add embedding model by default

llama_stack/templates/tgi/run-with-safety.yaml

@@ -79,10 +79,12 @@ models:
   model_id: ${env.INFERENCE_MODEL}
   provider_id: tgi-inference
   provider_model_id: null
+  model_type: llm
 - metadata: {}
   model_id: ${env.SAFETY_MODEL}
   provider_id: tgi-safety
   provider_model_id: null
+  model_type: llm
 shields:
 - params: null
   shield_id: ${env.SAFETY_MODEL}

llama_stack/templates/tgi/run.yaml

@@ -17,6 +17,9 @@ providers:
     provider_type: remote::tgi
     config:
       url: ${env.TGI_URL}
+  - provider_id: sentence-transformers
+    provider_type: inline::sentence-transformers
+    config: {}
   memory:
   - provider_id: faiss
     provider_type: inline::faiss
@@ -75,6 +78,13 @@ models:
   model_id: ${env.INFERENCE_MODEL}
   provider_id: tgi-inference
   provider_model_id: null
+  model_type: llm
+- metadata:
+    embedding_dim: 384
+  model_id: all-MiniLM-L6-v2
+  provider_id: sentence-transformers
+  provider_model_id: null
+  model_type: embedding
 shields: []
 memory_banks: []
 datasets: []

llama_stack/templates/tgi/tgi.py

@@ -6,7 +6,12 @@
 
 from pathlib import Path
 
+from llama_stack.apis.models.models import ModelType
+
 from llama_stack.distribution.datatypes import ModelInput, Provider, ShieldInput
+from llama_stack.providers.inline.inference.sentence_transformers import (
+    SentenceTransformersInferenceConfig,
+)
 from llama_stack.providers.inline.memory.faiss.config import FaissImplConfig
 from llama_stack.providers.remote.inference.tgi import TGIImplConfig
 from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
@@ -31,6 +36,11 @@ def get_distribution_template() -> DistributionTemplate:
             url="${env.TGI_URL}",
         ),
     )
+    embedding_provider = Provider(
+        provider_id="sentence-transformers",
+        provider_type="inline::sentence-transformers",
+        config=SentenceTransformersInferenceConfig.sample_run_config(),
+    )
     memory_provider = Provider(
         provider_id="faiss",
         provider_type="inline::faiss",
@@ -41,6 +51,14 @@ def get_distribution_template() -> DistributionTemplate:
         model_id="${env.INFERENCE_MODEL}",
         provider_id="tgi-inference",
     )
+    embedding_model = ModelInput(
+        model_id="all-MiniLM-L6-v2",
+        provider_id="sentence-transformers",
+        model_type=ModelType.embedding,
+        metadata={
+            "embedding_dim": 384,
+        },
+    )
     safety_model = ModelInput(
         model_id="${env.SAFETY_MODEL}",
         provider_id="tgi-safety",
@@ -57,10 +75,10 @@ def get_distribution_template() -> DistributionTemplate:
         run_configs={
             "run.yaml": RunConfigSettings(
                 provider_overrides={
-                    "inference": [inference_provider],
+                    "inference": [inference_provider, embedding_provider],
                     "memory": [memory_provider],
                 },
-                default_models=[inference_model],
+                default_models=[inference_model, embedding_model],
             ),
             "run-with-safety.yaml": RunConfigSettings(
                 provider_overrides={