mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-03 09:53:45 +00:00
fa7699d2c3
# What does this PR do? Add rerank API for NVIDIA Inference Provider. <!-- If resolving an issue, uncomment and update the line below --> Closes #3278 ## Test Plan Unit test: ``` pytest tests/unit/providers/nvidia/test_rerank_inference.py ``` Integration test: ``` pytest -s -v tests/integration/inference/test_rerank.py --stack-config="inference=nvidia" --rerank-model=nvidia/nvidia/nv-rerankqa-mistral-4b-v3 --env NVIDIA_API_KEY="" --env NVIDIA_BASE_URL="https://integrate.api.nvidia.com" ```
80 lines
3.1 KiB
Python
80 lines
3.1 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
|
|
|
|
from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
|
|
from llama_stack.schema_utils import json_schema_type
|
|
|
|
|
|
class NVIDIAProviderDataValidator(BaseModel):
|
|
nvidia_api_key: str | None = Field(
|
|
default=None,
|
|
description="API key for NVIDIA NIM models",
|
|
)
|
|
|
|
|
|
@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
|
|
rerank_model_to_url (dict[str, str]): Mapping of rerank model identifiers to their API 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.",
|
|
)
|
|
rerank_model_to_url: dict[str, str] = Field(
|
|
default_factory=lambda: {
|
|
"nv-rerank-qa-mistral-4b:1": "https://ai.api.nvidia.com/v1/retrieval/nvidia/reranking",
|
|
"nvidia/nv-rerankqa-mistral-4b-v3": "https://ai.api.nvidia.com/v1/retrieval/nvidia/nv-rerankqa-mistral-4b-v3/reranking",
|
|
"nvidia/llama-3.2-nv-rerankqa-1b-v2": "https://ai.api.nvidia.com/v1/retrieval/nvidia/llama-3_2-nv-rerankqa-1b-v2/reranking",
|
|
},
|
|
description="Mapping of rerank model identifiers to their API endpoints. ",
|
|
)
|
|
|
|
@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,
|
|
}
|