PDF Input URL

Fetch a PDF from a URL and summarize it with a Vertex AI Claude agent.

Vertex AI accepts only base64-encoded document sources, so fetch the PDF and pass its bytes with File(content=...). File(url=...) sends a URL document source, which Vertex AI rejects.

Code

import httpx

from agno.agent import Agent
from agno.media import File
from agno.models.vertexai.claude import Claude

agent = Agent(
    model=Claude(id="claude-sonnet-4-6"),
    markdown=True,
)

pdf_bytes = httpx.get(
    "https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"
).content

agent.print_response(
    "Summarize the contents of the attached file.",
    files=[
        File(content=pdf_bytes),
    ],
)

Usage

Complete the Vertex project, model enablement, permissions, and CLI prerequisites first. Use a region that serves Sonnet 4.6.

Set up your virtual environment

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

Set your environment variables

export CLOUD_ML_REGION="us-east5"
export GOOGLE_CLOUD_PROJECT=xxx

Authenticate your CLI session

gcloud auth application-default login
You don't need to authenticate your CLI every time.

Install dependencies

uv pip install -U 'anthropic[vertex]' agno

Run Agent

python pdf_input_url.py