This example shows how to add content from an Amazon S3 bucket to your knowledge base. This allows you to process documents stored in cloud storage without downloading them locally.

​
Code

s3.py
import asyncio
from agno.agent import Agent
from agno.db.postgres import PostgresDb
from agno.knowledge.knowledge import Knowledge
from agno.knowledge.remote_content.remote_content import S3Content
from agno.vectordb.pgvector import PgVector

contents_db = PostgresDb(
    db_url="postgresql+psycopg://ai:ai@localhost:5532/ai",
    knowledge_table="knowledge_contents",
)

# Create Knowledge Instance
knowledge = Knowledge(
    name="Basic SDK Knowledge Base",
    description="Agno 2.0 Knowledge Implementation",
    contents_db=contents_db,
    vector_db=PgVector(
        table_name="vectors", db_url="postgresql+psycopg://ai:ai@localhost:5532/ai"
    ),
)

# Add from S3 bucket
asyncio.run(
    knowledge.add_content_async(
        name="S3 PDF",
        remote_content=S3Content(
            bucket_name="agno-public", key="recipes/ThaiRecipes.pdf"
        ),
        metadata={"remote_content": "S3"},
    )
)

agent = Agent(
    name="My Agent",
    description="Agno 2.0 Agent Implementation",
    knowledge=knowledge,
    search_knowledge=True,
    debug_mode=True,
)

agent.print_response(
    "What is the best way to make a Thai curry?",
    markdown=True,
)

​
Usage

1

Install libraries

pip install -U agno sqlalchemy psycopg pgvector boto3
2

Configure AWS credentials

Set up your AWS credentials using one of these methods:
  • AWS CLI: aws configure
  • Environment variables: AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY
  • IAM roles (if running on AWS infrastructure)
3

Run PgVector

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
4

Run the example

python cookbook/knowledge/basic_operations/06_from_s3.py

​
Params

ParameterTypeDefaultDescription
bucket_namestr-Name of the S3 bucket containing the file.
bucketOptional[S3Bucket]-Pre-configured S3 bucket object.
keystr-S3 object key (file path) within the bucket.
objectOptional[S3Object]-Pre-configured S3 object.
prefixOptional[str]-Path prefix for organizing files in the bucket.