phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-07 19:12:09 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

added back secretstr and ran pre-commit

Browse source
This commit is contained in:
Chantal D Gama Rose 2025-03-04 01:23:12 -08:00
parent f7e5ae5dfc
commit 3298e50105
5 changed files with 7 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -7,7 +7,7 @@
import os import os
from typing import Any, Dict, Optional from typing import Any, Dict, Optional
from pydantic import BaseModel, Field from pydantic import BaseModel, Field, SecretStr
from llama_stack.schema_utils import json_schema_type from llama_stack.schema_utils import json_schema_type
@ -39,7 +39,7 @@ class NVIDIAConfig(BaseModel):
default_factory=lambda: os.getenv("NVIDIA_BASE_URL", "https://integrate.api.nvidia.com"), default_factory=lambda: os.getenv("NVIDIA_BASE_URL", "https://integrate.api.nvidia.com"),
description="A base url for accessing the NVIDIA NIM", description="A base url for accessing the NVIDIA NIM",
) )
api_key: Optional[str] = Field( api_key: Optional[SecretStr] = Field(
default_factory=lambda: os.getenv("NVIDIA_API_KEY"), default_factory=lambda: os.getenv("NVIDIA_API_KEY"),
description="The NVIDIA API key, only needed of using the hosted service", description="The NVIDIA API key, only needed of using the hosted service",
) )

2
llama_stack/providers/remote/inference/nvidia/nvidia.py
View file

@ -85,7 +85,7 @@ class NVIDIAInferenceAdapter(Inference, ModelRegistryHelper):
# make sure the client lives longer than any async calls # make sure the client lives longer than any async calls
self._client = AsyncOpenAI( self._client = AsyncOpenAI(
base_url=f"{self._config.url}/v1", base_url=f"{self._config.url}/v1",
api_key=(self._config.api_key if self._config.api_key else "NO KEY"), api_key=(self._config.api_key.get_secret_value() if self._config.api_key else "NO KEY"),
timeout=self._config.timeout, timeout=self._config.timeout,
) )

7
llama_stack/templates/nvidia/nvidia.py
View file

@ -6,14 +6,11 @@
from pathlib import Path from pathlib import Path
from llama_stack.distribution.datatypes import Provider, ToolGroupInput
from llama_stack.providers.remote.inference.nvidia import NVIDIAConfig
from llama_stack.providers.remote.inference.nvidia.models import MODEL_ENTRIES
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings, get_model_registry
from llama_stack.distribution.datatypes import ModelInput, Provider, ShieldInput, ToolGroupInput from llama_stack.distribution.datatypes import ModelInput, Provider, ShieldInput, ToolGroupInput
from llama_stack.providers.remote.inference.nvidia import NVIDIAConfig from llama_stack.providers.remote.inference.nvidia import NVIDIAConfig
from llama_stack.providers.remote.inference.nvidia.models import MODEL_ENTRIES
from llama_stack.providers.remote.safety.nvidia import NVIDIASafetyConfig from llama_stack.providers.remote.safety.nvidia import NVIDIASafetyConfig
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings from llama_stack.templates.template import DistributionTemplate, RunConfigSettings, get_model_registry
def get_distribution_template() -> DistributionTemplate: def get_distribution_template() -> DistributionTemplate:

2
tests/api/fixtures/recorded_responses/chat_completion.json
View file

@ -10630,4 +10630,4 @@
], ],
"type": "generator" "type": "generator"
} }
} }

2
tests/api/fixtures/recorded_responses/invoke_tool.json
View file

@ -290,4 +290,4 @@
"metadata": null "metadata": null
} }
} }
} }