swarmauri_tool_downloadpdf 0.11.0.dev1

Swarmauri document-ingestion tool for downloading PDFs and returning base64-encoded content.

Swarmauri Tool Download PDF

swarmauri_tool_downloadpdf is a Swarmauri document-ingestion tool for fetching a PDF from a URL and returning its contents as a base64-encoded string. It is useful for agent workflows, document capture, API handoffs, and pipelines that need PDF content in memory without writing directly to disk.

Why Use Swarmauri Tool Download PDF

• Retrieve PDFs from remote URLs inside Swarmauri workflows.
• Keep document transfer in-memory with base64 output.
• Hand off downloaded PDF content to parsers, storage layers, or APIs.
• Surface structured success or error responses from HTTP downloads.

FAQ

What does the tool return on success?
A dictionary with message and base64-encoded content.

Does it save files to disk?
No. It downloads bytes into memory and returns them encoded as base64.

What input does it expect?
The callable runtime surface currently expects a single url string.

How are download failures reported?
The tool returns an error key with a descriptive message.

Features

• Swarmauri ToolBase implementation registered as DownloadPDFTool.
• Fetches PDF bytes with httpx.
• Returns PDF content as base64 for easy transport.
• Avoids filesystem writes in the default flow.
• Supports Python 3.10, 3.11, 3.12, 3.13, and 3.14.

Installation

uv add swarmauri_tool_downloadpdf

pip install swarmauri_tool_downloadpdf

Usage

from swarmauri_tool_downloadpdf import DownloadPDFTool

tool = DownloadPDFTool()
result = tool("https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf")

print(result.keys())

Examples

Decode the returned PDF payload

import base64
from swarmauri_tool_downloadpdf import DownloadPDFTool

tool = DownloadPDFTool()
result = tool("https://example.com/report.pdf")

if "content" in result:
    pdf_bytes = base64.b64decode(result["content"])
    print(len(pdf_bytes))

Send PDF content to another API

import httpx
from swarmauri_tool_downloadpdf import DownloadPDFTool

tool = DownloadPDFTool()
result = tool("https://example.com/form.pdf")

if "content" in result:
    httpx.post("https://api.example.com/upload", json=result)

Use the tool in a Swarmauri collection

from swarmauri_standard.tools.ToolCollection import ToolCollection
from swarmauri_tool_downloadpdf import DownloadPDFTool

tools = ToolCollection(tools=[DownloadPDFTool()])
print(tools)

Related Packages

• swarmauri_parser_pypdf2
• swarmauri_parser_fitzpdf
• swarmauri_parser_pypdftk
• swarmauri_tool_webscraping

Swarmauri Foundations

• swarmauri
• swarmauri_core
• swarmauri_base
• swarmauri_standard

More Documentation

• HTTPX documentation
• Base64 encoding in Python
• Swarmauri SDK repository

Best Practices

• Validate and sanitize URLs before downloading untrusted documents.
• Guard against large PDFs if memory pressure matters in your runtime.
• Check for error before decoding returned content.
• Hand base64 output directly to downstream services when possible to avoid unnecessary temporary files.

License

This project is licensed under the Apache-2.0 License.