forked from phoenix-oss/llama-stack-mirror
928a39d17b
Groq has never supported raw completions anyhow. So this makes it easier to switch it to LiteLLM. All our test suite passes. I also updated all the openai-compat providers so they work with api keys passed from headers. `provider_data` ## Test Plan ```bash LLAMA_STACK_CONFIG=groq \ pytest -s -v tests/client-sdk/inference/test_text_inference.py \ --inference-model=groq/llama-3.3-70b-versatile --vision-inference-model="" ``` Also tested (openai, anthropic, gemini) providers. No regressions.
27 lines
840 B
Python
27 lines
840 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",
|
|
)
|
|
self.config = config
|
|
|
|
async def initialize(self) -> None:
|
|
await super().initialize()
|
|
|
|
async def shutdown(self) -> None:
|
|
await super().shutdown()
|