phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 12:07:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore: update the gemini inference impl to use openai-python for openai-compat functions (#3351)

Browse source 
# What does this PR do?

update the Gemini inference provider to use openai-python for the
openai-compat endpoints

partially addresses #3349, does not address /inference/completion or
/inference/chat-completion

## Test Plan

ci
This commit is contained in:
Matthew Farrellee 2025-09-06 15:22:20 -04:00 • committed by GitHub
parent 7cd1c2c238
commit d6c3b36390
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 8 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/providers/registry/inference.py
View file

@ -207,7 +207,7 @@ def available_providers() -> list[ProviderSpec]:
api=Api.inference, api=Api.inference,
adapter=AdapterSpec( adapter=AdapterSpec(
adapter_type="gemini", adapter_type="gemini",
pip_packages=["litellm"], pip_packages=["litellm", "openai"],
module="llama_stack.providers.remote.inference.gemini", module="llama_stack.providers.remote.inference.gemini",
config_class="llama_stack.providers.remote.inference.gemini.GeminiConfig", config_class="llama_stack.providers.remote.inference.gemini.GeminiConfig",
provider_data_validator="llama_stack.providers.remote.inference.gemini.config.GeminiProviderDataValidator", provider_data_validator="llama_stack.providers.remote.inference.gemini.config.GeminiProviderDataValidator",

8
llama_stack/providers/remote/inference/gemini/gemini.py
View file

@ -5,12 +5,13 @@
# the root directory of this source tree. # the root directory of this source tree.
from llama_stack.providers.utils.inference.litellm_openai_mixin import LiteLLMOpenAIMixin from llama_stack.providers.utils.inference.litellm_openai_mixin import LiteLLMOpenAIMixin
from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
from .config import GeminiConfig from .config import GeminiConfig
from .models import MODEL_ENTRIES from .models import MODEL_ENTRIES
class GeminiInferenceAdapter(LiteLLMOpenAIMixin): class GeminiInferenceAdapter(OpenAIMixin, LiteLLMOpenAIMixin):
def __init__(self, config: GeminiConfig) -> None: def __init__(self, config: GeminiConfig) -> None:
LiteLLMOpenAIMixin.__init__( LiteLLMOpenAIMixin.__init__(
self, self,
@ -21,6 +22,11 @@ class GeminiInferenceAdapter(LiteLLMOpenAIMixin):
) )
self.config = config self.config = config
get_api_key = LiteLLMOpenAIMixin.get_api_key
def get_base_url(self):
return "https://generativelanguage.googleapis.com/v1beta/openai/"
async def initialize(self) -> None: async def initialize(self) -> None:
await super().initialize() await super().initialize()