llama-stack-mirror/llama_stack/providers/registry/datasetio.py
Charlie Doern 686f87d138 feat: combine ProviderSpec datatypes
currently `RemoteProviderSpec` has an `AdapterSpec` embedded in it. Remove `AdapterSpec`, and put its leftover fields into `RemoteProviderSpec`.

Additionally, many of the fields were duplicated between `InlineProviderSpec` and `RemoteProviderSpec`. Move these to `ProviderSpec` so they are shared.

Fixup the distro codegen to use `RemoteProviderSpec` directly rather than `remote_provider_spec` which took an AdapterSpec and returned a full provider spec

Signed-off-by: Charlie Doern <cdoern@redhat.com>
2025-09-18 09:01:22 -04:00

49 lines
1.9 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.
from llama_stack.providers.datatypes import (
Api,
InlineProviderSpec,
ProviderSpec,
RemoteProviderSpec,
)
def available_providers() -> list[ProviderSpec]:
return [
InlineProviderSpec(
api=Api.datasetio,
provider_type="inline::localfs",
pip_packages=["pandas"],
module="llama_stack.providers.inline.datasetio.localfs",
config_class="llama_stack.providers.inline.datasetio.localfs.LocalFSDatasetIOConfig",
api_dependencies=[],
description="Local filesystem-based dataset I/O provider for reading and writing datasets to local storage.",
),
RemoteProviderSpec(
api=Api.datasetio,
adapter_type="huggingface",
provider_type="remote::huggingface",
pip_packages=[
"datasets>=4.0.0",
],
module="llama_stack.providers.remote.datasetio.huggingface",
config_class="llama_stack.providers.remote.datasetio.huggingface.HuggingfaceDatasetIOConfig",
description="HuggingFace datasets provider for accessing and managing datasets from the HuggingFace Hub.",
),
RemoteProviderSpec(
api=Api.datasetio,
adapter_type="nvidia",
provider_type="remote::nvidia",
module="llama_stack.providers.remote.datasetio.nvidia",
config_class="llama_stack.providers.remote.datasetio.nvidia.NvidiaDatasetIOConfig",
pip_packages=[
"datasets>=4.0.0",
],
description="NVIDIA's dataset I/O provider for accessing datasets from NVIDIA's data platform.",
),
]