MangoPig
106 lines
3.8 KiB
YAML
106 lines
3.8 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)
|
|
# Note: ch_sim and ch_tra are mutually exclusive, must download separately
|
|
if [ ! -f /opt/app-root/src/.cache/docling/models/EasyOcr/zh_sim_g2.pth ]; then
|
|
echo "Downloading Simplified Chinese OCR model..."
|
|
python3 -c "import easyocr; easyocr.Reader(['en','ch_sim'], gpu=False)"
|
|
cp -n /opt/app-root/src/.EasyOCR/model/*.pth /opt/app-root/src/.cache/docling/models/EasyOcr/ 2>/dev/null || true
|
|
fi
|
|
if [ ! -f /opt/app-root/src/.cache/docling/models/EasyOcr/zh_tra_g2.pth ]; then
|
|
echo "Downloading Traditional Chinese OCR model..."
|
|
python3 -c "import easyocr; easyocr.Reader(['en','ch_tra'], gpu=False)"
|
|
cp -n /opt/app-root/src/.EasyOCR/model/*.pth /opt/app-root/src/.cache/docling/models/EasyOcr/ 2>/dev/null || true
|
|
fi
|
|
exec docling-serve run --host 0.0.0.0 --port 5001
|
|
healthcheck:
|
|
test: ["CMD", "curl", "-sf", "http://localhost:5001/health"]
|
|
interval: 30s
|
|
timeout: 10s
|
|
retries: 5
|
|
start_period: 500s
|
|
|
|
# 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", "ollama", "list"]
|
|
interval: 30s
|
|
timeout: 10s
|
|
retries: 5
|
|
start_period: 120s
|
|
|
|
# Tools (Python FastAPI - Generic Excel API)
|
|
tools:
|
|
build: ./Tools/Service
|
|
container_name: jt-tools
|
|
restart: unless-stopped
|
|
environment:
|
|
DATA_ROOT: /data
|
|
volumes:
|
|
- /data/jingtian/BenjaminTeam:/data:rw
|
|
ports:
|
|
- "8000:8000"
|
|
healthcheck:
|
|
test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:8000/health')"]
|
|
interval: 30s
|
|
timeout: 10s
|
|
retries: 3
|
|
start_period: 10s
|
|
|
|
# Tracker (Go Orchestrator - Document Processing Pipeline)
|
|
tracker:
|
|
build: ./Tracker
|
|
container_name: jt-tracker
|
|
restart: unless-stopped
|
|
volumes:
|
|
- /data/jingtian/BenjaminTeam:/data:rw
|
|
- ./Tracker/config.yaml.example:/app/config.yaml:ro
|
|
depends_on:
|
|
docling:
|
|
condition: service_healthy
|
|
ollama:
|
|
condition: service_healthy
|
|
tools:
|
|
condition: service_healthy
|
|
healthcheck:
|
|
test: ["CMD", "pgrep", "-f", "tracker"]
|
|
interval: 30s
|
|
timeout: 5s
|
|
retries: 3
|
|
start_period: 10s
|
|
|
|
volumes:
|
|
docling_models:
|
|
name: jt-docling-models
|
|
ollama_data:
|
|
name: jt-ollama-data
|