Feat/fix palyground bug (#727)

* 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

---------

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

@@ -405,7 +405,7 @@ def generate_chat_response() -> Generator[str, None, None]:
                         readable_cube_ids=readable_cube_ids,
                         mode="fast",
                         internet_search=False,
-                        top_k=5,
+                        top_k=20,
                         chat_history=chat_req.history,
                         session_id=chat_req.session_id,
                         include_preference=True,
@@ -428,7 +428,7 @@ def generate_chat_response() -> Generator[str, None, None]:
                             memories_list = text_mem_results[0]["memories"]
 
                     # Filter memories by threshold
-                    filtered_memories = self._filter_memories_by_threshold(memories_list)
+                    filtered_memories = self._filter_memories_by_threshold(memories_list)[:5]
 
                     # Prepare reference data (first search)
                     reference = prepare_reference_data(filtered_memories)
@@ -459,9 +459,7 @@ def generate_chat_response() -> Generator[str, None, None]:
                     searcher = self.dependencies.searcher
                     parsed_goal = searcher.task_goal_parser.parse(
                         task_description=chat_req.query,
-                        context="\n".join(
-                            [memory.get("memory", "") for memory in filtered_memories]
-                        ),
+                        context="\n".join([memory.get("memory", "") for memory in memories_list]),
                         conversation=chat_req.history,
                         mode="fine",
                     )
@@ -481,7 +479,7 @@ def generate_chat_response() -> Generator[str, None, None]:
                     # ======  second deep search  ======
                     search_req = APISearchRequest(
                         query=(parsed_goal.rephrased_query or chat_req.query)
-                        + (f"{parsed_goal.tags}" if parsed_goal.tags else ""),
+                        + (f" {parsed_goal.memories}" if parsed_goal.memories else ""),
                         user_id=chat_req.user_id,
                         readable_cube_ids=readable_cube_ids,
                         mode="fast",

src/memos/memories/textual/tree_text_memory/retrieve/utils.py

@@ -4,7 +4,7 @@
 1. Keys: the high-level keywords directly relevant to the user’s task.
 2. Tags: thematic tags to help categorize and retrieve related memories.
 3. Goal Type: retrieval | qa | generation
-4. Rephrased instruction: Give a rephrased task instruction based on the former conversation to make it less confusing to look alone. Make full use of information related to the query, including user's personal information, such as user's name, location, preferences, etc. If you think the task instruction is easy enough to understand, or there is no former conversation, set "rephrased_instruction" to an empty string.
+4. Rephrased instruction: Give a rephrased task instruction based on the former conversation to make it less confusing to look alone. Make full use of information related to the query, including user's personal information, such as user's name, location, preferences, etc. If you think the task instruction is enough for search, or there is no former conversation, set "rephrased_instruction" to an empty string.
 5. Need for internet search: If the user's task instruction only involves objective facts or can be completed without introducing external knowledge, set "internet_search" to False. Otherwise, set it to True.
 6. Memories: Provide 2–5 short semantic expansions or rephrasings of the rephrased/original user task instruction. These are used for improved embedding search coverage. Each should be clear, concise, and meaningful for retrieval.