MangoPig
430cdf32cf
- Add entrypoint script to auto-download OCR models on first run - Include ch_sim (Simplified) and ch_tra (Traditional) for HK law firm use - Add docling_models volume for model persistence - Bump start_period to 120s for first-run download time
76 lines
2.7 KiB
YAML
76 lines
2.7 KiB
YAML
services:
|
|
# Docling
|
|
docling:
|
|
# https://github.com/docling-project/docling-serve
|
|
# 5001: Web UI + API
|
|
# OCR: EasyOCR with English + Chinese Simplified + Traditional (auto-downloaded on first run)
|
|
|
|
image: ghcr.io/docling-project/docling-serve-cpu:v1.13.0
|
|
container_name: jt-docling
|
|
restart: unless-stopped
|
|
environment:
|
|
DOCLING_SERVE_ENABLE_UI: "true"
|
|
volumes:
|
|
- docling_models:/opt/app-root/src/.cache/docling/models
|
|
ports:
|
|
- "5001:5001"
|
|
entrypoint: ["/bin/sh", "-c"]
|
|
command:
|
|
- |
|
|
# Download Chinese OCR models if missing (first run only)
|
|
if [ ! -f /opt/app-root/src/.cache/docling/models/EasyOcr/zh_sim_g2.pth ] || [ ! -f /opt/app-root/src/.cache/docling/models/EasyOcr/zh_tra_g2.pth ]; then
|
|
echo "Downloading Chinese OCR models (Simplified + Traditional)..."
|
|
python3 -c "import easyocr; easyocr.Reader(['en','ch_sim','ch_tra'], gpu=False)"
|
|
# Copy downloaded models to correct location
|
|
cp -n /opt/app-root/src/.EasyOCR/model/*.pth /opt/app-root/src/.cache/docling/models/EasyOcr/ 2>/dev/null || true
|
|
fi
|
|
exec uvicorn docling_serve.app:app --host 0.0.0.0 --port 5001
|
|
healthcheck:
|
|
test: ["CMD", "curl", "-sf", "http://localhost:5001/health"]
|
|
interval: 30s
|
|
timeout: 10s
|
|
retries: 3
|
|
start_period: 120s
|
|
|
|
# Ollama
|
|
ollama:
|
|
# https://hub.docker.com/r/ollama/ollama
|
|
# 11434: API port
|
|
# Model: qwen3:1.7b (auto-pulled on startup)
|
|
|
|
image: ollama/ollama:0.9.3
|
|
container_name: jt-ollama
|
|
restart: unless-stopped
|
|
volumes:
|
|
- ollama_data:/root/.ollama
|
|
ports:
|
|
- "11434:11434"
|
|
entrypoint: ["/bin/sh", "-c", "ollama serve & sleep 5 && ollama pull qwen3:1.7b && wait"]
|
|
healthcheck:
|
|
test: ["CMD", "curl", "-sf", "http://localhost:11434/api/tags"]
|
|
interval: 30s
|
|
timeout: 10s
|
|
retries: 5
|
|
start_period: 120s
|
|
|
|
# Tools (Python FastAPI - Excel operations)
|
|
# tools:
|
|
# build: ./Tools/Service
|
|
# container_name: jt-tools
|
|
# restart: unless-stopped
|
|
# volumes:
|
|
# - /data/jingtian/BenjaminTeam:/data:rw
|
|
# ports:
|
|
# - "8080:8080"
|
|
# healthcheck:
|
|
# test: ["CMD", "curl", "-sf", "http://localhost:8080/health"]
|
|
# interval: 30s
|
|
# timeout: 10s
|
|
# retries: 3
|
|
|
|
volumes:
|
|
docling_models:
|
|
name: jt-docling-models
|
|
ollama_data:
|
|
name: jt-ollama-data
|