add embedding model by default to distribution templates (#617)

# What does this PR do?
Adds the sentence transformer provider and the `all-MiniLM-L6-v2`
embedding model to the default models to register in the run.yaml for
all providers.

## Test Plan
llama stack build --template together --image-type conda
llama stack run
~/.llama/distributions/llamastack-together/together-run.yaml

llama_stack/templates/fireworks/fireworks.py

@@ -8,11 +8,15 @@ from pathlib import Path
 
 from llama_models.sku_list import all_registered_models
 
+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.fireworks import FireworksImplConfig
 from llama_stack.providers.remote.inference.fireworks.fireworks import MODEL_ALIASES
-
 from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
 
 
@@ -35,6 +39,11 @@ def get_distribution_template() -> DistributionTemplate:
         provider_type="remote::fireworks",
         config=FireworksImplConfig.sample_run_config(),
     )
+    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",
@@ -48,9 +57,18 @@ def get_distribution_template() -> DistributionTemplate:
         ModelInput(
             model_id=core_model_to_hf_repo[m.llama_model],
             provider_model_id=m.provider_model_id,
+            provider_id="fireworks",
         )
         for m in MODEL_ALIASES
     ]
+    embedding_model = ModelInput(
+        model_id="all-MiniLM-L6-v2",
+        provider_id="sentence-transformers",
+        model_type=ModelType.embedding,
+        metadata={
+            "embedding_dimension": 384,
+        },
+    )
 
     return DistributionTemplate(
         name=name,
@@ -63,10 +81,10 @@ 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=default_models,
+                default_models=default_models + [embedding_model],
                 default_shields=[ShieldInput(shield_id="meta-llama/Llama-Guard-3-8B")],
             ),
         },

llama_stack/templates/fireworks/run.yaml

@@ -16,8 +16,11 @@ providers:
   - provider_id: fireworks
     provider_type: remote::fireworks
     config:
-      url: https://api.fireworks.ai/inference
+      url: https://api.fireworks.ai/inference/v1
       api_key: ${env.FIREWORKS_API_KEY}
+  - provider_id: sentence-transformers
+    provider_type: inline::sentence-transformers
+    config: {}
   memory:
   - provider_id: faiss
     provider_type: inline::faiss
@@ -74,40 +77,55 @@ metadata_store:
 models:
 - metadata: {}
   model_id: meta-llama/Llama-3.1-8B-Instruct
-  provider_id: null
+  provider_id: fireworks
   provider_model_id: fireworks/llama-v3p1-8b-instruct
+  model_type: llm
 - metadata: {}
   model_id: meta-llama/Llama-3.1-70B-Instruct
-  provider_id: null
+  provider_id: fireworks
   provider_model_id: fireworks/llama-v3p1-70b-instruct
+  model_type: llm
 - metadata: {}
   model_id: meta-llama/Llama-3.1-405B-Instruct-FP8
-  provider_id: null
+  provider_id: fireworks
   provider_model_id: fireworks/llama-v3p1-405b-instruct
+  model_type: llm
 - metadata: {}
   model_id: meta-llama/Llama-3.2-1B-Instruct
-  provider_id: null
+  provider_id: fireworks
   provider_model_id: fireworks/llama-v3p2-1b-instruct
+  model_type: llm
 - metadata: {}
   model_id: meta-llama/Llama-3.2-3B-Instruct
-  provider_id: null
+  provider_id: fireworks
   provider_model_id: fireworks/llama-v3p2-3b-instruct
+  model_type: llm
 - metadata: {}
   model_id: meta-llama/Llama-3.2-11B-Vision-Instruct
-  provider_id: null
+  provider_id: fireworks
   provider_model_id: fireworks/llama-v3p2-11b-vision-instruct
+  model_type: llm
 - metadata: {}
   model_id: meta-llama/Llama-3.2-90B-Vision-Instruct
-  provider_id: null
+  provider_id: fireworks
   provider_model_id: fireworks/llama-v3p2-90b-vision-instruct
+  model_type: llm
 - metadata: {}
   model_id: meta-llama/Llama-Guard-3-8B
-  provider_id: null
+  provider_id: fireworks
   provider_model_id: fireworks/llama-guard-3-8b
+  model_type: llm
 - metadata: {}
   model_id: meta-llama/Llama-Guard-3-11B-Vision
-  provider_id: null
+  provider_id: fireworks
   provider_model_id: fireworks/llama-guard-3-11b-vision
+  model_type: llm
+- metadata:
+    embedding_dimension: 384
+  model_id: all-MiniLM-L6-v2
+  provider_id: sentence-transformers
+  provider_model_id: null
+  model_type: embedding
 shields:
 - params: null
   shield_id: meta-llama/Llama-Guard-3-8B