feat: initial release - OpenAI-compatible LLM server with llama-cpp-2

2026-07-25 11:00:03 +07:00
commit 33b42b789c
9 changed files with 1747 additions and 0 deletions
@@ -0,0 +1,27 @@
+services:
+  llm-api:
+    container_name: llm-api
+    image: ghcr.io/asepharyana/llm-api:latest
+    build:
+      context: .
+      dockerfile: Dockerfile
+    restart: always
+    networks:
+      app-shared-net:
+        aliases:
+          - llm-api
+    volumes:
+      - /root/models/gguf:/root/models/gguf:ro
+    environment:
+      - MODEL_PATH=/root/models/gguf/MiniCPM-V-4.6-Q4_K_M.gguf
+    healthcheck:
+      test: ['CMD-SHELL', 'curl -so /dev/null --connect-timeout 5 http://localhost:8080/health || test $? -eq 22']
+      interval: 30s
+      timeout: 10s
+      retries: 5
+      start_period: 30s
+
+networks:
+  app-shared-net:
+    name: app-shared-net
+    external: true