Documentation Index
Fetch the complete documentation index at: https://docs-v1.agno.com/llms.txt
Use this file to discover all available pages before exploring further.
Agno supports using PostgreSQL as a storage backend for Teams using the PostgresStorage class.
Usage
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/data/pgdata \
-v pgvolume:/var/lib/postgresql/data \
-p 5532:5432 \
--name pgvector \
agno/pgvector:16
postgres_storage_for_team.py
"""
Run: `pip install openai duckduckgo-search newspaper4k lxml_html_clean agno` to install the dependencies
"""
from typing import List
from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.storage.postgres import PostgresStorage
from agno.team import Team
from agno.tools.duckduckgo import DuckDuckGoTools
from agno.tools.hackernews import HackerNewsTools
from pydantic import BaseModel
db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"
class Article(BaseModel):
title: str
summary: str
reference_links: List[str]
hn_researcher = Agent(
name="HackerNews Researcher",
model=OpenAIChat("gpt-4o"),
role="Gets top stories from hackernews.",
tools=[HackerNewsTools()],
)
web_searcher = Agent(
name="Web Searcher",
model=OpenAIChat("gpt-4o"),
role="Searches the web for information on a topic",
tools=[DuckDuckGoTools()],
add_datetime_to_instructions=True,
)
hn_team = Team(
name="HackerNews Team",
mode="coordinate",
model=OpenAIChat("gpt-4o"),
members=[hn_researcher, web_searcher],
storage=PostgresStorage(
table_name="agent_sessions", db_url=db_url, auto_upgrade_schema=True
),
instructions=[
"First, search hackernews for what the user is asking about.",
"Then, ask the web searcher to search for each story to get more information.",
"Finally, provide a thoughtful and engaging summary.",
],
response_model=Article,
show_tool_calls=True,
markdown=True,
debug_mode=True,
show_members_responses=True,
)
hn_team.print_response("Write an article about the top 2 stories on hackernews")
Params
| Parameter | Type | Default | Description |
|---|
table_name | str | - | Name of the table to be used. |
schema | Optional[str] | "ai" | Schema name, default is "ai". |
db_url | Optional[str] | None | Database URL, if provided. |
db_engine | Optional[Engine] | None | Database engine to be used. |
schema_version | int | 1 | Version of the schema, default is 1. |
auto_upgrade_schema | bool | False | If true, automatically upgrades the schema when necessary. |
Developer Resources