phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-15 15:22:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: use SecretStr for inference provider auth credentials

Browse source 
- 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)
This commit is contained in:
Matthew Farrellee 2025-10-08 05:05:05 -04:00
parent 62bac0aad4
commit 6143b9b0c3
56 changed files with 157 additions and 144 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/providers/remote/inference/vertexai/config.py
View file

@ -6,7 +6,7 @@
from typing import Any
from pydantic import BaseModel, Field
from pydantic import BaseModel, Field, SecretStr
from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
from llama_stack.schema_utils import json_schema_type
@ -25,6 +25,8 @@ class VertexAIProviderDataValidator(BaseModel):
@json_schema_type
class VertexAIConfig(RemoteInferenceProviderConfig):
auth_credential: SecretStr | None = Field(default=None, exclude=True)
project: str = Field(
description="Google Cloud project ID for Vertex AI",
)