SqliteDb

SqliteDb is a class that implements the Db interface using SQLite as the backend storage system. It provides lightweight, file-based storage for agent sessions with support for JSON data types and schema versioning.

Parameter	Type	Default	Description
db_engine	Optional[Engine]	-	The SQLAlchemy database engine to use.
db_url	Optional[str]	-	The database URL to connect to.
db_file	Optional[str]	-	The database file to connect to.
session_table	Optional[str]	-	Name of the table to store Agent, Team and Workflow sessions.
memory_table	Optional[str]	-	Name of the table to store user memories.
metrics_table	Optional[str]	-	Name of the table to store metrics.
eval_table	Optional[str]	-	Name of the table to store evaluation runs data.
knowledge_table	Optional[str]	-	Name of the table to store knowledge documents data.

Methods

upsert_sessions

Bulk upsert multiple sessions for improved performance on large datasets.

Parameters:

• sessions (List[Session]): List of sessions to upsert
• deserialize (Optional[bool]): Whether to deserialize the sessions. Defaults to True

Returns: List[Union[Session, Dict[str, Any]]]

upsert_memories

Bulk upsert multiple memories for improved performance on large datasets.

Parameters:

• memories (List[UserMemory]): List of memories to upsert
• deserialize (Optional[bool]): Whether to deserialize the memories. Defaults to True

Returns: List[Union[UserMemory, Dict[str, Any]]]