Files
deer-flow/skills/public/pdf-processing/scripts/convert_pdf_to_images.py
DanielWalnut cfa97f7a96 feat: add skills system for specialized agent workflows (#6)
Implement a skills framework that enables specialized workflows for
specific tasks (e.g., PDF processing, web page generation). Skills are
discovered from the skills/ directory and automatically mounted in
sandboxes with path mapping support.

- Add SkillsConfig for configuring skills path and container mount point
- Implement dynamic skill loading from SKILL.md files with YAML frontmatter
- Add path mapping in LocalSandbox to translate container paths to local paths
- Mount skills directory in AIO Docker sandbox containers
- Update lead agent prompt to dynamically inject available skills
- Add setup documentation and expand config.example.yaml

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-16 14:44:51 +08:00

36 lines
1.1 KiB
Python

import os
import sys
from pdf2image import convert_from_path
# Converts each page of a PDF to a PNG image.
def convert(pdf_path, output_dir, max_dim=1000):
images = convert_from_path(pdf_path, dpi=200)
for i, image in enumerate(images):
# Scale image if needed to keep width/height under `max_dim`
width, height = image.size
if width > max_dim or height > max_dim:
scale_factor = min(max_dim / width, max_dim / height)
new_width = int(width * scale_factor)
new_height = int(height * scale_factor)
image = image.resize((new_width, new_height))
image_path = os.path.join(output_dir, f"page_{i+1}.png")
image.save(image_path)
print(f"Saved page {i+1} as {image_path} (size: {image.size})")
print(f"Converted {len(images)} pages to PNG images")
if __name__ == "__main__":
if len(sys.argv) != 3:
print("Usage: convert_pdf_to_images.py [input pdf] [output directory]")
sys.exit(1)
pdf_path = sys.argv[1]
output_directory = sys.argv[2]
convert(pdf_path, output_directory)