ai-api-ollama / docker-compose.yml
cygon
Initial deployment with Ollama support
d61feef
version: '3.8'
services:
api:
build: .
ports:
- "8000:8000"
environment:
- OPENAI_API_KEY=${OPENAI_API_KEY}
- HUGGINGFACE_API_KEY=${HUGGINGFACE_API_KEY}
- ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}
- PINECONE_API_KEY=${PINECONE_API_KEY}
- PINECONE_ENVIRONMENT=${PINECONE_ENVIRONMENT:-us-west1-gcp}
- PINECONE_INDEX_NAME=${PINECONE_INDEX_NAME:-ai-api-vectors}
- API_KEYS=${API_KEYS:-demo-key-1,demo-key-2}
- ADMIN_API_KEYS=${ADMIN_API_KEYS}
- RATE_LIMIT_DEFAULT=${RATE_LIMIT_DEFAULT:-60}
- RATE_LIMIT_PREMIUM=${RATE_LIMIT_PREMIUM:-300}
- RATE_LIMIT_ADMIN=${RATE_LIMIT_ADMIN:-1000}
- DEFAULT_CHAT_MODEL=${DEFAULT_CHAT_MODEL:-gpt-3.5-turbo}
- DEFAULT_EMBEDDING_MODEL=${DEFAULT_EMBEDDING_MODEL:-text-embedding-ada-002}
- DEFAULT_IMAGE_MODEL=${DEFAULT_IMAGE_MODEL:-dall-e-3}
- DEFAULT_VOICE_MODEL=${DEFAULT_VOICE_MODEL:-tts-1}
- MAX_FILE_SIZE_MB=${MAX_FILE_SIZE_MB:-10}
- CHUNK_SIZE=${CHUNK_SIZE:-1000}
- CHUNK_OVERLAP=${CHUNK_OVERLAP:-200}
- ENABLE_BACKGROUND_WORKERS=${ENABLE_BACKGROUND_WORKERS:-true}
- WORKER_CONCURRENCY=${WORKER_CONCURRENCY:-5}
- LOG_LEVEL=${LOG_LEVEL:-info}
- CORS_ORIGINS=${CORS_ORIGINS:-http://localhost:3000}
volumes:
- ./data:/app/data
restart: unless-stopped
healthcheck:
test: ["CMD", "wget", "--spider", "-q", "http://localhost:8000/health"]
interval: 30s
timeout: 10s
retries: 3
start_period: 40s
redis:
image: redis:7-alpine
ports:
- "6379:6379"
volumes:
- redis_data:/data
restart: unless-stopped
command: redis-server --appendonly yes
volumes:
redis_data: