mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
4e6c984c26
# What does this PR do? this PR adds a basic inference adapter to NVIDIA NIMs what it does - - chat completion api - tool calls - streaming - structured output - logprobs - support hosted NIM on integrate.api.nvidia.com - support downloaded NIM containers what it does not do - - completion api - embedding api - vision models - builtin tools - have certainty that sampling strategies are correct ## Feature/Issue validation/testing/test plan `pytest -s -v --providers inference=nvidia llama_stack/providers/tests/inference/ --env NVIDIA_API_KEY=...` all tests should pass. there are pydantic v1 warnings. ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [x] Did you read the [contributor guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md), Pull Request section? - [ ] Was this discussed/approved via a Github issue? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? - [x] Did you write any new necessary tests? Thanks for contributing 🎉!
48 lines
1.7 KiB
Python
48 lines
1.7 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 Optional
|
|
|
|
from llama_models.schema_utils import json_schema_type
|
|
from pydantic import BaseModel, Field
|
|
|
|
|
|
@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="https://integrate.api.nvidia.com",
|
|
description="A base url for accessing the NVIDIA NIM",
|
|
)
|
|
api_key: Optional[str] = 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",
|
|
)
|