oval/marker_api
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

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

Browse Source 
- 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
Download Patch File Download Diff File Expand all files Collapse all files
convert_both.py
+8 -7
View File
@@ -6,16 +6,17 @@ import requests
API_URL = os.environ.get("API_URL", "http://localhost:8001/v1/files/convert")
SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
TEST_FILES = [
"/home/oval/marker-api/test_files/enisa/enisa-international-strategy-2026.pdf",
"/home/oval/marker-api/test_files/enisa/nis-investments-2025.pdf",
"/home/oval/marker-api/test_files/enisa/enisa-nis360-2026.pdf",
"/home/oval/marker-api/test_files/enisa/enisa-stakeholder-strategy-2026-2028.pdf",
"/home/oval/marker-api/test_files/enisa/nis2-technical-implementation-guidance.pdf",
"/home/oval/marker-api/test_files/downloaded/attention.pdf",
os.path.join(SCRIPT_DIR, "test_files", "enisa", "enisa-international-strategy-2026.pdf"),
os.path.join(SCRIPT_DIR, "test_files", "enisa", "nis-investments-2025.pdf"),
os.path.join(SCRIPT_DIR, "test_files", "enisa", "enisa-nis360-2026.pdf"),
os.path.join(SCRIPT_DIR, "test_files", "enisa", "enisa-stakeholder-strategy-2026-2028.pdf"),
os.path.join(SCRIPT_DIR, "test_files", "enisa", "nis2-technical-implementation-guidance.pdf"),
os.path.join(SCRIPT_DIR, "test_files", "downloaded", "attention.pdf"),
]
OUTPUT_BASE = "/home/oval/marker-api/test_files/conversion_comparison"
OUTPUT_BASE = os.path.join(SCRIPT_DIR, "test_files", "conversion_comparison")
def convert(filepath, use_llm):
if not os.path.exists(filepath):