phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-09 15:17:46 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

(feat) Add synthetic_data_kit provider integration for synthetic_data_generation API

Browse source 
The synthetic_data_kit provider integration enables high-quality synthetic dataset
generation for fine-tuning LLMs. This commit sets up the initial provider
registration and fixes provider resolution to properly handle type casting and
imports, ensuring proper integration with llama-stack's provider system.

Implementation of the actual provider functionality will follow in a subsequent
commit.

Signed-off-by: Alina Ryan <aliryan@redhat.com>
This commit is contained in:
Alina Ryan 2025-05-29 14:56:12 -04:00
parent e867501073
commit f86f107f15
7 changed files with 209 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

19
llama_stack/apis/synthetic_data_generation/providers/__init__.py Normal file
View file

@ -0,0 +1,19 @@
# 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.
# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
#
# SPDX-License-Identifier: MIT
from typing import cast
from llama_stack.apis.synthetic_data_generation import SyntheticDataGeneration
from llama_stack.providers.utils.resolver import get_provider_impl as _get_provider_impl
def get_provider_impl() -> SyntheticDataGeneration:
return cast(SyntheticDataGeneration, _get_provider_impl(SyntheticDataGeneration))

13
llama_stack/apis/synthetic_data_generation/registry.py
View file

@ -1,13 +0,0 @@
# 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.apis.synthetic_data_generation import SyntheticDataGeneration
SYNTHETIC_DATA_GENERATION_PROVIDERS: dict[str, SyntheticDataGeneration] = {}
def get_provider(name: str = "meta_synthetic_data_kit") -> SyntheticDataGeneration:
raise NotImplementedError(f"No provider registered yet for synthetic_data_generation (requested: {name})")