#!/bin/sh # Start nginx nginx # Start llamafiler instances /usr/local/bin/llamafiler --model /base/gemma-2b.gguf --listen 0.0.0.0:8082 & GEMMA_PID=$! /usr/local/bin/llamafiler --model /base/embeddings.gguf --listen 0.0.0.0:8081 & EMBEDDINGS_PID=$! # Wait for services until curl -s --fail -X POST http://localhost:8080/v1/chat/completions \ -H "Content-Type: application/json" \ -d '{"model": "gemma-2b", "messages":[{"role":"user","content":"hi"}]}' >/dev/null 2>&1 && \ curl -s --fail -X POST http://localhost:8080/v1/embeddings \ -H "Content-Type: application/json" \ -d '{"input":"test"}' >/dev/null 2>&1 do sleep 1 echo "Waiting for services..." done echo 'Services are ready!' # Start the main application exec ./bin/entrypoint.sh node app/main.bundle.js