Refactor document handling and update Milvus collection settings

- Removed multiple failed document entries from `documents.json`.
- Added a new document entry with updated metadata and changed the index name to `regulations_dense_1024_v2`.
- Updated architecture documentation to reflect changes in the Milvus collection name.
- Adjusted requirements by removing the sqlalchemy dependency.
- Modified test cases to align with new document structure and naming conventions.
- Introduced a new test file for Milvus vector index runtime recovery and error handling.
- Updated assertions in various test files to ensure compatibility with the new schema.

backend/app/api/routes/__init__.py

@@ -7,6 +7,7 @@ from .knowledge import router as knowledge_router
 from .agent import router as agent_router
 from .status import router as status_router
 from .perception import router as perception_router
+from .rag import router as rag_router
 # Keep package boundaries explicit so backend imports stay predictable.
 
 
@@ -20,6 +21,7 @@ api_router.include_router(agent_router)
 api_router.include_router(compliance_router)
 api_router.include_router(status_router)
 api_router.include_router(perception_router)
+api_router.include_router(rag_router)
 
 __all__ = [
     "api_router",
@@ -29,4 +31,5 @@ __all__ = [
     "compliance_router",
     "status_router",
     "perception_router",
+    "rag_router",
 ]

backend/app/api/routes/knowledge.py

@@ -29,14 +29,19 @@ async def search_knowledge(request: SearchRequest):
         results=[
             SearchResultItem(
                 id=index + 1,
-                content=item.content,
+                content=item.text,
                 score=item.score,
                 metadata={
                     "doc_id": item.doc_id,
-                    "doc_name": item.doc_name,
+                    "doc_title": item.doc_title,
                     "chunk_id": item.chunk_id,
+                    "chunk_type": item.chunk_type,
                     "section_title": item.section_title,
-                    "page_number": item.page_number,
+                    "page_start": item.page_start,
+                    "page_end": item.page_end,
+                    "section_level": item.section_level,
+                    "chunk_index": item.chunk_index,
+                    "piece_index": item.piece_index,
                     **item.metadata,
                 },
             )

backend/app/api/routes/rag.py

@@ -50,8 +50,8 @@ async def rag_chat(request: RagChatRequest):
                     {
                         "id": str(s.get("chunk_id") or s.get("doc_id") or idx + 1),
                         "score": s.get("score", 0),
-                        "preview": s.get("content", "")[:200],
-                        "doc_name": s.get("doc_name", ""),
+                        "preview": s.get("text", s.get("content", ""))[:200],
+                        "doc_name": s.get("doc_title", s.get("doc_name", "")),
                         "clause": s.get("section_title", "法规片段"),
                         "doc_id": s.get("doc_id"),
                         "download_url": (