diff --git a/samples/managed-llm/compose.yaml b/samples/managed-llm/compose.yaml index 31ce0754..611efa72 100644 --- a/samples/managed-llm/compose.yaml +++ b/samples/managed-llm/compose.yaml @@ -8,7 +8,7 @@ services: restart: always environment: - ENDPOINT_URL=http://llm/api/v1/chat/completions # endpoint to the gateway service - - MODEL=anthropic.claude-3-haiku-20240307-v1:0 # LLM model ID used for the gateway + - MODEL=ai/nova-micro # LLM model ID used for the gateway - OPENAI_API_KEY=FAKE_TOKEN # the actual value will be ignored when using the gateway, but it should match the one in the llm service healthcheck: test: ["CMD", "python3", "-c", "import sys, urllib.request; urllib.request.urlopen(sys.argv[1]).read()", "http://localhost:8000/"] @@ -29,8 +29,6 @@ services: mode: host environment: - OPENAI_API_KEY=FAKE_TOKEN # this value must match the one in the app service - - USE_MODEL_MAPPING=false - - DEBUG=true # if using GCP for BYOC deployment, add these environment variables: # - GCP_PROJECT_ID=${GCP_PROJECT_ID} # - GCP_REGION=${GCP_REGION}