Async PostgreSQL

Use PostgreSQL asynchronously for session storage.

v2.1.5

Agno supports using PostgreSQL asynchronously, with the AsyncPostgresDb class.

Usage

postgres_for_agent.py

from agno.agent import Agent
from agno.db.postgres import AsyncPostgresDb

# Replace with your own connection string, and notice the `async_` prefix
db_url = "postgresql+psycopg_async://ai:ai@localhost:5532/ai"

# Setup your Database
db = AsyncPostgresDb(db_url=db_url)

# Setup your Agent with the Database
agent = Agent(db=db)

Run Postgres (with PgVector)

Install docker desktop and run PgVector on port 5532 using:

docker run -d \
  -e POSTGRES_DB=ai \
  -e POSTGRES_USER=ai \
  -e POSTGRES_PASSWORD=ai \
  -e PGDATA=/var/lib/postgresql/data/pgdata \
  -v pgvolume:/var/lib/postgresql/data \
  -p 5532:5432 \
  --name pgvector \
  agnohq/pgvector:16

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.

Developer Resources

• View Cookbook