Prepare for public git: .gitignore, .env, sanitized configs

- Add .gitignore excluding .env, __pycache__, test_files (copyrighted PDFs),
  session logs, marker/ submodule, and other generated/private files
- Add .env with local config (gitignored); expand .env.example with all
  supported environment variables
- docker-compose.yml: all hardcoded values now use default pattern
- Containerfile: install marker-pdf from GitHub instead of local submodule;
  fix AMD_COMPUTE default to false; sanitize default OLLAMA_HOST
- Remove marker/ submodule from git tracking (keep local checkout via .gitignore)
- Remove session transcript and copyrighted ENISA PDFs from git tracking
- Sanitize local IPs in README, kubernetes deployment, deploy-podman.sh
- Fix hardcoded paths in convert_both.py and compare_conversions.py
- Update requirements.txt to reference GitHub instead of local --editable
This commit is contained in:
oval
2026-06-08 12:29:43 +02:00
parent 3601d48f5a
commit 33997778f6
18 changed files with 126 additions and 8573 deletions
+6 -5
View File
@@ -5,24 +5,25 @@ import time
import json
import requests
API_URL = "http://localhost:8000/v1/files/convert"
SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
API_URL = os.environ.get("API_URL", "http://localhost:8001/v1/files/convert")
TEST_CASES = [
{
"name": "Text-focused Strategy Report",
"file": "/home/oval/marker-api/test_files/enisa/enisa-international-strategy-2026.pdf",
"file": os.path.join(SCRIPT_DIR, "test_files", "enisa", "enisa-international-strategy-2026.pdf"),
"pages": "1-2",
"desc": "Standard text-focused policy brief with small section headers."
},
{
"name": "Complex Policy Report with Tables",
"file": "/home/oval/marker-api/test_files/enisa/nis-investments-2025.pdf",
"file": os.path.join(SCRIPT_DIR, "test_files", "enisa", "nis-investments-2025.pdf"),
"pages": "5-6",
"desc": "Rich, multi-column cybersecurity report containing charts, lists, and formatted tables."
},
{
"name": "Dense Scientific Paper (arXiv)",
"file": "/home/oval/marker-api/test_files/downloaded/attention.pdf",
"file": os.path.join(SCRIPT_DIR, "test_files", "downloaded", "attention.pdf"),
"pages": "4-5",
"desc": "Attention Is All You Need. Pages 4-5 contain complex math equations, multi-head attention diagrams, and structured text."
}
@@ -113,7 +114,7 @@ def main():
})
# Generate the Markdown report
report_path = "/home/oval/marker-api/test_files/conversion_comparison_report.md"
report_path = os.path.join(SCRIPT_DIR, "test_files", "conversion_comparison_report.md")
report = []
report.append("# Marker API: AMD GPU vs. Deepseek-OCR (llama.cpp) Comparison")