fix(infra): deploy Ollama to prod/staging compose + fix broken model-init recipe #759
@@ -206,13 +206,17 @@ services:
|
||||
# first start; exits quickly on subsequent starts (model already cached).
|
||||
# The ollama/ollama image's ENTRYPOINT is `ollama` and the image ships WITHOUT
|
||||
# curl, so the entrypoint is overridden to a shell and readiness is probed with
|
||||
# `ollama list` (not curl). Backend degrades gracefully (503) if Ollama is absent.
|
||||
# `ollama list` (not curl). The pull is guarded by a `grep` on the cached model
|
||||
# list so a model already on the volume exits clean WITHOUT a registry round-trip
|
||||
# — a host reboot during a registry/network blip can no longer fail init (which
|
||||
# would block the ollama service via service_completed_successfully).
|
||||
# Backend degrades gracefully (503) if Ollama is absent.
|
||||
ollama-model-init:
|
||||
image: ollama/ollama:0.30.6
|
||||
restart: "no"
|
||||
entrypoint: ["/bin/sh", "-c"]
|
||||
command:
|
||||
- "ollama serve & until ollama list >/dev/null 2>&1; do sleep 1; done && ollama pull qwen2.5:7b-instruct-q4_K_M"
|
||||
- "ollama serve & until ollama list >/dev/null 2>&1; do sleep 1; done && (ollama list | grep -q 'qwen2.5:7b-instruct-q4_K_M' || ollama pull qwen2.5:7b-instruct-q4_K_M)"
|
||||
networks:
|
||||
- archiv-net
|
||||
volumes:
|
||||
|
||||
Reference in New Issue
Block a user