87 lines
2.8 KiB
YAML
87 lines
2.8 KiB
YAML
services:
|
|
localai:
|
|
# See https://localai.io/basics/container/#standard-container-images for
|
|
# a list of available container images (or build your own with the provided Dockerfile)
|
|
# Available images with CUDA, ROCm, SYCL, Vulkan
|
|
# Image list (quay.io): https://quay.io/repository/go-skynet/local-ai?tab=tags
|
|
# Image list (dockerhub): https://hub.docker.com/r/localai/localai
|
|
image: localai/localai:master-gpu-nvidia-cuda-12
|
|
command:
|
|
- mlabonne_gemma-3-27b-it-abliterated
|
|
# - qwen_qwq-32b
|
|
# Other good alternative options:
|
|
# - rombo-org_rombo-llm-v3.0-qwen-32b # minimum suggested model
|
|
# - arcee-agent
|
|
- granite-embedding-107m-multilingual
|
|
- flux.1-dev
|
|
- minicpm-v-2_6
|
|
environment:
|
|
# Enable if you have a single GPU which don't fit all the models
|
|
- LOCALAI_SINGLE_ACTIVE_BACKEND=true
|
|
healthcheck:
|
|
test: ["CMD", "curl", "-f", "http://localhost:8080/readyz"]
|
|
interval: 10s
|
|
timeout: 20m
|
|
retries: 20
|
|
ports:
|
|
- 8081:8080
|
|
environment:
|
|
- DEBUG=true
|
|
volumes:
|
|
- ./volumes/models:/build/models:cached
|
|
- ./volumes/images:/tmp/generated/images
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
count: 1
|
|
capabilities: [gpu]
|
|
localrecall:
|
|
image: quay.io/mudler/localrecall:main
|
|
ports:
|
|
- 8080
|
|
environment:
|
|
- COLLECTION_DB_PATH=/db
|
|
- EMBEDDING_MODEL=granite-embedding-107m-multilingual
|
|
- FILE_ASSETS=/assets
|
|
- OPENAI_API_KEY=sk-1234567890
|
|
- OPENAI_BASE_URL=http://localai:8080
|
|
volumes:
|
|
- ./volumes/localrag/db:/db
|
|
- ./volumes/localrag/assets/:/assets
|
|
|
|
localrecall-healthcheck:
|
|
depends_on:
|
|
localrecall:
|
|
condition: service_started
|
|
image: busybox
|
|
command: ["sh", "-c", "until wget -q -O - http://localrecall:8080 > /dev/null 2>&1; do echo 'Waiting for localrecall...'; sleep 1; done; echo 'localrecall is up!'"]
|
|
|
|
localagent:
|
|
depends_on:
|
|
localai:
|
|
condition: service_healthy
|
|
localrecall-healthcheck:
|
|
condition: service_completed_successfully
|
|
build:
|
|
context: .
|
|
dockerfile: Dockerfile.webui
|
|
ports:
|
|
- 8080:3000
|
|
image: quay.io/mudler/localagi:master
|
|
environment:
|
|
- LOCALAGENT_MODEL=mlabonne_gemma-3-27b-it-abliterated
|
|
- LOCALAGENT_LLM_API_URL=http://localai:8080
|
|
- LOCALAGENT_LLM_API_KEY=sk-1234567890
|
|
- LOCALAGENT_LOCALRAG_URL=http://localrecall:8080
|
|
- LOCALAGENT_STATE_DIR=/pool
|
|
- LOCALAGENT_TIMEOUT=5m
|
|
- LOCALAGENT_ENABLE_CONVERSATIONS_LOGGING=false
|
|
- LOCALAGENT_MULTIMODAL_MODEL=minicpm-v-2_6
|
|
- LOCALAGENT_IMAGE_MODEL=flux.1-dev
|
|
extra_hosts:
|
|
- "host.docker.internal:host-gateway"
|
|
volumes:
|
|
- ./volumes/localagent/:/pool
|