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
+5 -4
View File
@@ -1,6 +1,7 @@
#!/usr/bin/env bash
# ==================================================
# deploy-podman.sh -- local podman deployment
# deploy-podman.sh -- example local podman deployment
# (customize for your host before use)
# ==================================================
set -euo pipefail
@@ -42,15 +43,15 @@ echo ">> Starting container '${IMAGE_NAME}' on port ${PORT} ..."
podman run -d \
--name "${IMAGE_NAME}" \
--network host \
-p "${PORT}:8000" \
-p "${PORT}:${PORT}" \
-v /dev/kfd:/dev/kfd \
-v /dev/dri:/dev/dri \
-e OLLAMA_HOST="${OLLAMA_HOST:-http://10.0.1.127:11434}" \
-e OLLAMA_HOST="${OLLAMA_HOST:-http://localhost:11434}" \
-e DEESEEK_OCR_MODEL="${DEESEEK_OCR_MODEL:-deepseek-ocr}" \
-e AMD_COMPUTE="${AMD_COMPUTE:-true}" \
-e TORCH_DEVICE="${TORCH_DEVICE:-rocm}" \
-e MODEL_DTYPE="${MODEL_DTYPE:-float32}" \
-e PORT=8000 \
-e PORT="${PORT}" \
-e HOST=0.0.0.0 \
-e GUNICORN_WORKERS="${GUNICORN_WORKERS:-2}" \
-e GUNICORN_THREADS="${GUNICORN_THREADS:-4}" \