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
34 lines
1.1 KiB
Python
34 lines
1.1 KiB
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.
|
|
|
|
import os
|
|
from typing import Any
|
|
|
|
from pydantic import Field, SecretStr
|
|
|
|
from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
|
|
from llama_stack.schema_utils import json_schema_type
|
|
|
|
DEFAULT_BASE_URL = "https://api.cerebras.ai"
|
|
|
|
|
|
@json_schema_type
|
|
class CerebrasImplConfig(RemoteInferenceProviderConfig):
|
|
base_url: str = Field(
|
|
default=os.environ.get("CEREBRAS_BASE_URL", DEFAULT_BASE_URL),
|
|
description="Base URL for the Cerebras API",
|
|
)
|
|
api_key: SecretStr = Field(
|
|
default=SecretStr(os.environ.get("CEREBRAS_API_KEY")), # type: ignore[arg-type]
|
|
description="Cerebras API Key",
|
|
)
|
|
|
|
@classmethod
|
|
def sample_run_config(cls, api_key: str = "${env.CEREBRAS_API_KEY:=}", **kwargs) -> dict[str, Any]:
|
|
return {
|
|
"base_url": DEFAULT_BASE_URL,
|
|
"api_key": api_key,
|
|
}
|