Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
You are viewing v1 docs. For the latest documentation, visit docs.agno.com
Learn how to use PDFs from an S3 bucket in your knowledge base.
from agno.knowledge.s3.pdf import S3PDFKnowledgeBase
from agno.vectordb.pgvector import PgVector
db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"
knowledge_base = S3PDFKnowledgeBase(
bucket_name="agno-public",
key="recipes/ThaiRecipes.pdf",
vector_db=PgVector(table_name="recipes", db_url=db_url),
)
knowledge_base with an Agent:
from agno.agent import Agent
from knowledge_base import knowledge_base
agent = Agent(
knowledge=knowledge_base,
search_knowledge=True,
)
agent.knowledge.load(recreate=False)
agent.print_response("How to make Thai curry?")
| Parameter | Type | Default | Description |
|---|---|---|---|
bucket_name | str | None | The name of the S3 Bucket where the PDFs are. |
key | str | None | The key of the PDF file in the bucket. |
reader | S3PDFReader | S3PDFReader() | A S3PDFReader that converts the PDFs into Documents for the vector database. |
S3PDFKnowledgeBase is a subclass of the AgentKnowledge class and has access to the same params.
Was this page helpful?