AWS PDF Agent Bytes

Pass a PDF as bytes to Amazon Nova Pro on Bedrock and extract a recipe from it.

pdf_agent_bytes.py

"""
Aws Pdf Agent Bytes
===================

Cookbook example for `aws/bedrock/pdf_agent_bytes.py`.
"""

from pathlib import Path

from agno.agent import Agent
from agno.media import File
from agno.models.aws import AwsBedrock
from agno.utils.media import download_file

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------

pdf_path = Path(__file__).parent.joinpath("ThaiRecipes.pdf")

download_file(
    "https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf", str(pdf_path)
)

agent = Agent(
    model=AwsBedrock(id="amazon.nova-pro-v1:0"),
    markdown=True,
)

pdf_bytes = pdf_path.read_bytes()

agent.print_response(
    "Give the recipe of Gaeng Kiew Wan Goong",
    files=[File(content=pdf_bytes, format="pdf", name="Thai Recipes")],
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    pass

Run the Example

1. Set up your virtual environment

   Mac

   uv venv --python 3.12
   source .venv/bin/activate
   

   uv venv --python 3.12
   .venv\Scripts\activate
   
2. Install dependencies

   uv pip install -U agno aioboto3 boto3
   
3. Export environment variables

   Mac/Linux

   export AWS_ACCESS_KEY_ID="your_aws_access_key_id_here"
   export AWS_SECRET_ACCESS_KEY="your_aws_secret_access_key_here"
   

   $Env:AWS_ACCESS_KEY_ID="your_aws_access_key_id_here"
   $Env:AWS_SECRET_ACCESS_KEY="your_aws_secret_access_key_here"
   
4. Run the example

   Save the code above as pdf_agent_bytes.py, then run:

   python pdf_agent_bytes.py
   

Full source: cookbook/90_models/aws/bedrock/pdf_agent_bytes.py