mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-03 19:57:35 +00:00
c88c4ff2c6
# What does this PR do? Rather than have a single `LLAMA_STACK_VERSION`, we need to have a `_V1`, `_V1ALPHA`, and `_V1BETA` constant. This also necessitated addition of `level` to the `WebMethod` so that routing can be handeled properly. For backwards compat, the `v1` routes are being kept around and marked as `deprecated`. When used, the server will log a deprecation warning. Deprecation log: <img width="1224" height="134" alt="Screenshot 2025-09-25 at 2 43 36 PM" src="https://github.com/user-attachments/assets/0cc7c245-dafc-48f0-be99-269fb9a686f9" /> move: 1. post_training to `v1alpha` as it is under heavy development and not near its final state 2. eval: job scheduling is not implemented. Relies heavily on the datasetio API which is under development missing implementations of specific routes indicating the structure of those routes might change. Additionally eval depends on the `inference` API which is going to be deprecated, eval will likely need a major API surface change to conform to using completions properly implements leveling in #3317 note: integration tests will fail until the SDK is regenerated with v1alpha/inference as opposed to v1/inference ## Test Plan existing tests should pass with newly generated schema. Conformance will also pass as these routes are not the ones we currently test for stability Signed-off-by: Charlie Doern <cdoern@redhat.com>
55 lines
2 KiB
Python
55 lines
2 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 typing import Any, Protocol, runtime_checkable
|
|
|
|
from llama_stack.apis.common.responses import PaginatedResponse
|
|
from llama_stack.apis.datasets import Dataset
|
|
from llama_stack.apis.version import LLAMA_STACK_API_V1
|
|
from llama_stack.schema_utils import webmethod
|
|
|
|
|
|
class DatasetStore(Protocol):
|
|
def get_dataset(self, dataset_id: str) -> Dataset: ...
|
|
|
|
|
|
@runtime_checkable
|
|
class DatasetIO(Protocol):
|
|
# keeping for aligning with inference/safety, but this is not used
|
|
dataset_store: DatasetStore
|
|
|
|
@webmethod(route="/datasetio/iterrows/{dataset_id:path}", method="GET", level=LLAMA_STACK_API_V1)
|
|
async def iterrows(
|
|
self,
|
|
dataset_id: str,
|
|
start_index: int | None = None,
|
|
limit: int | None = None,
|
|
) -> PaginatedResponse:
|
|
"""Get a paginated list of rows from a dataset.
|
|
|
|
Uses offset-based pagination where:
|
|
- start_index: The starting index (0-based). If None, starts from beginning.
|
|
- limit: Number of items to return. If None or -1, returns all items.
|
|
|
|
The response includes:
|
|
- data: List of items for the current page.
|
|
- has_more: Whether there are more items available after this set.
|
|
|
|
:param dataset_id: The ID of the dataset to get the rows from.
|
|
:param start_index: Index into dataset for the first row to get. Get all rows if None.
|
|
:param limit: The number of rows to get.
|
|
:returns: A PaginatedResponse.
|
|
"""
|
|
...
|
|
|
|
@webmethod(route="/datasetio/append-rows/{dataset_id:path}", method="POST", level=LLAMA_STACK_API_V1)
|
|
async def append_rows(self, dataset_id: str, rows: list[dict[str, Any]]) -> None:
|
|
"""Append rows to a dataset.
|
|
|
|
:param dataset_id: The ID of the dataset to append the rows to.
|
|
:param rows: The rows to append to the dataset.
|
|
"""
|
|
...
|