Refa: cleanup synchronous functions in chat_model and implement synchronization for conversation and dialog chats (#11779)

### What problem does this PR solve?

Cleanup synchronous functions in chat_model and implement
synchronization for conversation and dialog chats.

### Type of change

- [x] Refactoring
- [x] Performance Improvement

api/apps/sdk/session.py

@@ -26,9 +26,10 @@ from api.db.db_models import APIToken
 from api.db.services.api_service import API4ConversationService
 from api.db.services.canvas_service import UserCanvasService, completion_openai
 from api.db.services.canvas_service import completion as agent_completion
-from api.db.services.conversation_service import ConversationService, iframe_completion
-from api.db.services.conversation_service import completion as rag_completion
-from api.db.services.dialog_service import DialogService, ask, chat, gen_mindmap, meta_filter
+from api.db.services.conversation_service import ConversationService
+from api.db.services.conversation_service import async_iframe_completion as iframe_completion
+from api.db.services.conversation_service import async_completion as rag_completion
+from api.db.services.dialog_service import DialogService, async_ask, async_chat, gen_mindmap, meta_filter
 from api.db.services.document_service import DocumentService
 from api.db.services.knowledgebase_service import KnowledgebaseService
 from api.db.services.llm_service import LLMBundle
@@ -141,7 +142,7 @@ async def chat_completion(tenant_id, chat_id):
         return resp
     else:
         answer = None
-        for ans in rag_completion(tenant_id, chat_id, **req):
+        async for ans in rag_completion(tenant_id, chat_id, **req):
             answer = ans
             break
         return get_result(data=answer)
@@ -245,7 +246,7 @@ async def chat_completion_openai_like(tenant_id, chat_id):
         # The value for the usage field on all chunks except for the last one will be null.
         # The usage field on the last chunk contains token usage statistics for the entire request.
         # The choices field on the last chunk will always be an empty array [].
-        def streamed_response_generator(chat_id, dia, msg):
+        async def streamed_response_generator(chat_id, dia, msg):
             token_used = 0
             answer_cache = ""
             reasoning_cache = ""
@@ -274,7 +275,7 @@ async def chat_completion_openai_like(tenant_id, chat_id):
             }
 
             try:
-                for ans in chat(dia, msg, True, toolcall_session=toolcall_session, tools=tools, quote=need_reference):
+                async for ans in async_chat(dia, msg, True, toolcall_session=toolcall_session, tools=tools, quote=need_reference):
                     last_ans = ans
                     answer = ans["answer"]
 
@@ -342,7 +343,7 @@ async def chat_completion_openai_like(tenant_id, chat_id):
         return resp
     else:
         answer = None
-        for ans in chat(dia, msg, False, toolcall_session=toolcall_session, tools=tools, quote=need_reference):
+        async for ans in async_chat(dia, msg, False, toolcall_session=toolcall_session, tools=tools, quote=need_reference):
             # focus answer content only
             answer = ans
             break
@@ -733,10 +734,10 @@ async def ask_about(tenant_id):
             return get_error_data_result(f"The dataset {kb_id} doesn't own parsed file")
     uid = tenant_id
 
-    def stream():
+    async def stream():
         nonlocal req, uid
         try:
-            for ans in ask(req["question"], req["kb_ids"], uid):
+            async for ans in async_ask(req["question"], req["kb_ids"], uid):
                 yield "data:" + json.dumps({"code": 0, "message": "", "data": ans}, ensure_ascii=False) + "\n\n"
         except Exception as e:
             yield "data:" + json.dumps(
@@ -827,7 +828,7 @@ async def chatbot_completions(dialog_id):
         resp.headers.add_header("Content-Type", "text/event-stream; charset=utf-8")
         return resp
 
-    for answer in iframe_completion(dialog_id, **req):
+    async for answer in iframe_completion(dialog_id, **req):
         return get_result(data=answer)
 
 
@@ -918,10 +919,10 @@ async def ask_about_embedded():
         if search_app := SearchService.get_detail(search_id):
             search_config = search_app.get("search_config", {})
 
-    def stream():
+    async def stream():
         nonlocal req, uid
         try:
-            for ans in ask(req["question"], req["kb_ids"], uid, search_config=search_config):
+            async for ans in async_ask(req["question"], req["kb_ids"], uid, search_config=search_config):
                 yield "data:" + json.dumps({"code": 0, "message": "", "data": ans}, ensure_ascii=False) + "\n\n"
         except Exception as e:
             yield "data:" + json.dumps(