or [],
-                fallback=True,
-            )
+            hits = self._to_hits(finalize(chunk_hits, self._final_k(request)))
+            return await self._build_response(request, route, hits, fallback=True)
 
         doc_ids = _unique((p.payload or {}).get("doc_id") for p in l1_hits)
 
@@ -125,12 +124,8 @@ class Retriever:
         logger.info("chunk 检索完成", hits=len(chunk_hits))
 
         final_points = finalize(rrf_fuse([chunk_hits]), self._final_k(request))
-        return SearchResponse(
-            query=request.query,
-            hits=self._to_hits(final_points),
-            routed_categories=route.filter_categories or [],
-            fallback=route.fallback,
-        )
+        hits = self._to_hits(final_points)
+        return await self._build_response(request, route, hits, fallback=route.fallback)
 
     async def _search_collection(
         self,
@@ -167,3 +162,33 @@ class Retriever:
                 )
             )
         return hits
+
+    async def _build_response(
+        self,
+        request: SearchRequest,
+        route: RouteDecision,
+        hits: list[SearchHit],
+        *,
+        fallback: bool,
+    ) -> SearchResponse:
+        """构造最终响应：组装 AI 提取信息，按需生成结果总结"""
+        parsed = route.parsed
+        extracted = ExtractedInfo(
+            rewrite=parsed.rewrite,
+            keywords=parsed.keywords,
+            entities=parsed.entities,
+            intent=parsed.intent,
+            time_range=parsed.time_range,
+            categories=[c.name for c in parsed.categories],
+        )
+        summary: str | None = None
+        if request.summarize:
+            summary = await self.result_summarizer.summarize(request.query, hits)
+        return SearchResponse(
+            query=request.query,
+            hits=hits,
+            routed_categories=route.filter_categories or [],
+            fallback=fallback,
+            extracted_info=extracted,
+            summary=summary,
+        )