llama-stack-mirror/llama_stack/providers/remote/inference/ollama/config.py
Matthew Farrellee 0066d986c5
feat: use SecretStr for inference provider auth credentials (#3724)
# 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
2025-10-10 07:32:50 -07:00

25 lines
757 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 typing import Any
from pydantic import Field, SecretStr
from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
DEFAULT_OLLAMA_URL = "http://localhost:11434"
class OllamaImplConfig(RemoteInferenceProviderConfig):
auth_credential: SecretStr | None = Field(default=None, exclude=True)
url: str = DEFAULT_OLLAMA_URL
@classmethod
def sample_run_config(cls, url: str = "${env.OLLAMA_URL:=http://localhost:11434}", **kwargs) -> dict[str, Any]:
return {
"url": url,
}