Sqlite for Agent

Kern supports using Sqlite as a storage backend for Agents using the SqliteDb class.

Usage

You need to provide either db_url, db_file or db_engine. The following example uses db_file.

1from kern.agent import Agent
2from kern.db.sqlite import SqliteDb
3from kern.tools.hackernews import HackerNewsTools
4
5# Setup the SQLite database
6db = SqliteDb(db_file="tmp/data.db")
7
8# Setup a basic agent with the SQLite database
9agent = Agent(
10    db=db,
11    tools=[HackerNewsTools()],
12    add_history_to_context=True,
13    add_datetime_to_context=True,
14)
15
16# The Agent sessions and runs will now be stored in SQLite
17agent.print_response("How many people live in Canada?")
18agent.print_response("What is their national anthem?")
19agent.print_response("List my messages one by one")

Params

Parameter	Type	Default	Description
`id`	`Optional[str]`	-	The ID of the database instance. UUID by default.
`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.