GCS Content

This example shows how to add content from a Google Cloud Storage (GCS) bucket to your knowledge base. This allows you to process documents stored in Google Cloud without downloading them locally.

Code

gcs.py

"""This cookbook shows how to add content from a GCS bucket to the knowledge base.
1. Run: `python cookbook/agent_concepts/knowledge/12_from_gcs.py` to run the cookbook
"""

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 GCSContent
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 GCS
asyncio.run(
    knowledge.add_content_async(
        name="GCS PDF",
        remote_content=GCSContent(
            bucket_name="thai-recepies", blob_name="ThaiRecipes.pdf"
        ),
        metadata={"remote_content": "GCS"},
    )
)


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 google-cloud-storage
   

2. Configure Google Cloud credentials

   Set up your GCS credentials using one of these methods:

   • Service Account Key: Set GOOGLE_APPLICATION_CREDENTIALS environment variable
   • gcloud CLI: gcloud auth application-default login
   • Workload Identity (if running on Google Cloud)
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

   Mac

   python cookbook/knowledge/basic_operations/07_from_gcs.py
   

Params

Parameter	Type	Default	Description
bucket_name	str	-	Name of the GCS bucket containing the file.
blob_name	str	-	Name of the blob (file) within the bucket.
prefix	Optional[str]	-	Path prefix for organizing files in the bucket.
bucket	Optional[Any]	-	Pre-configured GCS bucket object.