implement embedding generation in supported inference providers

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 +1,80 @@
+# 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
+
+    def check_model(self, request) -> None:
+        if request.model != self.config.model:
+            raise RuntimeError(
+                f"Model mismatch: {request.model} != {self.config.model}"
+            )
+
+    async def register_model(self, model: Model) -> None:
+        _ = self._get_embedding_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 NotImplementedError("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 NotImplementedError("Sentence transformers don't support chat completion")