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/inline/inference/sentence_transformers/__init__.py

@@ -0,0 +1,20 @@
+# 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.
+
+from llama_stack.providers.inline.inference.sentence_transformers.config import (
+    SentenceTransformersInferenceConfig,
+)
+
+
+async def get_provider_impl(
+    config: SentenceTransformersInferenceConfig,
+    _deps,
+):
+    from .sentence_transformers import SentenceTransformersInferenceImpl
+
+    impl = SentenceTransformersInferenceImpl(config)
+    await impl.initialize()
+    return impl

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

@@ -0,0 +1,10 @@
+# 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.
+
+from pydantic import BaseModel
+
+
+class SentenceTransformersInferenceConfig(BaseModel): ...

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

@@ -0,0 +1,74 @@
+# 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 AsyncGenerator, List, Optional, Union
+
+from llama_stack.apis.inference import (
+    CompletionResponse,
+    Inference,
+    LogProbConfig,
+    Message,
+    ResponseFormat,
+    SamplingParams,
+    ToolChoice,
+    ToolDefinition,
+    ToolPromptFormat,
+)
+from llama_stack.providers.datatypes import Model, ModelsProtocolPrivate
+from llama_stack.providers.utils.inference.embedding_mixin import (
+    SentenceTransformerEmbeddingMixin,
+)
+from .config import SentenceTransformersInferenceConfig
+
+log = logging.getLogger(__name__)
+
+
+class SentenceTransformersInferenceImpl(
+    SentenceTransformerEmbeddingMixin,
+    Inference,
+    ModelsProtocolPrivate,
+):
+    def __init__(self, config: SentenceTransformersInferenceConfig) -> None:
+        self.config = config
+
+    async def initialize(self) -> None:
+        pass
+
+    async def shutdown(self) -> None:
+        pass
+
+    async def register_model(self, model: Model) -> None:
+        _ = self._load_sentence_transformer_model(model.provider_resource_id)
+        return model
+
+    async def unregister_model(self, model_id: str) -> None:
+        pass
+
+    async def completion(
+        self,
+        model_id: str,
+        content: str,
+        sampling_params: Optional[SamplingParams] = SamplingParams(),
+        response_format: Optional[ResponseFormat] = None,
+        stream: Optional[bool] = False,
+        logprobs: Optional[LogProbConfig] = None,
+    ) -> Union[CompletionResponse, AsyncGenerator]:
+        raise ValueError("Sentence transformers don't support completion")
+
+    async def chat_completion(
+        self,
+        model_id: str,
+        messages: List[Message],
+        sampling_params: Optional[SamplingParams] = SamplingParams(),
+        response_format: Optional[ResponseFormat] = None,
+        tools: Optional[List[ToolDefinition]] = None,
+        tool_choice: Optional[ToolChoice] = ToolChoice.auto,
+        tool_prompt_format: Optional[ToolPromptFormat] = ToolPromptFormat.json,
+        stream: Optional[bool] = False,
+        logprobs: Optional[LogProbConfig] = None,
+    ) -> AsyncGenerator:
+        raise ValueError("Sentence transformers don't support chat completion")