simplify llama-stack-client-list-models.py

Author: makelinux

llm/llama-stack-client-completions-min.py

@@ -1,18 +1,16 @@
 #!/usr/bin/python3
 
-# export INFERENCE_MODEL=llama3.2:1b-instruct-fp16
-## start ollama:
+# export INFERENCE_MODEL=ollama/llama3.2:3b
 # ollama run $INFERENCE_MODEL
-## start llama-stack:
-# uv run --with llama-stack llama stack build --template ollama --image-type venv --image-name ~/my-ollama-llama-stack --run
+# llama stack run starter
 
 import os
 from llama_stack_client import LlamaStackClient
 
 c = LlamaStackClient(base_url="http://localhost:8321")
 
 r = c.chat.completions.create(
-    model=os.getenv("INFERENCE_MODEL", "gemini/models/gemini-2.5-pro"),
+    model=os.getenv("INFERENCE_MODEL", "ollama/llama3.2:3b"),
     messages=[
         {"role": "system", "content": "You are a helpful assistant."},
         {"role": "user", "content": "Write a haiku about coding"},

llm/llama-stack-client-list-models.py

@@ -1,13 +1,9 @@
 #!/usr/bin/python3
 
+# Prerequisite:
+# export LLAMA_STACK_CLIENT_BASE_URL=http://localhost:8321
+
 from llama_stack_client import LlamaStackClient
 
-# uses LLAMA_STACK_CLIENT_BASE_URL
 for m in LlamaStackClient().models.list():
-    try:
-        print(m.custom_metadata.get("provider_id"), m.custom_metadata['model_type'], m.id)
-    except Exception:
-        try:
-            print(m.model_type, m.identifier)
-        except Exception:
-            print(m)
+    print(m.custom_metadata.get("provider_id"), m.custom_metadata['model_type'], m.id)