feat: Enable setting a default embedding model in the stack (#3803)

# What does this PR do?

Enables automatic embedding model detection for vector stores and by
using a `default_configured` boolean that can be defined in the
`run.yaml`.

<!-- If resolving an issue, uncomment and update the line below -->
<!-- Closes #[issue-number] -->

## Test Plan
- Unit tests
- Integration tests
- Simple example below:

Spin up the stack:
```bash
uv run llama stack build --distro starter --image-type venv --run
```
Then test with OpenAI's client:
```python
from openai import OpenAI
client = OpenAI(base_url="http://localhost:8321/v1/", api_key="none")
vs = client.vector_stores.create()
```
Previously you needed:

```python
vs = client.vector_stores.create(
    extra_body={
        "embedding_model": "sentence-transformers/all-MiniLM-L6-v2",
        "embedding_dimension": 384,
    }
)
```

The `extra_body` is now unnecessary.

---------

Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>

llama_stack/providers/inline/inference/sentence_transformers/sentence_transformers.py

@@ -59,6 +59,7 @@ class SentenceTransformersInferenceImpl(
                 provider_id=self.__provider_id__,
                 metadata={
                     "embedding_dimension": 768,
+                    "default_configured": True,
                 },
                 model_type=ModelType.embedding,
             ),

llama_stack/providers/inline/vector_io/chroma/__init__.py

@@ -16,6 +16,11 @@ async def get_provider_impl(config: ChromaVectorIOConfig, deps: dict[Api, Any]):
         ChromaVectorIOAdapter,
     )
 
-    impl = ChromaVectorIOAdapter(config, deps[Api.inference], deps.get(Api.files))
+    impl = ChromaVectorIOAdapter(
+        config,
+        deps[Api.inference],
+        deps[Api.models],
+        deps.get(Api.files),
+    )
     await impl.initialize()
     return impl

llama_stack/providers/inline/vector_io/faiss/__init__.py

@@ -16,6 +16,11 @@ async def get_provider_impl(config: FaissVectorIOConfig, deps: dict[Api, Any]):
 
     assert isinstance(config, FaissVectorIOConfig), f"Unexpected config type: {type(config)}"
 
-    impl = FaissVectorIOAdapter(config, deps[Api.inference], deps.get(Api.files, None))
+    impl = FaissVectorIOAdapter(
+        config,
+        deps[Api.inference],
+        deps[Api.models],
+        deps.get(Api.files),
+    )
     await impl.initialize()
     return impl

llama_stack/providers/inline/vector_io/faiss/faiss.py

@@ -17,6 +17,7 @@ from numpy.typing import NDArray
 from llama_stack.apis.common.errors import VectorStoreNotFoundError
 from llama_stack.apis.files import Files
 from llama_stack.apis.inference import Inference, InterleavedContent
+from llama_stack.apis.models import Models
 from llama_stack.apis.vector_dbs import VectorDB
 from llama_stack.apis.vector_io import (
     Chunk,
@@ -199,10 +200,17 @@ class FaissIndex(EmbeddingIndex):
 
 
 class FaissVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtocolPrivate):
-    def __init__(self, config: FaissVectorIOConfig, inference_api: Inference, files_api: Files | None) -> None:
+    def __init__(
+        self,
+        config: FaissVectorIOConfig,
+        inference_api: Inference,
+        models_api: Models,
+        files_api: Files | None,
+    ) -> None:
         super().__init__(files_api=files_api, kvstore=None)
         self.config = config
         self.inference_api = inference_api
+        self.models_api = models_api
         self.cache: dict[str, VectorDBWithIndex] = {}
 
     async def initialize(self) -> None:

llama_stack/providers/inline/vector_io/milvus/__init__.py

@@ -14,6 +14,11 @@ from .config import MilvusVectorIOConfig
 async def get_provider_impl(config: MilvusVectorIOConfig, deps: dict[Api, Any]):
     from llama_stack.providers.remote.vector_io.milvus.milvus import MilvusVectorIOAdapter
 
-    impl = MilvusVectorIOAdapter(config, deps[Api.inference], deps.get(Api.files, None))
+    impl = MilvusVectorIOAdapter(
+        config,
+        deps[Api.inference],
+        deps[Api.models],
+        deps.get(Api.files),
+    )
     await impl.initialize()
     return impl

llama_stack/providers/inline/vector_io/qdrant/__init__.py

@@ -15,7 +15,11 @@ async def get_provider_impl(config: QdrantVectorIOConfig, deps: dict[Api, Any]):
     from llama_stack.providers.remote.vector_io.qdrant.qdrant import QdrantVectorIOAdapter
 
     assert isinstance(config, QdrantVectorIOConfig), f"Unexpected config type: {type(config)}"
-    files_api = deps.get(Api.files)
-    impl = QdrantVectorIOAdapter(config, deps[Api.inference], files_api)
+    impl = QdrantVectorIOAdapter(
+        config,
+        deps[Api.inference],
+        deps[Api.models],
+        deps.get(Api.files),
+    )
     await impl.initialize()
     return impl

llama_stack/providers/inline/vector_io/sqlite_vec/__init__.py

@@ -15,6 +15,11 @@ async def get_provider_impl(config: SQLiteVectorIOConfig, deps: dict[Api, Any]):
     from .sqlite_vec import SQLiteVecVectorIOAdapter
 
     assert isinstance(config, SQLiteVectorIOConfig), f"Unexpected config type: {type(config)}"
-    impl = SQLiteVecVectorIOAdapter(config, deps[Api.inference], deps.get(Api.files, None))
+    impl = SQLiteVecVectorIOAdapter(
+        config,
+        deps[Api.inference],
+        deps[Api.models],
+        deps.get(Api.files),
+    )
     await impl.initialize()
     return impl

llama_stack/providers/inline/vector_io/sqlite_vec/sqlite_vec.py

@@ -17,6 +17,7 @@ from numpy.typing import NDArray
 from llama_stack.apis.common.errors import VectorStoreNotFoundError
 from llama_stack.apis.files import Files
 from llama_stack.apis.inference import Inference
+from llama_stack.apis.models import Models
 from llama_stack.apis.vector_dbs import VectorDB
 from llama_stack.apis.vector_io import (
     Chunk,
@@ -409,11 +410,19 @@ class SQLiteVecVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtoc
     and creates a cache of VectorDBWithIndex instances (each wrapping a SQLiteVecIndex).
     """
 
-    def __init__(self, config, inference_api: Inference, files_api: Files | None) -> None:
+    def __init__(
+        self,
+        config,
+        inference_api: Inference,
+        models_api: Models,
+        files_api: Files | None,
+    ) -> None:
         super().__init__(files_api=files_api, kvstore=None)
         self.config = config
         self.inference_api = inference_api
+        self.models_api = models_api
         self.cache: dict[str, VectorDBWithIndex] = {}
+        self.vector_db_store = None
 
     async def initialize(self) -> None:
         self.kvstore = await kvstore_impl(self.config.kvstore)