mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-11 05:38:38 +00:00
0066d986c5
# What does this PR do? use SecretStr for OpenAIMixin providers - RemoteInferenceProviderConfig now has auth_credential: SecretStr - the default alias is api_key (most common name) - some providers override to use api_token (RunPod, vLLM, Databricks) - some providers exclude it (Ollama, TGI, Vertex AI) addresses #3517 ## Test Plan ci w/ new tests
45 lines
1.3 KiB
Python
45 lines
1.3 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 BaseModel, ConfigDict, Field
|
|
|
|
from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
|
|
from llama_stack.schema_utils import json_schema_type
|
|
|
|
|
|
class WatsonXProviderDataValidator(BaseModel):
|
|
model_config = ConfigDict(
|
|
from_attributes=True,
|
|
extra="forbid",
|
|
)
|
|
watsonx_api_key: str | None
|
|
|
|
|
|
@json_schema_type
|
|
class WatsonXConfig(RemoteInferenceProviderConfig):
|
|
url: str = Field(
|
|
default_factory=lambda: os.getenv("WATSONX_BASE_URL", "https://us-south.ml.cloud.ibm.com"),
|
|
description="A base url for accessing the watsonx.ai",
|
|
)
|
|
project_id: str | None = Field(
|
|
default=None,
|
|
description="The watsonx.ai project ID",
|
|
)
|
|
timeout: int = Field(
|
|
default=60,
|
|
description="Timeout for the HTTP requests",
|
|
)
|
|
|
|
@classmethod
|
|
def sample_run_config(cls, **kwargs) -> dict[str, Any]:
|
|
return {
|
|
"url": "${env.WATSONX_BASE_URL:=https://us-south.ml.cloud.ibm.com}",
|
|
"api_key": "${env.WATSONX_API_KEY:=}",
|
|
"project_id": "${env.WATSONX_PROJECT_ID:=}",
|
|
}
|