OpenAI-compatible completions and chats for litellm and together

This adds OpenAI-compatible completions and chat completions support
for the native Together provider as well as all providers implemented
with litellm.

llama_stack/providers/utils/inference/litellm_openai_mixin.py

@@ -4,7 +4,7 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from typing import AsyncGenerator, AsyncIterator, List, Optional, Union
+from typing import Any, AsyncGenerator, AsyncIterator, Dict, List, Optional, Union
 
 import litellm
 
@@ -30,6 +30,7 @@ from llama_stack.apis.inference import (
     ToolDefinition,
     ToolPromptFormat,
 )
+from llama_stack.apis.inference.inference import OpenAIChatCompletion, OpenAICompletion, OpenAIMessageParam
 from llama_stack.apis.models.models import Model
 from llama_stack.distribution.request_headers import NeedsRequestProviderData
 from llama_stack.log import get_logger
@@ -40,6 +41,7 @@ from llama_stack.providers.utils.inference.openai_compat import (
     convert_openai_chat_completion_stream,
     convert_tooldef_to_openai_tool,
     get_sampling_options,
+    prepare_openai_completion_params,
 )
 from llama_stack.providers.utils.inference.prompt_adapter import (
     interleaved_content_as_str,
@@ -245,3 +247,99 @@ class LiteLLMOpenAIMixin(
 
         embeddings = [data["embedding"] for data in response["data"]]
         return EmbeddingsResponse(embeddings=embeddings)
+
+    async def openai_completion(
+        self,
+        model: str,
+        prompt: str,
+        best_of: Optional[int] = None,
+        echo: Optional[bool] = None,
+        frequency_penalty: Optional[float] = None,
+        logit_bias: Optional[Dict[str, float]] = None,
+        logprobs: Optional[bool] = None,
+        max_tokens: Optional[int] = None,
+        n: Optional[int] = None,
+        presence_penalty: Optional[float] = None,
+        seed: Optional[int] = None,
+        stop: Optional[Union[str, List[str]]] = None,
+        stream: Optional[bool] = None,
+        stream_options: Optional[Dict[str, Any]] = None,
+        temperature: Optional[float] = None,
+        top_p: Optional[float] = None,
+        user: Optional[str] = None,
+    ) -> OpenAICompletion:
+        model_obj = await self._get_model(model)
+        params = await prepare_openai_completion_params(
+            model=model_obj.provider_resource_id,
+            prompt=prompt,
+            best_of=best_of,
+            echo=echo,
+            frequency_penalty=frequency_penalty,
+            logit_bias=logit_bias,
+            logprobs=logprobs,
+            max_tokens=max_tokens,
+            n=n,
+            presence_penalty=presence_penalty,
+            seed=seed,
+            stop=stop,
+            stream=stream,
+            stream_options=stream_options,
+            temperature=temperature,
+            top_p=top_p,
+            user=user,
+        )
+        return litellm.text_completion(**params)
+
+    async def openai_chat_completion(
+        self,
+        model: str,
+        messages: List[OpenAIMessageParam],
+        frequency_penalty: Optional[float] = None,
+        function_call: Optional[Union[str, Dict[str, Any]]] = None,
+        functions: Optional[List[Dict[str, Any]]] = None,
+        logit_bias: Optional[Dict[str, float]] = None,
+        logprobs: Optional[bool] = None,
+        max_completion_tokens: Optional[int] = None,
+        max_tokens: Optional[int] = None,
+        n: Optional[int] = None,
+        parallel_tool_calls: Optional[bool] = None,
+        presence_penalty: Optional[float] = None,
+        response_format: Optional[Dict[str, str]] = None,
+        seed: Optional[int] = None,
+        stop: Optional[Union[str, List[str]]] = None,
+        stream: Optional[bool] = None,
+        stream_options: Optional[Dict[str, Any]] = None,
+        temperature: Optional[float] = None,
+        tool_choice: Optional[Union[str, Dict[str, Any]]] = None,
+        tools: Optional[List[Dict[str, Any]]] = None,
+        top_logprobs: Optional[int] = None,
+        top_p: Optional[float] = None,
+        user: Optional[str] = None,
+    ) -> OpenAIChatCompletion:
+        model_obj = await self._get_model(model)
+        params = await prepare_openai_completion_params(
+            model=model_obj.provider_resource_id,
+            messages=messages,
+            frequency_penalty=frequency_penalty,
+            function_call=function_call,
+            functions=functions,
+            logit_bias=logit_bias,
+            logprobs=logprobs,
+            max_completion_tokens=max_completion_tokens,
+            max_tokens=max_tokens,
+            n=n,
+            parallel_tool_calls=parallel_tool_calls,
+            presence_penalty=presence_penalty,
+            response_format=response_format,
+            seed=seed,
+            stop=stop,
+            stream=stream,
+            stream_options=stream_options,
+            temperature=temperature,
+            tool_choice=tool_choice,
+            tools=tools,
+            top_logprobs=top_logprobs,
+            top_p=top_p,
+            user=user,
+        )
+        return litellm.completion(**params)

llama_stack/providers/utils/inference/openai_compat.py

@@ -1052,6 +1052,11 @@ async def convert_openai_chat_completion_stream(
     )
 
 
+async def prepare_openai_completion_params(**params):
+    completion_params = {k: v for k, v in params.items() if v is not None}
+    return completion_params
+
+
 class OpenAICompletionUnsupportedMixin:
     async def openai_completion(
         self,