Refa: make RAGFlow more asynchronous 2 (#11689)

### What problem does this PR solve?

Make RAGFlow more asynchronous 2. #11551, #11579, #11619.

### Type of change

- [x] Refactoring
- [x] Performance Improvement

rag/prompts/generator.py

@@ -13,6 +13,7 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import asyncio
 import datetime
 import json
 import logging
@@ -360,6 +361,10 @@ def analyze_task(chat_mdl, prompt, task_name, tools_description: list[dict], use
     return kwd
 
 
+async def analyze_task_async(chat_mdl, prompt, task_name, tools_description: list[dict], user_defined_prompts: dict={}):
+    return await asyncio.to_thread(analyze_task, chat_mdl, prompt, task_name, tools_description, user_defined_prompts)
+
+
 def next_step(chat_mdl, history:list, tools_description: list[dict], task_desc, user_defined_prompts: dict={}):
     if not tools_description:
         return ""
@@ -378,6 +383,10 @@ def next_step(chat_mdl, history:list, tools_description: list[dict], task_desc,
     return json_str, tk_cnt
 
 
+async def next_step_async(chat_mdl, history:list, tools_description: list[dict], task_desc, user_defined_prompts: dict={}):
+    return await asyncio.to_thread(next_step, chat_mdl, history, tools_description, task_desc, user_defined_prompts)
+
+
 def reflect(chat_mdl, history: list[dict], tool_call_res: list[Tuple], user_defined_prompts: dict={}):
     tool_calls = [{"name": p[0], "result": p[1]} for p in tool_call_res]
     goal = history[1]["content"]
@@ -429,6 +438,14 @@ def rank_memories(chat_mdl, goal:str, sub_goal:str, tool_call_summaries: list[st
     return re.sub(r"^.*</think>", "", ans, flags=re.DOTALL)
 
 
+async def reflect_async(chat_mdl, history: list[dict], tool_call_res: list[Tuple], user_defined_prompts: dict={}):
+    return await asyncio.to_thread(reflect, chat_mdl, history, tool_call_res, user_defined_prompts)
+
+
+async def rank_memories_async(chat_mdl, goal:str, sub_goal:str, tool_call_summaries: list[str], user_defined_prompts: dict={}):
+    return await asyncio.to_thread(rank_memories, chat_mdl, goal, sub_goal, tool_call_summaries, user_defined_prompts)
+
+
 def gen_meta_filter(chat_mdl, meta_data:dict, query: str) -> dict:
     meta_data_structure = {}
     for key, values in meta_data.items():