mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-26 06:07:43 +00:00
bf63470c22
This enhancement allows inference providers using LiteLLMOpenAIMixin to validate model availability against LiteLLM's official provider model listings, improving reliability and user experience when working with different AI service providers. - Add litellm_provider_name parameter to LiteLLMOpenAIMixin constructor - Add check_model_availability method to LiteLLMOpenAIMixin using litellm.models_by_provider - Update Gemini, Groq, and SambaNova inference adapters to pass litellm_provider_name
28 lines
884 B
Python
28 lines
884 B
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under the terms described in the LICENSE file in
|
|
# the root directory of this source tree.
|
|
|
|
from llama_stack.providers.utils.inference.litellm_openai_mixin import LiteLLMOpenAIMixin
|
|
|
|
from .config import GeminiConfig
|
|
from .models import MODEL_ENTRIES
|
|
|
|
|
|
class GeminiInferenceAdapter(LiteLLMOpenAIMixin):
|
|
def __init__(self, config: GeminiConfig) -> None:
|
|
LiteLLMOpenAIMixin.__init__(
|
|
self,
|
|
MODEL_ENTRIES,
|
|
api_key_from_config=config.api_key,
|
|
provider_data_api_key_field="gemini_api_key",
|
|
litellm_provider_name="gemini",
|
|
)
|
|
self.config = config
|
|
|
|
async def initialize(self) -> None:
|
|
await super().initialize()
|
|
|
|
async def shutdown(self) -> None:
|
|
await super().shutdown()
|