mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-03 18:00:36 +00:00
chore(package): migrate to src/ layout (#3920)
Migrates package structure to src/ layout following Python packaging best practices. All code moved from `llama_stack/` to `src/llama_stack/`. Public API unchanged - imports remain `import llama_stack.*`. Updated build configs, pre-commit hooks, scripts, and GitHub workflows accordingly. All hooks pass, package builds cleanly. **Developer note**: Reinstall after pulling: `pip install -e .`
This commit is contained in:
parent
98a5047f9d
commit
471b1b248b
791 changed files with 2983 additions and 456 deletions
64
src/llama_stack/providers/remote/inference/nvidia/config.py
Normal file
64
src/llama_stack/providers/remote/inference/nvidia/config.py
Normal file
|
|
@ -0,0 +1,64 @@
|
|||
# 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 Field
|
||||
|
||||
from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
|
||||
from llama_stack.schema_utils import json_schema_type
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class NVIDIAConfig(RemoteInferenceProviderConfig):
|
||||
"""
|
||||
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",
|
||||
)
|
||||
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,
|
||||
}
|
||||
Loading…
Add table
Add a link
Reference in a new issue