Async Postgres for Workflows

Agno supports using PostgreSQL asynchronously, with the AsyncPostgresDb class.

Usage

Install the sqlalchemy, psycopg, openai, and ddgs packages:

uv pip install sqlalchemy psycopg openai ddgs

Run 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 \
  -v pgvolume:/var/lib/postgresql \
  -p 5532:5432 \
  --name pgvector \
  agnohq/pgvector:18

async_postgres_for_workflow.py

import asyncio

from agno.agent import Agent
from agno.db.postgres import AsyncPostgresDb
from agno.models.openai import OpenAIResponses
from agno.team import Team
from agno.tools.hackernews import HackerNewsTools
from agno.tools.websearch import WebSearchTools
from agno.workflow.step import Step
from agno.workflow.workflow import Workflow

db_url = "postgresql+psycopg_async://ai:ai@localhost:5532/ai"
db = AsyncPostgresDb(db_url=db_url)

# Define agents
hackernews_agent = Agent(
    name="Hackernews Agent",
    model=OpenAIResponses(id="gpt-5.2"),
    tools=[HackerNewsTools()],
    role="Extract key insights and content from Hackernews posts",
)
web_agent = Agent(
    name="Web Agent",
    model=OpenAIResponses(id="gpt-5.2"),
    tools=[WebSearchTools()],
    role="Search the web for the latest news and trends",
)

# Define research team for complex analysis
research_team = Team(
    name="Research Team",
    members=[hackernews_agent, web_agent],
    instructions="Research tech topics from Hackernews and the web",
)

content_planner = Agent(
    name="Content Planner",
    model=OpenAIResponses(id="gpt-5.2"),
    instructions=[
        "Plan a content schedule over 4 weeks for the provided topic and research content",
        "Ensure that I have posts for 3 posts per week",
    ],
)

# Define steps
research_step = Step(
    name="Research Step",
    team=research_team,
)

content_planning_step = Step(
    name="Content Planning Step",
    agent=content_planner,
)

# Create and use workflow
if __name__ == "__main__":
    content_creation_workflow = Workflow(
        name="Content Creation Workflow",
        description="Automated content creation from blog posts to social media",
        db=db,
        steps=[research_step, content_planning_step],
    )
    asyncio.run(
        content_creation_workflow.aprint_response(
            input="AI trends in 2024",
            markdown=True,
        )
    )

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 async database 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.
culture_table	Optional[str]	-	Name of the table to store cultural knowledge.
traces_table	Optional[str]	-	Name of the table to store traces.
spans_table	Optional[str]	-	Name of the table to store spans.
versions_table	Optional[str]	-	Name of the table to store schema versions.
learnings_table	Optional[str]	-	Name of the table to store learnings.
schedules_table	Optional[str]	-	Name of the table to store cron schedules.
schedule_runs_table	Optional[str]	-	Name of the table to store schedule run history.
approvals_table	Optional[str]	-	Name of the table to store human approval requests.
auth_tokens_table	Optional[str]	-	Name of the table to store OAuth tokens for external services.
service_accounts_table	Optional[str]	-	Name of the table to store service accounts.
create_schema	bool	True	Whether to create the database schema if it doesn't exist. Set to False when the schema is managed externally.