Spaces:
Paused
Paused
File size: 1,586 Bytes
d8328bf | 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 | version: '3.8'
services:
model-server:
build:
context: .
dockerfile: Dockerfile
image: nexasci-agent:latest
container_name: nexasci-model-server
command: uvicorn agent.model_server:app --host 0.0.0.0 --port 8001
ports:
- "8001:8001"
volumes:
- ./models:/app/models
- ./agent:/app/agent
- ~/.cache/huggingface:/root/.cache/huggingface
environment:
- CUDA_VISIBLE_DEVICES=0
- TOKENIZERS_PARALLELISM=false
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: 1
capabilities: [gpu]
restart: unless-stopped
tool-server:
build:
context: .
dockerfile: Dockerfile
image: nexasci-agent:latest
container_name: nexasci-tool-server
command: uvicorn tools.server:app --host 0.0.0.0 --port 8000
ports:
- "8000:8000"
volumes:
- ./tools:/app/tools
- ./pipeline:/app/pipeline
- ./index:/app/index
- ./tmp:/app/tmp
environment:
- TOKENIZERS_PARALLELISM=false
restart: unless-stopped
depends_on:
- model-server
agent:
build:
context: .
dockerfile: Dockerfile
image: nexasci-agent:latest
container_name: nexasci-agent
command: python examples/demo_agent.py --prompt "Hello, test the agent system."
volumes:
- ./examples:/app/examples
- ./agent:/app/agent
environment:
- TOKENIZERS_PARALLELISM=false
depends_on:
- model-server
- tool-server
stdin_open: true
tty: true
|