Pull ollama embedding model if necessary

llama_stack/providers/remote/inference/ollama/ollama.py

@@ -281,6 +281,8 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
 
     async def register_model(self, model: Model) -> Model:
         if model.model_type == ModelType.embedding:
+            log.info(f"Pulling embedding model `{model.provider_resource_id}` if necessary...")
+            await self.client.pull(model.provider_resource_id)
             response = await self.client.list()
         else:
             response = await self.client.ps()

llama_stack/templates/ollama/build.yaml

@@ -6,6 +6,7 @@ distribution_spec:
     - remote::ollama
     vector_io:
     - inline::faiss
+    - inline::sqlite_vec
     - remote::chromadb
     - remote::pgvector
     safety: