refactor(rag/nlp): standardize knowledge graph retrieval to use DocumentChunk and add debug logging

The knowledge graph retrieval logic in `search.py` was updated to consistently return `DocumentChunk` instances instead of raw dictionaries, improving type safety and alignment with the RAG pipeline's expected data structure. Additionally, debug logging was enhanced in `draft_run_service.py` to log the full `retrieve_chunks_result` before extracting page content, aiding troubleshooting.

api/app/services/draft_run_service.py

@@ -223,8 +223,8 @@ def create_knowledge_retrieval_tool(kb_config, kb_ids, user_id, citations_collec
 
             retrieve_chunks_result = knowledge_retrieval(query, kb_config)
             if retrieve_chunks_result:
+                logger.warning(f"检索知识结果：{retrieve_chunks_result}")
                 retrieval_knowledge = [i.page_content for i in retrieve_chunks_result]
-                logger.warning(f"检索知识结果：{retrieval_knowledge}")
                 context = '\n\n'.join(retrieval_knowledge)
                 logger.info(
                     "知识库检索成功",