File size: 2,040 Bytes
0fa4cc9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 |
version: '3.8'
# Load environment variables from .env file
x-env: &env
env_file: .env
environment:
- OLLAMA_PORT=${OLLAMA_PORT:-11434}
- OLLAMA_HOST=${OLLAMA_HOST:-0.0.0.0}
- STREAMLIT_SERVER_PORT=${STREAMLIT_SERVER_PORT:-8501}
- STREAMLIT_SERVER_ADDRESS=${STREAMLIT_SERVER_ADDRESS:-0.0.0.0}
- DEFAULT_MODEL=${DEFAULT_MODEL:-mistral:7b-instruct}
services:
# Ollama - LLM Engine (minimalna konfiguracja)
ollama:
image: ollama/ollama:latest
container_name: ollama-engine
<<: *env
ports:
- "${OLLAMA_PORT:-11434}:11434"
volumes:
- ollama_data:/root/.ollama
# deploy:
# resources:
# reservations:
# devices:
# - driver: nvidia
# count: 1
# capabilities: [gpu]
restart: unless-stopped
# Streamlit UI (Python frontend)
streamlit-ui:
build: .
container_name: llm-ui
<<: *env
ports:
- "${STREAMLIT_SERVER_PORT:-8501}:8501"
depends_on:
- ollama
environment:
- OLLAMA_URL=http://ollama:${OLLAMA_PORT:-11434}
- STREAMLIT_SERVER_PORT=${STREAMLIT_SERVER_PORT:-8501}
- STREAMLIT_SERVER_ADDRESS=${STREAMLIT_SERVER_ADDRESS:-0.0.0.0}
restart: unless-stopped
volumes:
- ./app:/app
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:${STREAMLIT_SERVER_PORT:-8501}/_stcore/health"]
interval: 30s
timeout: 10s
retries: 3
# Model Setup (inicjalizacja modelu)
model-setup:
image: ollama/ollama:latest
container_name: model-setup
<<: *env
depends_on:
- ollama
volumes:
- ollama_data:/root/.ollama
environment:
- OLLAMA_HOST=http://ollama:${OLLAMA_PORT:-11434}
- DEFAULT_MODEL=${DEFAULT_MODEL:-mistral:7b-instruct}
command: >
sh -c "
echo 'Waiting for Ollama to be ready...' &&
sleep 10 &&
ollama pull ${DEFAULT_MODEL:-mistral:7b-instruct} &&
echo 'Model loaded successfully!'
"
restart: "no"
volumes:
ollama_data: |