phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-31 04:43:52 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Clean up some more usage of direct OpenAI types

Browse source
This commit is contained in:
Ben Browning 2025-04-08 09:10:52 -04:00
parent 92fdf6d0c9
commit 5bc5fed6df
4 changed files with 10 additions and 64 deletions
Download patch file Download diff file Expand all files Collapse all files

62
llama_stack/providers/inline/inference/sentence_transformers/sentence_transformers.py
View file

@ -5,10 +5,7 @@
# the root directory of this source tree.
import logging
from typing import Any, AsyncGenerator, Dict, List, Optional, Union
from openai.types.chat import ChatCompletion as OpenAIChatCompletion
from openai.types.completion import Completion as OpenAICompletion
from typing import AsyncGenerator, List, Optional, Union
from llama_stack.apis.inference import (
CompletionResponse,
@ -22,11 +19,14 @@ from llama_stack.apis.inference import (
ToolDefinition,
ToolPromptFormat,
)
from llama_stack.apis.inference.inference import OpenAIMessageParam
from llama_stack.providers.datatypes import Model, ModelsProtocolPrivate
from llama_stack.providers.utils.inference.embedding_mixin import (
SentenceTransformerEmbeddingMixin,
)
from llama_stack.providers.utils.inference.openai_compat import (
OpenAIChatCompletionUnsupportedMixin,
OpenAICompletionUnsupportedMixin,
)
from .config import SentenceTransformersInferenceConfig
@ -34,6 +34,8 @@ log = logging.getLogger(__name__)
class SentenceTransformersInferenceImpl(
OpenAIChatCompletionUnsupportedMixin,
OpenAICompletionUnsupportedMixin,
SentenceTransformerEmbeddingMixin,
Inference,
ModelsProtocolPrivate,
@ -78,53 +80,3 @@ class SentenceTransformersInferenceImpl(
tool_config: Optional[ToolConfig] = None,
) -> AsyncGenerator:
raise ValueError("Sentence transformers don't support chat completion")
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:
raise ValueError("Sentence transformers don't support openai completion")
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:
raise ValueError("Sentence transformers don't support openai chat completion")