Merge branch 'main' into fix-knowledgestorage-default-instantiation

src/crewai/knowledge/knowledge.py

@@ -14,13 +14,13 @@ class Knowledge(BaseModel):
     Knowledge is a collection of sources and setup for the vector store to save and query relevant context.
     Args:
         sources: List[BaseKnowledgeSource] = Field(default_factory=list)
-        storage: KnowledgeStorage = Field(default_factory=KnowledgeStorage)
+        storage: Optional[KnowledgeStorage] = Field(default=None)
         embedder_config: Optional[Dict[str, Any]] = None
     """
 
     sources: List[BaseKnowledgeSource] = Field(default_factory=list)
     model_config = ConfigDict(arbitrary_types_allowed=True)
-    storage: KnowledgeStorage = Field(default_factory=KnowledgeStorage)
+    storage: Optional[KnowledgeStorage] = Field(default=None)
     embedder_config: Optional[Dict[str, Any]] = None
     collection_name: Optional[str] = None
 

src/crewai/knowledge/source/base_file_knowledge_source.py

@@ -22,7 +22,7 @@ class BaseFileKnowledgeSource(BaseKnowledgeSource, ABC):
         default_factory=list, description="The path to the file"
     )
     content: Dict[Path, str] = Field(init=False, default_factory=dict)
-    storage: KnowledgeStorage = Field(default_factory=KnowledgeStorage)
+    storage: Optional[KnowledgeStorage] = Field(default=None)
     safe_file_paths: List[Path] = Field(default_factory=list)
 
     @field_validator("file_path", "file_paths", mode="before")
@@ -62,7 +62,10 @@ class BaseFileKnowledgeSource(BaseKnowledgeSource, ABC):
 
     def _save_documents(self):
         """Save the documents to the storage."""
-        self.storage.save(self.chunks)
+        if self.storage:
+            self.storage.save(self.chunks)
+        else:
+            raise ValueError("No storage found to save documents.")
 
     def convert_to_path(self, path: Union[Path, str]) -> Path:
         """Convert a path to a Path object."""

src/crewai/knowledge/source/base_knowledge_source.py

@@ -16,7 +16,7 @@ class BaseKnowledgeSource(BaseModel, ABC):
     chunk_embeddings: List[np.ndarray] = Field(default_factory=list)
 
     model_config = ConfigDict(arbitrary_types_allowed=True)
-    storage: KnowledgeStorage = Field(default_factory=KnowledgeStorage)
+    storage: Optional[KnowledgeStorage] = Field(default=None)
     metadata: Dict[str, Any] = Field(default_factory=dict)  # Currently unused
     collection_name: Optional[str] = Field(default=None)
 
@@ -46,4 +46,7 @@ class BaseKnowledgeSource(BaseModel, ABC):
         Save the documents to the storage.
         This method should be called after the chunks and embeddings are generated.
         """
-        self.storage.save(self.chunks)
+        if self.storage:
+            self.storage.save(self.chunks)
+        else:
+            raise ValueError("No storage found to save documents.")

src/crewai/memory/entity/entity_memory.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from crewai.memory.entity.entity_memory_item import EntityMemoryItem
 from crewai.memory.memory import Memory
 from crewai.memory.storage.rag_storage import RAGStorage
@@ -40,7 +38,7 @@ class EntityMemory(Memory):
             )
         super().__init__(storage)
 
-    def save(self, item: EntityMemoryItem, custom_key: Optional[str] = None) -> None:  # type: ignore # BUG?: Signature of "save" incompatible with supertype "Memory"
+    def save(self, item: EntityMemoryItem) -> None:  # type: ignore # BUG?: Signature of "save" incompatible with supertype "Memory"
         """Saves an entity item into the SQLite storage."""
         if self.memory_provider == "mem0":
             data = f"""
@@ -51,7 +49,7 @@ class EntityMemory(Memory):
             """
         else:
             data = f"{item.name}({item.type}): {item.description}"
-        super().save(data, item.metadata, custom_key=custom_key)
+        super().save(data, item.metadata)
 
     def reset(self) -> None:
         try:

src/crewai/memory/long_term/long_term_memory.py

@@ -1,4 +1,4 @@
-from typing import Any, Dict, List, Optional
+from typing import Any, Dict, List
 
 from crewai.memory.long_term.long_term_memory_item import LongTermMemoryItem
 from crewai.memory.memory import Memory
@@ -19,12 +19,9 @@ class LongTermMemory(Memory):
             storage = LTMSQLiteStorage(db_path=path) if path else LTMSQLiteStorage()
         super().__init__(storage)
 
-    def save(self, item: LongTermMemoryItem, custom_key: Optional[str] = None) -> None:  # type: ignore # BUG?: Signature of "save" incompatible with supertype "Memory"
+    def save(self, item: LongTermMemoryItem) -> None:  # type: ignore # BUG?: Signature of "save" incompatible with supertype "Memory"
         metadata = item.metadata
         metadata.update({"agent": item.agent, "expected_output": item.expected_output})
-        if custom_key:
-            metadata.update({"custom_key": custom_key})
-            
         self.storage.save(  # type: ignore # BUG?: Unexpected keyword argument "task_description","score","datetime" for "save" of "Storage"
             task_description=item.task,
             score=metadata["quality"],
@@ -32,8 +29,8 @@ class LongTermMemory(Memory):
             datetime=item.datetime,
         )
 
-    def search(self, task: str, latest_n: int = 3, custom_key: Optional[str] = None) -> List[Dict[str, Any]]:  # type: ignore # signature of "search" incompatible with supertype "Memory"
-        return self.storage.load(task, latest_n, custom_key)  # type: ignore # BUG?: "Storage" has no attribute "load"
+    def search(self, task: str, latest_n: int = 3) -> List[Dict[str, Any]]:  # type: ignore # signature of "search" incompatible with supertype "Memory"
+        return self.storage.load(task, latest_n)  # type: ignore # BUG?: "Storage" has no attribute "load"
 
     def reset(self) -> None:
         self.storage.reset()

src/crewai/memory/memory.py

@@ -5,10 +5,7 @@ from crewai.memory.storage.rag_storage import RAGStorage
 
 class Memory:
     """
-    Base class for memory, now supporting agent tags, generic metadata, and custom keys.
-    
-    Custom keys allow scoping memories to specific entities (users, accounts, sessions),
-    retrieving memories contextually, and preventing data leakage across logical boundaries.
+    Base class for memory, now supporting agent tags and generic metadata.
     """
 
     def __init__(self, storage: RAGStorage):
@@ -19,13 +16,10 @@ class Memory:
         value: Any,
         metadata: Optional[Dict[str, Any]] = None,
         agent: Optional[str] = None,
-        custom_key: Optional[str] = None,
     ) -> None:
         metadata = metadata or {}
         if agent:
             metadata["agent"] = agent
-        if custom_key:
-            metadata["custom_key"] = custom_key
 
         self.storage.save(value, metadata)
 
@@ -34,12 +28,7 @@ class Memory:
         query: str,
         limit: int = 3,
         score_threshold: float = 0.35,
-        custom_key: Optional[str] = None,
     ) -> List[Any]:
-        filter_dict = None
-        if custom_key:
-            filter_dict = {"custom_key": {"$eq": custom_key}}
-            
         return self.storage.search(
-            query=query, limit=limit, score_threshold=score_threshold, filter=filter_dict
+            query=query, limit=limit, score_threshold=score_threshold
         )

src/crewai/memory/short_term/short_term_memory.py

@@ -46,31 +46,22 @@ class ShortTermMemory(Memory):
         value: Any,
         metadata: Optional[Dict[str, Any]] = None,
         agent: Optional[str] = None,
-        custom_key: Optional[str] = None,
     ) -> None:
         item = ShortTermMemoryItem(data=value, metadata=metadata, agent=agent)
         if self.memory_provider == "mem0":
             item.data = f"Remember the following insights from Agent run: {item.data}"
 
-        super().save(value=item.data, metadata=item.metadata, agent=item.agent, custom_key=custom_key)
+        super().save(value=item.data, metadata=item.metadata, agent=item.agent)
 
     def search(
         self,
         query: str,
         limit: int = 3,
         score_threshold: float = 0.35,
-        custom_key: Optional[str] = None,
     ):
-        filter_dict = None
-        if custom_key:
-            filter_dict = {"custom_key": {"$eq": custom_key}}
-            
         return self.storage.search(
-            query=query, 
-            limit=limit, 
-            score_threshold=score_threshold,
-            filter=filter_dict
-        )
+            query=query, limit=limit, score_threshold=score_threshold
+        )  # type: ignore # BUG? The reference is to the parent class, but the parent class does not have this parameters
 
     def reset(self) -> None:
         try:

src/crewai/memory/storage/ltm_sqlite_storage.py

@@ -70,31 +70,22 @@ class LTMSQLiteStorage:
             )
 
     def load(
-        self, task_description: str, latest_n: int, custom_key: Optional[str] = None
+        self, task_description: str, latest_n: int
     ) -> Optional[List[Dict[str, Any]]]:
         """Queries the LTM table by task description with error handling."""
         try:
             with sqlite3.connect(self.db_path) as conn:
                 cursor = conn.cursor()
-                
-                query = """
+                cursor.execute(
+                    f"""
                     SELECT metadata, datetime, score
                     FROM long_term_memories
                     WHERE task_description = ?
-                """
-                
-                params = [task_description]
-                
-                if custom_key:
-                    query += " AND json_extract(metadata, '$.custom_key') = ?"
-                    params.append(custom_key)
-                
-                query += f"""
                     ORDER BY datetime DESC, score ASC
                     LIMIT {latest_n}
-                """
-                
-                cursor.execute(query, params)
+                """,  # nosec
+                    (task_description,),
+                )
                 rows = cursor.fetchall()
                 if rows:
                     return [

src/crewai/memory/storage/rag_storage.py

@@ -120,11 +120,7 @@ class RAGStorage(BaseRAGStorage):
 
         try:
             with suppress_logging():
-                response = self.collection.query(
-                    query_texts=query, 
-                    n_results=limit,
-                    where=filter
-                )
+                response = self.collection.query(query_texts=query, n_results=limit)
 
             results = []
             for i in range(len(response["ids"][0])):

src/crewai/memory/user/user_memory.py

@@ -26,27 +26,20 @@ class UserMemory(Memory):
         value,
         metadata: Optional[Dict[str, Any]] = None,
         agent: Optional[str] = None,
-        custom_key: Optional[str] = None,
     ) -> None:
         # TODO: Change this function since we want to take care of the case where we save memories for the usr
         data = f"Remember the details about the user: {value}"
-        super().save(data, metadata, custom_key=custom_key)
+        super().save(data, metadata)
 
     def search(
         self,
         query: str,
         limit: int = 3,
         score_threshold: float = 0.35,
-        custom_key: Optional[str] = None,
     ):
-        filter_dict = None
-        if custom_key:
-            filter_dict = {"custom_key": {"$eq": custom_key}}
-            
         results = self.storage.search(
             query=query,
             limit=limit,
             score_threshold=score_threshold,
-            filter=filter_dict,
         )
         return results

tests/memory/custom_key_memory_test.py

@@ -1,57 +0,0 @@
-import pytest
-from unittest.mock import patch, MagicMock
-
-from crewai.memory.short_term.short_term_memory import ShortTermMemory
-from crewai.memory.short_term.short_term_memory_item import ShortTermMemoryItem
-from crewai.agent import Agent
-from crewai.crew import Crew
-from crewai.task import Task
-
-
-@pytest.fixture
-def short_term_memory():
-    """Fixture to create a ShortTermMemory instance"""
-    agent = Agent(
-        role="Researcher",
-        goal="Search relevant data and provide results",
-        backstory="You are a researcher at a leading tech think tank.",
-        tools=[],
-        verbose=True,
-    )
-
-    task = Task(
-        description="Perform a search on specific topics.",
-        expected_output="A list of relevant URLs based on the search query.",
-        agent=agent,
-    )
-    return ShortTermMemory(crew=Crew(agents=[agent], tasks=[task]))
-
-
-def test_save_with_custom_key(short_term_memory):
-    """Test that save method correctly passes custom_key to storage"""
-    with patch.object(short_term_memory.storage, 'save') as mock_save:
-        short_term_memory.save(
-            value="Test data",
-            metadata={"task": "test_task"},
-            agent="test_agent",
-            custom_key="user123",
-        )
-        
-        called_args = mock_save.call_args[0]
-        called_kwargs = mock_save.call_args[1]
-        
-        assert "custom_key" in called_args[1]
-        assert called_args[1]["custom_key"] == "user123"
-
-
-def test_search_with_custom_key(short_term_memory):
-    """Test that search method correctly passes custom_key to storage"""
-    expected_results = [{"context": "Test data", "metadata": {"custom_key": "user123"}, "score": 0.95}]
-    
-    with patch.object(short_term_memory.storage, 'search', return_value=expected_results) as mock_search:
-        results = short_term_memory.search("test query", custom_key="user123")
-        
-        mock_search.assert_called_once()
-        filter_arg = mock_search.call_args[1].get('filter')
-        assert filter_arg == {"custom_key": {"$eq": "user123"}}
-        assert results == expected_results