mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-07 12:47:37 +00:00
d23ed26238
# What does this PR do? - implement get_api_key instead of relying on LiteLLMOpenAIMixin.get_api_key - remove use of LiteLLMOpenAIMixin - add default initialize/shutdown methods to OpenAIMixin - remove __init__s to allow proper pydantic construction - remove dead code from vllm adapter and associated / duplicate unit tests - update vllm adapter to use openaimixin for model registration - remove ModelRegistryHelper from fireworks & together adapters - remove Inference from nvidia adapter - complete type hints on embedding_model_metadata - allow extra fields on OpenAIMixin, for model_store, __provider_id__, etc - new recordings for ollama - enhance the list models error handling - update cerebras (remove cerebras-cloud-sdk) and anthropic (custom model listing) inference adapters - parametrized test_inference_client_caching - remove cerebras, databricks, fireworks, together from blanket mypy exclude - removed unnecessary litellm deps ## Test Plan ci
21 lines
630 B
Python
21 lines
630 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.remote.inference.groq.config import GroqConfig
|
|
from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
|
|
|
|
|
|
class GroqInferenceAdapter(OpenAIMixin):
|
|
config: GroqConfig
|
|
|
|
provider_data_api_key_field: str = "groq_api_key"
|
|
|
|
def get_api_key(self) -> str:
|
|
return self.config.api_key or ""
|
|
|
|
def get_base_url(self) -> str:
|
|
return f"{self.config.url}/openai/v1"
|