vh
e376d0aec9
Captures the full workspace state built up to this point:
- CLAUDE.md + README.md describing conventions and the four-host fleet
(ana-ml2, ana-docker, nh3-docker, esh-docker-vm).
- Per-host notes under servers/<host>/ with ssh-target fallback files
and latest system-details snapshots (two in-compose credential leaks
scrubbed; the upstream compose files still need to move those to .env).
- scripts/: server_inspect.sh (read-only remote diagnostic),
refresh-server-info.sh (dir-driven discovery + snapshot capture with
validation warnings), add-host.sh, sync-stacks.sh (pull
compose/conf trees), deploy-stack.sh (push with per-file diff + prompt).
- stacks/: canonical compose for backrest, beszel, dozzle, llama-swap,
rest-server-ana, rest-server-nh3, vllm-qwen3, plus the retired
infinity reference. All use the .env-driven + traefik-net + homepage
label pattern.
- configs/restic/ana-docker/: first resticprofile config + pre-backup
hook (Synapse pg_dump, Seafile mysqldump, Vaultwarden SQLite); templates
for the other three hosts to come.
- docs/pfi/: general infrastructure reference carried over.
- .gitignore excludes .env, stacks-mirror/, and assorted secret/state
filenames to prevent re-leaks on later commits.
64 lines
1.8 KiB
YAML
64 lines
1.8 KiB
YAML
# Infinity — OpenAI-compatible embeddings + reranker server.
|
|
#
|
|
# Serves embedding and reranker models simultaneously from one container
|
|
# on port 7997 (HTTP). Consumers: AIPA agents (search/retrieval), LibreChat
|
|
# RAG, anything that needs vector embeddings.
|
|
#
|
|
# All tunables live in .env — edit that, not this file.
|
|
#
|
|
# Pre-download models to avoid first-run delay:
|
|
# HF_HOME=/tank/aimodels/huggingface hf download Qwen/Qwen3-Embedding-0.6B
|
|
# HF_HOME=/tank/aimodels/huggingface hf download Qwen/Qwen3-Reranker-0.6B
|
|
|
|
services:
|
|
infinity:
|
|
image: michaelf34/infinity:${INFINITY_VERSION}
|
|
container_name: infinity
|
|
restart: unless-stopped
|
|
ports:
|
|
- "${INFINITY_PORT}:7997"
|
|
volumes:
|
|
- /tank/aimodels/huggingface:/hfcache
|
|
environment:
|
|
- HF_HOME=/hfcache
|
|
- HF_HUB_CACHE=/hfcache/hub
|
|
- HUGGING_FACE_HUB_TOKEN=${HF_TOKEN:-}
|
|
command: >
|
|
v2
|
|
--model-id ${EMBED_MODEL}
|
|
--model-id ${RERANK_MODEL}
|
|
--engine ${ENGINE}
|
|
--device cuda
|
|
--batch-size ${BATCH_SIZE}
|
|
--host 0.0.0.0
|
|
--port 7997
|
|
--api-key ${API_KEY:-}
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
device_ids:
|
|
- "${GPU_ID}"
|
|
capabilities:
|
|
- gpu
|
|
healthcheck:
|
|
test: ["CMD", "curl", "-f", "http://localhost:7997/health"]
|
|
interval: 30s
|
|
timeout: 10s
|
|
retries: 3
|
|
start_period: 120s
|
|
networks:
|
|
- tnet
|
|
labels:
|
|
- homepage.group=AI Systems
|
|
- homepage.name=Infinity
|
|
- homepage.icon=mdi-vector-arrange-below
|
|
- homepage.description=Embeddings + Reranker API (ana-ml2)
|
|
- homepage.href=http://10.250.50.54:7997/docs
|
|
|
|
networks:
|
|
tnet:
|
|
name: traefik-net
|
|
external: true
|