Feat/fix palyground bug (#729)

* fix playground bug, internet search judge

* fix playground internet bug

* modify delete mem

* modify tool resp bug in multi cube

* fix bug in playground chat handle and search inter

* modify prompt

* fix bug in playground

* fix bug playfround

* fix bug

* fix code

* fix model bug in playground

* modify plan b

* llm param modify

* add logger in playground

* modify code

* fix bug

* modify code

* modify code

* fix bug

* fix search bug in plarground

* fixx bug

* move schadualr to back

* modify pref location

* modify fast net search

* add tags and new package

* modify prompt fix bug

* remove nltk due to image promblem

* prompt modify

* modify bug remove redundant field

* modify bug

* fix playground bug

* fix bug

* bust internet topk

* bust to 50

* fix bug cite

* modify search

* remote query add in playground

* modify bug

* modify pref bug

* move add position

* modify chat prompt

* modify overthinking

* add logger in playground chat

* midify mem

* remove must in prompt

* add logger

---------

Co-authored-by: yuan.wang <[email protected]>
Co-authored-by: chunyu li <[email protected]>
Co-authored-by: CaralHsi <[email protected]>

Author: 4 people

src/memos/api/handlers/chat_handler.py

@@ -8,6 +8,7 @@
 import asyncio
 import json
 import re
+import time
 import traceback
 
 from collections.abc import Generator
@@ -170,12 +171,18 @@ def handle_chat_complete(self, chat_req: APIChatCompleteRequest) -> dict[str, An
                 )
 
             model = chat_req.model_name_or_path or next(iter(self.chat_llms.keys()))
+
+            self.logger.info(f"[Cloud Service Chat Complete Model]: {model}")
+            strat = time.time()
             response = self.chat_llms[model].generate(current_messages, model_name_or_path=model)
+            end = time.time()
+            self.logger.info(f"[Cloud Service Chat Complete Time]: {end - strat} seconds")
 
             # Step 4: start add after chat asynchronously
             if chat_req.add_message_on_answer:
                 # Resolve writable cube IDs (for add)
                 writable_cube_ids = chat_req.writable_cube_ids or [chat_req.user_id]
+                start = time.time()
                 self._start_add_to_memory(
                     user_id=chat_req.user_id,
                     writable_cube_ids=writable_cube_ids,
@@ -184,6 +191,8 @@ def handle_chat_complete(self, chat_req: APIChatCompleteRequest) -> dict[str, An
                     full_response=response,
                     async_mode="async",
                 )
+                end = time.time()
+                self.logger.info(f"[Cloud Service Chat Add Time]: {end - start} seconds")
 
             match = re.search(r"<think>([\s\S]*?)</think>", response)
             reasoning_text = match.group(1) if match else None
@@ -295,9 +304,14 @@ def generate_chat_response() -> Generator[str, None, None]:
                         )
 
                     model = chat_req.model_name_or_path or next(iter(self.chat_llms.keys()))
+                    self.logger.info(f"[Cloud Service Chat Stream Model]: {model}")
+
+                    start = time.time()
                     response_stream = self.chat_llms[model].generate_stream(
                         current_messages, model_name_or_path=model
                     )
+                    end = time.time()
+                    self.logger.info(f"[Cloud Service Chat Stream Time]: {end - start} seconds")
 
                     # Stream the response
                     buffer = ""
@@ -329,6 +343,7 @@ def generate_chat_response() -> Generator[str, None, None]:
                         writable_cube_ids = chat_req.writable_cube_ids or (
                             [chat_req.mem_cube_id] if chat_req.mem_cube_id else [chat_req.user_id]
                         )
+                        start = time.time()
                         self._start_add_to_memory(
                             user_id=chat_req.user_id,
                             writable_cube_ids=writable_cube_ids,
@@ -337,7 +352,10 @@ def generate_chat_response() -> Generator[str, None, None]:
                             full_response=full_response,
                             async_mode="async",
                         )
-
+                        end = time.time()
+                        self.logger.info(
+                            f"[Cloud Service Chat Stream Add Time]: {end - start} seconds"
+                        )
                 except Exception as e:
                     self.logger.error(f"Error in chat stream: {e}", exc_info=True)
                     error_data = f"data: {json.dumps({'type': 'error', 'content': str(traceback.format_exc())})}\n\n"