fix: use user-defined rerank model's top_k parameter when knowledge Q&A conversation (#1396)

### What problem does this PR solve?

During knowledge Q&A conversations, the user-defined rerank model's
top_k parameter was not used

#1395

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

api/db/services/dialog_service.py

@@ -127,7 +127,7 @@ def chat(dialog, messages, stream=True, **kwargs):
                                         dialog.similarity_threshold,
                                         dialog.vector_similarity_weight,
                                         doc_ids=kwargs["doc_ids"].split(",") if "doc_ids" in kwargs else None,
-                                        top=1024, aggs=False, rerank_mdl=rerank_mdl)
+                                        top=dialog.top_k, aggs=False, rerank_mdl=rerank_mdl)
     knowledges = [ck["content_with_weight"] for ck in kbinfos["chunks"]]
     #self-rag
     if dialog.prompt_config.get("self_rag") and not relevant(dialog.tenant_id, dialog.llm_id, questions[-1], knowledges):
@@ -136,7 +136,7 @@ def chat(dialog, messages, stream=True, **kwargs):
                                         dialog.similarity_threshold,
                                         dialog.vector_similarity_weight,
                                         doc_ids=kwargs["doc_ids"].split(",") if "doc_ids" in kwargs else None,
-                                        top=1024, aggs=False, rerank_mdl=rerank_mdl)
+                                        top=dialog.top_k, aggs=False, rerank_mdl=rerank_mdl)
         knowledges = [ck["content_with_weight"] for ck in kbinfos["chunks"]]
 
     chat_logger.info(