Async Sqlite for Agent

Kern supports using Sqlite asynchronously as a storage backend for Agents, with the AsyncSqliteDb class.

Usage

1"""
2Run `uv pip install openai sqlalchemy aiosqlite` to install dependencies.
3"""
4import asyncio
5
6from kern.agent import Agent
7from kern.db.sqlite import AsyncSqliteDb
8from kern.tools.hackernews import HackerNewsTools
9
10# Initialize AsyncSqliteDb
11db = AsyncSqliteDb(db_file="agent_storage.db")
12
13agent = Agent(
14    db=db,
15    tools=[HackerNewsTools()],
16    add_history_to_context=True,
17    add_datetime_to_context=True,
18)
19
20asyncio.run(agent.aprint_response("How many people live in Canada?"))
21asyncio.run(agent.aprint_response("What is their national anthem called?"))

Params

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.
`traces_table`	`Optional[str]`	-	Name of the table to store traces.
`spans_table`	`Optional[str]`	-	Name of the table to store spans.