mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
feat: Add NVIDIA NeMo datastore (#1852)
# What does this PR do? Implemetation of NeMO Datastore register, unregister API. Open Issues: - provider_id gets set to `localfs` in client.datasets.register() as it is specified in routing_tables.py: DatasetsRoutingTable see: #1860 Currently I have passed `"provider_id":"nvidia"` in metadata and have parsed that in `DatasetsRoutingTable` (Not the best approach, but just a quick workaround to make it work for now.) ## Test Plan - Unit test cases: `pytest tests/unit/providers/nvidia/test_datastore.py` ```bash ========================================================== test session starts =========================================================== platform linux -- Python 3.10.0, pytest-8.3.5, pluggy-1.5.0 rootdir: /home/ubuntu/llama-stack configfile: pyproject.toml plugins: anyio-4.9.0, asyncio-0.26.0, nbval-0.11.0, metadata-3.1.1, html-4.1.1, cov-6.1.0 asyncio: mode=strict, asyncio_default_fixture_loop_scope=None, asyncio_default_test_loop_scope=function collected 2 items tests/unit/providers/nvidia/test_datastore.py .. [100%] ============================================================ warnings summary ============================================================ ====================================================== 2 passed, 1 warning in 0.84s ====================================================== ``` cc: @dglogo, @mattf, @yanxi0830
This commit is contained in:
parent
c149cf2e0f
commit
e6bbf8d20b
17 changed files with 514 additions and 9 deletions
61
llama_stack/providers/remote/datasetio/nvidia/config.py
Normal file
61
llama_stack/providers/remote/datasetio/nvidia/config.py
Normal file
|
@ -0,0 +1,61 @@
|
|||
# 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
|
||||
import warnings
|
||||
from typing import Any, Dict, Optional
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
|
||||
class NvidiaDatasetIOConfig(BaseModel):
|
||||
"""Configuration for NVIDIA DatasetIO implementation."""
|
||||
|
||||
api_key: Optional[str] = Field(
|
||||
default_factory=lambda: os.getenv("NVIDIA_API_KEY"),
|
||||
description="The NVIDIA API key.",
|
||||
)
|
||||
|
||||
dataset_namespace: Optional[str] = Field(
|
||||
default_factory=lambda: os.getenv("NVIDIA_DATASET_NAMESPACE", "default"),
|
||||
description="The NVIDIA dataset namespace.",
|
||||
)
|
||||
|
||||
project_id: Optional[str] = Field(
|
||||
default_factory=lambda: os.getenv("NVIDIA_PROJECT_ID", "test-project"),
|
||||
description="The NVIDIA project ID.",
|
||||
)
|
||||
|
||||
datasets_url: str = Field(
|
||||
default_factory=lambda: os.getenv("NVIDIA_DATASETS_URL", "http://nemo.test"),
|
||||
description="Base URL for the NeMo Dataset API",
|
||||
)
|
||||
|
||||
# warning for default values
|
||||
def __post_init__(self):
|
||||
default_values = []
|
||||
if os.getenv("NVIDIA_PROJECT_ID") is None:
|
||||
default_values.append("project_id='test-project'")
|
||||
if os.getenv("NVIDIA_DATASET_NAMESPACE") is None:
|
||||
default_values.append("dataset_namespace='default'")
|
||||
if os.getenv("NVIDIA_DATASETS_URL") is None:
|
||||
default_values.append("datasets_url='http://nemo.test'")
|
||||
|
||||
if default_values:
|
||||
warnings.warn(
|
||||
f"Using default values: {', '.join(default_values)}. \
|
||||
Please set the environment variables to avoid this default behavior.",
|
||||
stacklevel=2,
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def sample_run_config(cls, **kwargs) -> Dict[str, Any]:
|
||||
return {
|
||||
"api_key": "${env.NVIDIA_API_KEY:}",
|
||||
"dataset_namespace": "${env.NVIDIA_DATASET_NAMESPACE:default}",
|
||||
"project_id": "${env.NVIDIA_PROJECT_ID:test-project}",
|
||||
"datasets_url": "${env.NVIDIA_DATASETS_URL:http://nemo.test}",
|
||||
}
|
Loading…
Add table
Add a link
Reference in a new issue