phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-12 13:57:57 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore: refactor (chat)completions endpoints to use shared params struct (#3761)

Browse source 
# What does this PR do?

Converts openai(_chat)_completions params to pydantic BaseModel to
reduce code duplication across all providers.

## Test Plan
CI









---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with
[ReviewStack](https://reviewstack.dev/llamastack/llama-stack/pull/3761).
* #3777
* __->__ #3761
This commit is contained in:
ehhuang 2025-10-10 15:46:34 -07:00 • committed by GitHub
parent 6954fe2274
commit 80d58ab519
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
33 changed files with 599 additions and 890 deletions
Download patch file Download diff file Expand all files Collapse all files

25
llama_stack/providers/remote/inference/llama_openai_compat/llama.py
View file

@ -3,9 +3,7 @@
#
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
from typing import Any
from llama_stack.apis.inference.inference import OpenAICompletion, OpenAIEmbeddingsResponse
from llama_stack.apis.inference.inference import OpenAICompletion, OpenAICompletionRequest, OpenAIEmbeddingsResponse
from llama_stack.log import get_logger
from llama_stack.providers.remote.inference.llama_openai_compat.config import LlamaCompatConfig
from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
@ -31,26 +29,7 @@ class LlamaCompatInferenceAdapter(OpenAIMixin):
async def openai_completion(
self,
model: str,
prompt: str | list[str] | list[int] | list[list[int]],
best_of: int | None = None,
echo: bool | None = None,
frequency_penalty: float | None = None,
logit_bias: dict[str, float] | None = None,
logprobs: bool | None = None,
max_tokens: int | None = None,
n: int | None = None,
presence_penalty: float | None = None,
seed: int | None = None,
stop: str | list[str] | None = None,
stream: bool | None = None,
stream_options: dict[str, Any] | None = None,
temperature: float | None = None,
top_p: float | None = None,
user: str | None = None,
guided_choice: list[str] | None = None,
prompt_logprobs: int | None = None,
suffix: str | None = None,
params: OpenAICompletionRequest,
) -> OpenAICompletion:
raise NotImplementedError()