mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-12 21:58:38 +00:00
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
This commit is contained in:
parent
6d8f61206e
commit
0066d986c5
57 changed files with 158 additions and 149 deletions
|
@ -7,7 +7,7 @@
|
|||
import os
|
||||
from typing import Any
|
||||
|
||||
from pydantic import Field, SecretStr
|
||||
from pydantic import Field
|
||||
|
||||
from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
|
||||
from llama_stack.schema_utils import json_schema_type
|
||||
|
@ -40,10 +40,6 @@ class NVIDIAConfig(RemoteInferenceProviderConfig):
|
|||
default_factory=lambda: os.getenv("NVIDIA_BASE_URL", "https://integrate.api.nvidia.com"),
|
||||
description="A base url for accessing the NVIDIA NIM",
|
||||
)
|
||||
api_key: SecretStr | None = Field(
|
||||
default_factory=lambda: SecretStr(os.getenv("NVIDIA_API_KEY")),
|
||||
description="The NVIDIA API key, only needed of using the hosted service",
|
||||
)
|
||||
timeout: int = Field(
|
||||
default=60,
|
||||
description="Timeout for the HTTP requests",
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue