chore: Updating how default embedding model is set in stack (#3818)

# What does this PR do?

Refactor setting default vector store provider and embedding model to
use an optional `vector_stores` config in the `StackRunConfig` and clean
up code to do so (had to add back in some pieces of VectorDB). Also
added remote Qdrant and Weaviate to starter distro (based on other PR
where inference providers were added for UX).

New config is simply (default for Starter distro):

```yaml
vector_stores:
  default_provider_id: faiss
  default_embedding_model:
    provider_id: sentence-transformers
    model_id: nomic-ai/nomic-embed-text-v1.5
```

## Test Plan
CI and Unit tests.

---------

Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>

llama_stack/distributions/starter/build.yaml

@@ -26,6 +26,8 @@ distribution_spec:
     - provider_type: inline::milvus
     - provider_type: remote::chromadb
     - provider_type: remote::pgvector
+    - provider_type: remote::qdrant
+    - provider_type: remote::weaviate
     files:
     - provider_type: inline::localfs
     safety:

llama_stack/distributions/starter/run.yaml

@@ -128,6 +128,21 @@ providers:
       persistence:
         namespace: vector_io::pgvector
         backend: kv_default
+  - provider_id: ${env.QDRANT_URL:+qdrant}
+    provider_type: remote::qdrant
+    config:
+      api_key: ${env.QDRANT_API_KEY:=}
+      persistence:
+        namespace: vector_io::qdrant_remote
+        backend: kv_default
+  - provider_id: ${env.WEAVIATE_CLUSTER_URL:+weaviate}
+    provider_type: remote::weaviate
+    config:
+      weaviate_api_key: null
+      weaviate_cluster_url: ${env.WEAVIATE_CLUSTER_URL:=localhost:8080}
+      persistence:
+        namespace: vector_io::weaviate
+        backend: kv_default
   files:
   - provider_id: meta-reference-files
     provider_type: inline::localfs
@@ -253,3 +268,8 @@ server:
   port: 8321
 telemetry:
   enabled: true
+vector_stores:
+  default_provider_id: faiss
+  default_embedding_model:
+    provider_id: sentence-transformers
+    model_id: nomic-ai/nomic-embed-text-v1.5

llama_stack/distributions/starter/starter.py

@@ -11,8 +11,10 @@ from llama_stack.core.datatypes import (
     BuildProvider,
     Provider,
     ProviderSpec,
+    QualifiedModel,
     ShieldInput,
     ToolGroupInput,
+    VectorStoresConfig,
 )
 from llama_stack.core.utils.dynamic import instantiate_class_type
 from llama_stack.distributions.template import DistributionTemplate, RunConfigSettings
@@ -31,6 +33,8 @@ from llama_stack.providers.remote.vector_io.chroma.config import ChromaVectorIOC
 from llama_stack.providers.remote.vector_io.pgvector.config import (
     PGVectorVectorIOConfig,
 )
+from llama_stack.providers.remote.vector_io.qdrant.config import QdrantVectorIOConfig
+from llama_stack.providers.remote.vector_io.weaviate.config import WeaviateVectorIOConfig
 from llama_stack.providers.utils.sqlstore.sqlstore import PostgresSqlStoreConfig
 
 
@@ -113,6 +117,8 @@ def get_distribution_template(name: str = "starter") -> DistributionTemplate:
             BuildProvider(provider_type="inline::milvus"),
             BuildProvider(provider_type="remote::chromadb"),
             BuildProvider(provider_type="remote::pgvector"),
+            BuildProvider(provider_type="remote::qdrant"),
+            BuildProvider(provider_type="remote::weaviate"),
         ],
         "files": [BuildProvider(provider_type="inline::localfs")],
         "safety": [
@@ -221,12 +227,35 @@ def get_distribution_template(name: str = "starter") -> DistributionTemplate:
                                 password="${env.PGVECTOR_PASSWORD:=}",
                             ),
                         ),
+                        Provider(
+                            provider_id="${env.QDRANT_URL:+qdrant}",
+                            provider_type="remote::qdrant",
+                            config=QdrantVectorIOConfig.sample_run_config(
+                                f"~/.llama/distributions/{name}",
+                                url="${env.QDRANT_URL:=}",
+                            ),
+                        ),
+                        Provider(
+                            provider_id="${env.WEAVIATE_CLUSTER_URL:+weaviate}",
+                            provider_type="remote::weaviate",
+                            config=WeaviateVectorIOConfig.sample_run_config(
+                                f"~/.llama/distributions/{name}",
+                                cluster_url="${env.WEAVIATE_CLUSTER_URL:=}",
+                            ),
+                        ),
                     ],
                     "files": [files_provider],
                 },
                 default_models=[],
                 default_tool_groups=default_tool_groups,
                 default_shields=default_shields,
+                vector_stores_config=VectorStoresConfig(
+                    default_provider_id="faiss",
+                    default_embedding_model=QualifiedModel(
+                        provider_id="sentence-transformers",
+                        model_id="nomic-ai/nomic-embed-text-v1.5",
+                    ),
+                ),
             ),
         },
         run_config_env_vars={