Files
GenAIExamples/AgentQnA/docker_compose/amd/gpu/rocm/compose_vllm.yaml
2025-04-21 15:27:28 +08:00

129 lines
4.1 KiB
YAML

# Copyright (C) 2025 Advanced Micro Devices, Inc.
services:
vllm-service:
image: ${REGISTRY:-opea}/vllm-rocm:${TAG:-latest}
container_name: vllm-service
ports:
- "${VLLM_SERVICE_PORT:-8081}:8011"
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
HF_HUB_DISABLE_PROGRESS_BARS: 1
HF_HUB_ENABLE_HF_TRANSFER: 0
WILM_USE_TRITON_FLASH_ATTENTION: 0
PYTORCH_JIT: 0
volumes:
- "${MODEL_CACHE:-./data}:/data"
shm_size: 20G
devices:
- /dev/kfd:/dev/kfd
- /dev/dri/:/dev/dri/
cap_add:
- SYS_PTRACE
group_add:
- video
security_opt:
- seccomp:unconfined
- apparmor=unconfined
command: "--model ${VLLM_LLM_MODEL_ID} --swap-space 16 --disable-log-requests --dtype float16 --tensor-parallel-size 4 --host 0.0.0.0 --port 8011 --num-scheduler-steps 1 --distributed-executor-backend \"mp\""
ipc: host
worker-rag-agent:
image: ${REGISTRY:-opea}/agent:${TAG:-latest}
container_name: rag-agent-endpoint
volumes:
- ${TOOLSET_PATH}:/home/user/tools/
ports:
- "${WORKER_RAG_AGENT_PORT:-9095}:9095"
ipc: host
environment:
ip_address: ${ip_address}
strategy: rag_agent_llama
with_memory: false
recursion_limit: ${recursion_limit_worker}
llm_engine: vllm
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
llm_endpoint_url: ${LLM_ENDPOINT_URL}
model: ${LLM_MODEL_ID}
temperature: ${temperature}
max_new_tokens: ${max_new_tokens}
stream: false
tools: /home/user/tools/worker_agent_tools.yaml
require_human_feedback: false
RETRIEVAL_TOOL_URL: ${RETRIEVAL_TOOL_URL}
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY}
LANGCHAIN_TRACING_V2: ${LANGCHAIN_TRACING_V2}
LANGCHAIN_PROJECT: "opea-worker-agent-service"
port: 9095
worker-sql-agent:
image: ${REGISTRY:-opea}/agent:${TAG:-latest}
container_name: sql-agent-endpoint
volumes:
- "${WORKDIR}/tests/Chinook_Sqlite.sqlite:/home/user/chinook-db/Chinook_Sqlite.sqlite:rw"
ports:
- "${WORKER_SQL_AGENT_PORT:-9096}:9096"
ipc: host
environment:
ip_address: ${ip_address}
strategy: sql_agent_llama
with_memory: false
db_name: ${db_name}
db_path: ${db_path}
use_hints: false
recursion_limit: ${recursion_limit_worker}
llm_engine: vllm
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
llm_endpoint_url: ${LLM_ENDPOINT_URL}
model: ${LLM_MODEL_ID}
temperature: ${temperature}
max_new_tokens: ${max_new_tokens}
stream: false
require_human_feedback: false
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
port: 9096
supervisor-react-agent:
image: ${REGISTRY:-opea}/agent:${TAG:-latest}
container_name: react-agent-endpoint
depends_on:
- worker-rag-agent
volumes:
- ${TOOLSET_PATH}:/home/user/tools/
ports:
- "${SUPERVISOR_REACT_AGENT_PORT:-9090}:9090"
ipc: host
environment:
ip_address: ${ip_address}
strategy: react_llama
with_memory: true
recursion_limit: ${recursion_limit_supervisor}
llm_engine: vllm
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
llm_endpoint_url: ${LLM_ENDPOINT_URL}
model: ${LLM_MODEL_ID}
temperature: ${temperature}
max_new_tokens: ${max_new_tokens}
stream: true
tools: /home/user/tools/supervisor_agent_tools.yaml
require_human_feedback: false
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY}
LANGCHAIN_TRACING_V2: ${LANGCHAIN_TRACING_V2}
LANGCHAIN_PROJECT: "opea-supervisor-agent-service"
CRAG_SERVER: ${CRAG_SERVER}
WORKER_AGENT_URL: ${WORKER_AGENT_URL}
SQL_AGENT_URL: ${SQL_AGENT_URL}
port: 9090