Async Postgres for Agent

Kern supports using PostgreSQL asynchronously, with the AsyncPostgresDb class.

Usage

Run PgVector

Install docker desktop and run PgVector on port 5532 using:

1docker run -d \
2  -e POSTGRES_DB=ai \
3  -e POSTGRES_USER=ai \
4  -e POSTGRES_PASSWORD=ai \
5  -e PGDATA=/var/lib/postgresql/data/pgdata \
6  -v pgvolume:/var/lib/postgresql/data \
7  -p 5532:5432 \
8  --name pgvector \
9  agnohq/pgvector:16

1import asyncio
2
3from kern.agent import Agent
4from kern.db.postgres import AsyncPostgresDb
5from kern.tools.hackernews import HackerNewsTools
6
7db_url = "postgresql+psycopg_async://ai:ai@localhost:5532/ai"
8db = AsyncPostgresDb(db_url=db_url)
9
10agent = Agent(
11    db=db,
12    tools=[HackerNewsTools()],
13    add_history_to_context=True,
14    add_datetime_to_context=True,
15)
16
17asyncio.run(agent.aprint_response("How many people live in Canada?"))
18asyncio.run(agent.aprint_response("What is their national anthem called?"))

Params

Parameter	Type	Default	Description
`id`	`Optional[str]`	-	The ID of the database instance. UUID by default.
`db_url`	`Optional[str]`	-	The database URL to connect to.
`db_engine`	`Optional[AsyncEngine]`	-	The SQLAlchemy asyncdatabase engine to use.
`db_schema`	`Optional[str]`	-	The database schema to use.
`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 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 content.
`traces_table`	`Optional[str]`	-	Name of the table to store traces.
`spans_table`	`Optional[str]`	-	Name of the table to store spans.