ODS V3 Pre-Release: Public testing and refinement ahead of the official V3 launch. Turn your PC, Mac, or Linux box into a private AI server.
Python ai-agentsamdcomfyuidockerllama-cppllmlocal-ain8nnvidiaopen-webuiragself-hostedspeech-to-textstrix-halotext-to-speechworkflow-automation
services:
embeddings:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.9.1@sha256:b7772cdd9dcbced147b16a7dff17d4aed1ab36333f8d3e686c50d2175e1d2126
platform: linux/amd64 # Release tags are amd64 only: Rosetta 2 on Apple Silicon, compose.arm64.yaml on Linux arm64
container_name: ods-embeddings
restart: unless-stopped
security_opt:
- no-new-privileges:true
environment:
- MODEL_ID=${EMBEDDING_MODEL:-BAAI/bge-base-en-v1.5}
- HF_HUB_DOWNLOAD_TIMEOUT=${HF_HUB_DOWNLOAD_TIMEOUT:-120}
- HF_HUB_ETAG_TIMEOUT=${HF_HUB_ETAG_TIMEOUT:-30}
volumes:
- ./data/embeddings:/data:z
ports:
- "127.0.0.1:${EMBEDDINGS_PORT:-8090}:80"
deploy:
resources:
limits:
cpus: '2.0'
memory: ${EMBEDDINGS_MEMORY_LIMIT:-4G}
reservations:
cpus: '0.5'
memory: 1G
healthcheck:
test: ["CMD", "curl", "-f", "http://127.0.0.1:80/health"]
interval: 30s
timeout: 10s
retries: 5
start_period: 600s
logging:
driver: "json-file"
options:
max-size: "10m"
max-file: "3"