mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
bedfea38c3
* Removes a bunch of distros * Removed distros were added into the "starter" distribution * Doc for "starter" has been added * Partially reverts https://github.com/meta-llama/llama-stack/pull/2482 since inference providers are disabled by default and can be turned on manually via env variable. * Disables safety in starter distro Closes: #2502 Signed-off-by: Sébastien Han <seb@redhat.com>
67 lines
2.4 KiB
Python
67 lines
2.4 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, Field, SecretStr
|
|
|
|
from llama_stack.schema_utils import json_schema_type
|
|
|
|
|
|
@json_schema_type
|
|
class NVIDIAConfig(BaseModel):
|
|
"""
|
|
Configuration for the NVIDIA NIM inference endpoint.
|
|
|
|
Attributes:
|
|
url (str): A base url for accessing the NVIDIA NIM, e.g. http://localhost:8000
|
|
api_key (str): The access key for the hosted NIM endpoints
|
|
|
|
There are two ways to access NVIDIA NIMs -
|
|
0. Hosted: Preview APIs hosted at https://integrate.api.nvidia.com
|
|
1. Self-hosted: You can run NVIDIA NIMs on your own infrastructure
|
|
|
|
By default the configuration is set to use the hosted APIs. This requires
|
|
an API key which can be obtained from https://ngc.nvidia.com/.
|
|
|
|
By default the configuration will attempt to read the NVIDIA_API_KEY environment
|
|
variable to set the api_key. Please do not put your API key in code.
|
|
|
|
If you are using a self-hosted NVIDIA NIM, you can set the url to the
|
|
URL of your running NVIDIA NIM and do not need to set the api_key.
|
|
"""
|
|
|
|
url: str = Field(
|
|
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: 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",
|
|
)
|
|
append_api_version: bool = Field(
|
|
default_factory=lambda: os.getenv("NVIDIA_APPEND_API_VERSION", "True").lower() != "false",
|
|
description="When set to false, the API version will not be appended to the base_url. By default, it is true.",
|
|
)
|
|
|
|
@classmethod
|
|
def sample_run_config(
|
|
cls,
|
|
url: str = "${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com}",
|
|
api_key: str = "${env.NVIDIA_API_KEY:+}",
|
|
append_api_version: bool = "${env.NVIDIA_APPEND_API_VERSION:=True}",
|
|
**kwargs,
|
|
) -> dict[str, Any]:
|
|
return {
|
|
"url": url,
|
|
"api_key": api_key,
|
|
"append_api_version": append_api_version,
|
|
}
|