Merge pull request #500 from DefangLabs/eric/make-implicit-env-explicit

Author: nullfunc

samples/managed-llm-provider/app/Dockerfile

@@ -19,4 +19,4 @@ EXPOSE 8000
 ENV PORT=8000
 
 # Run the app with the correct module path using shell form to interpolate environment variable
-CMD ["sh", "-c", "uvicorn app:app --host 0.0.0.0 --port $PORT"]
+CMD ["sh", "-c", "uvicorn app:app --host 0.0.0.0 --port $PORT --no-access-log"]

samples/managed-llm-provider/app/app.py

@@ -32,6 +32,11 @@ def get_api_key():
 async def home():
     return FileResponse("static/index.html", media_type="text/html")
 
+# Health check endpoint
+@app.get("/health")
+async def health():
+    return {"status": "healthy"}
+
 # Handle form submission
 @app.post("/ask", response_class=JSONResponse)
 async def ask(prompt: str = Form(...)):

samples/managed-llm-provider/compose.yaml

@@ -9,9 +9,10 @@ services:
     environment:
       - LLM_URL=http://llm/api/v1/
       - LLM_MODEL=default
+      - OPENAI_API_KEY=FAKE_TOKEN
       # For other models, see https://docs.defang.io/docs/concepts/managed-llms/openai-access-gateway#model-mapping
     healthcheck:
-      test: ["CMD", "python3", "-c", "import sys, urllib.request; urllib.request.urlopen(sys.argv[1]).read()", "http://localhost:8000/"]
+      test: ["CMD", "python3", "-c", "import sys, urllib.request; urllib.request.urlopen(sys.argv[1]).read()", "http://localhost:8000/health"]
       interval: 30s
       timeout: 5s
       retries: 3
@@ -32,6 +33,8 @@ services:
       options:
         model: ai/smollm2
     x-defang-llm: true
+    environment:
+      - OPENAI_API_KEY=FAKE_TOKEN
     deploy:
       resources:
         reservations: