fix ollama.py bug

llama_stack/templates/ollama/ollama.py

@@ -93,7 +93,7 @@ def get_distribution_template() -> DistributionTemplate:
                     "inference": [inference_provider],
                     "vector_io": [vector_io_provider_sqlite],
                 },
-                default_models=[inference_model],
+                default_models=[inference_model, embedding_model],
                 default_tool_groups=default_tool_groups,
             ),
             "run-with-safety.yaml": RunConfigSettings(

llama_stack/templates/ollama/run.yaml

@@ -87,6 +87,12 @@ models:
   model_id: ${env.INFERENCE_MODEL}
   provider_id: ollama
   model_type: llm
+- metadata:
+    embedding_dimension: 384
+  model_id: all-MiniLM-L6-v2
+  provider_id: ollama
+  provider_model_id: all-minilm:latest
+  model_type: embedding
 shields: []
 vector_dbs: []
 datasets: []