Make embedding generation go through inference (#606)

This PR does the following:
1) adds the ability to generate embeddings in all supported inference
providers.
2) Moves all the memory providers to use the inference API and improved
the memory tests to setup the inference stack correctly and use the
embedding models

This is a merge from #589 and #598

llama_stack/providers/utils/inference/embedding_mixin.py

@@ -0,0 +1,47 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+import logging
+from typing import List
+
+from llama_models.llama3.api.datatypes import InterleavedTextMedia
+
+from llama_stack.apis.inference.inference import EmbeddingsResponse, ModelStore
+
+EMBEDDING_MODELS = {}
+
+
+log = logging.getLogger(__name__)
+
+
+class SentenceTransformerEmbeddingMixin:
+    model_store: ModelStore
+
+    async def embeddings(
+        self,
+        model_id: str,
+        contents: List[InterleavedTextMedia],
+    ) -> EmbeddingsResponse:
+        model = await self.model_store.get_model(model_id)
+        embedding_model = self._load_sentence_transformer_model(
+            model.provider_resource_id
+        )
+        embeddings = embedding_model.encode(contents)
+        return EmbeddingsResponse(embeddings=embeddings)
+
+    def _load_sentence_transformer_model(self, model: str) -> "SentenceTransformer":
+        global EMBEDDING_MODELS
+
+        loaded_model = EMBEDDING_MODELS.get(model)
+        if loaded_model is not None:
+            return loaded_model
+
+        log.info(f"Loading sentence transformer for {model}...")
+        from sentence_transformers import SentenceTransformer
+
+        loaded_model = SentenceTransformer(model)
+        EMBEDDING_MODELS[model] = loaded_model
+        return loaded_model

llama_stack/providers/utils/inference/model_registry.py

@@ -9,6 +9,7 @@ from typing import List, Optional
 
 from llama_models.sku_list import all_registered_models
 
+from llama_stack.apis.models.models import ModelType
 from llama_stack.providers.datatypes import Model, ModelsProtocolPrivate
 
 from llama_stack.providers.utils.inference import (
@@ -77,7 +78,13 @@ class ModelRegistryHelper(ModelsProtocolPrivate):
             return None
 
     async def register_model(self, model: Model) -> Model:
-        provider_resource_id = self.get_provider_model_id(model.provider_resource_id)
+        if model.model_type == ModelType.embedding_model:
+            # embedding models are always registered by their provider model id and does not need to be mapped to a llama model
+            provider_resource_id = model.provider_resource_id
+        else:
+            provider_resource_id = self.get_provider_model_id(
+                model.provider_resource_id
+            )
         if provider_resource_id:
             model.provider_resource_id = provider_resource_id
         else: