phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

feat: expand set of known openai models, allow using openai canonical model names (#2164)

Browse source 
note: the openai provider exposes the litellm specific model names to
the user. this change is compatible with that. the litellm names should
be deprecated.
This commit is contained in:
Matthew Farrellee 2025-05-14 16:18:15 -04:00 • committed by GitHub
parent 5052c3cbf3
commit aa5bef8e05
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 222 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

7
llama_stack/providers/remote/inference/openai/openai.py
View file

@ -19,6 +19,13 @@ class OpenAIInferenceAdapter(LiteLLMOpenAIMixin):
provider_data_api_key_field="openai_api_key",
)
self.config = config
# we set is_openai_compat so users can use the canonical
# openai model names like "gpt-4" or "gpt-3.5-turbo"
# and the model name will be translated to litellm's
# "openai/gpt-4" or "openai/gpt-3.5-turbo" transparently.
# if we do not set this, users will be exposed to the
# litellm specific model names, an abstraction leak.
self.is_openai_compat = True
async def initialize(self) -> None:
await super().initialize()