Merge branch 'dev' into dev

Author: tangg555

docker/requirements.txt

@@ -15,6 +15,7 @@ click==8.2.1
 cobble==0.1.4
 colorama==0.4.6
 coloredlogs==15.0.1
+concurrent-log-handler==0.9.28
 cryptography==45.0.5
 cyclopts==3.22.2
 defusedxml==0.7.1

poetry.lock

@@ -471,7 +471,7 @@ def get_internet_config() -> dict[str, Any]:
         return {
             "backend": "bocha",
             "config": {
-                "api_key": os.getenv("BOCHA_API_KEY"),
+                "api_key": os.getenv("BOCHA_API_KEY", "bocha"),
                 "max_results": 15,
                 "num_per_request": 10,
                 "reader": {

src/memos/api/config.py

@@ -200,7 +200,6 @@ def init_server() -> dict[str, Any]:
     )
 
     logger.debug("Memory manager initialized")
-
     tokenizer = FastTokenizer()
     # Initialize text memory
     text_mem = SimpleTreeTextMemory(

src/memos/api/handlers/component_init.py

@@ -318,7 +318,7 @@ def _vector_recall(
         query_embedding: list[list[float]],
         memory_scope: str,
         top_k: int = 20,
-        max_num: int = 5,
+        max_num: int = 20,
         status: str = "activated",
         cube_name: str | None = None,
         search_filter: dict | None = None,

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

@@ -4,6 +4,7 @@
 from pathlib import Path
 from typing import Any
 
+
 import numpy as np
 
 from memos.dependency import require_python_package

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

@@ -284,6 +284,49 @@ def _parse_task(
 
         return parsed_goal, query_embedding, context, query
 
+    @timed
+    def _retrieve_simple(
+        self,
+        query: str,
+        top_k: int,
+        search_filter: dict | None = None,
+        user_name: str | None = None,
+        **kwargs,
+    ):
+        """Retrieve from by keywords and embedding"""
+        query_words = []
+        if self.tokenizer:
+            query_words = self.tokenizer.tokenize_mixed(query)
+        else:
+            query_words = query.strip().split()
+        query_words = [query, *query_words]
+        logger.info(f"[SIMPLESEARCH] Query words: {query_words}")
+        query_embeddings = self.embedder.embed(query_words)
+
+        items = self.graph_retriever.retrieve_from_mixed(
+            top_k=top_k * 2,
+            memory_scope=None,
+            query_embedding=query_embeddings,
+            search_filter=search_filter,
+            user_name=user_name,
+            use_fast_graph=self.use_fast_graph,
+        )
+        logger.info(f"[SIMPLESEARCH] Items count: {len(items)}")
+        documents = [getattr(item, "memory", "") for item in items]
+        documents_embeddings = self.embedder.embed(documents)
+        similarity_matrix = cosine_similarity_matrix(documents_embeddings)
+        selected_indices, _ = find_best_unrelated_subgroup(documents, similarity_matrix)
+        selected_items = [items[i] for i in selected_indices]
+        logger.info(
+            f"[SIMPLESEARCH] after unrelated subgroup selection items count: {len(selected_items)}"
+        )
+        return self.reranker.rerank(
+            query=query,
+            query_embedding=query_embeddings[0],
+            graph_results=selected_items,
+            top_k=top_k,
+        )
+
     @timed
     def _retrieve_paths(
         self,
@@ -367,7 +410,6 @@ def _retrieve_paths(
                         mode=mode,
                     )
                 )
-
             results = []
             for t in tasks:
                 results.extend(t.result())