From 9239b338d5368963aaeb5d422e807edfc6742d46 Mon Sep 17 00:00:00 2001
From: Ben Browning <bbrownin@redhat.com>
Date: Wed, 25 Jun 2025 09:16:01 -0400
Subject: [PATCH] Add OLLAMA_EMBEDDING_MODEL to starter distro

This allows a user to specify the Ollama Embedding Model to use, if any.

Signed-off-by: Ben Browning <bbrownin@redhat.com>
---
 llama_stack/templates/starter/run.yaml   |  6 ++++++
 llama_stack/templates/starter/starter.py | 15 +++++++++++++++
 2 files changed, 21 insertions(+)

diff --git a/llama_stack/templates/starter/run.yaml b/llama_stack/templates/starter/run.yaml
index de0c12d90..30df39e5d 100644
--- a/llama_stack/templates/starter/run.yaml
+++ b/llama_stack/templates/starter/run.yaml
@@ -542,6 +542,12 @@ models:
   provider_id: ollama
   provider_model_id: ${env.OLLAMA_INFERENCE_MODEL:__disabled__}
   model_type: llm
+- metadata:
+    embedding_dimension: ${env.OLLAMA_EMBEDDING_DIMENSION:384}
+  model_id: ollama/${env.OLLAMA_EMBEDDING_MODEL:__disabled__}
+  provider_id: ollama
+  provider_model_id: ${env.OLLAMA_EMBEDDING_MODEL:__disabled__}
+  model_type: embedding
 - metadata: {}
   model_id: anthropic/claude-3-5-sonnet-latest
   provider_id: anthropic
diff --git a/llama_stack/templates/starter/starter.py b/llama_stack/templates/starter/starter.py
index 357f1aec1..ec01d08e9 100644
--- a/llama_stack/templates/starter/starter.py
+++ b/llama_stack/templates/starter/starter.py
@@ -88,6 +88,13 @@ def get_inference_providers() -> tuple[list[Provider], dict[str, list[ProviderMo
                     provider_model_id="${env.OLLAMA_INFERENCE_MODEL:__disabled__}",
                     model_type=ModelType.llm,
                 ),
+                ProviderModelEntry(
+                    provider_model_id="${env.OLLAMA_EMBEDDING_MODEL:__disabled__}",
+                    model_type=ModelType.embedding,
+                    metadata={
+                        "embedding_dimension": "${env.OLLAMA_EMBEDDING_DIMENSION:384}",
+                    },
+                ),
             ],
             OllamaImplConfig.sample_run_config(
                 url="${env.OLLAMA_URL:http://localhost:11434}", raise_on_connect_error=False
@@ -286,5 +293,13 @@ def get_distribution_template() -> DistributionTemplate:
                 "",
                 "Optional Ollama Inference Model to register on startup",
             ),
+            "OLLAMA_EMBEDDING_MODEL": (
+                "",
+                "Optional Ollama Embedding Model to register on startup",
+            ),
+            "OLLAMA_EMBEDDING_DIMENSION": (
+                "384",
+                "Ollama Embedding Dimension",
+            ),
         },
     )