phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-03 09:21:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix: add missing openai_ methods

Browse source
This commit is contained in:
Philippe Martin 2025-04-17 11:53:22 +02:00
parent cfc68012f7
commit a5ab39a497
1 changed files with 63 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

66
llama_stack/providers/remote/inference/podman_ai_lab/podman_ai_lab.py
View file

@ -5,7 +5,7 @@
# the root directory of this source tree.
from typing import AsyncGenerator, List, Optional, Union
from typing import Any, AsyncGenerator, AsyncIterator, Dict, List, Optional, Union
from ollama import AsyncClient
@ -24,6 +24,10 @@ from llama_stack.apis.inference import (
Inference,
LogProbConfig,
Message,
OpenAIChatCompletion,
OpenAIChatCompletionChunk,
OpenAIMessageParam,
OpenAIResponseFormatParam,
ResponseFormat,
SamplingParams,
TextTruncation,
@ -32,6 +36,10 @@ from llama_stack.apis.inference import (
ToolDefinition,
ToolPromptFormat,
)
from llama_stack.apis.inference.inference import (
OpenAICompletion,
)
from llama_stack.apis.models import Model, Models
from llama_stack.log import get_logger
from llama_stack.providers.datatypes import ModelsProtocolPrivate
@ -271,6 +279,60 @@ class PodmanAILabInferenceAdapter(Inference, ModelsProtocolPrivate):
async def register_model(self, model: Model) -> Model:
return model
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[OpenAIResponseFormatParam] = 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,
) -> Union[OpenAIChatCompletion, AsyncIterator[OpenAIChatCompletionChunk]]:
pass
async def openai_completion(
self,
model: str,
prompt: Union[str, List[str], List[int], List[List[int]]],
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,
guided_choice: Optional[List[str]] = None,
prompt_logprobs: Optional[int] = None,
) -> OpenAICompletion:
pass
async def register_model(self, model: Model) -> Model:
return model
async def convert_message_to_openai_dict_for_podman_ai_lab(message: Message) -> List[dict]:
async def _convert_content(content) -> dict:
@ -292,6 +354,4 @@ async def convert_message_to_openai_dict_for_podman_ai_lab(message: Message) ->
else:
return [await _convert_content(message.content)]
async def register_model(self, model: Model) -> Model:
return model